CN113218404B - A method for determining road data errors, related methods and devices - Google Patents
A method for determining road data errors, related methods and devicesInfo
- Publication number
- CN113218404B CN113218404B CN202010071495.2A CN202010071495A CN113218404B CN 113218404 B CN113218404 B CN 113218404B CN 202010071495 A CN202010071495 A CN 202010071495A CN 113218404 B CN113218404 B CN 113218404B
- Authority
- CN
- China
- Prior art keywords
- road
- matched
- probability
- track
- determining
- 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
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/28—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network with correlation of data from several navigational instruments
- G01C21/30—Map- or contour-matching
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
Landscapes
- Engineering & Computer Science (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Automation & Control Theory (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a method for determining road data errors, a related method and a related device. The method comprises the steps of obtaining a driving track represented by a series of track points meeting quality standards, obtaining a road to be matched in a preset distance range around the driving track, wherein the road to be matched comprises a manufacturing attribute and a virtual attribute, the value of the virtual attribute is opposite to that of the manufacturing attribute, determining first projection probability and first transition probability of each track point in the driving track to the road to be matched based on the manufacturing attribute of the road to be matched to obtain first matching probability of the driving track to the road to be matched, determining second projection probability and second transition probability of each track point in the driving track to the road to be matched to obtain second matching probability of the driving track to the road to be matched based on the virtual attribute of the road to be matched, and determining that the manufacturing attribute of the road to be matched is wrong when the second matching probability is larger than the first matching probability. A solution is provided to accurately find erroneous road data.
Description
Technical Field
The present invention relates to the field of geographic information technologies, and in particular, to a method for determining a road data error, and a related method and apparatus.
Background
In the field of geographic information technology, the integrity and correctness of road data are very important, and once the road data are wrong, the business based on the road data can be wrong. For example, an erroneous direction of traffic on the road may cause an error in the result of navigation route planning. Therefore, accurately finding erroneous road data is a technical problem that needs to be solved by those skilled in the art.
Disclosure of Invention
The present invention has been made in view of the above-mentioned problems, and it is an object of the present invention to provide a method, related method and apparatus for determining road data errors that overcomes or at least partially solves the above-mentioned problems.
In a first aspect, an embodiment of the present invention provides a method for determining a road data error, including the following steps:
acquiring a driving track represented by a series of track points meeting quality standards, wherein the quality standards comprise a consistency standard, a volatility standard and a quantity standard of the track points;
Obtaining a road to be matched within a preset distance range around the driving track, wherein the road to be matched comprises a manufacturing attribute and a virtual attribute, and the value of the virtual attribute is opposite to that of the manufacturing attribute;
Determining a first projection probability and a first transition probability of each track point in the driving track to the road to be matched according to a preset projection probability and a transition probability algorithm based on the manufacturing attribute of the road to be matched, and obtaining a first matching probability of the driving track to the road to be matched based on the first projection probability and the first transition probability;
Determining a second projection probability and a second transition probability of each track point in the driving track to the road to be matched based on the virtual attribute of the road to be matched, and obtaining a second matching probability of the driving track to the road to be matched based on the second projection probability and the second transition probability;
and when the second matching probability of the driving track to the road to be matched is larger than the first matching probability, determining that the production attribute of the road to be matched is wrong.
In a second aspect, an embodiment of the present invention provides a method for determining a road data error type, including the following steps:
Determining whether the manufacturing attribute of the road to be matched of the driving track is wrong;
if yes, determining the error type of the road to be matched according to the virtual attribute of the road to be matched;
the step of determining whether the production attribute of the road to be matched of the driving track is wrong or not adopts the road data wrong determination method.
In a third aspect, an embodiment of the present invention provides a device for determining a road data error, including:
The track extraction module is used for obtaining the driving track represented by a series of track points meeting the quality standard, wherein the quality standard comprises the consistency standard, the volatility standard and the quantity standard of the track points;
The road obtaining module is used for obtaining a road to be matched in a preset distance range around the travelling path, the road to be matched comprises a manufacturing attribute and a virtual attribute, and the value of the virtual attribute is opposite to that of the manufacturing attribute;
The first matching probability determining module is used for determining a first projection probability and a first transition probability of each track point in the driving track to the road to be matched according to a preset projection probability and a transition probability algorithm based on the manufacturing attribute of the road to be matched, and obtaining a first matching probability of the driving track to the road to be matched based on the first projection probability and the first transition probability;
The second matching probability determining module is used for determining second projection probability and second transition probability of each track point in the driving track to the road to be matched based on the virtual attribute of the road to be matched, and obtaining second matching probability of the driving track to the road to be matched based on the second projection probability and the second transition probability;
and the road data error determining module is used for comparing the first matching probability obtained by the first matching probability determining module with the second matching probability obtained by the second matching probability determining module, and determining that the manufacturing attribute of the road to be matched is wrong when the second matching probability is larger than the first matching probability.
In a fourth aspect, an embodiment of the present invention provides a device for determining a road data error type, including:
the data error judging module is used for determining whether the manufacturing attribute of the road to be matched of the driving track is wrong;
The type error determining module is used for determining the error type of the road to be matched according to the virtual attribute of the road to be matched when the manufacturing attribute of the road to be matched of the driving track is wrong;
the step of determining whether the production attribute of the road to be matched of the driving track is wrong or not adopts the road data wrong determination method.
In a fifth aspect, embodiments of the present invention provide a computer-readable storage medium having stored thereon computer instructions that, when executed by a processor, implement the above-described road error determination method, or implement the above-described road data error type determination method.
