CN115752489B - Positioning method and device of movable equipment and electronic equipment - Google Patents
Positioning method and device of movable equipment and electronic equipment Download PDFInfo
- Publication number
- CN115752489B CN115752489B CN202211146449.XA CN202211146449A CN115752489B CN 115752489 B CN115752489 B CN 115752489B CN 202211146449 A CN202211146449 A CN 202211146449A CN 115752489 B CN115752489 B CN 115752489B
- Authority
- CN
- China
- Prior art keywords
- target
- line features
- features
- monocular image
- line
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 75
- 238000005259 measurement Methods 0.000 claims abstract description 53
- 238000012216 screening Methods 0.000 claims abstract description 43
- 230000002159 abnormal effect Effects 0.000 claims abstract description 17
- 230000006870 function Effects 0.000 claims description 36
- 238000001514 detection method Methods 0.000 claims description 32
- 238000012545 processing Methods 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 15
- 238000000605 extraction Methods 0.000 claims description 8
- 238000003860 storage Methods 0.000 claims description 8
- 230000000903 blocking effect Effects 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims 1
- 238000005286 illumination Methods 0.000 description 13
- 238000010586 diagram Methods 0.000 description 12
- 238000004422 calculation algorithm Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 5
- 239000011159 matrix material Substances 0.000 description 5
- 230000004807 localization Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000004220 aggregation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000001747 exhibiting effect Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Landscapes
- Image Analysis (AREA)
Abstract
The invention provides a positioning method and device of movable equipment and electronic equipment, wherein the method comprises the following steps: acquiring a target monocular image and inertial measurement unit data acquired by movable equipment; extracting a plurality of point features and a plurality of line features corresponding to the target monocular image; removing abnormal points from the point features to obtain target point features corresponding to the target monocular image; combining the plurality of line features according to the distance between the endpoints of every two line features in the plurality of line features to obtain a plurality of first line features; screening the first line features to obtain a plurality of target line features corresponding to the target monocular image; and then, according to the target point characteristics, the target line characteristics and the inertial measurement unit data, positioning operation of the movable equipment is performed. Thus, the positioning operation of the movable equipment is jointly executed by combining the target point characteristics, the target point characteristics and the inertial measurement unit data, and the accuracy of the positioning result can be effectively improved.
Description
Technical Field
The present invention relates to the field of data processing technologies, and in particular, to a method and an apparatus for positioning a mobile device, and an electronic device.
Background
In some scenes related to positioning, taking a synchronous positioning and map construction (Simultaneous Localization AND MAPPING, SLAM) scene as an example, the SLAM scene mainly helps a vehicle to sense the surrounding environment in real time, and better completes tasks such as navigation, obstacle avoidance, path planning and the like, which depend on the positioning accuracy.
At present, when a vehicle is positioned, a monocular image of the surrounding environment is usually acquired based on a monocular camera arranged on the vehicle, and the vehicle is positioned based on the acquired monocular image, but by adopting the method, particularly for urban areas with insufficient illumination, low texture and dense texture, the accuracy of a positioning result is lower.
Disclosure of Invention
The invention provides a positioning method and device of movable equipment and electronic equipment, and improves the accuracy of a positioning result.
The invention provides a positioning method of a movable device, which can comprise the following steps:
And respectively acquiring a target monocular image and inertial measurement unit data acquired by the movable equipment.
And extracting a plurality of point features and a plurality of line features corresponding to the target monocular image.
And removing abnormal points from the plurality of point features to obtain a plurality of target point features corresponding to the target monocular image.
Combining the plurality of line features according to the distance between the endpoints of every two line features in the plurality of line features to obtain a plurality of first line features; screening the first line features to obtain a plurality of target line features corresponding to the target monocular image;
and performing a positioning operation of the movable device according to the target point characteristics, the target point characteristics and the inertial measurement unit data.
According to the positioning method of the movable equipment provided by the invention, the plurality of line features corresponding to the target monocular image are extracted, and the method comprises the following steps:
And performing blocking processing on the target monocular image to obtain a plurality of image blocks corresponding to the target monocular image.
And respectively extracting line characteristics in each image block to obtain a plurality of line characteristics corresponding to the target monocular image.
According to the positioning method of the mobile device provided by the invention, the screening processing is performed on the plurality of first line features to obtain a plurality of target line features corresponding to the target monocular image, including:
And screening the first line features according to the width and the height of the target monocular image, the number of the first line features and the length factor, and determining a second line features from the first line features.
And screening the plurality of second line features according to the fact that the distance between the target monocular image and the monocular image of the immediately previous frame is smaller than a preset threshold value, and determining a plurality of third line features from the plurality of second features.
And screening the plurality of third line features according to vanishing points corresponding to the plurality of third line features to obtain the plurality of target line features.
According to the positioning method of the mobile device provided by the invention, the screening process is performed on the plurality of third line features according to vanishing points corresponding to the plurality of third line features to obtain the plurality of target line features, including:
and screening the plurality of third line features according to vanishing points corresponding to the plurality of third line features to obtain a plurality of fourth line features.
And removing abnormal line features from the fourth line features according to the Hamming distance and the angle between each fourth line feature and the line feature corresponding to the monocular image of the previous frame, so as to obtain the target line features.
According to the positioning method of the movable device provided by the invention, the positioning operation of the movable device is executed according to the target point characteristics, the target point characteristics and the inertial measurement unit data, and the positioning method comprises the following steps:
Constructing a state function corresponding to the movable equipment; wherein the state function includes a position, a velocity, and a direction of the inertial measurement unit data in a world coordinate system, an inverse depth of each of the plurality of target point features, and an orthogonal representation of each of the plurality of target point features.
And optimizing the state function according to the inertia measurement unit residual error, the point characteristic residual error, the line characteristic residual error, the vanishing point residual error and the prior residual error to obtain an optimized target state function.
Determining an initial position, an initial speed and an initial direction corresponding to the movable equipment based on the target state function; and determining initial pose information of the movable equipment according to the initial position, the initial speed and the initial direction.
Under the condition that loop detection exists between the target monocular image and a immediately previous frame monocular image, correcting the initial position information through point characteristics and pose information corresponding to the previous frame monocular image to obtain target pose information of the movable equipment; the target pose information is a positioning result of the movable equipment.
