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

Abstract

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

Technical Field

[0001] The present invention relates to the technical field of image matching, and in particular to a method for visually monitoring the growth status of toads throughout their life cycle. Background Art

[0002] Toad farming refers to the use of artificial environments to raise, reproduce and manage toads. By monitoring the growth status of toads throughout their entire life cycle from fertilized eggs, tadpoles, metamorphosis, larvae to adults and finally reproduction, including body size, weight, appearance characteristics and behavioral activities, the individual health and development level of toads can be accurately measured.

[0003] At present, automated visual detection technology is used to monitor the growth status of toads throughout their life cycle in real time, and feature information is extracted through image processing methods to determine the toads' growth stage, behavioral status and possible health abnormalities.

[0004] However, occlusion is prone to occur during toad monitoring, which makes it impossible to fully track the toads and results in poor accuracy in monitoring the toad growth status. Summary of the Invention

[0005] The embodiment of the present invention provides a method for visually monitoring the growth status of toads throughout their life cycle, which can improve the accuracy of monitoring the growth status of toads.

[0006] A first aspect of an embodiment of the present invention provides a method for visually monitoring the growth status of toads throughout their life cycle, comprising:

[0007] Performing visual monitoring on the target toad and acquiring the first toad outline image of the target toad in real time;

[0008] In the case where the monitoring of the target toad is interrupted, the suspected location area of ​​the target toad is predicted based on each first toad outline image;

[0009] Determining a feature matching degree between each candidate toad and the target toad in the suspected position area based on each first toad outline image and the regional feature image of the suspected position area;

[0010] Determine the consistency of the growth trajectories of each candidate toad and the target toad in the suspected location area based on the second toad outline image of each reference toad in the toad group to which the target toad belongs. 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.

[0011] Determine the overall matching degree between each candidate toad and the target toad based on the matching degree of characteristics and the conformity of growth trajectory;

[0012] The candidate toad with the greatest overall matching degree is identified as the target toad, and visual monitoring of the target toad is resumed.

[0013] In the visual monitoring method for the growth status of toads throughout their life cycle, provided by an embodiment of the present invention, if monitoring of a target toad is interrupted, the target toad's suspected location area is first predicted based on each first toad outline image of the target toad. This provides an approximate location for subsequent positioning of the target toad, narrowing the matching range. Then, based on each first toad outline image and the regional feature image of the suspected location area, the degree of feature matching between each candidate toad and the target toad in the suspected location area is determined. Simultaneously, 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 between the growth trajectory of each candidate toad and the target toad in the suspected location area is determined. In this way, relying on reference toads with similar growth trajectories to the target toad and the feature matching between each candidate toad and the target toad in the suspected location area, the target toad's position within the suspected location area can be accurately determined. In summary, even if monitoring of the target toad is interrupted due to occlusion or other reasons during toad monitoring, the target toad can still be accurately tracked, thereby improving the accuracy of toad growth status monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0015] Figure 1 A schematic flow chart of a first method for visually monitoring the growth status of toads throughout their life cycle provided by one embodiment of the present invention;

[0016] Figure 2 A schematic flow chart of a second method for visually monitoring the growth status of toads throughout their life cycle provided by one embodiment of the present invention;

[0017] Figure 3 A schematic flow chart of a third method for visually monitoring the growth status of toads throughout their life cycle provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0018] In order to further illustrate the technical means and effects adopted by the present invention to achieve the predetermined purpose of the invention, the following is a detailed description of the method for visually monitoring the growth status of toad farming throughout its life cycle proposed in accordance with the present invention, in conjunction with the accompanying drawings and preferred embodiments, its specific implementation method, structure, characteristics and effects are described as follows. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0019] 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.

[0020] It should be noted that the acquisition, storage, use, and processing of data in the technical solution of the present invention comply with the relevant provisions of laws and regulations.

[0021] It should be noted that in the embodiments of the present invention, certain software, components, models and other existing solutions in the industry may be mentioned. They should be regarded as exemplary and their purpose is only to illustrate the feasibility of implementing the technical solution of the present invention, but it does not mean that the applicant has or will necessarily use the solution.