In a sixth aspect, an embodiment of the present invention provides a server, including a processor and a memory for storing a command executable by the processor, where the processor is configured to perform the above-described road error determination method or the above-described road data error type determination method.
The technical scheme provided by the embodiment of the invention has the beneficial effects that at least:
According to the method for determining the road data errors, which is provided by the embodiment of the invention, the road to be matched in the peripheral preset distance range of the road is obtained by obtaining the road path represented by a series of track points meeting the quality standard, when the track is matched, the corresponding virtual attribute is introduced into the manufacturing attribute corresponding to the road to be matched, the first matching probability and the second matching probability of the road to be matched corresponding to the road to be matched are respectively obtained according to the manufacturing attribute and the virtual attribute, and the first matching probability and the second matching probability are compared, and if the second matching probability is larger than the first matching probability, the road data errors are represented. The embodiment of the invention utilizes the vehicle track meeting the quality standard to measure the correctness of the road data of the road to be matched, introduces the virtual attribute of the road to be matched to assume various possible errors of the road to be matched in the process of road matching, further can determine whether the manufacturing attribute of the road to be matched is wrong or not through comparison of the matching results, provides a solution for accurately finding the road data with errors, provides a good basis for subsequent correction of the road data, and ensures accurate realization of various services based on the road data.
The method for determining the road data error type provided by the embodiment of the invention not only can realize accurate judgment of whether the road data is wrong, but also can further accurately determine the road data error type corresponding to the road to be matched according to the determined virtual attribute value of the road to be matched when the production attribute of the road to be matched is wrong, and has the advantages of simple and easy realization, and convenience and higher efficiency for correcting the data error of the road.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims thereof as well as the appended drawings.
The technical scheme of the invention is further described in detail through the drawings and the embodiments.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a flowchart of a method for determining road data errors in an embodiment of the present invention;
FIG. 2 is a flowchart of a method for extracting a vehicle track meeting quality criteria in an embodiment of the present invention;
FIG. 3 is a schematic diagram of a road network error type according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a track matching track and a road in a road network according to an embodiment of the present invention;
FIG. 5 is a flowchart of a method for determining a road data error type according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of a road data error determining apparatus according to an embodiment of the present invention;
Fig. 7 is a schematic structural diagram of a road data error type determining apparatus according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
The embodiment of the invention provides a method for determining road data errors, which aims at the problems existing in the prior art, and the flow of the method is shown by referring to fig. 1, and comprises the following steps:
s11, acquiring a driving track represented by a series of track points meeting quality standards, wherein the quality standards comprise continuity standards, volatility standards and quantity standards of the track points;
s12, acquiring a road to be matched within a preset distance range around the driving track, wherein the road to be matched comprises a manufacturing attribute and a virtual attribute, and the value of the virtual attribute is opposite to that of the manufacturing attribute;
The road to be matched comprises a point coordinate sequence of road data, a road passing direction and a road connection relation. The threshold value of the preset distance range may be set according to practical situations, which is not limited in the embodiment of the present invention.
S13, determining a first projection probability and a first transition probability of each track point in the driving track to the road to be matched according to a preset projection probability and a transition probability algorithm based on the manufacturing attribute of the road to be matched, and obtaining a first matching probability of the driving track to the road to be matched based on the first projection probability and the first transition probability;
S14, determining a second projection probability and a second transition probability of each track point in the driving track to the road to be matched based on the virtual attribute of the road to be matched, and obtaining a second matching probability of the driving track to the road to be matched based on the second projection probability and the second transition probability;
and S15, determining that the production attribute of the road to be matched is wrong when the second matching probability of the driving locus and the road to be matched is larger than the first matching probability.
According to the method for determining the road data errors, which is provided by the embodiment of the invention, the road to be matched in the peripheral preset distance range of the road is obtained by obtaining the road path represented by a series of track points meeting the quality standard, when the track is matched, the corresponding virtual attribute is introduced into the manufacturing attribute corresponding to the road to be matched, the first matching probability and the second matching probability of the road to be matched corresponding to the road to be matched are respectively obtained according to the manufacturing attribute and the virtual attribute, and the first matching probability and the second matching probability are compared, and if the second matching probability is larger than the first matching probability, the road data errors are represented.
The embodiment of the invention utilizes the vehicle track meeting the quality standard to measure the correctness of the road data of the road to be matched, introduces the virtual attribute of the road to be matched to assume various possible errors of the road to be matched in the process of road matching, further can determine whether the manufacturing attribute of the road to be matched is wrong or not through comparison of the matching results, provides a solution for accurately finding the road data with errors, provides a good basis for subsequent correction of the road data, and ensures accurate realization of various services based on the road data.
The inventor of the present invention found that the prior art scheme mainly uses a track matching method based on an HMM model, and the precondition of the method is that the road of the road network is supposed to be right, and the running track may be wrong, so focusing on how to provide an optimal matching result, rather than how to determine road data errors and repair the road data. After the matching result of the driving track and the road is obtained, the road data error problem can only be deduced after the obtained matching result. The accuracy and efficiency of the processing of road data errors is not high. The inventor of the invention obtains the vehicle track represented by a series of track points with quality meeting the quality standard by processing the original vehicle track, and the vehicle track meeting the quality standard has good continuity, small fluctuation and the number of track points meeting the track matching requirement, thereby being beneficial to accurately judging whether the road in the road network has road data errors. Therefore, before the road data error judgment is performed, the problem of how to acquire the vehicle track meeting the quality standard needs to be solved in advance.