According to the positioning method of the mobile device provided by the invention, the correcting the initial position information through the point characteristics and the pose information corresponding to the monocular image of the previous frame comprises the following steps:
Taking point characteristics and pose information corresponding to the monocular image of the previous frame as constraint items of the target state function, and determining a target position, a target speed and a target direction corresponding to the movable equipment; and determining target pose information of the movable equipment according to the target position, the target speed and the target direction.
And correcting the initial position information according to the target pose information.
According to the positioning method of the movable equipment provided by the invention, the method further comprises the following steps:
And initially detecting whether loop exists between the target monocular image and the monocular image of the immediately previous frame, and if loop exists in the initial detection, determining a plurality of candidate monocular images.
And performing feature matching on every two candidate frame monocular images in the plurality of candidate frame monocular images, and determining that loop detection exists between the target monocular image and the previous frame monocular image if the number of inner points of the two candidate frame monocular images is larger than a number threshold value.
The present invention also provides a positioning device of a movable apparatus, which may include:
And the acquisition unit is used for respectively acquiring the target monocular image acquired by the movable equipment and the inertial measurement unit data.
And the extraction unit is used for extracting a plurality of point features and a plurality of line features corresponding to the target monocular image.
And the rejecting unit is used for rejecting abnormal points from the plurality of point features to obtain a plurality of target point features corresponding to the target monocular image.
The processing unit is used for combining the plurality of line features according to the distance between the endpoints of every two line features in the plurality of line features to obtain a plurality of first line features; and screening the first line features to obtain a plurality of target line features corresponding to the target monocular image.
And the execution unit is used for executing positioning operation of the movable equipment according to the target point characteristics, the target point characteristics and the inertial measurement unit data.
According to the positioning device of the movable equipment, the extraction unit is specifically used for performing blocking processing on the target monocular image to obtain a plurality of image blocks corresponding to the target monocular image; and respectively extracting line characteristics in each image block to obtain a plurality of line characteristics corresponding to the target monocular image.
According to the positioning device of the mobile device provided by the invention, the extracting unit is specifically configured to perform screening processing on the plurality of first line features according to the width and the height of the target monocular image, the number of the plurality of first line features and the length factor, and determine a plurality of second line features from the plurality of first line features; screening the plurality of second line features according to the fact that the distance between the target monocular image and the monocular image of the immediately previous frame is smaller than a preset threshold value, and determining a plurality of third line features from the plurality of second features; and screening the plurality of third line features according to vanishing points corresponding to the plurality of third line features to obtain the plurality of target line features.
According to the positioning device of the mobile device provided by the invention, the extracting unit is specifically configured to screen the plurality of third line features according to vanishing points corresponding to the plurality of third line features to obtain a plurality of fourth line features; and removing abnormal line features from the fourth line features according to the Hamming distance and the angle between each fourth line feature and the line feature corresponding to the monocular image of the previous frame, so as to obtain the target line features.
According to the positioning device of the movable equipment, the execution unit is specifically used for constructing a state function corresponding to the movable equipment; wherein the state function includes a position, a velocity, and a direction of the inertial measurement unit data in a world coordinate system, an inverse depth of each of the plurality of target point features, and an orthogonal representation of each of the plurality of target point features; optimizing the state function according to the inertia measurement unit residual error, the point characteristic residual error, the line characteristic residual error, the vanishing point residual error and the prior residual error to obtain an optimized target state function; determining an initial position, an initial speed and an initial direction corresponding to the movable equipment based on the target state function; determining initial pose information of the movable equipment according to the initial position, the initial speed and the initial direction; under the condition that loop detection exists between the target monocular image and a immediately previous frame monocular image, correcting the initial position information through point characteristics and pose information corresponding to the previous frame monocular image to obtain target pose information of the movable equipment; the target pose information is a positioning result of the movable equipment.
According to the positioning device of the movable equipment provided by the invention, the execution unit is specifically used for determining the target position, the target speed and the target direction corresponding to the movable equipment by taking the point characteristics and the pose information corresponding to the monocular image of the previous frame as constraint items of the target state function; determining target pose information of the movable equipment according to the target position, the target speed and the target direction; and correcting the initial position information according to the target pose information.
According to the positioning device of the movable equipment, provided by the invention, the device further comprises a detection unit;
The detection unit is used for initially detecting whether loop exists between the target monocular image and the monocular image of the immediately previous frame, and if loop exists in the initial detection, determining a plurality of candidate monocular images; and performing feature matching on every two candidate frame monocular images in the plurality of candidate frame monocular images, and determining that loop detection exists between the target monocular image and the previous frame monocular image if the number of inner points of the two candidate frame monocular images is larger than a number threshold value.
The invention also provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing a method of positioning a mobile device as described in any one of the above when executing the program.
The invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method of positioning a mobile device as described in any of the above.
The invention also provides a computer program product comprising a computer program which, when executed by a processor, implements a method of positioning a mobile device as described in any of the above.
According to the positioning method and device of the movable equipment and the electronic equipment, the target monocular image and the inertial measurement unit data acquired by the movable equipment are acquired; extracting a plurality of point features and a plurality of line features corresponding to the target monocular image; removing abnormal points from the point features to obtain target point features corresponding to the target monocular image; combining the plurality of line features according to the distance between the endpoints of every two line features in the plurality of line features to obtain a plurality of first line features; screening the first line features to obtain a plurality of target line features corresponding to the target monocular image; and then, according to the target point characteristics, the target line characteristics and the inertial measurement unit data, positioning operation of the movable equipment is performed. In this way, the accuracy of the positioning result can be effectively improved by processing the point characteristics and the line characteristics respectively and executing the positioning operation of the movable equipment together according to the processed target point characteristics, target line characteristics and inertial measurement unit data.
