[go: up one dir, main page]

CN120164004B - A visual monitoring method for the growth status of toads throughout their life cycle - Google Patents

A visual monitoring method for the growth status of toads throughout their life cycle

Info

Publication number
CN120164004B
CN120164004B CN202510226778.2A CN202510226778A CN120164004B CN 120164004 B CN120164004 B CN 120164004B CN 202510226778 A CN202510226778 A CN 202510226778A CN 120164004 B CN120164004 B CN 120164004B
Authority
CN
China
Prior art keywords
toad
target
growth
toads
image
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
Application number
CN202510226778.2A
Other languages
Chinese (zh)
Other versions
CN120164004A (en
Inventor
张晨
张虎晨
董昌锋
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Binzhou Fengrun Qinjia Agricultural Technology Co ltd
Original Assignee
Binzhou Fengrun Qinjia Agricultural Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Binzhou Fengrun Qinjia Agricultural Technology Co ltd filed Critical Binzhou Fengrun Qinjia Agricultural Technology Co ltd
Priority to CN202510226778.2A priority Critical patent/CN120164004B/en
Publication of CN120164004A publication Critical patent/CN120164004A/en
Application granted granted Critical
Publication of CN120164004B publication Critical patent/CN120164004B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
    • G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/02—Agriculture; Fishing; Forestry; Mining
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
    • Y02A40/80—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in fisheries management
    • Y02A40/81—Aquaculture, e.g. of fish

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Health & Medical Sciences (AREA)
  • Business, Economics & Management (AREA)
  • Health & Medical Sciences (AREA)
  • Tourism & Hospitality (AREA)
  • Marine Sciences & Fisheries (AREA)
  • Marketing (AREA)
  • Primary Health Care (AREA)
  • Strategic Management (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Economics (AREA)
  • General Business, Economics & Management (AREA)
  • Mining & Mineral Resources (AREA)
  • Human Resources & Organizations (AREA)
  • Animal Husbandry (AREA)
  • Agronomy & Crop Science (AREA)
  • Artificial Intelligence (AREA)
  • Computing Systems (AREA)
  • Databases & Information Systems (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Image Analysis (AREA)

Abstract

本发明公开了一种蟾蜍养殖的全生命周期生长状态视觉监测方法，涉及图像匹配技术领域。该方法包括：对目标蟾蜍进行视觉监测，获取目标蟾蜍的第一蟾蜍轮廓图像；在对目标蟾蜍监测中断的情况下，根据各第一蟾蜍轮廓图像，预测目标蟾蜍的疑似位置区域；根据各第一蟾蜍轮廓图像以及疑似位置区域的区域特征图像，确定疑似位置区域中各候选蟾蜍与目标蟾蜍之间的特征匹配度；根据目标蟾蜍所属的蟾蜍组中各参考蟾蜍的第二蟾蜍轮廓图像，确定疑似位置区域中各候选蟾蜍与目标蟾蜍之间的生长轨迹符合度；根据特征匹配度以及生长轨迹符合度，确定各候选蟾蜍与目标蟾蜍的整体匹配度；将整体匹配度最大的候选蟾蜍确定为目标蟾蜍，恢复对目标蟾蜍的视觉监测。

The present invention discloses a method for visually monitoring the growth status of toads throughout their entire life cycle, and relates to the field of image matching technology. The method comprises: visually monitoring a target toad and obtaining a first toad outline image of the target toad; in the event that monitoring of the target toad is interrupted, predicting a suspected location region of the target toad based on each first toad outline image; determining a feature matching degree between each candidate toad and the target toad in the suspected location region based on each first toad outline image and a regional feature image of the suspected location region; determining a growth trajectory matching degree between each candidate toad and the target toad in the suspected location region based on a second toad outline image of each reference toad in the toad group to which the target toad belongs; determining an overall matching degree between each candidate toad and the target toad based on the feature matching degree and the growth trajectory matching degree; determining the candidate toad with the greatest overall matching degree as the target toad, and resuming visual monitoring of the target toad.

Description

Visual monitoring method for growth state of toad culture in full life cycle
Technical Field
The invention relates to the technical field of image matching, in particular to a visual monitoring method for a full life cycle growth state of toad cultivation.
Background
The toad breeding refers to breeding, breeding and managing toads by utilizing an artificial environment, and can accurately measure individual health and development level of the toads by monitoring growth states of the toads in a complete life cycle from fertilized eggs, tadpoles, metamorphosis period, larvae to adults until breeding, including aspects of body size, weight, appearance characteristics, behavioral activities and the like.
At present, an automatic visual detection technology is adopted to monitor the growth state of the whole life cycle of the toad in real time, and characteristic information is extracted through an image processing method, so that the growth stage, the behavior state and possible health abnormality of the toad are judged.
However, shielding is easy to occur in the toad monitoring process, so that complete toad tracking cannot be performed, and the accuracy of toad growth state monitoring is poor.
Disclosure of Invention
The embodiment of the invention provides a visual monitoring method for the growth state of a whole life cycle of toad culture, which can improve the accuracy of monitoring the growth state of the toad.
In a first aspect of the embodiment of the present invention, a method for visually monitoring a growth state of a toad culture in a full life cycle is provided, including:
performing visual monitoring on a target toad, and acquiring a first toad contour image of the target toad in real time;
under the condition that monitoring of the target toad is interrupted, predicting a suspected position area of the target toad according to each first toad contour image;
Determining the feature matching degree between each candidate toad and the target toad in the suspected position area according to the outline image of each first toad and the area feature image of the suspected position area;
Determining the growth track coincidence degree between each candidate toad and the target toad in the suspected position area according to the second toad outline image of each reference toad in the toad group to which the target toad belongs, wherein each toad in the toad group comprises toads with similar growth tracks, and the reference toad is a toad which is normally monitored except the target toad in the toad group;
Determining the overall matching degree of each candidate toad and the target toad according to the characteristic matching degree and the growth track coincidence degree;
and determining the candidate toad with the highest overall matching degree as the target toad, and recovering the visual monitoring of the target toad.
In the visual monitoring method for the growth state of the whole life cycle of toad cultivation provided by the embodiment of the invention, under the condition that the monitoring of the target toad is interrupted, the suspected position area of the target toad is predicted according to the outline images of each first toad of the target toad. Therefore, the approximate position can be provided for the subsequent positioning of the target toad, and the matching range is reduced. And determining the degree of feature matching between each candidate toad and the target toad in the suspected position area according to the first toad contour image and the area feature image of the suspected position area, and simultaneously determining the degree of growth track coincidence between each candidate toad and the target toad in the suspected position area according to the second toad contour image of each reference toad in the toad group to which the target toad belongs. Thus, depending on the reference toad having a similar growth trajectory as the target toad and the feature matching condition between each candidate toad and the target toad in the suspected location area, the location of the target toad in the suspected location area can be accurately determined. In summary, under the condition that the monitoring of the target toad is interrupted due to shielding phenomenon and the like in the toad monitoring process, the target toad can be accurately tracked, so that the accuracy of monitoring the growth state of the toad is improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages 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 only 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 method for visually monitoring the growth state of a whole life cycle of a first toad culture according to an embodiment of the invention;
Fig. 2 is a flow chart of a visual monitoring method for growth status of a second toad cultivation full life cycle according to an embodiment of the invention;
fig. 3 is a flow chart of a visual monitoring method for growth state of a third toad cultivation full life cycle according to an embodiment of the invention.
Detailed Description
In order to further explain the technical means and effects adopted by the invention to achieve the preset aim, the following is a detailed description of the specific implementation, structure, characteristics and effects of the method for visually monitoring the growth state of the whole life cycle of toad culture according to the invention, which is provided by the invention, with reference to the accompanying drawings and the preferred embodiment. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It should be noted that, in the technical scheme of the invention, the acquisition, storage, use, processing and the like of the data all conform to the relevant regulations of laws and regulations.
It should be noted that, in the embodiments of the present invention, some existing solutions in the industry such as software, components, models, etc. may be mentioned, and they should be regarded as exemplary, only for illustrating the feasibility of implementing the technical solution of the present invention, but it does not mean that the applicant has or must not use the solution.
The toad breeding refers to breeding, breeding and managing toads by utilizing an artificial environment, and can accurately measure individual health and development level of the toads by monitoring growth states of the toads in a complete life cycle from fertilized eggs, tadpoles, metamorphosis period, larvae to adults until breeding, including aspects of body size, weight, appearance characteristics, behavioral activities and the like.
At present, an automatic visual detection technology is adopted to monitor the growth state of the whole life cycle of the toad in real time, and characteristic information is extracted through an image processing method, so that the growth stage, the behavior state and possible health abnormality of the toad are judged. However, shielding is easy to occur in the toad monitoring process, so that complete toad tracking cannot be performed, and the accuracy of toad growth state monitoring is poor.
The invention aims to provide a visual monitoring method for the growth state of toad cultivation in a full life cycle. In the visual monitoring method for the growth state of the whole life cycle of toad cultivation provided by the embodiment of the invention, under the condition that the monitoring of the target toad is interrupted, the suspected position area of the target toad is predicted according to the outline images of each first toad of the target toad. Therefore, the approximate position can be provided for the subsequent positioning of the target toad, and the matching range is reduced. And determining the degree of feature matching between each candidate toad and the target toad in the suspected position area according to the first toad contour image and the area feature image of the suspected position area, and simultaneously determining the degree of growth track coincidence between each candidate toad and the target toad in the suspected position area according to the second toad contour image of each reference toad in the toad group to which the target toad belongs. Thus, depending on the reference toad having a similar growth trajectory as the target toad and the feature matching condition between each candidate toad and the target toad in the suspected location area, the location of the target toad in the suspected location area can be accurately determined. In summary, under the condition that the monitoring of the target toad is interrupted due to shielding phenomenon and the like in the toad monitoring process, the target toad can be accurately tracked, so that the accuracy of monitoring the growth state of the toad is improved.
The following describes a specific embodiment of a visual monitoring method for the growth state of the whole life cycle of toad cultivation.
Fig. 1 provides a flow chart of a visual monitoring method for a full life cycle growth state of toad cultivation, which can be applied to a server, and the visual monitoring method for the full life cycle growth state of toad cultivation can include the following steps S101 to S106.
S101, performing visual monitoring on a target toad, and acquiring a first toad contour image of the target toad in real time.
In this example, the target toad is used to characterize the toad for which visual monitoring is desired.
As an example, a monitoring device such as a high-definition camera or other vision sensor is installed in the active area of the target toad to ensure that a clear image can be captured. Then, the server acquires target toad images according to a preset frequency through monitoring equipment, and processes the acquired target toad images by utilizing an image processing algorithm (such as edge detection, contour extraction and the like) to extract a first toad contour image of the target toad.
S102, when monitoring the target toad is interrupted, predicting a suspected position area of the target toad according to each first toad contour image.
In this embodiment, the interruption of the monitoring of the target toad is the loss of the target toad. For example, in the case where there is an obstacle to shade a target toad, a situation may occur in which monitoring of the target toad is interrupted.
The suspected position area is used for representing the area where the estimated target toad is suspected to be located after the monitoring and interruption of the target toad.
As an example, in the case that the server side cannot acquire the first toad contour image of the toad image through the monitoring device, the location of the target toad may be considered to be lost, that is, the monitoring of the target toad is interrupted.
At this time, the server uses the first toad contour image of the target toad history to estimate the movement rule of the target toad by a machine learning or statistical analysis method, so as to predict the suspected position area that the target toad will reach after being blocked.
S103, determining the feature matching degree between each candidate toad and the target toad in the suspected position area according to the outline image of each first toad and the area feature image of the suspected position area.
In this embodiment, the region feature image is used to characterize an image of the suspected location region at the current time, and the candidate toads are used to characterize the individual toads included in the region feature image.
The feature matching degree is used for representing the similarity degree of the features between the candidate toads and the target toads. For example, the degree of similarity of features that may include skin roughness, speckle distribution, body edges, eye and limb contours, etc.
As an example, the server identifies all candidate toads from the regional feature images of the suspected location area, and extracts features of the candidate toads and the target toads according to the first toad contour image of the target toad and the regional feature image of the suspected location area.
Then, the feature matching degree between each candidate toad and the target toad is calculated using a feature matching algorithm (e.g., template matching, similarity calculation, etc.).
S104, determining the growth track coincidence degree between each candidate toad and the target toad in the suspected position area according to the second toad outline image of each reference toad in the toad group to which the target toad belongs, wherein each toad in the toad group comprises toads with similar growth tracks, and the reference toad is a toad which is normally monitored except the target toad in the toad group.
In this embodiment, the bufo group includes a plurality of bufo gargargarizans, each of which has a similar growth track. The reference toad is a normal toad of the toad group except the target toad, namely, a toad of the toad group which is not subjected to monitoring interruption.
The second toad contour image is used for representing a toad contour image corresponding to the reference toad, and the growth track coincidence degree is used for representing the degree of coincidence of the growth tracks between the candidate toad and the target toad.
As an example, the server obtains a second toad contour image of each reference toad in the toad group to which the target toad belongs. Then, according to the outline image of each second toad of the reference toad, the growth track of the reference toad is obtained by analysis through technologies such as image processing, time sequence analysis and the like.
Then, the current growth condition of the target toad is estimated according to the growth track of each reference toad. And finally, comparing the current growth condition of the candidate toads with the presumed current growth condition of the target toads, and judging the growth track coincidence between the candidate toads and the target toads.
S105, determining the overall matching degree of each candidate toad and the target toad according to the characteristic matching degree and the growth track coincidence degree.
In this embodiment, different weights are allocated to the feature matching degree and the growth track coincidence degree according to actual requirements.
And then, the server combines the characteristic matching degree and the growth track coincidence degree by using a weighted average or other comprehensive calculation method, and calculates the overall matching degree of each candidate toad and the target toad.
As an example, the overall matching degree of the candidate toad and the target toad can be specifically determined by the following formula 1:
y i＝Zi×(1+Fi) equation 1
In the formula 1, Y i is used for representing the overall matching degree of the ith candidate toad and the target toad, Z i is used for representing the characteristic matching degree of the ith candidate toad and the target toad, and F i is used for representing the growth track coincidence degree of the ith candidate toad and the target toad.
S106, determining the candidate toad with the largest overall matching degree as the target toad, and recovering the visual monitoring of the target toad.
In this embodiment, among the candidate toads, one having the greatest overall matching degree is determined as the target toad.
Then, the server controls and adjusts parameters such as the angle, the focal length and the like of the monitoring equipment to ensure that images of the target toads can be clearly captured, so that tracking and visual monitoring of the target toads are recovered.
In the method for visually monitoring the growth state of the whole life cycle of toad cultivation provided by the embodiment, under the condition that the monitoring of the target toad is interrupted, the suspected position area of the target toad is predicted according to the outline images of each first toad of the target toad. Therefore, the approximate position can be provided for the subsequent positioning of the target toad, and the matching range is reduced. And determining the degree of feature matching between each candidate toad and the target toad in the suspected position area according to the first toad contour image and the area feature image of the suspected position area, and simultaneously determining the degree of growth track coincidence between each candidate toad and the target toad in the suspected position area according to the second toad contour image of each reference toad in the toad group to which the target toad belongs. Thus, depending on the reference toad having a similar growth trajectory as the target toad and the feature matching condition between each candidate toad and the target toad in the suspected location area, the location of the target toad in the suspected location area can be accurately determined. In summary, under the condition that the monitoring of the target toad is interrupted due to shielding phenomenon and the like in the toad monitoring process, the target toad can be accurately tracked, so that the accuracy of monitoring the growth state of the toad is improved.
As an alternative embodiment, S102 may specifically include:
Under the condition of interruption of target toad monitoring, determining motion vectors of all pixel points of the target toads between the first toad contour images adjacent in time through an optical flow algorithm according to all the first toad contour images;
predicting suspected displacement of the target toad according to the motion vector of each pixel point of the target toad;
And determining a suspected position area of the target toad according to the position before interruption and the suspected displacement of the target toad.
In this embodiment, first, the server performs preprocessing including denoising, graying, and the like on two frames of first toad contour images adjacent to each other in time, so as to ensure accuracy of subsequent optical flow calculation.
Then, an optical flow algorithm (for example, lucas-Kanade algorithm, horn-Schunck algorithm, etc.) is applied between the two frames of images, so as to obtain the local motion vector of each pixel point of the target toad between the two frames of images. The basic idea of the optical flow algorithm is, among other things, to estimate the motion of an object by comparing the brightness variations of pixels between adjacent frames in an image sequence. For the Lucas-Kanade algorithm it is assumed that the motion of all pixels is uniform within a small window and then the motion vector is solved by minimizing the luminance error function, for the Horn-Schunck algorithm it introduces a global smoothness constraint, it is assumed that the motion field is smoothly varying and the motion vector is obtained by solving an energy minimization problem.
Then, since the target toad may be composed of a plurality of pixels, the overall motion of the target toad may be approximated by the average or weight of the motion vectors of the pixels, so that the global motion vector between the two frames of images is obtained according to the average or weight of the motion vectors of the pixels. In the weighted averaging, the weights may be assigned according to the distance between the pixel points and the center of the target toad.
Then, after the global motion vectors corresponding to two adjacent first toad contour images at each time are averaged, the global motion vectors are converted into the displacement of the target toad, and the suspected displacement of the target toad can be obtained.
And finally, adding the final position before the interruption of monitoring and the calculated suspected displacement to obtain the predicted position of the target toad after the interruption of monitoring. Since there may be an error in the motion prediction, not only one point is predicted as the position of the target toad, but one region is predicted. This region may be a rectangular, oval or other shaped region of a certain size and shape centered on the predicted position. The size and shape of the region can be determined according to the uncertainty of the displacement amount, the moving speed of the target toad and other factors.
With the present embodiment, in the case of monitoring interruption, the suspected location area of the target toad is predicted based on the optical flow algorithm. Therefore, the area where the target toad is located can be estimated approximately, the calculated amount can be reduced for subsequent recovery tracking, and the recovery tracking efficiency of the target toad can be improved.
As an alternative embodiment, S103 may specifically include:
for each candidate toad in the suspected location area, the following steps are respectively executed:
For each first toad contour image and each regional characteristic image, respectively extracting local descriptors of key characteristic points, wherein the local descriptors are used for describing characteristic information of local regions of the key characteristic points;
For each first toad contour image, respectively acquiring local descriptors of key feature points of the first toad contour image and a first Euclidean distance average value between the local descriptors of the key feature points corresponding to the regional feature images;
And determining the feature matching degree between the candidate toad and the target toad by using the average value of the first Euclidean distances.