In one embodiment, in the step S11, the vehicle track represented by the series of track points satisfying the quality standard may be manually selected from the original vehicle tracks by an operator according to the quality standard, or may be obtained by processing the original vehicle tracks according to the quality standard by a machine through a set standard value or the like.
As a specific implementation manner of the embodiment of the present invention, referring to fig. 2, a track represented by a series of track points with quality satisfying a quality standard is obtained, which may be specifically implemented by the following steps:
S21, segmenting the original driving track at two adjacent track points which do not meet the consistency standard to obtain at least one segmented track meeting the consistency standard;
specifically, whether two adjacent track points in the original driving track meet a preset continuity standard or not can be judged by, for example, the following modes:
Judging whether the distance between two adjacent track points is greater than a set distance threshold value according to the coordinates of the track points in the original track, and/or,
Judging whether the observation time of two adjacent track points is greater than a set time threshold according to the observation time of the track points in the original driving track;
if yes, determining that the two adjacent track points do not meet the continuity standard.
Because each track point of the original driving track has four-dimensional information of longitude, latitude, speed and driving direction and observation time information of the track point, the distance between two adjacent track points can be determined according to the four-dimensional information of the track point, the observation time interval between the two adjacent track points can be determined according to the observation time information of the track point, when the track is segmented, a distance threshold value or a time threshold value is set, and if the distance between the two adjacent track points is smaller than or equal to the distance threshold value or the observation time interval is smaller than or equal to the time threshold value, the two track points are indicated to meet the continuity standard.
S22, judging whether the number of track points in each segmented track meets the number standard, and discarding segmented tracks of which the number of track points does not meet the number standard;
If the number of track points in the track after segmentation is smaller than the preset number threshold, the track points are indicated to be too small, the information contained in the track is less, the effect of the track on the subsequent road data erroneous determination is very small, and the number of the track points is not satisfied, so that the track with too small number of the track points needs to be discarded.
S23, screening out track fragments which do not meet the volatility standard aiming at each segmented track to obtain at least one screened track;
Whether the track after the segmentation meets the volatility standard can be judged by the following way:
Traversing each segmented track by using a preset number of point sequence windows in a convolutional network (Convolutional Neural Networks, CNN) model obtained through training, and determining the probability that the volatility of a track segment formed by each preset number of track points in the segmented track meets quality qualification;
Judging whether the probability is larger than a set probability threshold, if so, determining that the track segments formed by the track points with the preset number are track segments meeting the volatility standard, and if not, determining that the track segments formed by the track points with the preset number are track segments not meeting the volatility standard, so that the track segments not meeting the quality standard are required to be discarded.
For example, a segmented track has 50 track points, a sliding window of a 10 by 4 point sequence (namely, 10 points comprising four-dimensional information of longitude, latitude, speed and running direction) is used for traversing the segmented track, namely, a first sliding serial port is arranged on the 1 st to 10 th track points, a second sliding window is arranged on the 2 nd to 11 th track points, and the like, so that the probability that the volatility of a track segment formed by the adjacent 10 track points meets the requirement of a volatility standard is output, and whether the probability is larger than a set probability threshold value is judged. Assuming that the probability that the fluctuation of the track segment formed by the 21 st to 30 th track points is smaller than the set threshold, determining the track segment as a track segment with unqualified quality, and screening out the track segment, thereby obtaining two tracks formed by the 1 st to 20 th track points and a track formed by the 31 st to 50 th track points.
S24, determining that the track with the number of track points meeting the number standard in at least one screened track is a driving track meeting the quality standard.
In the step S24, whether the number of track points in one screened track meets the number standard can be judged by judging whether the number of track points in the screened track exceeds a preset number threshold, if yes, the screened track is determined to be the driving track meeting the quality standard, and if no, the screened track is discarded.
After the driving track meeting the quality standard is obtained, the driving track meeting the quality standard can be ensured to be correct in the process of matching the driving track with the road, so that whether at least one similar road data error exists on the road in the circuit breaking network is judged. According to the relation between the driving track meeting the quality standard and the road in the road network, at least one type of road data error is assumed to exist on the road of the road network, and the real attribute (also called the production attribute, namely various attributes of the road existing in the road network) and the virtual attribute (namely the virtual attribute corresponding to the assumed data error) respectively representing the road to be matched are introduced into the road data.
In general, errors including one or more of a road traffic direction error, a road topology connection error, and a road loss error may occur in road data of a road network. The road traffic direction is wrong, for example, a road which can pass in two directions actually is a road which can pass in two directions, but the road data is only made into a one-way traffic road, the road topology is wrong, for example, a connection relationship exists between two adjacent roads in the actual road, but the topology of the road data is made into a state that the two adjacent roads are not connected, the road is wrong, for example, a road exists in the actual road network, but the road data is not made.
In order to implement the method for determining the road data error provided by the embodiment of the present invention, in the embodiment of the present invention, the manufacturing attribute and the virtual attribute of the road to be matched may include any one or a combination of several aspects of attributes, that is, one or a combination of more of a road traffic direction, a road topology connection relationship, and a road loss, where:
If the value of the road traffic direction in the production attribute indicates that the road traffic direction is unidirectional, the value of the road traffic direction in the virtual attribute indicates that the road traffic direction is bidirectional, or if the value of the road traffic direction in the production attribute indicates that the road traffic direction is bidirectional, the value of the road traffic direction in the virtual attribute indicates that the road traffic direction is unidirectional;
If the value of the road topology connection relationship in the production attribute indicates that the road topology is not connected, the value of the road topology connection relationship in the virtual attribute indicates that the road topology is connected, or if the value of the road topology connection relationship in the production attribute indicates that the road topology is connected, the value of the road topology connection relationship in the virtual attribute indicates that the road topology is not connected;
if the value of the road missing in the production attribute indicates no road, the value of the road missing in the virtual attribute indicates a road, or if the value of the road missing in the production attribute indicates a road, the value of the road missing in the virtual attribute indicates no road.