Drawings
In order to more clearly illustrate the invention or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flow chart of a positioning method of a mobile device according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of tracking according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of another tracking method according to an embodiment of the present invention;
FIG. 4 is a prior art trajectory heatmap for localization in a low-light scene;
FIG. 5 is a thermal diagram of a trajectory located in a low light scene provided by an embodiment of the present invention;
FIG. 6 is a prior art trajectory heat map for localization in low texture scenes;
FIG. 7 is a thermal diagram of a trajectory located in a low texture scene provided by an embodiment of the present invention;
Fig. 8 is a schematic structural diagram of a positioning device of a mobile device according to an embodiment of the present invention;
Fig. 9 is a schematic entity structure diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In embodiments of the present invention, "at least one" means one or more, and "a plurality" means two or more. "and/or", describes an association relationship of an association object, and indicates that there may be three relationships, for example, a and/or B, and may indicate: there are three cases, a alone, a and B together, and B alone, wherein a, B may be singular or plural. In the text description of the present invention, the character "/" generally indicates that the front-rear associated object is an or relationship.
The technical scheme provided by the embodiment of the invention can be applied to positioning scenes. In many cases, it is necessary to perform a positioning operation. For example, it is necessary to perform a positioning operation for controlling a team of mobile robots to move in a warehouse and sort shelves, or for controlling an automated driving vehicle to park in an empty parking space, or the like. Taking synchronous positioning and map construction (Simultaneous Localization AND MAPPING, SLAM) as an example, the SLAM scene mainly helps a vehicle to sense the surrounding environment in real time by means of a camera, an inertial measurement unit, a global positioning system (Global Positioning System, GPS), a global navigation satellite system (Global Navigation SATELLITE SYSTEM, GNSS) and other sensors, and navigation, obstacle avoidance, path planning and other tasks are completed better, and all depend on positioning accuracy.
At present, when a vehicle is positioned, a monocular image of the surrounding environment is usually acquired based on a monocular camera arranged on the vehicle, and the vehicle is positioned based on the acquired monocular image, but by adopting the method, particularly for urban areas with insufficient illumination, low texture and dense texture, the accuracy of a positioning result is lower.
In order to improve accuracy of a positioning result, the embodiment of the invention provides a positioning method of movable equipment, which is implemented by respectively acquiring a target monocular image and inertial measurement unit data acquired by the movable equipment; extracting a plurality of point features and a plurality of line features corresponding to the target monocular image; removing abnormal points from the point features to obtain target point features corresponding to the target monocular image; combining the plurality of line features according to the distance between the endpoints of every two line features in the plurality of line features to obtain a plurality of first line features; screening the first line features to obtain a plurality of target line features corresponding to the target monocular image; and then, according to the target point characteristics, the target line characteristics and the inertial measurement unit data, positioning operation of the movable equipment is performed. In this way, the accuracy of the positioning result can be effectively improved by processing the point characteristics and the line characteristics respectively and executing the positioning operation of the movable equipment together according to the processed target point characteristics, target line characteristics and inertial measurement unit data.
By way of example, the mobile device may be a robot, an autonomous vehicle, etc., and may be specifically set according to actual needs.
It can be understood that the positioning method of the mobile device provided by the embodiment of the invention can be realized by a robot operating system (Robot Operating System, ROS) and a c++ language, and the fusion between the point characteristics and the line characteristics is performed by using an OpenCv library. In addition, in order to verify the positioning method of the mobile device provided by the embodiment of the invention, a comparison experiment with the VINS-MONO and OKVIS algorithm is carried out on the EuRoC dataset later, and the experiment shows that the accuracy of the positioning result can be effectively improved by adopting the positioning method of the mobile device provided by the embodiment of the invention. Even in some environments with insufficient illumination and low texture and dense texture, the positioning result has higher accuracy and stronger robustness.
In the following, the positioning method of the mobile device according to the present invention will be described in detail by means of the following several specific embodiments. It is to be understood that the following embodiments may be combined with each other and that some embodiments may not be repeated for the same or similar concepts or processes.
Fig. 1 is a flowchart of a positioning method of a mobile device according to an embodiment of the present invention, where the positioning method of the mobile device may be performed by software and/or hardware devices. For example, referring to fig. 1, the positioning method of the mobile device may include:
S101, respectively acquiring a target monocular image and inertial measurement unit data acquired by the movable equipment.
The target monocular image may be understood as a frame of monocular image acquired most recently in a sliding window, and in order to distinguish from other monocular images in the sliding window, in the embodiment of the present invention, the frame of monocular image acquired most recently in the sliding window may be recorded as the target monocular image.
For example, when the movable device acquires the target monocular image, the target monocular image may be acquired by a monocular camera provided in the movable device; when the inertial measurement unit data is acquired, the inertial measurement unit data can be acquired through an inertial measurement unit (Inertial Measurement Unit, IMU) arranged in the movable device, so that a target monocular image and the inertial measurement unit data are acquired.
S102, extracting a plurality of point features and a plurality of line features corresponding to the target monocular image.
For example, when extracting a plurality of point features corresponding to the target monocular image, the ORB (oriented fastand rotated BRIEF) technology may be used to extract the point features, thereby extracting the plurality of point features. For example, after extracting a plurality of point features, the KLT (Kanade-Lucas-Tomasi) method may be further used for optical flow tracking of the point features. For example, referring to fig. 2 and fig. 3, fig. 2 is a schematic diagram of tracking provided by an embodiment of the present invention, fig. 3 is another schematic diagram of tracking provided by an embodiment of the present invention, where fig. 2 is a schematic diagram of tracking in a low-illumination scene, and fig. 3 is a schematic diagram of tracking in a low-texture scene, so that the tracking effect is better.
For example, when extracting a plurality of line features corresponding to a target monocular image, in order to enable the extracted line features to have good rotation and scale invariance, the extraction time is short and the distribution is uniform, in the embodiment of the invention, the target monocular image can be firstly subjected to block processing to obtain a plurality of image blocks corresponding to the target monocular image; by way of example, the target monocular image can be segmented into 12×12 image blocks, and line features in each image block are extracted respectively to obtain a plurality of line features corresponding to the target monocular image, so that the extracted line features can be effectively guaranteed to have good rotation and scale invariance, and the extraction time is short and the distribution is uniform.
After extracting the plurality of point features and the plurality of line features corresponding to the target monocular image, the plurality of point features and the plurality of line features may be respectively processed, that is, the following S103 and S104 are executed:
S103, eliminating abnormal points from the point features to obtain target point features corresponding to the target monocular image.
For example, when outliers are removed from the plurality of point features, a geometric constraint algorithm of RANSAC may be used to remove outliers, i.e., outliers, from the plurality of point features, so as to obtain a plurality of point features after outliers are removed, and for convenience of distinction, the plurality of point features after outliers are taken as a plurality of target point features.