In the present embodiment, the local descriptor is used to describe feature information of a local region of the key feature point. In particular, the local descriptors may be extracted by a Scale-invariant feature transform (SIFT) feature extraction algorithm.
As an example, the feature matching degree between the candidate toad and the target toad can be specifically determined by the following formula 2:
In formula 2, Z i is used to characterize the feature matching degree between the ith candidate toad and the target toad, g i,n is used to characterize the number of interval frames between the ith candidate toad and the n th frame of first toad contour image before shielding of the target toad in the region feature image, and D i,n is used to characterize the first euclidean distance average value between the ith candidate toad and the n th frame of first toad contour image before shielding of the target toad in the region feature image. N is used to characterize the total number of first toad profile images and exp is used to characterize the exponential function operation.
Wherein, the The smaller the number of interval frames between the ith candidate toad and the n-th first toad contour image of the target toad before shielding in the regional characteristic image is, the larger the reference meaning of the first Euclidean distance average value is, namely the closer the time is to the first toad contour image of the regional characteristic image after shielding is, the more the reference meaning is provided.
According to the embodiment, the feature matching degree between each candidate toad and the target toad in the suspected position area can be accurately determined according to the outline image of each first toad and the area feature image of the suspected position area. Thereby being beneficial to accurately positioning the target toad according to the characteristic matching degree in the follow-up process, and improving the accuracy of monitoring the growth state of the toad.
As an alternative embodiment, as shown in fig. 2, S104 may specifically include the following S201 to S203:
s201, respectively executing the steps of determining the growth state change rate of the reference toad in each second toad contour image according to each second toad contour image of the reference toad;
S202, respectively executing the steps of determining the growth state referenceof the reference toad according to the growth state change rate of the reference toad and the second Euclidean distance average value between the local descriptors of the key feature points of the second toad contour image of the reference toad and the local descriptors of the corresponding key feature points in the first toad contour image of the target toad;
s203, determining the growth track coincidence degree between the candidate toad and the target toad according to the growth track coincidence degree between the candidate toad and each reference toad and the growth state referential property of each reference toad.
In this example, the growth state change rate was used to characterize the change rate of profile of the reference toad in each of the second toad profile images.
Growth state references are used to characterize the extent to which the growth state of a reference toad can be used as a reference for a target toad.
The second toad contour image is used for representing a toad contour image corresponding to the reference toad.
As an alternative embodiment, the server first collects second toad contour images of each reference toad at different time points. For each second toad contour image, the contour of the toad is extracted using image processing algorithms (e.g., edge detection, contour tracking, etc.).
Then, for each second toad contour image, the key feature points corresponding to the previous second toad contour image are found through a feature point matching algorithm (such as SIFT, SURF, etc.). And calculating the displacement of each key feature point in adjacent time according to the matched key feature points, and further calculating the change rate of the whole contour, namely the change rate of the growth state of the reference toad in the second toad contour image. In particular, this may be achieved by calculating the mean, standard deviation, or other statistic of the key feature point displacements.
Then, for each of the second toad contour image of the reference toad and the first toad contour image of the target toad, local descriptors of key feature points are calculated. The similarity between the two is measured by calculating the Euclidean distance average value between the local descriptors of the corresponding key feature points. And determining the growth state referenceof the reference toad by combining the growth state change rate of the reference toad with the second Euclidean distance average value by using a weighted summation, a product or other combination method.
Finally, for each candidate toad, the growth trajectory similarity between it and each reference toad was calculated. Specifically, this can be achieved by comparing profile changes of candidate and reference toads at different time points, using similarity metrics (e.g., profile matching, shape context, etc.) to evaluate growth trajectory similarity. And then, according to the growth state referential of each reference toad, weighting and summing the growth track similarity between the candidate toad and each reference toad, thereby obtaining the growth track coincidence degree between the candidate toad and the target toad. The weight can be determined according to the growth state referential of the reference toad, and the higher the referential is, the larger the weight is.
According to the embodiment, the growth track coincidence degree between each candidate toad and the target toad in the suspected position area is determined according to the second toad contour image of each reference toad in the toad group to which the target toad belongs. Thus, the growth locus coincidence degree between the candidate toad and the target toad can be accurately calculated depending on the reference toad having a similar growth locus to the target toad as a reference. Thereby being beneficial to accurately screening candidate toads according to the follow-up growth track conformity, and improving the accuracy of monitoring the growth state of the toads.
As an alternative embodiment, S201 may specifically include:
Obtaining straight line distances of each key point pair of the reference toad in the target second toad contour image and the adjacent toad contour images of the target second toad contour image, wherein the key point pairs are point pairs formed by any two key characteristic points;
And determining the growth state change rate of the reference toad in the target second toad contour image by utilizing the linear distance of each key point pair in the target second toad contour image and the adjacent toad contour images of the target second toad contour image.
In this embodiment, the growth state change rate of the reference toad in the target second toad contour image can be specifically determined by the following formula 3:
In equation 3, S is used to characterize the growth state change rate, and T is used to characterize the number of key point pairs. R is used to characterize the number of images, i.e. the number of target second toad contour images and neighboring toad contour images of the target second toad contour images. Wherein, the second toad contour image of five frames before and after the target second toad contour image can be preset as the adjacent toad contour image of the target second toad contour image. L t,r is used for representing the linear distance of the t-th key point pair in the r-th frame image, and L t,r+1 is used for representing the linear distance of the t-th key point pair in the r+1st frame image.
Wherein, the The key point pair used for representing the toad is the difference between the distance ratio and 1 in the adjacent image frames. The larger the value, the larger the change of the toad morphology, namely the larger the change rate of the toad growth state.
According to the embodiment, the growth state change rate of the reference toad in the target second toad contour image can be accurately determined by utilizing the linear distances of each key point pair of the toad in the target second toad contour image and the adjacent toad contour images of the target second toad contour image. Thus, the method is beneficial to determining the growth state referential of the reference toad according to the growth state change rate, thereby improving the accuracy of monitoring the growth state of the toad.
As an alternative embodiment, S202 may specifically include:
constructing a growth state change rate sequence of the reference toad based on each growth state change rate of the reference toad;
Forming a descriptor distance sequence based on local descriptors of key feature points of a second toad contour image of the reference toad and second Euclidean distance average values between the local descriptors of the key feature points corresponding to the first toad contour image of the target toad, wherein each second Euclidean distance average value is included in the descriptor distance sequence;
determining the growth state referential of the reference toad by using the growth state change rate sequence and the descriptor distance sequence.
In this embodiment, the growth state change rate sequence includes the growth state change rate of the reference toad in each of the second toad contour images.
The descriptor distance sequence comprises local descriptors of key feature points of each second toad contour image and second Euclidean distance average values between the local descriptors of the corresponding key feature points in each first toad contour image of the target toad.
As an example, the growth state referenceness of the reference toad can be determined specifically by the following formula 4:
Q w＝ρ(Sw,exp(-Dw)) equation 4
In formula 4, Q w is used to characterize the growth state referencing of the w-th reference toad, S w is used to characterize the growth state change rate sequence of the w-th reference toad, D w is used to characterize the descriptor distance sequence of the w-th reference toad, and ρ is used to characterize the pearson correlation coefficient.
Wherein the stronger the correlation between the growth state change rate sequence of the w-th reference toad and the descriptor distance sequence of the w-th reference toad, the greater the growth state referencing of the w-th reference toad.
By the embodiment, the growth state referential of the reference toad can be accurately estimated by using the growth state change rate sequence formed by the growth state change rates and the descriptor distance sequence formed by the second Euclidean distance average values. Thereby being beneficial to determining the growth track coincidence degree between the candidate toads and the target toads according to the growth state referential, and being capable of improving the accuracy of monitoring the growth state of the toads.
As an alternative embodiment, S203 may specifically include:
accumulating the growth state references of all the reference toads to obtain a first accumulated value;
Accumulating products of growth state referential property of each referential toad and corresponding growth track similarity to obtain a second accumulated value;
And determining the growth track coincidence degree between the candidate toad and the target toad by using the second accumulated value and the first accumulated value.
In this embodiment, the growth trajectory coincidence degree between the candidate toad and the target toad can be specifically determined by the following equation 5:
In formula 5, Q w is used to characterize the growth state referential of the W-th reference toad, X i,w is used to characterize the growth track similarity of the i-th candidate toad and the W-th reference toad, W is used to characterize the number of reference toads, and F i is used to characterize the growth track coincidence degree between the i-th candidate toad and the target toad.
The growth track similarity of the candidate toads and each reference toad is greater, the growth track coincidence between the candidate toads and the target toads is greater, and the growth state of the reference toads is greater, the growth track similarity of the candidate toads and the reference toads is of reference significance.
Through the embodiment, the growth track similarity between the candidate toad and each reference toad and the growth state referential of each reference toad are utilized to accurately determine the growth track coincidence degree between the candidate toad and the target toad. Thereby being beneficial to accurately positioning the target toad according to the follow-up growth track conformity degree, and being capable of improving the accuracy of monitoring the growth state of the toad.
As an alternative embodiment, as shown in fig. 3, before S104, the method for visually monitoring the growth state of the whole life cycle of the toad culture may further include the following steps S301 to S302:
s301, determining the similarity of growth tracks between the first toad and the second toad according to the third toad contour image of the first toad and the fourth toad contour image of the second toad;
s302, performing density clustering based on the similarity of the growth tracks to obtain at least one toad group.
In this embodiment, the first toad and the second toad are any two toads, the third toad contour image is a toad contour image corresponding to the first toad, and the fourth toad contour image is a toad contour image corresponding to the second toad.
As one example, the server evaluates growth trajectory similarity between the first and second toads using similarity metrics (e.g., profile matching, shape context, etc.) by comparing profile changes between a third toad profile image of the first toad and a fourth toad profile image of the second toad.
Then, a density clustering algorithm, such as DBSCAN or HDBSCAN, is selected. And parameters of the clustering algorithm, such as minimum number of samples (MinPts) and radius (Eps), etc., are set. And clustering by using a selected clustering algorithm according to the similarity of growth tracks among the toads to obtain at least one toad group.
According to the embodiment, density clustering is carried out on the toads according to the growth track similarity among the toads, so that at least one toad group is obtained. Therefore, the obtained toad group comprises the toads with similar growth tracks, so that the accurate tracking of the target toads is realized depending on the reference toads with similar growth tracks with the target toads under the condition that the monitoring of the target toads is interrupted, and the accuracy of the monitoring of the growth state of the toads is improved.
As an alternative embodiment, S301 may specifically include:
Matching the third toad contour image of the first toad with the fourth toad contour image of the second toad to obtain a matched image group, wherein the matched image group comprises the third toad contour image and the fourth toad contour image at the same moment;
obtaining local descriptors of key feature points of a third toad contour image in the matched image group and a third Euclidean distance average value between the local descriptors of the key feature points corresponding to the fourth toad contour image;
and determining the similarity of the growth tracks between the first toad and the second toad by using the average value of the third Euclidean distances.
In this embodiment, the matching image group includes a third toad contour image of the first toad and a fourth toad contour image of the second toad, which are acquired at the same time.
As an example, the growth trajectory similarity between the first toad and the second toad can be determined specifically by the following formula 6:
in formula 6, X a,b is used to characterize the similarity of growth trajectories between the a-th and b-th toads, And an average value used for characterizing the average value of the third Euclidean distances between the a-th toad and the b-th toad. OD a,b,k is used to characterize the third euclidean distance average of the a-th and b-th toads in the k-th matched image set, and OD a,b,k+1 is used to characterize the third euclidean distance average of the a-th and b-th toads in the k+1-th matched image set. K is used for representing the number of matched image groups, exp is used for representing exponential function operation.
Wherein, |od a,b,k-ODa,b,k+1 | is used to characterize the difference between the third euclidean distance averages in adjacent consecutive frame toad profile images. The larger the value, the less similar the growth track, i.e. the less similar the growth track between two toads.
According to the embodiment, the growth track similarity between the first toad and the second toad can be accurately measured by using the third Euclidean distance average value between the local descriptors of the key feature points of the third toad contour image of the first toad and the local descriptors of the key feature points corresponding to the fourth toad contour image of the second toad. Thereby facilitating the accurate grouping of the toads with similar growth tracks according to the growth track similarity.
As an optional embodiment, after S106, the method for visually monitoring the growth state of the whole life cycle of the toad culture may further include:
Determining a growth state result of the target toad according to each first toad contour image of the target toad;
comparing the growth state result of the target toad with a standard growth model to obtain a state comparison result;
And triggering an alarm mechanism under the condition that the state comparison result indicates abnormal growth state.
In this example, the growth status results were used to quantify the status of target toad growth, and standard growth models included the status results of normal toad growth at each stage.
The server calculates characteristics related to the growth state of the target toad, such as body length, body width, weight and the like, according to the outline images of the first toads of the target toad, so as to obtain a growth state result of the target toad. These features may be obtained by image measurement techniques such as pixel counting, scale calculations, etc.
Then, a standard growth model is established according to the growth rule and the historical data of the toads. This standard growth model may include a time-based growth curve, a relationship of body weight to body length, and the like. And then matching the growth state result of the target toad with the standard growth model, so as to evaluate whether the growth state of the target toad accords with the standard growth model.
And finally, immediately triggering an alarm mechanism under the condition of judging that the growth state is abnormal. Specifically, the method can comprise the steps of sending an email, a short message or a telephone notice to related personnel, or starting an automatic emergency response program, such as automatically adjusting the feeding environment, increasing the monitoring frequency and the like.
According to the embodiment, the growth state of the target toad is monitored according to each first toad contour image of the target toad. Under the condition of abnormal growth state, an alarm mechanism is triggered in time, so that the improvement of the toad breeding effect is facilitated.
It should be understood that the invention is not limited to the particular arrangements and instrumentality described above and shown in the drawings. For the sake of brevity, a detailed description of known methods is omitted here. In the above embodiments, several specific steps are described and shown as examples. The method processes of the present invention are not limited to the specific steps described and shown, but various changes, modifications and additions, or the order between steps may be made by those skilled in the art after appreciating the spirit of the present invention.
It should also be noted that the exemplary embodiments mentioned in this disclosure describe some methods or systems based on a series of steps or devices. The present invention is not limited to the order of the above-described steps, that is, the steps may be performed in the order mentioned in the embodiments, or may be performed in a different order from the order in the embodiments, or several steps may be performed simultaneously.
In the foregoing, only the specific embodiments of the present invention are described, and it will be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the systems, modules and units described above may refer to the corresponding processes in the foregoing method embodiments, which are not repeated herein. It should be understood that the scope of the present invention is not limited thereto, and any equivalent modifications or substitutions can be easily made by those skilled in the art within the technical scope of the present invention, and they should be included in the scope of the present invention.

Claims (9)

1.一种蟾蜍养殖的全生命周期生长状态视觉监测方法，其特征在于，所述方法包括：1. A method for visually monitoring the growth status of toads throughout their life cycle, comprising: 对目标蟾蜍进行视觉监测，实时获取所述目标蟾蜍的第一蟾蜍轮廓图像；Performing visual monitoring on a target toad and acquiring a first toad outline image of the target toad in real time; 在对所述目标蟾蜍监测中断的情况下，根据各所述第一蟾蜍轮廓图像，预测所述目标蟾蜍的疑似位置区域；When monitoring of the target toad is interrupted, predicting the suspected location area of the target toad based on each of the first toad outline images; 根据各所述第一蟾蜍轮廓图像以及所述疑似位置区域的区域特征图像，确定所述疑似位置区域中各候选蟾蜍与所述目标蟾蜍之间的特征匹配度；Determining a feature matching degree between each candidate toad and the target toad in the suspected location area according to each of the first toad outline images and the regional feature image of the suspected location area; 根据所述目标蟾蜍所属的蟾蜍组中各参考蟾蜍的第二蟾蜍轮廓图像，确定所述疑似位置区域中各候选蟾蜍与所述目标蟾蜍之间的生长轨迹符合度，所述蟾蜍组中包括生长轨迹相似的各个蟾蜍，所述参考蟾蜍为所述蟾蜍组中除所述目标蟾蜍之外被正常监测的蟾蜍；Determining, based on the second toad outline image of each reference toad in the toad group to which the target toad belongs, the degree of conformity of the growth trajectories of each candidate toad and the target toad in the suspected location area, wherein the toad group includes toads with similar growth trajectories, and the reference toads are toads in the toad group that are normally monitored except the target toad; 根据所述特征匹配度以及所述生长轨迹符合度，确定各所述候选蟾蜍与所述目标蟾蜍的整体匹配度；Determining the overall matching degree between each candidate toad and the target toad based on the feature matching degree and the growth trajectory conformity; 将所述整体匹配度最大的所述候选蟾蜍确定为所述目标蟾蜍，恢复对所述目标蟾蜍的视觉监测；Determine the candidate toad with the largest overall matching degree as the target toad, and resume visual monitoring of the target toad; 所述确定所述疑似位置区域中各候选蟾蜍与所述目标蟾蜍之间的生长轨迹符合度，包括：Determining the consistency of the growth trajectories of the candidate toads and the target toad in the suspected location area includes: 针对各所述参考蟾蜍，分别执行：根据所述参考蟾蜍的各所述第二蟾蜍轮廓图像，确定所述参考蟾蜍在各所述第二蟾蜍轮廓图像的生长状态变化速率；For each of the reference toads, respectively performing: determining, based on each of the second toad outline images of the reference toad, a growth state change rate of the reference toad in each of the second toad outline images; 针对各所述参考蟾蜍，分别执行：根据所述参考蟾蜍的各所述生长状态变化速率，以及所述参考蟾蜍的所述第二蟾蜍轮廓图像的关键特征点的局部描述符，与所述目标蟾蜍的所述第一蟾蜍轮廓图像中相对应的关键特征点的局部描述符之间的第二欧式距离平均值，确定所述参考蟾蜍的生长状态参考性；For each of the reference toads, respectively performing: determining the growth state reference of the reference toad based on the growth state change rate of each of the reference toads and the average second Euclidean distance between the local descriptors of the key feature points of the second toad outline image of the reference toad and the local descriptors of the corresponding key feature points in the first toad outline image of the target toad; 根据所述候选蟾蜍与各所述参考蟾蜍之间的生长轨迹相似性，以及各所述参考蟾蜍的生长状态参考性，确定所述候选蟾蜍与所述目标蟾蜍之间的生长轨迹符合度。The degree of conformity of the growth trajectory between the candidate toad and the target toad is determined based on the similarity of the growth trajectory between the candidate toad and each of the reference toads, as well as the reference of the growth status of each of the reference toads. 2.根据权利要求1所述的蟾蜍养殖的全生命周期生长状态视觉监测方法，其特征在于，所述在对所述目标蟾蜍监测中断的情况下，根据各所述第一蟾蜍轮廓图像，预测所述目标蟾蜍的疑似位置区域，包括：2. The visual monitoring method for the full life cycle growth status of toad breeding according to claim 1, characterized in that when the monitoring of the target toad is interrupted, the suspected position area of the target toad is predicted according to each of the first toad outline images, comprising: 在对所述目标蟾蜍监测中断的情况下，根据各所述第一蟾蜍轮廓图像，通过光流算法确定时间相邻的所述第一蟾蜍轮廓图像之间所述目标蟾蜍的各像素点的运动矢量；In the case where monitoring of the target toad is interrupted, determining, based on each of the first toad outline images, a motion vector of each pixel of the target toad between the first toad outline images adjacent in time by an optical flow algorithm; 根据所述目标蟾蜍的各像素点的运动矢量，预测所述目标蟾蜍的疑似位移量；Predicting the suspected displacement of the target toad according to the motion vector of each pixel point of the target toad; 根据所述目标蟾蜍监测中断前的位置以及所述疑似位移量，确定所述目标蟾蜍的疑似位置区域。The suspected position area of the target toad is determined based on the position of the target toad before monitoring is interrupted and the suspected displacement. 3.根据权利要求1所述的蟾蜍养殖的全生命周期生长状态视觉监测方法，其特征在于，所述根据各所述第一蟾蜍轮廓图像以及所述疑似位置区域的区域特征图像，确定所述疑似位置区域中各候选蟾蜍与所述目标蟾蜍之间的特征匹配度，包括：3. The visual monitoring method for the growth status of toads throughout their life cycle according to claim 1, wherein the step of determining the feature matching degree between each candidate toad and the target toad in the suspected position area based on each of the first toad outline images and the regional feature image of the suspected position area comprises: 针对所述疑似位置区域中各候选蟾蜍，分别执行以下步骤：For each candidate toad in the suspected location area, perform the following steps respectively: 对于各所述第一蟾蜍轮廓图像以及所述区域特征图像，分别提取关键特征点的局部描述符，所述局部描述符用于描述所述关键特征点局部区域的特征信息；For each of the first toad outline images and the regional feature images, extracting local descriptors of key feature points, respectively, wherein the local descriptors are used to describe feature information of a local area of the key feature points; 针对各所述第一蟾蜍轮廓图像，分别获取所述第一蟾蜍轮廓图像的关键特征点的局部描述符，与所述区域特征图像中相对应的关键特征点的局部描述符之间的第一欧式距离平均值；For each of the first toad outline images, respectively obtaining the average first Euclidean distance between the local descriptors of the key feature points of the first toad outline image and the local descriptors of the corresponding key feature points in the regional feature image; 利用各所述第一欧式距离平均值，确定所述候选蟾蜍与所述目标蟾蜍之间的特征匹配度。The feature matching degree between the candidate toad and the target toad is determined by using the average value of each of the first Euclidean distances. 4.根据权利要求1所述的蟾蜍养殖的全生命周期生长状态视觉监测方法，其特征在于，所述根据所述参考蟾蜍的各所述第二蟾蜍轮廓图像，确定所述参考蟾蜍在各所述第二蟾蜍轮廓图像的生长状态变化速率，包括：4. The method for visually monitoring the growth status of toads during their entire life cycle according to claim 1, wherein the step of determining the growth status change rate of the reference toad in each of the second toad outline images based on the reference toad comprises: 获取所述参考蟾蜍的各关键点对在目标第二蟾蜍轮廓图像以及所述目标第二蟾蜍轮廓图像的邻近蟾蜍轮廓图像中的直线距离，所述关键点对为任意两个所述关键特征点构成的点对；Obtaining straight-line distances between key point pairs of the reference toad in a target second toad outline image and an adjacent toad outline image of the target second toad outline image, wherein the key point pair is a point pair consisting of any two key feature points; 利用各所述关键点对在所述目标第二蟾蜍轮廓图像以及所述目标第二蟾蜍轮廓图像的邻近蟾蜍轮廓图像中的直线距离，确定所述参考蟾蜍在所述目标第二蟾蜍轮廓图像的生长状态变化速率。The growth state change rate of the reference toad in the target second toad outline image is determined by using the straight-line distances of each key point pair in the target second toad outline image and the adjacent toad outline images of the target second toad outline image. 5.根据权利要求1所述的蟾蜍养殖的全生命周期生长状态视觉监测方法，其特征在于，所述根据所述参考蟾蜍的各所述生长状态变化速率，以及所述参考蟾蜍的所述第二蟾蜍轮廓图像的关键特征点的局部描述符，与所述目标蟾蜍的所述第一蟾蜍轮廓图像中相对应的关键特征点的局部描述符之间的第二欧式距离平均值，确定所述参考蟾蜍的生长状态参考性，包括：5. The visual monitoring method for the growth status of toad farming throughout its life cycle according to claim 1, wherein the reference toad's growth status change rate is determined based on the local descriptors of the key feature points of the second toad outline image of the reference toad and the second Euclidean distance average between the local descriptors of the key feature points corresponding to the first toad outline image of the target toad, comprising: 基于所述参考蟾蜍的各所述生长状态变化速率，构成所述参考蟾蜍的生长状态变化速率序列；Based on the growth state change rates of the reference toads, a growth state change rate sequence of the reference toads is formed; 基于所述参考蟾蜍的所述第二蟾蜍轮廓图像的关键特征点的局部描述符，与所述目标蟾蜍的所述第一蟾蜍轮廓图像中相对应的关键特征点的局部描述符之间的第二欧式距离平均值，构成描述符距离序列，所述描述符距离序列中包括各所述第二欧式距离平均值；forming a descriptor distance sequence based on average second Euclidean distances between local descriptors of key feature points of the second toad outline image of the reference toad and local descriptors of corresponding key feature points in the first toad outline image of the target toad, wherein the descriptor distance sequence includes the average second Euclidean distances; 利用所述生长状态变化速率序列与所述描述符距离序列，确定所述参考蟾蜍的生长状态参考性。The growth state reference of the reference toad is determined by using the growth state change rate sequence and the descriptor distance sequence. 6.根据权利要求1所述的蟾蜍养殖的全生命周期生长状态视觉监测方法，其特征在于，所述根据所述候选蟾蜍与各所述参考蟾蜍之间的生长轨迹相似性，以及各所述参考蟾蜍的生长状态参考性，确定所述候选蟾蜍与所述目标蟾蜍之间的生长轨迹符合度，包括：6. The method for visually monitoring the growth status of the whole life cycle of toad breeding according to claim 1, wherein the growth trajectory similarity between the candidate toad and each of the reference toads, and the growth status reference of each of the reference toads, is determined to determine the growth trajectory conformity between the candidate toad and the target toad, comprising: 将各所述参考蟾蜍的生长状态参考性进行累加，得到第一累加值；Accumulating the growth status references of the reference toads to obtain a first accumulated value; 将各所述参考蟾蜍的生长状态参考性与对应的所述生长轨迹相似性的乘积进行累加，得到第二累加值；Accumulating the product of the growth status reference of each reference toad and the corresponding growth trajectory similarity to obtain a second accumulated value; 利用所述第二累加值以及所述第一累加值，确定所述候选蟾蜍与所述目标蟾蜍之间的生长轨迹符合度。The second accumulated value and the first accumulated value are used to determine the degree of consistency of the growth trajectories between the candidate toad and the target toad. 7.根据权利要求1所述的蟾蜍养殖的全生命周期生长状态视觉监测方法，其特征在于，所述根据所述目标蟾蜍所属的蟾蜍组中各参考蟾蜍的第二蟾蜍轮廓图像，确定所述疑似位置区域中各候选蟾蜍与所述目标蟾蜍之间的生长轨迹符合度之前，所述方法还包括：7. The method for visually monitoring the growth status of toads throughout their life cycle according to claim 1, wherein the method further comprises: 根据第一蟾蜍的第三蟾蜍轮廓图像与第二蟾蜍的第四蟾蜍轮廓图像，确定所述第一蟾蜍与所述第二蟾蜍之间的生长轨迹相似性；determining, based on the third toad outline image of the first toad and the fourth toad outline image of the second toad, similarity in growth trajectories between the first toad and the second toad; 基于各所述生长轨迹相似性进行密度聚类，得到至少一个所述蟾蜍组。Density clustering is performed based on the similarity of each growth trajectory to obtain at least one toad group. 8.根据权利要求7所述的蟾蜍养殖的全生命周期生长状态视觉监测方法，其特征在于，所述根据第一蟾蜍的第三蟾蜍轮廓图像与第二蟾蜍的第四蟾蜍轮廓图像，确定所述第一蟾蜍与所述第二蟾蜍之间的生长轨迹相似性，包括：8. The method for visually monitoring the growth status of toads throughout their life cycle according to claim 7, wherein determining the similarity of growth trajectories between the first toad and the second toad based on the third toad outline image of the first toad and the fourth toad outline image of the second toad comprises: 将所述第一蟾蜍的第三蟾蜍轮廓图像与所述第二蟾蜍的第四蟾蜍轮廓图像进行匹配，得到匹配图像组，所述匹配图像组中包括相同时刻的所述第三蟾蜍轮廓图像与所述第四蟾蜍轮廓图像；Matching the third toad outline image of the first toad with the fourth toad outline image of the second toad to obtain a matching image group, wherein the matching image group includes the third toad outline image and the fourth toad outline image at the same moment; 获取所述匹配图像组中所述第三蟾蜍轮廓图像的关键特征点的局部描述符，与所述第四蟾蜍轮廓图像中相对应的关键特征点的局部描述符之间的第三欧式距离平均值；Obtaining an average third Euclidean distance between the local descriptors of the key feature points of the third toad outline image in the matching image group and the local descriptors of the corresponding key feature points in the fourth toad outline image; 利用各所述第三欧式距离平均值，确定所述第一蟾蜍与所述第二蟾蜍之间的生长轨迹相似性。The similarity of the growth trajectories between the first toad and the second toad is determined by using the average values of the third Euclidean distances. 9.根据权利要求1所述的蟾蜍养殖的全生命周期生长状态视觉监测方法，其特征在于，所述将所述整体匹配度最大的所述候选蟾蜍确定为所述目标蟾蜍，恢复对所述目标蟾蜍的视觉监测之后，所述方法还包括：9. The method for visually monitoring the growth status of toads throughout their life cycle according to claim 1, wherein the candidate toad with the largest overall matching degree is determined as the target toad, and after visual monitoring of the target toad is resumed, the method further comprises: 根据所述目标蟾蜍的各所述第一蟾蜍轮廓图像，确定所述目标蟾蜍的生长状态结果；determining the growth status result of the target toad according to each of the first toad outline images of the target toad; 将所述目标蟾蜍的生长状态结果与标准生长模型进行比较，得到状态比较结果；Comparing the growth status result of the target toad with the standard growth model to obtain a status comparison result; 在所述状态比较结果指示生长状态异常的情况下，触发报警机制。In the case where the status comparison result indicates that the growth status is abnormal, an alarm mechanism is triggered.
CN202510226778.2A 2025-02-27 2025-02-27 A visual monitoring method for the growth status of toads throughout their life cycle Active CN120164004B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202510226778.2A CN120164004B (en) 2025-02-27 2025-02-27 A visual monitoring method for the growth status of toads throughout their life cycle

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202510226778.2A CN120164004B (en) 2025-02-27 2025-02-27 A visual monitoring method for the growth status of toads throughout their life cycle

Publications (2)

Publication Number Publication Date
CN120164004A CN120164004A (en) 2025-06-17
CN120164004B true CN120164004B (en) 2025-08-22

Family

ID=96008172

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202510226778.2A Active CN120164004B (en) 2025-02-27 2025-02-27 A visual monitoring method for the growth status of toads throughout their life cycle

Country Status (1)

Country Link
CN (1) CN120164004B (en)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112580476A (en) * 2020-12-14 2021-03-30 深圳创怀医疗科技有限公司 Sperm identification and multi-target track tracking method
CN117726648A (en) * 2023-11-01 2024-03-19 北京盈迪曼德科技有限公司 Target object determination method and system to be tracked and robot

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
AU2012244276A1 (en) * 2012-10-30 2014-05-15 Canon Kabushiki Kaisha Method, apparatus and system for detecting a supporting surface region in an image

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112580476A (en) * 2020-12-14 2021-03-30 深圳创怀医疗科技有限公司 Sperm identification and multi-target track tracking method
CN117726648A (en) * 2023-11-01 2024-03-19 北京盈迪曼德科技有限公司 Target object determination method and system to be tracked and robot

Also Published As

Publication number Publication date
CN120164004A (en) 2025-06-17

Similar Documents

Publication Publication Date Title
CN107480704B (en) Real-time visual target tracking method with shielding perception mechanism
CN108222749B (en) Intelligent automatic door control method based on image analysis
CN103854292B (en) A kind of number and the computational methods and device in crowd movement direction
CN110633643A (en) Abnormal behavior detection method and system for smart community
CN110717934B (en) A STRCF-Based Anti-Occlusion Target Tracking Method
Pinho et al. Efficient approximation of the Mahalanobis distance for tracking with the Kalman filter
CN120108161B (en) Tunnel construction monitoring analysis method and system based on AI video monitoring
CN111368770B (en) Gesture recognition method based on skeleton point detection and tracking
CN112233145A (en) A multi-target occlusion tracking method based on RGB-D spatiotemporal context model
CN107301657A (en) A kind of video target tracking method for considering target movable information
CN113344968A (en) Orchard fruit identification and yield statistical system and method
CN112307897A (en) Pet tracking method based on local feature recognition and adjacent frame matching in community monitoring scene
CN110349188A (en) Multi-object tracking method, device and storage medium based on TSK fuzzy model
CN110956141B (en) A Rapid Analysis Method of Human Continuous Motion Based on Partial Recognition
CN119479075A (en) Subway fall detection method and system based on cloud-edge collaboration and X-CLIP model
CN120164004B (en) A visual monitoring method for the growth status of toads throughout their life cycle
CN114118528B (en) Ship track real-time forecasting method based on combination of linear filter and nonlinear filter
CN113192110A (en) Multi-target tracking method, device, equipment and storage medium
Zhang et al. Uncertain motion tracking combined markov chain monte carlo and correlation filters
CN107067411B (en) Mean-shift tracking method combined with dense features
CN113591702A (en) Video image foreground extraction method and device
Liu et al. Research on A Binocular Fish Dimension Measurement Method Based on Instance Segmentation and Fish Tracking
CN113313734A (en) Moving target tracking method based on linear extrapolation prediction
CN117455918B (en) Anti-blocking feeding method and system based on image analysis
CN112508962B (en) Target image region subsequence separation method based on time-associated image sequence

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