Of course, the embodiments of the present invention are not limited to the several ways listed above.
In one embodiment, the preset projection probability and transition probability algorithm in step S13 may be, for example, a Viterbi algorithm based on a hidden markov model (Hidden Markov Model, HMM).
And matching the vehicle track meeting the quality standard with the roads adjacent to the vehicle track in the road network, obtaining a first matching probability according to the manufacturing attribute of the road to be matched, and determining which roads to be matched are on which the track points of the vehicle track meeting the quality standard fall, in other words, the vehicle track is matched with each road to be matched of the road network. For example, the first projection probability of a track point and a road to be matched can be obtained by the following formula (1):
Wherein Z t is a track point of the track meeting the quality standard, r i is a projection point of the track meeting the quality standard, which is vertically projected onto the road to be matched, x t,i is the road to be matched, |z t-xt,i|great circle represents the distance between the track point Z t and the road to be matched, and sigma z is a constant;
obtaining a first transition probability between a road to be matched corresponding to one track point and a road to be matched corresponding to the next track point through the following formula (2):
Wherein d t is a difference value between a distance between the track point Z t and the next track point Z t+1 and a distance between the road to be matched x t,i corresponding to the track point Z t and the road to be matched x t+1,j corresponding to the next track point Z t+1;
In the above-mentioned formula (2), Beta is a constant.
In one embodiment, in the step S13, the first probability of matching the vehicle track with the road to be matched is obtained based on the first projection probability and the first transition probability of each track point in the vehicle track with the road to be matched, for example, by respectively determining the product of the first projection probability of each track point in the vehicle track with the road to be matched and the product of the first transition probability of each track point in the vehicle track with the road to be matched, and fusing the product of the first projection probability and the product of the first transition probability corresponding to the obtained vehicle track to finally obtain the first probability of matching the vehicle track with the road to be matched. The fusion method may be various, for example, the product of the first projection probability and the first transition probability corresponding to the driving track may be weighted, so as to obtain the weighted maximum probability, i.e. the first matching probability. The weights of the product of the first projection probability and the product of the first transition probability corresponding to the driving track can be selected according to experience, for example. The embodiment of the invention is not limited.
In one embodiment, in the step S14, based on the virtual attribute of the road to be matched, a second projection probability and a second transition probability of each track point in the driving track to the road to be matched are determined, which is specifically implemented by the following steps:
And determining a second projection probability and a second transition probability of the first track point and the road to be matched according to a preset projection probability and transition probability algorithm based on the virtual attribute of the road to be matched, and determining the second projection probability and the second transition probability of the track point sequenced after the first track point and the road to be matched according to the preset projection probability and transition probability algorithm. The algorithm of the second projection probability and the second transition probability corresponding to each track point may be the same as or similar to the algorithm of the first projection probability and the second transition probability in the step S13, and specifically, reference may be made to the description in the step S13.
In one embodiment, in the steps S13 and S14, the production attribute of the road to be matched and the corresponding virtual attribute may be continuously determined in real time and put into the corresponding road data in the process of matching the track meeting the quality standard to the surrounding road. For example, the road to be matched in the preset distance range around the driving track is obtained, and in the process of road matching, the values of the induced production attribute and the virtual attribute are respectively determined by the following possible modes:
1. According to four-dimensional information and observation time information of each track point of the track meeting the quality standard and the acquired road data of the road to be matched, if the track point of the track cannot be matched with the road to be matched, adding a value which indicates no road in a production attribute into the road data, and introducing a value which indicates a road in a virtual attribute;
2. according to four-dimensional information and observation time information of each track point of the track meeting the quality standard and the acquired road data of the road to be matched, if the track point of the track needs to jump to a road with non-connected topological relation, adding a value which indicates that the road topology is not connected in a production attribute into the road data, and introducing a value which indicates that the road topology is connected in a virtual attribute;
3. According to four-dimensional information and observation time information of each track point of the track meeting the quality standard and the acquired road data of the road to be matched, if the track point of the track needs to be matched to a reverse road which does not exist in a road network, adding a value which indicates that the road traffic direction is unidirectional in one production attribute into the road data, and introducing a value which indicates that the road traffic direction is bidirectional in one virtual attribute.
It is assumed that at least one type of road data error exists in the roads in the road network, namely at least one type of production attribute and virtual attribute are introduced into the roads to be matched. For the road to be matched, no matter how many types of manufacturing attributes are introduced, the road data in the road network are unique, so that only one value of the first matching probability corresponding to the optimal matching result is obtained by using the Viterbi algorithm based on the manufacturing attributes of the road to be matched by adopting the obtained driving paths meeting the quality standard.
For the virtual attribute of the road to be matched, because the value of the virtual attribute is opposite to the value of the manufacturing attribute, and one or more possible virtual attributes may be introduced in the calculation process, the method is equivalent to performing one or more assumptions on the road attribute of the road data of the road to be matched in the road network, so that one or more possible assumed roads corresponding to the road to be matched under the condition of the virtual attribute are obtained respectively, and for convenience, the one or more possible assumed roads are referred to as the virtual road to be matched.