S104, combining the plurality of line features according to the distance between the endpoints of every two line features in the plurality of line features to obtain a plurality of first line features; and screening the first line features to obtain a plurality of target line features corresponding to the target monocular image.
Illustratively, in an embodiment of the present invention, a plurality of line features corresponding to a target monocular image may be added to a setAggregationIndicating that n line features are shared in the i-th frame image,Representing the nth line feature in the ith frame image. For every two line features in the plurality of line features corresponding to the target monocular image, assuming that the two line features are (l i,lj), merging the line features l i and l j according to the distance between the endpoints of the line feature l i and the line feature l j, and if only one endpoint of the line feature l i is close to the endpoint of the line feature l j, merging the line feature l i and the line feature l j into a longer line segment; if both end points of the feature l i are close to the line feature l j and the distance threshold between the two end points is smaller than the distance threshold, for example, 10px, the line feature l i and the line feature l j can be combined into a new line segment, so that a plurality of new line features can be obtained and recorded as a plurality of first line features, and by combining, redundant short line segments and line segments with relatively close distances are eliminated, so that the matching precision and the matching speed of the line features can be effectively improved, and the mismatching phenomenon caused by the short line segments can be reduced, so that the problem of difficult initialization process and the like is caused.
After the plurality of first line features are obtained through the merging process, the plurality of first line features may be further subjected to a screening process. For example, when the screening process is performed on the plurality of first line features, the screening process may be performed on the plurality of first line features according to the width and the height of the target monocular image, the number of the plurality of first line features, and the length factor, and the plurality of second line features may be determined from the plurality of first line features; screening the plurality of second line features according to the fact that the distance between the target monocular image and the monocular image of the immediately previous frame is smaller than a preset threshold value, and determining a plurality of third line features from the plurality of second features; and screening the plurality of third line features according to vanishing points corresponding to the plurality of third line features to obtain a plurality of target line features.
For example, in the embodiment of the present invention, when the screening process is performed on the plurality of first line features according to the width, the height, the number of the plurality of first line features and the length factor of the target monocular image, the following formula 1 may be referred to as follows:
Where W represents the width of the target monocular image, H represents the height of the target monocular image, α represents the length factor, and n represents the number of the plurality of first line features.
After the first line features are filtered according to the above formula 1 to obtain the second line features satisfying the above formula 1, the second line features may be filtered according to the distance between the target monocular image and the monocular image of the immediately previous frame being smaller than the preset threshold, and the third line features may be determined from the second line features. The value of the preset threshold can be set according to actual needs, and the embodiment of the invention is not particularly limited.
For example, when screening the plurality of third line features according to vanishing points corresponding to the plurality of third line features, the vanishing points corresponding to the plurality of third line features may be calculated first, for example, vanishing point detection may be performed by using a J-link algorithm, and vanishing points corresponding to the plurality of third line features may be calculated; screening the plurality of third line features according to the vanishing points corresponding to the plurality of third line features obtained through calculation to obtain a plurality of fourth line features; and removing abnormal line features from the fourth line features according to the Hamming distance and the angle between each fourth line feature and the line feature corresponding to the monocular image of the previous frame, so as to obtain a plurality of target line features. For example, a corresponding fourth line feature having a hamming distance greater than 30px, and/or an angle less than 0.1rad, may be determined as an outlier feature and the outlier feature may be culled.
After the plurality of target point features and the plurality of target line features corresponding to the target monocular image are acquired through the above-described S103 and S104, respectively, the following S105 may be performed:
S105, performing a positioning operation of the movable device based on the plurality of target point features, the plurality of target line features, and the inertial measurement unit data.
For example, when performing a positioning operation of the movable device according to the target point features, the target point features and the inertial measurement unit data, a state function corresponding to the movable device may be constructed first; wherein the state function includes a position, a velocity, and a direction of the inertial measurement unit data in the world coordinate system, an inverse depth of each of the plurality of target point features, and an orthogonal representation of each of the plurality of target point features; and optimizing the state function according to the inertia measurement unit residual error, the point characteristic residual error, the line characteristic residual error, the vanishing point residual error and the prior residual error to obtain an optimized target state function.
Illustratively, in an embodiment of the present invention, the state function corresponding to the constructed movable device may be shown in the following equation 2:
Wherein χ represents a state corresponding to the movable device, X i represents a state of the IMU corresponding to the capturing of the i-th monocular image, including a position, a speed, and a direction of the i-th inertial measurement unit data in the sliding window in the world coordinate system, an accelerometer bias, a gyroscope bias, λ represents an inverse depth of each of a plurality of target point features included in each of the monocular images in the sliding window, wherein the inverse depth of each of the plurality of target point features included in each of the monocular images in the sliding window is included, and O represents an orthogonal representation of each of the plurality of target point features included in each of the monocular images in the sliding window, wherein the orthogonal representation of each of the plurality of target point features included in each of the monocular images in the sliding window is included. n p,nm,nl represents the sum of key frames in the sliding window, the total number of point features and line features observed for all key frames, respectively.
It will be appreciated that the initialization may be performed first when constructing the corresponding state function of the removable device. For example, if the rotation profile is unknown, the rotation profile is estimated first; determining a plurality of target point features included in each frame of monocular image and pose of each target point feature under a camera coordinate system, calibrating IMU angular velocity bias by using constraint of camera rotation, and solving initialization parameters by using translation of the IMU: gravity, velocity, and scale factor, these initial values are used to guide subsequent VIO-based nonlinear optimization. Second, the initialization process requires alignment of the vision and IMU for frequency inconsistencies.
For example, when the state function is optimized according to the inertial measurement unit residual error, the point feature residual error, the line feature residual error, the vanishing point residual error and the prior residual error, the optimized target state function may be shown in the following formula 3:
where r 0 represents the a priori residual, Representing the residual error of the inertial measurement unit,The point feature residuals are represented and the point feature residuals,The line characteristic residual is represented by a graph,Representing vanishing point residuals, J p represents a priori jacobian matrix from the Hessian matrix obtained after previous optimization, where ρ p,ρl and ρ v satisfy Huber rules, P, L and V represent sets of point features, line features and vanishing points in the camera coordinate system, respectively.AndThe IMU, point, line and vanishing point measurement covariance matrices are represented, respectively.