[0022] Toad farming refers to the use of artificial environments to raise, reproduce and manage toads. By monitoring the growth status of toads throughout their entire life cycle from fertilized eggs, tadpoles, metamorphosis, larvae to adults and finally reproduction, including body size, weight, appearance characteristics and behavioral activities, the individual health and development level of toads can be accurately measured.

[0023] Currently, automated visual inspection technology is used to monitor the growth status of toads throughout their life cycle in real time. Image processing methods are used to extract feature information to determine the toads' growth stage, behavioral status, and possible health abnormalities. However, occlusion is common during toad monitoring, making it impossible to fully track the toads, resulting in poor accuracy in toad growth status monitoring.

[0024] The present invention aims to provide a method for visually monitoring the growth status of toads throughout their entire life cycle. In the method provided by an embodiment of the present invention, if monitoring of a target toad is interrupted, the target toad's suspected location area is first predicted based on each first toad outline image of the target toad. This provides an approximate location for subsequent positioning of the target toad, narrowing the matching range. Then, based on each first toad outline image and the regional feature image of the suspected location area, the degree of feature matching between each candidate toad and the target toad in the suspected location area is determined. Simultaneously, 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 between the growth trajectory of each candidate toad and the target toad in the suspected location area is determined. In this way, relying on reference toads with similar growth trajectories to the target toad and the feature matching between each candidate toad and the target toad in the suspected location area, the target toad's position within the suspected location area can be accurately determined. In summary, even if the monitoring of the target toad is interrupted due to occlusion or the like during the toad monitoring process, the target toad can still be accurately tracked, thereby improving the accuracy of the toad growth status monitoring.

[0025] The following describes a specific embodiment of a method for visually monitoring the growth status of toads throughout their life cycle, as provided by an embodiment of the present invention.

[0026] Figure 1 A flow chart of a method for visually monitoring the growth status of toads throughout their life cycle is provided. The method can be applied to a server and may include steps S101 to S106.

[0027] S101, visually monitoring a target toad, and acquiring a first toad outline image of the target toad in real time.

[0028] In this example, target toads were used to characterize toads that required visual monitoring.

[0029] For example, a high-definition camera or other visual sensor is installed within the target toad's activity area to ensure clear images. The server then uses the monitoring device to collect images of the target toad at a preset frequency and processes the collected images using image processing algorithms (such as edge detection and contour extraction) to extract the first contour image of the target toad.

[0030] S102 , when monitoring of the target toad is interrupted, predicting the suspected location area of ​​the target toad based on each first toad outline image.

[0031] In this embodiment, the interruption of monitoring the target toad means losing the position of the target toad. For example, when there is an obstacle blocking the target toad, the interruption of monitoring the target toad will occur.

[0032] The suspected location area is used to characterize the area where the target toad is suspected to be located after the monitoring of the target toad is interrupted.

[0033] As an example, when the server cannot collect the first toad outline image of the toad image through the monitoring device, it can be considered that the position of the target toad is lost, that is, the monitoring of the target toad is interrupted.

[0034] At this time, the server uses the first toad outline image of the target toad in history to infer the movement pattern of the target toad through machine learning or statistical analysis, thereby predicting the suspected location area where the target toad will reach after being blocked.

[0035] S103 , determining a feature matching degree between each candidate toad and the target toad in the suspected position area according to each first toad outline image and the regional feature image of the suspected position area.

[0036] In this embodiment, the region feature image is used to represent the image of the suspected location region at the current moment, and the candidate toads are used to represent the individual toads included in the region feature image.

[0037] The feature matching degree is used to characterize the similarity between the candidate toad and the target toad. For example, the similarity can include skin roughness, spot distribution, body edge, eyes, and limb outlines.

[0038] As an example, the server identifies all candidate toads from the regional feature image of the suspected location area, and extracts features of the candidate toads and the target toad respectively based on the first toad outline image of the target toad and the regional feature image of the suspected location area.

[0039] Then, a feature matching algorithm (such as template matching, similarity calculation, etc.) is used to calculate the feature matching degree between each candidate toad and the target toad.

[0040] S104, determining the consistency of the growth trajectories of each candidate toad and the target toad in the suspected position area based on the second toad outline image of each reference toad in the toad group to which the target toad belongs, wherein the toad group includes toads with similar growth trajectories, and the reference toads are the toads in the toad group that are normally monitored except the target toad.

[0041] In this embodiment, the toad group includes multiple toads, and the growth trajectories of the toads in the toad group are similar. The reference toads are the toads in the toad group that are normally monitored except the target toad, that is, the toads in the toad group that have not been interrupted in monitoring.

[0042] The second toad outline image is used to characterize the toad outline image corresponding to the reference toad, and the growth trajectory conformity is used to characterize the degree of conformity between the growth trajectories of the candidate toad and the target toad.

[0043] As an example, the server obtains the second outline image of each reference toad in the toad group to which the target toad belongs. Then, based on the second outline image of each reference toad, the server uses image processing and time series analysis techniques to analyze the growth trajectory of the reference toad.

[0044] Then, based on the growth trajectories of the reference toads, the current growth status of the target toad is inferred. Finally, the current growth status of the candidate toad is compared with the inferred current growth status of the target toad to determine the degree of consistency between the growth trajectories of the candidate toad and the target toad.

[0045] S105, determining the overall matching degree between each candidate toad and the target toad based on the feature matching degree and the growth trajectory conformity.

[0046] In this embodiment, different weights are assigned to the feature matching degree and the growth trajectory conformity according to actual needs.

[0047] Then, the server uses weighted average or other comprehensive calculation methods to combine the feature matching and growth trajectory conformity to calculate the overall matching degree between each candidate toad and the target toad.

[0048] As an example, the overall matching degree between the candidate toad and the target toad can be determined by the following formula 1:

[0049] Y i =Z i ×(1+F i ) Formula 1

[0050] In formula 1, Y i It is used to characterize the overall matching degree between the i-th candidate toad and the target toad, Z i It is used to characterize the matching degree between the i-th candidate toad and the target toad, F i Used to characterize the consistency of the growth trajectory of the i-th candidate toad and the target toad.

[0051] S106, determining the candidate toad with the largest overall matching degree as the target toad, and resuming visual monitoring of the target toad.

[0052] In this embodiment, among the candidate toads, the one with the largest overall matching degree is determined as the target toad.

[0053] Then, the server controls and adjusts the monitoring equipment's parameters such as angle and focal length to ensure that the image of the target toad can be clearly captured, thereby resuming tracking and visual monitoring of the target toad.

[0054] In the visual monitoring method for the growth status of toads throughout their life cycle provided by this embodiment, when monitoring of a target toad is interrupted, the target toad's suspected location area is first predicted based on each first toad outline image of the target toad. This allows for the subsequent positioning of the target toad to provide an approximate location and narrows the scope of the match. Then, based on each first toad outline image and the regional feature image of the suspected location area, the feature matching degree between each candidate toad and the target toad in the suspected location area is determined. Simultaneously, based on the second toad outline image of each reference toad in the toad group to which the target toad belongs, the growth trajectory conformity between each candidate toad and the target toad in the suspected location area is determined. In this way, relying on reference toads with similar growth trajectories to the target toad and the feature matching between each candidate toad and the target toad in the suspected location area, the position of the target toad in the suspected location area can be accurately determined. In summary, even when monitoring of the target toad is interrupted due to occlusion or the like during toad monitoring, the target toad can still be accurately tracked, thereby improving the accuracy of toad growth status monitoring.

[0055] As an optional embodiment, S102 may specifically include:

[0056] In the case where the monitoring of the target toad is interrupted, the motion vector of each pixel point of the target toad between the first toad outline images adjacent in time is determined by an optical flow algorithm according to each first toad outline image;

[0057] According to the motion vector of each pixel point of the target toad, the suspected displacement of the target toad is predicted;

[0058] Based on the target toad's position before monitoring was interrupted and the suspected displacement, the suspected location area of ​​the target toad was determined.

[0059] In this embodiment, first, the server preprocesses two temporally adjacent frames of the first toad outline image, including denoising, grayscale conversion, etc., to ensure the accuracy of subsequent optical flow calculation.

[0060] Then, an optical flow algorithm (such as the Lucas-Kanade algorithm or the Horn-Schunck algorithm) is applied between the two frames to obtain the local motion vector of each pixel of the target toad between the two frames. The basic idea of ​​the optical flow algorithm is to estimate the motion of an object by comparing the brightness changes of pixels between adjacent frames in the image sequence. For the Lucas-Kanade algorithm, it assumes that the motion of all pixels in a small window is consistent, and then solves the motion vector by minimizing the brightness error function; for the Horn-Schunck algorithm, it introduces a global smoothness constraint, assuming that the motion field changes smoothly, and obtains the motion vector by solving an energy minimization problem.

[0061] Since the target toad may be composed of multiple pixels, its overall motion can be approximated by averaging or weighting the motion vectors of these pixels. This allows the global motion vector between the two frames to be obtained based on the average or weighted average of the motion vectors of these pixels. When performing the weighted average, the weights can be assigned based on the distance of the pixels relative to the center of the target toad.

[0062] Then, the global motion vectors corresponding to the two adjacent frames of the first toad outline image at each time are averaged and then converted into the displacement of the target toad to obtain the suspected displacement of the target toad.

[0063] Finally, the final position before monitoring was interrupted is added to the calculated suspected displacement to obtain the predicted position of the target toad after monitoring was interrupted. Because motion prediction can be erroneous, the target toad's position is not predicted at a single point, but rather as an area. This area can be a rectangle, ellipse, or other shape centered at the predicted position and of a specific size and shape. The size and shape of the area can be determined based on factors such as the uncertainty of the displacement and the target toad's movement speed.

[0064] Through this embodiment, when monitoring is interrupted, the suspected location area of ​​the target toad is predicted based on the optical flow algorithm. This allows the target toad's location to be roughly estimated, thereby reducing the amount of calculation for subsequent recovery tracking and improving the efficiency of target toad recovery tracking.

[0065] As an optional embodiment, S103 may specifically include:

[0066] For each candidate toad in the suspected location area, perform the following steps:

[0067] For each first toad outline image and regional feature image, extract local descriptors of key feature points respectively, where the local descriptors are used to describe feature information of a local region of the key feature points;

[0068] For each first toad outline image, 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;

[0069] The average value of each first Euclidean distance is used to determine the feature matching degree between the candidate toad and the target toad.

[0070] In this embodiment, the local descriptor is used to describe the feature information of the local area of ​​the key feature point. Specifically, the local descriptor can be extracted by using a Scale-Invariant Feature Transform (SIFT) feature extraction algorithm.

[0071] As an example, the feature matching degree between the candidate toad and the target toad can be determined by the following formula 2:

[0072]

[0073] In formula 2, Z i It is used to characterize the matching degree between the i-th candidate toad and the target toad, g i,n The number of frames between the first toad outline image of the nth frame before occlusion used to represent the i-th candidate toad in the regional feature image and the target toad, D i,n This is used to represent the average first Euclidean distance between the i-th candidate toad and the first toad outline image of the target toad in the n-th frame before occlusion in the regional feature image. N is used to represent the total number of first toad outline images, and exp is used to represent the exponential function operation.

[0074] in, The fewer the interval frames between the first toad outline image of the nth frame before occlusion used to represent the i-th candidate toad in the regional feature image and the target toad, the greater the reference significance of the average value of the first Euclidean distance. That is, the closer the time of the first toad outline image is to the regional feature image after occlusion, the more reference significance it has.

[0075] This embodiment accurately determines the degree of feature matching between each candidate toad and the target toad in the suspected location region based on the first toad outline image and the regional feature image of the suspected location region. This facilitates subsequent accurate positioning of the target toad based on the feature matching, thereby improving the accuracy of toad growth status monitoring.

[0076] As an optional embodiment, Figure 2 As shown, S104 may specifically include the following S201 to S203:

[0077] S201, for each reference toad, respectively performing: determining, based on each second toad outline image of the reference toad, a growth state change rate of the reference toad in each second toad outline image;

[0078] S202, for each reference toad, respectively performing: determining the growth state reference of the reference toad based on the growth state change rate of each reference toad and the average of the second Euclidean distances 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;

[0079] S203, determining the growth trajectory conformity between the candidate toad and the target toad based on the growth trajectory conformity between the candidate toad and each reference toad, and the growth status reference of each reference toad.

[0080] In this embodiment, the growth state change rate is used to characterize the change rate of the reference toad's outline in each second toad outline image.

[0081] Growth status reference is used to characterize the extent to which the growth status of a reference toad can be used as a reference for the target toad.

[0082] The second toad outline image is used to characterize the toad outline image corresponding to the reference toad.

[0083] As an optional embodiment, the server first collects the second toad outline images of each reference toad at different time points. For each second toad outline image, an image processing algorithm (such as edge detection, outline tracking, etc.) is used to extract the outline of the toad.

[0084] Then, for each second toad outline image, a feature point matching algorithm (such as SIFT, SURF, etc.) is used to find the key feature points corresponding to the previous second toad outline image. Based on the matched key feature points, the displacement of each key feature point at adjacent times is calculated, and then the rate of change of the entire outline is calculated, that is, the rate of change of the growth state of the reference toad in the second toad outline image. Specifically, this can be achieved by calculating the mean value, standard deviation or other statistics of the key feature point displacements.

[0085] Next, for each reference toad's second outline image and the target toad's first outline image, local descriptors of key feature points are calculated. The similarity between the two is measured by calculating the average Euclidean distance between the local descriptors of the corresponding key feature points. The growth status of the reference toad is then determined using a weighted summation, product, or other combination of methods, combined with the growth status change rate of the reference toad and the average second Euclidean distance.

[0086] Finally, for each candidate toad, calculate the growth track similarity between itself and each reference toad. Specifically, this can be achieved by comparing the profile changes of candidate toad and reference toad at different time points, using similarity metrics (such as profile matching, shape context, etc.) to evaluate growth track similarity. According to the growth state reference of each reference toad, the growth track similarity between candidate toad and each reference toad is weighted and summed, thereby obtaining the growth track compliance between candidate toad and target toad. Wherein, weight can be determined according to the growth state reference of reference toad, and the higher the reference, the greater the weight.

[0087] By the present embodiment, according to the second toad outline image of each reference toad in the toad group to which the target toad belongs, the growth track conformity between each candidate toad and the target toad in the suspected position area is determined. In this way, relying on a reference toad with a similar growth track as the target toad as a reference, the growth track conformity between the candidate toad and the target toad can be accurately calculated. Thereby contributing to the subsequent accurate screening of candidate toads according to the growth track conformity, thereby improving the accuracy of toad growth status monitoring.

[0088] As an optional embodiment, S201 may specifically include:

[0089] Obtaining straight-line distances between key point pairs of the reference toad in the target second toad outline image and the adjacent toad outline images of the target second toad outline image, wherein the key point pair is a point pair consisting of any two key feature points;

[0090] 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.

[0091] In this embodiment, the growth state change rate of the reference toad in the target second toad outline image can be specifically determined by the following formula 3:

[0092]

[0093] In Formula 3, S is used to represent the growth state change rate, and T is used to represent the number of key point pairs. R is used to represent the number of images, that is, the number of the target second toad outline image and the number of toad outline images adjacent to the target second toad outline image. Among them, the second toad outline images of the five frames before and after the target second toad outline image can be preset as the adjacent toad outline images of the target second toad outline image. L t,r Used to represent the straight-line distance between the t-th key point pair in the r-th frame image, L t,r+1 Used to represent the straight-line distance between the t-th key point pair in the r+1-th frame image.

[0094] in, The difference between the distance ratio of the key point pairs used to characterize the toad in adjacent image frames and 1. The larger the value, the greater the change in the toad's morphology, that is, the faster the rate of change in the toad's growth state.

[0095] This embodiment uses the linear distances between key pairs of toads in the target second toad outline image and the adjacent toad outline images of the target second toad outline image to accurately determine the rate of change in the growth status of the reference toad in the target second toad outline image. This helps to subsequently determine the reference value of the growth status of the reference toad based on the growth status change rate, thereby improving the accuracy of toad growth status monitoring.

[0096] As an optional embodiment, S202 may specifically include:

[0097] Based on the change rates of each growth state of the reference toad, a growth state change rate sequence of the reference toad is constructed;

[0098] A descriptor distance sequence is formed based on the average second Euclidean distances 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, wherein the descriptor distance sequence includes the average second Euclidean distances;

[0099] The growth state reference of the reference toad was determined using the growth state change rate sequence and the descriptor distance sequence.

[0100] In this embodiment, the growth state change rate sequence includes the growth state change rate of the reference toad in each second toad outline image.

[0101] The descriptor distance sequence includes the average second Euclidean distances between the local descriptors of the key feature points of each second toad outline image and the local descriptors of the corresponding key feature points in each first toad outline image of the target toad.

[0102] As an example, the growth status of a reference toad can be determined by the following formula 4:

[0103] Q w =ρ(S w ,exp(-D w )) Formula 4

[0104] In formula 4, Q w Used to characterize the growth status of the wth reference toad, S w Used to characterize the growth state change rate sequence of the wth reference toad, D wis used to characterize the descriptor distance sequence of the w-th reference toad, and ρ is used to characterize the Pearson correlation coefficient.

[0105] Among them, 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 reference of the growth state of the w-th reference toad.

[0106] This embodiment uses a growth state change rate sequence composed of the growth state change rates and a descriptor distance sequence composed of the average values ​​of the second Euclidean distances to accurately assess the growth state referenceability of a reference toad. This facilitates subsequent determination of the degree of consistency between the growth trajectories of candidate toads and target toads based on the growth state referenceability, thereby improving the accuracy of toad growth state monitoring.

[0107] As an optional embodiment, S203 may specifically include:

[0108] Accumulating the growth status references of the reference toads to obtain a first accumulated value;

[0109] Accumulating the product of the growth state reference of each reference toad and the corresponding growth trajectory similarity to obtain a second accumulated value;

[0110] The second accumulated value and the first accumulated value are used to determine the degree of conformity of the growth trajectories between the candidate toad and the target toad.

[0111] In this embodiment, the growth trajectory consistency between the candidate toad and the target toad can be determined by the following formula 5:

[0112]

[0113] In formula 5, Q w Used to characterize the growth status of the w-th reference toad, X i,w It is used to characterize the similarity of the growth trajectory between the i-th candidate toad and the w-th reference toad, W is used to characterize the number of reference toads, and F i Used to characterize the consistency of the growth trajectory between the i-th candidate toad and the target toad.

[0114] Among them, the greater the similarity between the growth trajectory of the candidate toad and each reference toad, the greater the consistency of the growth trajectory between the candidate toad and the target toad; the greater the reference of the growth status of the reference toad, the more reference significance the similarity between the growth trajectory of the candidate toad and the reference toad has.

[0115] This embodiment utilizes the similarity of the growth trajectories between a candidate toad and each reference toad, as well as the reference growth status of each reference toad, to accurately determine the degree of conformity between the growth trajectories of the candidate toad and the target toad. This facilitates subsequent precise positioning of the target toad based on the conformity of the growth trajectories, thereby improving the accuracy of toad growth status monitoring.

[0116] As an optional embodiment, Figure 3 As shown, before S104, the visual monitoring method for the growth status of toad farming throughout its life cycle may further include the following S301 to S302:

[0117] S301, 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;

[0118] S302, performing density clustering based on the similarity of each growth trajectory to obtain at least one toad group.

[0119] In this embodiment, the first toad and the second toad are any two toads, the third toad outline image is the toad outline image corresponding to the first toad, and the fourth toad outline image is the toad outline image corresponding to the second toad.

[0120] As an example, the server uses a similarity metric (such as contour matching, shape context, etc.) to evaluate the similarity of the growth trajectories between the first toad and the second toad by comparing the contour changes between the third toad contour image of the first toad and the fourth toad contour image of the second toad.

[0121] Next, select a density clustering algorithm, such as DBSCAN or HDBSCAN, and set its parameters, such as the minimum number of samples (MinPts) and the radius (Eps). Then, based on the similarity of the growth trajectories of the toads, apply the selected clustering algorithm to cluster them, resulting in at least one toad group.

[0122] Through this embodiment, based on the similarity of the growth trajectories of the toads, density clustering is performed on the toads to obtain at least one toad group. The resulting toad group thus includes toads with similar growth trajectories. This facilitates subsequent tracking of the target toad by relying on reference toads with similar growth trajectories if monitoring of the target toad is interrupted, thereby improving the accuracy of toad growth status monitoring.

[0123] As an optional embodiment, S301 may specifically include:

[0124] 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 time;

[0125] Obtaining an average third Euclidean distance between the local descriptor of the key feature point in the third toad outline image in the matching image group and the local descriptor of the corresponding key feature point in the fourth toad outline image;

[0126] The similarity of the growth trajectories between the first and second toads was determined using the average of the third Euclidean distances.

[0127] In this embodiment, the matching image group includes the third toad outline image of the first toad and the fourth toad outline image of the second toad that are acquired at the same time.

[0128] As an example, the similarity of the growth trajectories between the first toad and the second toad can be determined by the following formula 6:

[0129]

[0130] In formula 6, X a,b Used to characterize the similarity of the growth trajectories between the ath toad and the bth toad, The average value of the third Euclidean distance between the ath toad and the bth toad. a,b,k The average value of the third Euclidean distance between the a-th toad and the b-th toad in the k-th matching image group, OD a,b,k+1 This is used to represent the average third Euclidean distance between the a-th toad and the b-th toad in the k+1-th matching image group. K represents the number of matching image groups, and exp represents the exponential function operation.

[0131] Among them, |OD a,b,k -OD a,b,k+1 |This parameter represents the difference between the average third Euclidean distances in consecutive frames of toad outline images. A larger value indicates a less similar growth trajectory, meaning the growth trajectories of the two toads are less similar.

[0132] This embodiment uses the average third Euclidean distance between the local descriptors of key feature points in the third toad's outline image and the corresponding local descriptors of key feature points in the fourth toad's outline image to accurately measure the similarity of the growth trajectories between the first and second toads. This facilitates the subsequent accurate grouping of toads with similar growth trajectories based on growth trajectory similarity.

[0133] As an optional embodiment, after S106, the method for visually monitoring the growth status of toads during their entire life cycle may further include:

[0134] determining a growth status result of the target toad according to each first toad outline image of the target toad;

[0135] Comparing the growth status results of the target toad with the standard growth model to obtain status comparison results;

[0136] When the status comparison result indicates that the growth status is abnormal, an alarm mechanism is triggered.

[0137] In this embodiment, the growth status results are used to quantify the growth status of the target toad, and the standard growth model includes the normal growth status results of the toad at each stage.

[0138] The server calculates features related to the target toad's growth status, such as body length, body width, and weight, based on each first toad outline image, thereby obtaining the target toad's growth status. These features can be obtained through image measurement techniques, such as pixel counting and ratio calculation.

[0139] Then, based on toad growth patterns and historical data, a standard growth model is established. This standard growth model can include time-based growth curves, the relationship between weight and body length, and other factors. The target toad's growth status results are then matched with the standard growth model to assess whether the target toad's growth status conforms to the standard growth model.

[0140] Finally, if the growth status is judged to be abnormal, an alarm mechanism is immediately triggered. This may include sending an email, text message or phone notification to relevant personnel, or launching an automatic emergency response program, such as automatically adjusting the breeding environment or increasing the monitoring frequency.

[0141] Through this embodiment, the growth status of the target toad is monitored based on each first toad outline image of the target toad. In the case of abnormal growth status, an alarm mechanism is triggered in time, thereby helping to improve the effect of toad breeding.

[0142] It should be understood that the present invention is not limited to the specific configurations and processes described above and illustrated in the figures. For the sake of brevity, a detailed description of known methods is omitted. In the above embodiments, several specific steps are described and illustrated as examples. However, the method of the present invention is not limited to the specific steps described and illustrated. Those skilled in the art may make various changes, modifications, and additions, or change the order of the steps after understanding the spirit of the present invention.

[0143] It should also be noted that the exemplary embodiments described herein describe methods or systems based on a series of steps or devices. However, the present invention is not limited to the order of the steps described above. In other words, the steps may be performed in the order described in the embodiments, or in a different order, or several steps may be performed simultaneously.

[0144] The above description is only a specific embodiment of the present invention. Those skilled in the art will clearly understand that for the convenience and brevity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present invention is not limited to this. Any person skilled in the art can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention.

Claims

1. A method for visually monitoring the growth status of toads throughout their life cycle, characterized in that: The method comprises: Performing visual monitoring on a target toad and acquiring a first toad outline image of the target toad in real time; 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; 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; 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; Determining the overall matching degree between each candidate toad and the target toad based on the feature matching degree and the growth trajectory conformity; Determine the candidate toad with the largest overall matching degree as the target toad, and resume visual monitoring of the target toad; Determining the consistency of the growth trajectories of the candidate toads and the target toad in the suspected location area includes: 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; 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; 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. The method for visually monitoring the growth status of toads during their entire life cycle according to claim 1, wherein: 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 includes: 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; Predicting the suspected displacement of the target toad according to the motion vector of each pixel point of the target toad; 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. The method for visually monitoring the growth status of toads during their entire life cycle according to claim 1, wherein: The determining, based on each of the first toad outline images and the regional feature image of the suspected location area, a feature matching degree between each candidate toad and the target toad in the suspected location area includes: For each candidate toad in the suspected location area, perform the following steps respectively: 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; 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; 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. The method for visually monitoring the growth status of toads during their entire life cycle according to claim 1, wherein: The determining, based on each of the second toad outline images of the reference toad, a rate of change of the growth state of the reference toad in each of the second toad outline images comprises: 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; 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. The method for visually monitoring the growth status of toads during their entire life cycle according to claim 1, wherein: Determining the reference property of the growth state of the reference toad according to the growth state change rate of each of the reference toads and the average value of second Euclidean distances between the local descriptors of the key feature points of the second toad outline image of the reference toad and the corresponding key feature points in the first toad outline image of the target toad includes: Based on the growth state change rates of the reference toads, a growth state change rate sequence of the reference toads is formed; 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; The growth state reference of the reference toad is determined by using the growth state change rate sequence and the descriptor distance sequence.

6. The method for visually monitoring the growth status of toads during their entire life cycle according to claim 1, wherein: The determining of the conformity of the growth trajectory between the candidate toad and the target toad based on the similarity of the growth trajectory between the candidate toad and each of the reference toads, and the reference of the growth status of each of the reference toads, includes: Accumulating the growth status references of the reference toads to obtain a first accumulated value; Accumulating the product of the growth status reference of each reference toad and the corresponding growth trajectory similarity to obtain a second accumulated value; 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. The method for visually monitoring the growth status of toads during their entire life cycle according to claim 1, wherein: Before determining the consistency of the growth trajectories of the candidate toads in the suspected position area with the target toad based on the second toad outline image of each reference toad in the toad group to which the target toad belongs, the method further comprises: 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; Density clustering is performed based on the similarity of each growth trajectory to obtain at least one toad group.

8. The method for visually monitoring the growth status of toads during their entire life cycle according to claim 7, wherein: The determining, based on the third toad outline image of the first toad and the fourth toad outline image of the second toad, the similarity of the growth trajectories between the first toad and the second toad includes: 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; 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; 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. The method for visually monitoring the growth status of toads during their entire life cycle according to claim 1, wherein: After determining the candidate toad with the greatest overall matching degree as the target toad and resuming visual monitoring of the target toad, the method further comprises: determining the growth status result of the target toad according to each of the first toad outline images of the target toad; Comparing the growth status result of the target toad with the standard growth model to obtain a status comparison result; In the case where the status comparison result indicates that the growth status is abnormal, an alarm mechanism is triggered.

Images