For example, referring to fig. 3, the shape of the continuous arrow is used to represent the driving track, each arrow direction is the driving direction of the track point of the driving track, the black solid line is used to represent the road data of the road to be matched in the road network, and the black arrow is used to represent the road traffic direction. Assuming that the trajectories are paired, it may be assumed that the production attribute of the road data in the road network has one or more of a road shape error, a road direction error, a road topology connection error, and a road absence error. In fig. 3, the running direction of the track point of the track is inconsistent with the road passing direction, so that in the road matching process, a value representing a manufacturing attribute of unidirectional road passing direction and a value representing a virtual attribute of bidirectional road passing direction can be introduced for the road data of the road to be matched in the road network, the track can turn right at the intersection, and the topological connection relationship in the road data is that the road is not communicated, so that in the road matching process, a value representing a manufacturing attribute of non-communicated road topology and a value representing a virtual attribute of communicated road topology can be introduced for the road data of the road to be matched in the road network, and the track point of the track can not be matched to the road in the road network, so that in the road matching process, a value representing a manufacturing attribute of no road and a value representing a virtual attribute of road can be introduced for the road data to be matched in the road network.
In the road matching process, the value of each virtual attribute introduced to the road in the road network is equivalent to the processing of the road data in the road network, so as to obtain a virtual road to be matched corresponding to the road to be matched in the road network. Therefore, the value of one or more virtual attributes can be introduced in the road matching process, so that at least one virtual road to be matched corresponding to the road to be matched under the condition of the virtual attributes can be obtained, namely, one or more virtual roads with corrected errors are assumed, the hidden Markov model and the Viterbi algorithm are used for reversely pushing whether the former assumption is true or not, if so, the original virtual attributes are confirmed to be correct, and the original manufacturing attributes of the road are wrong.
In step S14, similarly to the calculation process of the first matching probability, in order to obtain the second matching probability of the vehicle track and the road to be matched under the virtual attribute condition, the projection probability and the transition probability of each track point in the vehicle track to the at least one virtual road to be matched may be determined first, so as to obtain at least one second projection probability and one second transition probability of the vehicle track to the road to be matched under the virtual attribute condition, and then at least one second matching probability of the vehicle track to the road to be matched may be obtained according to the obtained at least one second projection probability and second transition probability.
In a specific embodiment, because the value of the road to be matched under the condition of the virtual attribute may be one or more, the road to be matched is processed according to the value of the virtual attribute of each road to be matched, so that at least one virtual road to be matched can be obtained. When road matching is carried out, for each virtual road to be matched in at least one virtual road to be matched, firstly determining the projection probability and the transition probability of the first track point of the driving track and the virtual road to be matched, and then determining the projection probability and the transition probability of other track points sequenced after the first track point and the virtual road to be matched according to a preset projection probability and transition probability algorithm. And counting to obtain the projection probability and the transition probability of each track point in the driving track to the at least one virtual road to be matched, namely at least one second projection probability and at least one second transition probability of the driving track to the road to be matched under the condition of the virtual attribute.
In a specific embodiment, referring to fig. 4, it is assumed that the continuous arrows form a track that meets the quality standard, each arrow represents a track point, the direction of each arrow represents the driving direction of a track point, and during the road matching process, each track point can obtain at least one road to be matched within the peripheral preset distance range. In the prior art, the matching degree of the driving track and the road to be matched is represented by the projection probability and the transition probability, and the larger the projection probability and the transition probability, the smaller the distance between the track point representing the track and the road, and the larger the obtained projection probability and the transition probability can be if the road has no road network error.
Assuming that there is no road data error in the road network, there are many selection states in the matching of the vehicle track and the road, as can be seen in fig. 4, when the vehicle track is finally matched to the road marked by the black line in the road network, the projection probability and the transition probability between the vehicle track and the road to be matched are the maximum, and the projection probability and the transition probability at this time are the first projection probability and the first transition probability, but cannot match the road with the nearest road missing relative to each track point, because under the condition that the road error of the road network is not considered, the track is matched to the road marked by the black line, although the values of the first projection probability and the first transition probability are smaller, the first matching probability obtained by fusion is the maximum probability value obtained by the viterbi algorithm, that is, although the optimal matching result is obtained, the deviation still exists between the road marked by the black line in the road network and the actual road through which the vehicle track passes, indicating that the road data in the road network is wrong.
In the embodiment of the invention, in the road matching process, when the track point cannot be matched to the road of the road network, the track point is assumed to correspond to a missing road, namely, a virtual road to be matched is added at the missing position of the road in the graph, a hard jump is made on the road which is not communicated in the road network, the road data is actively repaired, and a value of a manufacturing attribute and a virtual attribute is introduced into the road data. At this time, based on the virtual attribute of the road to be matched, the second projection probability and the second transition probability when the track is matched to the virtual road to be matched closest to each track point are both larger than the first projection probability and the first transition probability when the track is matched to the road marked by the black line in the road network, so that the second matching probability obtained by fusing the second projection probability and the second transition probability is larger than the first matching probability, which means that the matching result when the driving track is matched to the repaired virtual road is better than the matching result when the driving track is matched to the road marked by the black line in the road network, thereby indicating that the manufacturing attribute of the road in the road network is wrong.
Based on the same inventive concept, referring to fig. 5, an embodiment of the present invention further provides a method for determining a road data error type, including:
s51, determining whether the manufacturing attribute of the road to be matched of the driving track is wrong;
If yes, go to step 52, if no, go to step S53;
S52, determining the error type of the road to be matched according to the virtual attribute of the road to be matched;
s53, exiting the current flow.