The calculation of the line feature residuals can be seen in equation 4 below:
where l, K' and K represent the line features of the re-projection, the projection matrix of the line features and the internal parameters of the camera, respectively. K' and K are both identity matrices. (f x,fy) and (c x,cy) represent the focal length and principal point of the image, respectively. In the embodiment of the invention, the line segment of the re-projection is equal to the normal vector.
Thus, the line characteristic residual can be found in equation 5 below:
Where r l denotes the line characteristic residual, d denotes the distance between the two endpoints of the observed line segment and the re-projected line segment, and p s and p e are the endpoints of the line segment observed in the monocular image.
The calculation of vanishing point residuals can be seen from equation 6 below, where vanishing points are equivalent to the projection of points at infinity on a three-dimensional line.
Where V 0 represents a point in a three-dimensional line segment, p=kj [ i|0] represents a projection matrix of the camera, in the embodiment of the present invention, the vanishing point derived from the line segment is equivalent to a direction vector of the line segment, and the intersection point of V i and the image plane is an estimate of the vanishing point, so the vanishing point residual is expressed as follows:
Where r v denotes vanishing point residual, and p v denotes observation of vanishing point.
In combination with the above description, after the target state function is obtained through optimization, the target state function can be solved, and the initial position, the initial speed and the initial direction corresponding to the movable equipment are determined; and further determining initial pose information of the movable device according to the initial position, the initial speed and the initial direction. After the initial pose information of the movable equipment is determined, whether the target monocular image and the immediately previous frame monocular image are detected in a loop or not can be further detected, and under the condition that the target monocular image and the immediately previous frame monocular image are determined to have loop detection, the initial position information is corrected through the point characteristics and the pose information corresponding to the previous frame monocular image, so that the target pose information of the movable equipment is obtained; the target pose information is a positioning result of the movable equipment.
In the embodiment of the present invention, when determining whether loop detection exists between the target monocular image and the immediately previous frame monocular image, whether loop exists between the target monocular image and the immediately previous frame monocular image can be initially detected, and if loop exists in the initial detection, a plurality of candidate frame monocular images are determined; and performing feature matching on every two candidate frame monocular images in the plurality of candidate frame monocular images, and determining that loop detection exists between the target monocular image and the previous frame monocular image if the number of inner points of the two candidate frame monocular images is larger than the number threshold, so that loop detection can be accurately performed through double detection of initial detection and inner point number detection, and the accuracy of a loop detection result is improved. The number threshold may be set according to actual needs, where the embodiment of the present invention is not limited further for a specific value of the number threshold.
For example, when the loop is detected initially between the target monocular image and the immediately previous frame monocular image, the target point features corresponding to the target monocular image may be adopted, and in consideration of that in order to make the point features corresponding to the target monocular image sufficiently large, a preset number of point features may be additionally added on the basis of the corresponding target point features, so as to be used for the initial loop detection together, so that better loop detection can be better realized. In addition, in the embodiment of the invention, only the descriptors of all the point features used for feature retrieval can be reserved, and the monocular image is discarded to reduce the occupation of the memory.
For example, when feature matching is performed on every two candidate frame monocular images in the plurality of candidate frame monocular images, in the case that both the two candidate frame monocular images are 2D images, namely 2D-2D, an F matrix test can be performed by adopting a geometric constraint algorithm of RANSAC to realize feature matching; in the case where two candidate frame monocular images are 3D images, one being a 2D image, i.e. 3D-2D: pnP test can be performed by adopting a geometric constraint algorithm of RANSAC to realize feature matching, and the configuration can be specifically performed according to actual needs.
When it is determined that loop detection exists between the target monocular image and the immediately previous frame monocular image, the initial position information is corrected by the point feature and the pose information corresponding to the previous frame monocular image, for example, the point feature and the pose information corresponding to the previous frame monocular image may be used as constraint terms of the target state function, which may be shown in the following formula 8:
Wherein, Is the pose in loop detection, (p, m) represents the p-th point feature observed in the m-th frame monocular image under loop detection.
In combination with the above description, after the point feature and the pose information corresponding to the monocular image of the previous frame are taken as constraint terms of the target state function, a new position, a new speed and a new direction corresponding to the movable device can be calculated based on the above formula 8, and in the embodiment of the present invention, the new position can be recorded as a target position, the new speed can be recorded as a target speed, and the new direction can be recorded as a target direction; determining target pose information of the movable equipment according to the target position, the target speed and the target direction, and correcting the initial position information according to the target pose information to obtain the target pose information of the movable equipment; the target pose information is a positioning result of the movable equipment.
It can be seen that in the embodiment of the invention, the target monocular image and the inertial measurement unit data acquired by the movable equipment are acquired; extracting a plurality of point features and a plurality of line features corresponding to the target monocular image; removing abnormal points from the point features to obtain target point features corresponding to the target monocular image; combining the plurality of line features according to the distance between the endpoints of every two line features in the plurality of line features to obtain a plurality of first line features; screening the first line features to obtain a plurality of target line features corresponding to the target monocular image; and then, according to the target point characteristics, the target line characteristics and the inertial measurement unit data, positioning operation of the movable equipment is performed. In this way, the accuracy of the positioning result can be effectively improved by processing the point characteristics and the line characteristics respectively and executing the positioning operation of the movable equipment together according to the processed target point characteristics, target line characteristics and inertial measurement unit data.
The above embodiments describe the positioning method of the mobile device provided by the embodiment of the present invention in detail. In addition, the positioning method of the movable equipment provided by the embodiment of the invention can be verified through a robot operating system, and the accuracy and instantaneity of the positioning result are analyzed and proved.
In order to show the performance in a low-texture scene and a scene with larger illumination intensity variation, the mobile robot is respectively moved into a scene with darker illumination and a scene with lower illumination, and the positioning results provided by the embodiment of the invention are shown by combining the two scenes. When the positioning result is displayed, the positioning result is mainly displayed from two aspects, one aspect is positioning precision, and the other aspect is positioning instantaneity. When the positioning accuracy is shown, taking the example that the mobile robot moves to a scene with darker illumination, namely, insufficient illumination as an example, as shown in fig. 4 and fig. 5, fig. 4 is a track heat map positioned in the scene with insufficient illumination provided by the prior art, fig. 5 is a track heat map positioned in the scene with insufficient illumination provided by the embodiment of the invention, wherein the track heat map shown in fig. 4 is obtained based on OKVIS, the track heat map shown in fig. 5 is obtained based on the technical scheme provided by the embodiment of the invention, and it can be seen that in the scene with darker illumination intensity, the maximum track error obtained by OKVIS reaches 1.709m, and the maximum error rate obtained by adopting the technical scheme provided by the embodiment of the invention is only 0.152m, and the positioning accuracy is improved by 1024.342% compared with OKVIS.
Taking the movement of the mobile robot into the low-texture scene as an example, as shown in fig. 6 and fig. 7, fig. 6 is a track heat map positioned in the low-texture scene provided by the prior art, fig. 7 is a track heat map positioned in the low-texture scene provided by the embodiment of the invention, wherein the track heat map shown in fig. 6 is obtained based on OKVIS, and the track heat map shown in fig. 7 is obtained based on the technical scheme provided by the embodiment of the invention, it can be seen that, in the scene with darker illumination intensity, the maximum track error obtained by OKVIS reaches 0.704m, and the maximum error rate obtained by adopting the technical scheme provided by the embodiment of the invention is only 0.092m, and the positioning accuracy is improved by 665.217% compared with OKVIS. Furthermore, it is clear that the rapid rotation and movement of the camera has a significant impact on estimating its direction, and that light ray variations are particularly challenging to track the dotted line features. The positioning method provided by the embodiment of the invention can meet the requirements of complex environments and has good positioning precision, and can provide good pose estimation for the mobile robot.
In the case of exhibiting positioning instantaneity, taking as an example the average running time of each module on mh_05 sequence, see table 1 below, where VPL-VINS represents the positioning method provided by the embodiment of the present invention, and VINS-Mono represents the positioning method provided by the prior art.
TABLE 1
As can be seen from table 1, the front endpoint line feature extraction and matching operation time is shorter, and the detection efficiency is higher. Compared with VINS-Mono, the method has the advantages that the line feature extraction and tracking time is short, and the point feature extraction and matching based on ORB achieve high efficiency. The back end of the VPL-VINS is time consuming compared to the lightweight front end. Therefore, the positioning method provided by the invention can meet the real-time requirement of SLAM in a complex environment.
The positioning device of the movable equipment provided by the invention is described below, and the positioning device of the movable equipment described below and the positioning method of the movable equipment described above can be correspondingly referred to each other.
Fig. 8 is a schematic structural diagram of a positioning device for a mobile device according to an embodiment of the present invention, for example, referring to fig. 8, the positioning device 80 for a mobile device may include:
An acquiring unit 801, configured to acquire a target monocular image and inertial measurement unit data acquired by a mobile device, respectively.
The extracting unit 802 is configured to extract a plurality of point features and a plurality of line features corresponding to the target monocular image.
And a rejecting unit 803, configured to reject the outlier from the plurality of point features, so as to obtain a plurality of target point features corresponding to the target monocular image.
A processing unit 804, configured to combine the plurality of line features according to the distance between the endpoints of every two line features in the plurality of line features to obtain a plurality of first line features; and screening the first line features to obtain a plurality of target line features corresponding to the target monocular image.
An execution unit 805 for executing a positioning operation of the movable device based on the plurality of target point features, the plurality of target line features, and the inertial measurement unit data.
Optionally, the extracting unit 802 is specifically configured to perform a blocking process on the target monocular image to obtain a plurality of image blocks corresponding to the target monocular image; and respectively extracting line characteristics in each image block to obtain a plurality of line characteristics corresponding to the target monocular image.
Optionally, the extracting unit 802 is specifically configured to perform a screening process on the plurality of first line features according to the width, the height, the number of the plurality of first line features and the length factor of the target monocular image, and determine a plurality of second line features from the plurality of first features; screening the plurality of second line features according to the fact that the distance between the target monocular image and the monocular image of the immediately previous frame is smaller than a preset threshold value, and determining a plurality of third line features from the plurality of second features; and screening the plurality of third line features according to vanishing points corresponding to the plurality of third line features to obtain a plurality of target line features.
Optionally, the extracting unit 802 is specifically configured to perform screening processing on the plurality of third line features according to vanishing points corresponding to the plurality of third line features, to obtain a plurality of fourth line features; and removing abnormal line features from the fourth line features according to the Hamming distance and the angle between each fourth line feature and the line feature corresponding to the monocular image of the previous frame, so as to obtain a plurality of target line features.
Optionally, the execution unit 805 is specifically configured to construct a state function corresponding to the mobile device; wherein the state function includes a position, a velocity, and a direction of the inertial measurement unit data in the world coordinate system, an inverse depth of each of the plurality of target point features, and an orthogonal representation of each of the plurality of target point features; optimizing the state function according to the inertia measurement unit residual error, the point characteristic residual error, the line characteristic residual error, the vanishing point residual error and the prior residual error to obtain an optimized target state function; determining an initial position, an initial speed and an initial direction corresponding to the movable equipment based on the target state function; determining initial pose information of the movable equipment according to the initial position, the initial speed and the initial direction; under the condition that the loop detection exists between the target monocular image and the monocular image of the immediately previous frame, correcting the initial position information through the point characteristics and the pose information corresponding to the monocular image of the previous frame to obtain target pose information of the movable equipment; the target pose information is a positioning result of the movable equipment.
Optionally, the execution unit 805 is specifically configured to determine, using the point feature and pose information corresponding to the monocular image of the previous frame as constraint items of the target state function, a target position, a target speed, and a target direction corresponding to the movable device; determining target pose information of the movable equipment according to the target position, the target speed and the target direction; and correcting the initial position information according to the target pose information.
Optionally, the positioning device 80 of the movable apparatus further comprises a detection unit.
The detection unit is used for initially detecting whether loop exists between the target monocular image and the monocular image of the immediately previous frame, and if loop exists in the initial detection, determining a plurality of candidate monocular images; and performing feature matching on every two candidate frame monocular images in the plurality of candidate frame monocular images, and if the number of the inner points of the two candidate frame monocular images is larger than a number threshold value, determining that loop detection exists between the target monocular image and the previous frame monocular image.