In the step S51, the step of determining whether the production attribute of the road to be matched of the driving track is wrong may be implemented by using the method for determining the road data error.
In the above step S52, the error type of the road to be matched may be determined by:
Comparing and determining the maximum value of at least one second matching probability;
Determining the value of the virtual attribute of the road to be matched corresponding to the maximum value of the second matching probability;
And determining the error type of the road to be matched according to the determined value of the virtual attribute of the road to be matched.
In the road matching process, virtual attributes can be introduced into the road data of each road to be matched, when at least one second matching probability is determined to be larger than the first matching probability, errors in the manufacturing attributes of the roads to be matched are indicated, and according to the description of the road data error determining method, the bigger the projection probability and the transition probability are, the better the matching degree of the travelling path and the roads is indicated, so that the matching degree of the roads to be matched corresponding to the maximum value in the at least one determined second matching probability is optimal. Therefore, according to the value of the virtual attribute of the road to be matched corresponding to the maximum value of the second matching probability, it is possible to determine which type of error of the road data of the road to be matched is.
The method for determining the road data error type provided by the embodiment of the invention not only can realize accurate judgment of whether the road data is wrong, but also can further accurately determine the road data error type corresponding to the road to be matched according to the determined virtual attribute value of the road to be matched when the production attribute of the road to be matched is wrong, and has the advantages of simple and easy realization, and convenience and higher efficiency for correcting the data error of the road.
In one embodiment, the method for determining the road data error type further comprises correcting the road data of the road network according to the determined value of the virtual attribute of the road to be matched. For example, reverse iteration may be performed according to the determined virtual attribute value of the road to be matched, so as to correct the point coordinate sequence of the road data of the road network, the road traffic direction and the road connection relationship.
The way of correcting the road error can be a manual way, a machine-implemented automatic way or a way of combining manual and automatic ways, which is not limited by the embodiment of the invention.
In the embodiment of the invention, in the process of matching according to the driving track and obtaining the roads to be matched within the preset distance range around the driving track, one or more values of the manufacturing attribute and the virtual attribute can be introduced into each road to be matched, so as to obtain the first matching probability and at least one second matching probability of the track points corresponding to the matching result of the roads to be matched. In each matching result, the values of the production attribute and the virtual attribute introduced in the road data of the road to be matched are determined, so that whether the road data of the road to be matched is wrong or not and the type of the error in the wrong state can be determined according to the production attribute and the virtual attribute of the road data. When the road data is determined to be in error, continuously correcting the road data in the road network according to the road data of the road to be matched corresponding to the maximum value of the second matching probability, so that the road in the corrected road network is closer to the road in the actual road network in reality.
Based on the same inventive concept, the embodiments of the present invention further provide a road data error determining device, a road data error type determining device, a related storage medium, and a server, and because the principle of the problems solved by these devices, related storage media, and servers is similar to the foregoing road network error determining method, implementation of the devices, related storage media, and servers may refer to implementation of the foregoing method, and repeated descriptions are omitted.
Referring to fig. 6, an embodiment of the present invention provides a road network error determining apparatus, including:
a track extraction module 61, configured to obtain a vehicle track represented by a series of track points that meets quality criteria, where the quality criteria include a consistency criterion, a volatility criterion, and a number criterion of the track points;
The road obtaining module 62 is configured to obtain a road to be matched within a preset distance range around the vehicle track, where the road to be matched includes a production attribute and a virtual attribute, and the value of the virtual attribute is opposite to the value of the production attribute;
The first matching probability determining module 63 is configured to determine a first projection probability and a first transition probability of each track point in the track to the road to be matched according to a preset projection probability and a transition probability algorithm based on the manufacturing attribute of the road to be matched, and obtain a first matching probability of the track to the road to be matched based on the first projection probability and the first transition probability;
The second matching probability determining module 64 is configured to determine a second projection probability and a second transition probability of each track point in the vehicle track to the road to be matched according to the virtual attribute based on the road to be matched, and obtain a second matching probability of the vehicle track to the road to be matched based on the second projection probability and the second transition probability;
The road data error determining module 65 is configured to compare the first matching probability obtained by the first matching probability determining module with the second matching probability obtained by the second matching probability determining module, and determine that the production attribute of the road to be matched is wrong when the second matching probability is greater than the first matching probability.
In one embodiment, the second matching probability determining module 64 is specifically configured to determine, for the driving track, based on the virtual attribute of the road to be matched, a second projection probability and a second transition probability of a first track point and the road to be matched, and determine, according to a preset projection probability and a transition probability algorithm, the second projection probability and the second transition probability of the track point sequenced after the first track point and the road to be matched.
In one embodiment, the second matching probability determining module 64 is specifically configured to determine, based on the virtual attribute of the road to be matched, at least one virtual road to be matched corresponding to the road to be matched under the condition of the virtual attribute;
Respectively determining the projection probability and the transition probability of each track point in the driving track to the at least one virtual road to be matched, and obtaining at least one second projection probability and at least one second transition probability of each track point in the driving track to the road to be matched under the condition of the virtual attribute;
and obtaining at least one second matching probability from the driving track to the road to be matched according to the obtained at least one second projection probability and the at least one second transition probability.
In one embodiment, the second matching probability determination module 64 is specifically configured to compare the at least one second matching probability with the first matching probability;
And if any one of the at least one second matching probability is larger than the first matching probability, determining that the production attribute of the road to be matched is wrong.
Referring to fig. 7, an embodiment of the present invention provides a device for determining a road data error type, including:
the data error judging module 71 is configured to determine whether an error occurs in a manufacturing attribute of a road to be matched of a driving track;
a type error determining module 72, configured to determine, when an error occurs in a production attribute of a road to be matched of a driving track, an error type of the road to be matched according to a virtual attribute of the road to be matched;
The data error judging module 71 adopts the above-mentioned road data error determining method to determine whether the production attribute of the road to be matched of the driving track is wrong.
The embodiment of the invention provides a computer readable storage medium, on which computer instructions are stored, which when executed by a processor, implement the road network error determination method or implement the road data error type determination method.
The embodiment of the invention provides a server which comprises a processor and a memory for storing executable commands of the processor, wherein the processor is configured to execute the road network error determination method or the road data error type determination method.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, magnetic disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (11)
1.A method for determining road data errors, comprising:
acquiring a driving track represented by a series of track points meeting quality standards, wherein the quality standards comprise a consistency standard, a volatility standard and a quantity standard of the track points;
Obtaining a road to be matched within a preset distance range around the driving track, wherein the road to be matched comprises a manufacturing attribute and a virtual attribute, and the value of the virtual attribute is opposite to that of the manufacturing attribute;
Determining a first projection probability and a first transition probability of each track point in the driving track to the road to be matched according to a preset projection probability and a transition probability algorithm based on the manufacturing attribute of the road to be matched, and obtaining a first matching probability of the driving track to the road to be matched based on the first projection probability and the first transition probability;
Determining a second projection probability and a second transition probability of each track point in the driving track to the road to be matched based on the virtual attribute of the road to be matched, and obtaining a second matching probability of the driving track to the road to be matched based on the second projection probability and the second transition probability;
and when the second matching probability of the driving track to the road to be matched is larger than the first matching probability, determining that the production attribute of the road to be matched is wrong.
2. The method of claim 1, wherein determining the second projection probability and the second transition probability of each track point in the track to the road to be matched based on the virtual attribute of the road to be matched comprises:
and determining a second projection probability and a second transition probability of the first track point and the road to be matched according to a preset projection probability and transition probability algorithm based on the virtual attribute of the road to be matched, and determining the second projection probability and the second transition probability of the track point sequenced after the first track point and the road to be matched according to the preset projection probability and transition probability algorithm.
3. The method of claim 1 or 2, wherein the production attribute and the virtual attribute comprise one or more of road traffic direction, road topology connection relationship, and road absence.
4. The method of claim 3, determining a second projection probability and a second transition probability of each track point in the driving track to the road to be matched based on the virtual attribute of the road to be matched, and obtaining a second matching probability of the driving track to the road to be matched based on the second projection probability and the second transition probability, comprising:
determining at least one virtual road to be matched, which corresponds to the road to be matched under the condition of the virtual attribute, based on the virtual attribute of the road to be matched;
respectively determining the projection probability and the transition probability of each track point in the track to the at least one virtual road to be matched, and obtaining at least one second projection probability and at least one second transition probability of the track to the road to be matched under the condition of the virtual attribute;
And obtaining at least one second matching probability from the driving track to the road to be matched according to the obtained at least one second projection probability and the second transition probability.
5. The method of claim 4, wherein determining that the production attribute of the road to be matched is wrong when the second probability of matching the vehicle track to the road to be matched is greater than the first probability of matching, comprises:
Comparing the at least one second match probability with the first match probability;
And if any one of the at least one second matching probability is larger than the first matching probability, determining that the production attribute of the road to be matched is wrong.
6. A method for determining a type of road data error, comprising:
Determining whether the manufacturing attribute of the road to be matched of the driving track is wrong;
if yes, determining the error type of the road to be matched according to the virtual attribute of the road to be matched;
The step of determining whether the production attribute of the road to be matched of the driving track is wrong or not adopts the road data wrong determination method according to any one of claims 1-5.
7. The method of claim 6, determining the error type of the road to be matched according to the virtual attribute of the road to be matched, comprising:
Comparing and determining the maximum value of at least one second matching probability;
Determining the value of the virtual attribute of the road to be matched corresponding to the maximum value of the second matching probability;
And determining the error type of the road to be matched according to the determined value of the virtual attribute of the road to be matched.
8. A road data error determination apparatus, comprising:
The track extraction module is used for obtaining the driving track represented by a series of track points meeting the quality standard, wherein the quality standard comprises the consistency standard, the volatility standard and the quantity standard of the track points;
The road obtaining module is used for obtaining a road to be matched in a preset distance range around the travelling path, the road to be matched comprises a manufacturing attribute and a virtual attribute, and the value of the virtual attribute is opposite to that of the manufacturing attribute;
The first matching probability determining module is used for determining a first projection probability and a first transition probability of each track point in the driving track to the road to be matched according to a preset projection probability and a transition probability algorithm based on the manufacturing attribute of the road to be matched, and obtaining a first matching probability of the driving track to the road to be matched based on the first projection probability and the first transition probability;
The second matching probability determining module is used for determining second projection probability and second transition probability of each track point in the driving track to the road to be matched based on the virtual attribute of the road to be matched, and obtaining second matching probability of the driving track to the road to be matched based on the second projection probability and the second transition probability;
and the road data error determining module is used for comparing the first matching probability obtained by the first matching probability determining module with the second matching probability obtained by the second matching probability determining module, and determining that the manufacturing attribute of the road to be matched is wrong when the second matching probability is larger than the first matching probability.
9. A road data error type determining apparatus, comprising:
the data error judging module is used for determining whether the manufacturing attribute of the road to be matched of the driving track is wrong;
The type error determining module is used for determining the error type of the road to be matched according to the virtual attribute of the road to be matched when the manufacturing attribute of the road to be matched of the driving track is wrong;
The step of determining whether the production attribute of the road to be matched of the driving track is wrong or not adopts the road data wrong determination method according to any one of claims 1-5.
10. A computer-readable storage medium having stored thereon computer instructions which, when executed by a processor, implement the method of determining a road data error as claimed in any one of claims 1 to 5, or implement the method of determining a road data error type as claimed in claim 6 or 7.
11. A server includes a processor, a memory for storing processor executable commands;
The processor is configured to perform the method for determining a road data error according to any one of claims 1 to 5, or the method for determining a road data error type according to claim 6 or 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010071495.2A CN113218404B (en) | 2020-01-21 | 2020-01-21 | A method for determining road data errors, related methods and devices |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010071495.2A CN113218404B (en) | 2020-01-21 | 2020-01-21 | A method for determining road data errors, related methods and devices |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113218404A CN113218404A (en) | 2021-08-06 |
| CN113218404B true CN113218404B (en) | 2025-08-08 |
Family
ID=77085244
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010071495.2A Active CN113218404B (en) | 2020-01-21 | 2020-01-21 | A method for determining road data errors, related methods and devices |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113218404B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115534976A (en) * | 2022-08-31 | 2022-12-30 | 北京罗克维尔斯科技有限公司 | Trajectory screening method and device, electronic equipment, storage medium and vehicle |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103499828A (en) * | 2013-10-22 | 2014-01-08 | 北京世纪高通科技有限公司 | Floating car track map matching method and device |
| CN106595680A (en) * | 2016-12-15 | 2017-04-26 | 福州大学 | Vehicle GPS data map matching method based on hidden markov model |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100498986B1 (en) * | 2002-09-02 | 2005-07-01 | 엘지전자 주식회사 | Map matching method using street traffic code |
| US8645061B2 (en) * | 2010-06-16 | 2014-02-04 | Microsoft Corporation | Probabilistic map matching from a plurality of observational and contextual factors |
| CN108253974B (en) * | 2017-12-29 | 2019-09-10 | 深圳市城市交通规划设计研究中心有限公司 | Floating Car location data automatic adaptation cushion route matching system and method |
| CN108763558B (en) * | 2018-05-25 | 2020-12-18 | 武汉大学 | A crowdsourced map road quality improvement method based on map matching |
| CN109522385B (en) * | 2018-11-22 | 2021-05-11 | 首都师范大学 | A method for judging M-N matching mode of multi-scale road network |
| CN110426050B (en) * | 2019-08-07 | 2021-08-03 | 北京百度网讯科技有限公司 | Map matching correction method, device, equipment and storage medium |
-
2020
- 2020-01-21 CN CN202010071495.2A patent/CN113218404B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103499828A (en) * | 2013-10-22 | 2014-01-08 | 北京世纪高通科技有限公司 | Floating car track map matching method and device |
| CN106595680A (en) * | 2016-12-15 | 2017-04-26 | 福州大学 | Vehicle GPS data map matching method based on hidden markov model |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113218404A (en) | 2021-08-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109974718B (en) | Map matching method, apparatus, device and medium | |
| CN113155139B (en) | Vehicle track deviation rectifying method and device and electronic equipment | |
| US10323948B2 (en) | GPS data repair | |
| CN108763558B (en) | A crowdsourced map road quality improvement method based on map matching | |
| CN106323301B (en) | A method and device for obtaining road information | |
| CN110174110B (en) | Map corresponding method and device, electronic equipment and computer readable medium | |
| US20230154203A1 (en) | Path planning method and system using the same | |
| CN112747755A (en) | Road route determining method, road route determining device, readable storage medium and map updating system | |
| CN106250515A (en) | Miss path restoration methods based on historical data | |
| CN113837268A (en) | Method, apparatus, device and medium for determining the state of a track point | |
| CN114461936A (en) | Map verification method, map verification device, computer equipment and storage medium | |
| CN113218404B (en) | A method for determining road data errors, related methods and devices | |
| CN114743165A (en) | Method and device for determining vehicle trajectory, storage medium and electronic device | |
| CN114462609A (en) | A Trajectory Restoration Method for Floating Car Data Based on Hidden Markov Model | |
| CN110473405B (en) | Driving state detection method and device, readable storage medium and electronic equipment | |
| CN117848311A (en) | High-precision map speed limit information fusion method and system based on multi-source data | |
| CN113639757A (en) | Map matching method and system based on bidirectional scoring model and retrospective correction mechanism | |
| CN116772871B (en) | Map positioning and matching method based on finite state machine | |
| CN114638859B (en) | Method, device, electronic device and readable storage medium for correcting movement trajectory | |
| CN114935773B (en) | Online road matching method, device, medium and equipment based on Beidou positioning | |
| CN119058744A (en) | Vehicle driving decision method, device, electronic device and storage medium | |
| CN118607028A (en) | Road model generation method, device, vehicle and storage medium | |
| CN117152958A (en) | Vehicle track recognition method, device, recognition equipment and readable storage medium | |
| CN111613045A (en) | Method and device for verifying road traffic condition | |
| CN114353812A (en) | Map closed-loop generation method and device, electronic device and storage medium |
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 |