The positioning device 80 for a mobile device according to the embodiment of the present invention may execute the technical scheme of the positioning method for a mobile device in any of the foregoing embodiments, and the implementation principle and beneficial effects of the positioning method for a mobile device are similar to those of the positioning method for a mobile device, which can be seen, and will not be described herein.
Fig. 9 is a schematic physical structure diagram of an electronic device according to an embodiment of the present invention, where, as shown in fig. 9, the electronic device may include: processor 910, communication interface (Communications Interface) 920, memory 930, and communication bus 940, wherein processor 910, communication interface 920, and memory 930 communicate with each other via communication bus 940. Processor 910 may invoke logic instructions in memory 930 to perform a method of positioning a removable device, the method comprising: respectively acquiring a target monocular image and inertial measurement unit data acquired by movable equipment; extracting a plurality of point features and a plurality of line features corresponding to a target monocular image; removing abnormal points from the point features to obtain target point features corresponding to the target monocular image; combining the plurality of line features according to the distance between the endpoints of every two line features in the plurality of line features to obtain a plurality of first line features; screening the first line features to obtain a plurality of target line features corresponding to the target monocular image; a positioning operation of the movable device is performed based on the plurality of target point features, the plurality of target line features, and the inertial measurement unit data.
Further, the logic instructions in the memory 930 described above may be implemented in the form of software functional units and may be stored in a computer-readable storage medium when sold or used as a stand-alone product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
In another aspect, the present invention also provides a computer program product comprising a computer program, the computer program being storable on a non-transitory computer readable storage medium, the computer program, when executed by a processor, being capable of performing the method of locating a mobile device provided by the methods described above, the method comprising: respectively acquiring a target monocular image and inertial measurement unit data acquired by movable equipment; extracting a plurality of point features and a plurality of line features corresponding to a target monocular image; removing abnormal points from the point features to obtain target point features corresponding to the target monocular image; combining the plurality of line features according to the distance between the endpoints of every two line features in the plurality of line features to obtain a plurality of first line features; screening the first line features to obtain a plurality of target line features corresponding to the target monocular image; a positioning operation of the movable device is performed based on the plurality of target point features, the plurality of target line features, and the inertial measurement unit data.
In yet another aspect, the present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, is implemented to perform a method of positioning a mobile device provided by the above methods, the method comprising: respectively acquiring a target monocular image and inertial measurement unit data acquired by movable equipment; extracting a plurality of point features and a plurality of line features corresponding to a target monocular image; removing abnormal points from the point features to obtain target point features corresponding to the target monocular image; combining the plurality of line features according to the distance between the endpoints of every two line features in the plurality of line features to obtain a plurality of first line features; screening the first line features to obtain a plurality of target line features corresponding to the target monocular image; a positioning operation of the movable device is performed based on the plurality of target point features, the plurality of target line features, and the inertial measurement unit data.
The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. A method of locating a mobile device, comprising:
Respectively acquiring a target monocular image and inertial measurement unit data acquired by movable equipment;
extracting a plurality of point features and a plurality of line features corresponding to the target monocular image;
Removing abnormal points from the plurality of point features to obtain a plurality of target point features corresponding to the target monocular image;
Combining the plurality of line features according to the distance between the endpoints of every two line features in the plurality of line features to obtain a plurality of first line features; screening the first line features to obtain a plurality of target line features corresponding to the target monocular image;
Performing a positioning operation of the movable device based on the plurality of target point features, the plurality of target line features, and the inertial measurement unit data;
the screening processing is performed on the plurality of first line features to obtain a plurality of target line features corresponding to the target monocular image, including:
Screening the first line features according to the width and the height of the target monocular image, the number of the first line features and the length factor, and determining a plurality of second line features from the first line features;
screening the plurality of second line features according to the fact that the distance between the target monocular image and the monocular image of the immediately previous frame is smaller than a preset threshold value, and determining a plurality of third line features from the plurality of second line features;
And screening the plurality of third line features according to vanishing points corresponding to the plurality of third line features to obtain the plurality of target line features.
2. The positioning method of a mobile device according to claim 1, wherein extracting a plurality of line features corresponding to the target monocular image includes:
performing blocking processing on the target monocular image to obtain a plurality of image blocks corresponding to the target monocular image;
and respectively extracting line characteristics in each image block to obtain a plurality of line characteristics corresponding to the target monocular image.
3. The positioning method of a mobile device according to claim 1, wherein the filtering the plurality of third line features according to vanishing points corresponding to the plurality of third line features to obtain the plurality of target line features includes:
screening the plurality of third line features according to vanishing points corresponding to the plurality of third line features to obtain a plurality of fourth line features;
And removing abnormal line features from the fourth line features according to the Hamming distance and the angle between each fourth line feature and the line feature corresponding to the monocular image of the previous frame, so as to obtain the target line features.
4. The positioning method of a movable apparatus according to claim 1 or 2, wherein the performing the positioning operation of the movable apparatus based on the plurality of target point features, the plurality of target line features, and the inertial measurement unit data includes:
Constructing a state function corresponding to the movable equipment; wherein the state function includes a position, a velocity, and a direction of the inertial measurement unit data in a world coordinate system, an inverse depth of each of the plurality of target point features, and an orthogonal representation of each of the plurality of target point features;
Optimizing the state function according to the inertia measurement unit residual error, the point characteristic residual error, the line characteristic residual error, the vanishing point residual error and the prior residual error to obtain an optimized target state function;
Determining an initial position, an initial speed and an initial direction corresponding to the movable equipment based on the target state function; determining initial pose information of the movable equipment according to the initial position, the initial speed and the initial direction;
under the condition that loop detection exists between the target monocular image and a immediately previous frame monocular image, correcting the initial position information through point characteristics and pose information corresponding to the previous frame monocular image to obtain target pose information of the movable equipment; the target pose information is a positioning result of the movable equipment.
5. The method for locating a mobile device according to claim 4, wherein correcting the initial position information by the point feature and pose information corresponding to the previous monocular image includes:
Taking point characteristics and pose information corresponding to the monocular image of the previous frame as constraint items of the target state function, and determining a target position, a target speed and a target direction corresponding to the movable equipment; determining target pose information of the movable equipment according to the target position, the target speed and the target direction;
and correcting the initial position information according to the target pose information.
6. The method of locating a mobile device according to claim 4, wherein the method further comprises:
Initially detecting whether loop exists between the target monocular image and the monocular image of the immediately previous frame, and if loop exists in the initial detection, determining a plurality of candidate monocular images;
And performing feature matching on every two candidate frame monocular images in the plurality of candidate frame monocular images, and determining that loop detection exists between the target monocular image and the previous frame monocular image if the number of inner points of the two candidate frame monocular images is larger than a number threshold value.
7. A positioning apparatus for a mobile device, comprising:
the acquisition unit is used for respectively acquiring the target monocular image acquired by the movable equipment and the inertial measurement unit data;
the extraction unit is used for extracting a plurality of point features and a plurality of line features corresponding to the target monocular image;
A rejecting unit, configured to reject abnormal points from the plurality of point features, to obtain a plurality of target point features corresponding to the target monocular image;
The processing unit is used for combining the plurality of line features according to the distance between the endpoints of every two line features in the plurality of line features to obtain a plurality of first line features; screening the first line features to obtain a plurality of target line features corresponding to the target monocular image;
An execution unit configured to execute a positioning operation of the movable apparatus based on the plurality of target point features, the plurality of target line features, and the inertial measurement unit data;
the screening processing is performed on the plurality of first line features to obtain a plurality of target line features corresponding to the target monocular image, including:
Screening the first line features according to the width and the height of the target monocular image, the number of the first line features and the length factor, and determining a plurality of second line features from the first line features;
screening the plurality of second line features according to the fact that the distance between the target monocular image and the monocular image of the immediately previous frame is smaller than a preset threshold value, and determining a plurality of third line features from the plurality of second line features;
And screening the plurality of third line features according to vanishing points corresponding to the plurality of third line features to obtain the plurality of target line features.
8. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the positioning method of the removable device according to any of claims 1 to 6 when executing the program.
9. A non-transitory computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when executed by a processor, implements a positioning method of a removable device according to any of claims 1 to 6.
10. A computer program product comprising a computer program, characterized in that the computer program, when executed by a processor, implements a positioning method of a mobile device according to any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211146449.XA CN115752489B (en) | 2022-09-20 | 2022-09-20 | Positioning method and device of movable equipment and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211146449.XA CN115752489B (en) | 2022-09-20 | 2022-09-20 | Positioning method and device of movable equipment and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115752489A CN115752489A (en) | 2023-03-07 |
| CN115752489B true CN115752489B (en) | 2024-09-06 |
Family
ID=85350506
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211146449.XA Active CN115752489B (en) | 2022-09-20 | 2022-09-20 | Positioning method and device of movable equipment and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115752489B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116295425A (en) * | 2023-03-22 | 2023-06-23 | 北京集度科技有限公司 | Device, vehicle, method and program product for determining positioning information |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113720323A (en) * | 2021-07-30 | 2021-11-30 | 安徽大学 | Monocular vision through-guidance SLAM method and device based on dotted line feature fusion |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10872435B2 (en) * | 2018-10-19 | 2020-12-22 | Here Global B.V. | Method and apparatus for iteratively establishing object position |
| CN114485640A (en) * | 2022-01-20 | 2022-05-13 | 河北工业职业技术学院 | Monocular visual-inertial synchronous positioning and mapping method and system based on point and line features |
| CN115031735B (en) * | 2022-05-20 | 2025-08-12 | 北京理工大学 | Pose estimation method of monocular vision inertial odometer system based on structural features |
-
2022
- 2022-09-20 CN CN202211146449.XA patent/CN115752489B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113720323A (en) * | 2021-07-30 | 2021-11-30 | 安徽大学 | Monocular vision through-guidance SLAM method and device based on dotted line feature fusion |
Non-Patent Citations (1)
| Title |
|---|
| 改进点线特征的双目视觉SLAM算法;林利蒙 等;《计算机测量与控制》;20190930;第27卷(第9期);第156-162页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115752489A (en) | 2023-03-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10133279B2 (en) | Apparatus of updating key frame of mobile robot and method thereof | |
| US10275649B2 (en) | Apparatus of recognizing position of mobile robot using direct tracking and method thereof | |
| KR101725060B1 (en) | Apparatus for recognizing location mobile robot using key point based on gradient and method thereof | |
| US10399228B2 (en) | Apparatus for recognizing position of mobile robot using edge based refinement and method thereof | |
| US20200218929A1 (en) | Visual slam method and apparatus based on point and line features | |
| US10307910B2 (en) | Apparatus of recognizing position of mobile robot using search based correlative matching and method thereof | |
| EP3680809A1 (en) | Visual slam method and apparatus based on point and line characteristic | |
| JP6095018B2 (en) | Detection and tracking of moving objects | |
| US8238612B2 (en) | Method and apparatus for vision based motion determination | |
| US9672634B2 (en) | System and a method for tracking objects | |
| CN109636828A (en) | Object tracking methods and device based on video image | |
| CN119124215A (en) | A method, device, equipment and medium for optimizing visual inertial odometer of unmanned aerial vehicle | |
| CN115752489B (en) | Positioning method and device of movable equipment and electronic equipment | |
| Vatavu et al. | Real-time modeling of dynamic environments in traffic scenarios using a stereo-vision system | |
| CN119149765A (en) | Indoor vision positioning method and positioning system based on shielding and clearing algorithm | |
| CN112313707B (en) | Tracking methods and movable platforms | |
| KR101828710B1 (en) | Apparatus and method for object occlusion detection | |
| JP4836065B2 (en) | Edge tracking method and computer program therefor | |
| Tombari et al. | Stereo for robots: quantitative evaluation of efficient and low-memory dense stereo algorithms | |
| WO2023281647A1 (en) | Machine learning device | |
| WO2024148551A1 (en) | Apparatus and methods for tracking features within images | |
| US12296488B2 (en) | Method and system to detect and estimate dynamic obstacles using RGB-D sensors for robot navigation | |
| Engler et al. | Recursive 3D scene estimation with multiple camera pairs | |
| Zhou et al. | Dynamic Scene Vision SLAM Based on Target Detection in RGB-D Images | |
| Westaway | An empirical assessment of real-time progressive stereo reconstruction |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |