Method and Device for Predicting Animal Migration Routes Based on Infrared Camera Monitoring Data
By using an animal migration route prediction method based on infrared camera monitoring data and employing monitoring grids and clustering calculations, accurate animal migration routes are generated, solving the problem of inconsistent predicted paths in existing technologies and achieving efficient prediction based on natural laws.
Patent Information
- Application Number
- CN202311191800.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-09-14
- Publication Date
- 2026-11-17
- Estimated Expiration
- 2043-09-14
AI Technical Summary
Existing methods for predicting animal migration routes rely on researchers' experience, resulting in significant differences in the accuracy of predicted routes and making it impossible to standardize them.
Using a method based on infrared camera monitoring data, the target monitoring area is divided into multiple monitoring grids, infrared cameras are configured, and high-density areas are identified and adjacent grids are merged through image data analysis and clustering calculations to generate animal migration routes.
It achieves accurate prediction of animal migration routes based on seasonal order, avoiding the difference in results caused by human prediction and conforming to the natural laws of animal migration.
Smart Images

Figure CN117351413B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of machine vision technology, and in particular to a method and apparatus for predicting animal migration routes based on infrared camera monitoring data. Background Technology
[0002] Animal migration route prediction has significant implications and applications in ecological conservation, species protection, ecological research, agriculture and resource management, and climate change research. It plays a crucial role in promoting sustainable development, protecting natural ecosystems, and safeguarding human well-being.
[0003] Current predictions of animal migration routes are often made by researchers such as zoologists based on experience, combined with some monitoring tools, such as:
[0004] 1. GPS Tracking: By equipping animals with GPS devices, their location information can be tracked and recorded in real time. These devices can transmit data via satellite to obtain detailed data on animal migration routes and behavior.
[0005] 2. Satellite Remote Sensing: Satellite remote sensing technology is used to acquire information about the Earth's surface, such as vegetation type and ocean temperature. By analyzing satellite images and remote sensing data, it is possible to reveal the environmental preferences and route choices of animal migration.
[0006] 3. Biomarkers: By implanting or attaching various biomarker devices, such as rings, wireless tags, and chips, to animals, their location information can be tracked and recorded in real time. These marking devices can provide valuable migration routes and behavioral data.
[0007] This approach is highly dependent on the researchers' experience level, which can lead to significant differences in the accuracy of path predictions made by different individuals, making it impossible to standardize the approach. Summary of the Invention
[0008] The purpose of this invention is to at least address one of the shortcomings of the prior art by providing a method and apparatus for predicting animal migration routes based on infrared camera monitoring data.
[0009] To achieve the above objectives, the present invention adopts the following technical solution:
[0010] Specifically, a method for predicting animal migration routes based on infrared camera monitoring data is proposed, including the following:
[0011] Step 110: Divide the target monitoring area into multiple monitoring grids based on the monitoring range of the infrared cameras, and configure an infrared camera in each monitoring grid;
[0012] For each season, for any monitoring grid,
[0013] Step 120: Obtain image data captured by its infrared camera, and based on the image data, obtain the types and corresponding quantities of animals monitored by the monitoring grid;
[0014] Step 130: Obtain the target animal species and the selected time range, and count the number of target animal species monitored in the seasons included in the selected time range;
[0015] For each time period within the selected time range,
[0016] Step 140: Perform clustering calculation on the number of monitoring of the target animal species N(i) based on all monitoring grids, where N(i) represents the number of monitoring in the i-th monitoring grid. Obtain multiple K categories based on the number of monitoring in the monitoring grids. Summarize the values of the cluster centers C(k) of the 1 to K categories, where C(k) represents the value of the k-th cluster center, and k takes the value of 1-K. Find the largest C(k) value and let k = X at this time. Search for the minimum value M of the number of monitoring records in the X-th category. Find all monitoring grids with a number of monitoring greater than M and define such monitoring grids as high-density grids for the target animal species.
[0017] Step 150: Merge adjacent high-density grids into high-density regions for the target animal species to obtain multiple high-density regions;
[0018] Step 160: Obtain the migration route of the target animal based on the high-density area.
[0019] Furthermore, specifically, the specifications of the monitoring grid are divided based on the size of the target monitoring area, and an area threshold is set. If the target monitoring area is larger than the area threshold, a kilometer grid is used; if the target monitoring area is not larger than the area threshold, a hectare grid is used.
[0020] Furthermore, specifically, the clustering algorithm used to cluster the monitored numbers of target animal species is the k-means clustering algorithm.
[0021] Furthermore, specifically, obtaining the migration routes of target animals based on high-density areas includes,
[0022] Assume there are a total of I time periods within the selected time period, where i is a certain time period, Zone(Ji) is the high-density region with the largest sequence number in the i-th time period, and Zone(ji) is the j-th high-density region in the i-th time period. Let i cyclically execute steps 140-150 from 1 to I to obtain multiple high-density regions.
[0023] For time i, perform the following steps from i=2 to i=1:
[0024] Step 210: Calculate the high-density regions in time i-1 as Zone(j(i-1))~Zone(J(i-1)), and calculate the high-density regions in time i as Zone(ji)~Zone(Ji).
[0025] Step 220: Search for the nearest high-density region in Zone (j(i-1)). Assume that the high-density region in i is Zone (Mi) and the nearest high-density region in i-1 is Zone (N(i-1)). Draw a directional connecting line from Zone (N(i-1)) to Zone (Mi), with the arrow of the connecting line pointing to Zone (Mi).
[0026] Step 230: Perform the operation of step 220 on each high-density region in time period i to obtain the connection map of each high-density region, which is the migration route of the target animal species within the selected time period.
[0027] This invention also proposes an animal migration route prediction device based on infrared camera monitoring data, comprising:
[0028] The monitoring grid division module is used to divide the target monitoring area into multiple monitoring grids based on the monitoring range of the infrared camera, and configure an infrared camera in each monitoring grid;
[0029] For each season, for any monitoring grid,
[0030] The image processing module is used to acquire image data captured by its infrared camera, and to obtain the types and quantities of animals monitored by the monitoring grid based on the image data.
[0031] The monitoring quantity statistics module is used to obtain the target animal species and the selected time range, and to count the monitoring quantity of the target animal species in the seasons included in the selected time range;
[0032] For each time period within the selected time range,
[0033] The high-density grid search module is used to perform cluster calculations on the monitoring quantity of target animal species, obtain multiple classifications based on the monitoring quantity, find the classification with the most monitoring quantity, search for the minimum monitoring quantity value M in the classification, find the monitoring grid with a monitoring quantity greater than M, and define such monitoring grids as high-density grids for the target animal species.
[0034] The high-density region division module is used to merge adjacent high-density grids into multiple high-density regions for the target animal species.
[0035] The migration route calculation module is used to obtain the migration route of the target animal based on high-density areas.
[0036] Furthermore, specifically, the specifications of the monitoring grid are divided based on the size of the target monitoring area, and an area threshold is set. If the target monitoring area is larger than the area threshold, a kilometer grid is used; if the target monitoring area is not larger than the area threshold, a hectare grid is used.
[0037] Furthermore, specifically, the clustering algorithm used to cluster the monitored numbers of target animal species is the k-means clustering algorithm.
[0038] Furthermore, specifically, obtaining the migration routes of target animals based on high-density areas includes,
[0039] Assume there are a total of I time periods within the selected time period, where i is a certain time period, Zone(Ji) is the high-density region with the largest sequence number in the i-th time period, and Zone(ji) is the j-th high-density region in the i-th time period. Let i cyclically execute steps 140-150 from 1 to I to obtain multiple high-density regions.
[0040] For time i, perform the following steps from i=2 to i=1:
[0041] Step 210: Calculate the high-density regions in time i-1 as Zone(j(i-1))~Zone(J(i-1)), and calculate the high-density regions in time i as Zone(ji)~Zone(Ji).
[0042] Step 220: Search for the nearest high-density region in Zone (j(i-1)). Assume that the high-density region in i is Zone (Mi) and the nearest high-density region in i-1 is Zone (N(i-1)). Draw a directional connecting line from Zone (N(i-1)) to Zone (Mi), with the arrow of the connecting line pointing to Zone (Mi).
[0043] Step 230: Perform the operation of step 220 on each high-density region in time period i to obtain the connection map of each high-density region, which is the migration route of the target animal species within the selected time period.
[0044] The beneficial effects of this invention are as follows:
[0045] This invention proposes a method for predicting animal migration routes based on infrared camera monitoring data. It analyzes the changes in high-density areas of wild animals at different times (monthly, quarterly) within a set time period using infrared camera monitoring data, connects these high-density areas according to seasonal order, and thus determines the migration routes of wild animals between different seasons. This invention can predict animal migration routes after the infrared cameras are deployed, facilitating the prediction process. Furthermore, based on seasonal order, it conforms to the natural laws of animal migration, enabling accurate predictions and avoiding the significant discrepancies in results caused by human prediction. Attached Figure Description
[0046] The above and other features of this disclosure will become more apparent from the detailed description of the embodiments illustrated in conjunction with the accompanying drawings. In the accompanying drawings, the same reference numerals denote the same or similar elements. Obviously, the drawings described below are merely some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained from these drawings without any creative effort. In the drawings:
[0047] Figure 1 The diagram shows a flowchart of the animal migration route prediction method based on infrared camera monitoring data according to the present invention. Detailed Implementation
[0048] The following will provide a clear and complete description of the concept, specific structure, and technical effects of the present invention in conjunction with embodiments and accompanying drawings, so as to fully understand the purpose, solution, and effects of the present invention. It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. The same reference numerals used throughout the accompanying drawings indicate the same or similar parts.
[0049] Reference Figure 1 Example 1: This invention proposes a method for predicting animal migration routes based on infrared camera monitoring data, including the following:
[0050] Step 110: Divide the target monitoring area into multiple monitoring grids based on the monitoring range of the infrared cameras, and configure an infrared camera in each monitoring grid;
[0051] For each season, for any monitoring grid,
[0052] Step 120: Obtain image data captured by its infrared camera, and based on the image data, obtain the types and corresponding quantities of animals monitored by the monitoring grid;
[0053] Step 130: Obtain the target animal species and the selected time range, and count the number of target animal species monitored in the seasons included in the selected time range;
[0054] For each time period within the selected time range,
[0055] Step 140: Perform clustering calculation on the number of monitoring of the target animal species N(i) based on all monitoring grids, where N(i) represents the number of monitoring in the i-th monitoring grid. Obtain multiple K categories based on the number of monitoring in the monitoring grids. Summarize the values of the cluster centers C(k) of the 1 to K categories, where C(k) represents the value of the k-th cluster center, and k takes the value of 1-K. Find the largest C(k) value and let k = X at this time. Search for the minimum value M of the number of monitoring records in the X-th category. Find all monitoring grids with a number of monitoring greater than M and define such monitoring grids as high-density grids for the target animal species.
[0056] Step 150: Merge adjacent high-density grids into high-density regions for the target animal species to obtain multiple high-density regions;
[0057] Step 160: Obtain the migration route of the target animal based on the high-density area.
[0058] Example 1 analyzes wildlife monitoring data from infrared cameras to identify changes in high-density areas of wild animals during different seasons (monthly or quarterly) within a set time period. These high-density areas are connected in seasonal order to determine the migration routes of wild animals between different seasons. This invention can predict animal migration routes after the infrared cameras are deployed, facilitating such predictions. Furthermore, the seasonal order aligns with the natural laws of animal migration, ensuring accurate predictions and avoiding significant discrepancies caused by human-induced predictions. The seasons can be monthly or quarterly.
[0059] In a preferred embodiment of the present invention, the specifications of the monitoring grid are divided based on the size of the target monitoring area, and an area threshold is set. If the target monitoring area is larger than the area threshold, a kilometer grid is used; if the target monitoring area is not larger than the area threshold, a hectare grid is used.
[0060] As a preferred embodiment of the present invention, specifically, the clustering algorithm used for clustering the monitoring quantity of the target animal species is the k-means clustering algorithm.
[0061] Specifically, the k-means clustering algorithm is an iterative clustering analysis algorithm. Its steps are as follows: First, the data is pre-divided into K groups. Then, K objects are randomly selected as initial cluster centers. Next, the distance between each object and each seed cluster center is calculated, and each object is assigned to the nearest cluster center. Each cluster center and the objects assigned to it represent a cluster. Each time a sample is assigned, the cluster centers are recalculated based on the existing objects in the cluster. This process is repeated until a termination condition is met. The termination condition could be that no (or a minimum number) objects are reassigned to different clusters, no (or a minimum number) cluster centers change, or the sum of squared errors reaches a local minimum. Therefore, it is used in this invention to monitor the number of target animal species.
[0062] In a preferred embodiment of the present invention, specifically, obtaining the migration route of the target animal based on high-density areas includes,
[0063] Assume there are a total of I time periods within the selected time period, where i is a certain time period, Zone(Ji) is the high-density region with the largest sequence number in the i-th time period, and Zone(ji) is the j-th high-density region in the i-th time period. Let i cyclically execute steps 140-150 from 1 to I to obtain multiple high-density regions.
[0064] For time i, perform the following steps from i=2 to i=1:
[0065] Step 210: Calculate the high-density regions in time i-1 as Zone(j(i-1))~Zone(J(i-1)), and calculate the high-density regions in time i as Zone(ji)~Zone(Ji).
[0066] Step 220: Search for the nearest high-density region in Zone (j(i-1)). Assume that the high-density region in i is Zone (Mi) and the nearest high-density region in i-1 is Zone (N(i-1)). Draw a directional connecting line from Zone (N(i-1)) to Zone (Mi), with the arrow of the connecting line pointing to Zone (Mi).
[0067] Step 230: Perform the operation of step 220 on each high-density region in time period i to obtain the connection map of each high-density region, which is the migration route of the target animal species within the selected time period.
[0068] This invention also proposes an animal migration route prediction device based on infrared camera monitoring data, comprising:
[0069] The monitoring grid division module is used to divide the target monitoring area into multiple monitoring grids based on the monitoring range of the infrared camera, and configure an infrared camera in each monitoring grid;
[0070] For each season, for any monitoring grid,
[0071] The image processing module is used to acquire image data captured by its infrared camera, and to obtain the types and quantities of animals monitored by the monitoring grid based on the image data.
[0072] The monitoring quantity statistics module is used to obtain the target animal species and the selected time range, and to count the monitoring quantity of the target animal species in the seasons included in the selected time range;
[0073] For each time period within the selected time range,
[0074] The high-density grid search module is used to perform cluster calculations on the monitoring quantity of target animal species, obtain multiple classifications based on the monitoring quantity, find the classification with the most monitoring quantity, search for the minimum monitoring quantity value M in the classification, find the monitoring grid with a monitoring quantity greater than M, and define such monitoring grids as high-density grids for the target animal species.
[0075] The high-density region division module is used to merge adjacent high-density grids into multiple high-density regions for the target animal species.
[0076] The migration route calculation module is used to obtain the migration route of the target animal based on high-density areas.
[0077] In a preferred embodiment of the present invention, the specifications of the monitoring grid are divided based on the size of the target monitoring area, and an area threshold is set. If the target monitoring area is larger than the area threshold, a kilometer grid is used; if the target monitoring area is not larger than the area threshold, a hectare grid is used.
[0078] As a preferred embodiment of the present invention, specifically, the clustering algorithm used for clustering the monitoring quantity of the target animal species is the k-means clustering algorithm.
[0079] In a preferred embodiment of the present invention, specifically, obtaining the migration route of the target animal based on high-density areas includes,
[0080] Assume there are a total of I time periods within the selected time period, where i is a certain time period, Zone(Ji) is the high-density region with the largest sequence number in the i-th time period, and Zone(ji) is the j-th high-density region in the i-th time period. Let i cyclically execute steps 140-150 from 1 to I to obtain multiple high-density regions.
[0081] For time i, perform the following steps from i=2 to i=1:
[0082] Step 210: Calculate the high-density regions in time i-1 as Zone(j(i-1))~Zone(J(i-1)), and calculate the high-density regions in time i as Zone(ji)~Zone(Ji).
[0083] Step 220: Search for the nearest high-density region in Zone (j(i-1)). Assume that the high-density region in i is Zone (Mi) and the nearest high-density region in i-1 is Zone (N(i-1)). Draw a directional connecting line from Zone (N(i-1)) to Zone (Mi), with the arrow of the connecting line pointing to Zone (Mi).
[0084] Step 230: Perform the operation of step 220 on each high-density region in time period i to obtain the connection map of each high-density region, which is the migration route of the target animal species within the selected time period.
[0085] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of the solution in this embodiment, depending on actual needs.
[0086] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated modules described above can be implemented in hardware or as software functional modules.
[0087] If the integrated module is implemented as a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or system capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc.
[0088] Although the description of the invention has been quite detailed and particularly of several described embodiments, it is not intended to limit it to any of these details or embodiments or any particular embodiment, but should be considered as providing a broad possible interpretation of the claims by referring to the appended claims and taking into account the prior art, thereby effectively covering the intended scope of the invention. Furthermore, the invention has been described above with respect to embodiments foreseeable by the inventors in order to provide a useful description, and non-substantial modifications to the invention that have not yet been foreseen may still represent equivalent modifications.
[0089] The above description is merely a preferred embodiment of the present invention. The present invention is not limited to the above-described embodiments. Any embodiment that achieves the technical effects of the present invention using the same means should fall within the protection scope of the present invention. Within the protection scope of the present invention, various modifications and variations can be made to the technical solutions and / or implementation methods.
Claims
1. A method for predicting animal migration routes based on infrared camera monitoring data, characterized in that, Including the following: Step 110: Divide the target monitoring area into multiple monitoring grids based on the monitoring range of the infrared cameras, and configure an infrared camera in each monitoring grid; For each season, for any monitoring grid, Step 120: Obtain image data captured by its infrared camera, and based on the image data, obtain the types and corresponding quantities of animals monitored by the monitoring grid; Step 130: Obtain the target animal species and the selected time range, and count the number of target animal species monitored in the seasons included in the selected time range; For each season within a selected time range, where the season is either a month or a quarter, Step 140: Perform clustering calculation on the number of monitoring of the target animal species N(q) based on all monitoring grids, where N(q) represents the number of monitoring in the q-th monitoring grid. This yields multiple K categories based on the number of monitoring in each grid. Summarize the cluster center values C(k) of categories 1 to K, where C(k) represents the value of the k-th cluster center, and k takes the value 1-K. Find the largest C(k) value and set k=X. Search for the minimum value R of the number of monitoring records in the X-th category. Find all monitoring grids with a number of monitoring greater than R and define such monitoring grids as high-density grids for the target animal species. Step 150: Merge adjacent high-density grids into high-density regions for the target animal species to obtain multiple high-density regions; Step 160: Obtain the migration route of the target animal based on the high-density area; Specifically, the migration routes of target animals obtained based on high-density areas include: Assume there are a total of I time periods within the selected time period, where i is a certain time period, Zone(Ji) is the high-density region with the largest sequence number in the i-th time period, and Zone(ji) is the j-th high-density region in the i-th time period. Let i be cyclically executed from 1 to I to perform steps 140-150, resulting in multiple high-density regions; For instruction i, perform the following steps from i=2 to i=1: Step 210: Calculate the high-density regions in time i-1 as Zone(j(i-1))~Zone(J(i-1)), and calculate the high-density regions in time i as Zone(ji)~Zone(Ji). Step 220: Search for the high-density region in Zone (j(i-1)) whose geographical location is closest to the high-density region in current time i. Assume that the high-density region in current time i is Zone (Mi), and the high-density region in time i-1 whose geographical location is closest to the high-density region in current time i is Zone (N(i-1)). Then draw a directional connecting line from Zone (N(i-1)) to Zone (Mi), with the arrow of the connecting line pointing to Zone (Mi). Step 230: Perform the operation of step 220 on each high-density region in time period i to obtain the connection map of each high-density region, which is the migration route of the target animal species within the selected time period.
2. The method for predicting animal migration routes based on infrared camera monitoring data according to claim 1, characterized in that, Specifically, the specifications of the monitoring grid are divided based on the size of the target monitoring area. An area threshold is set. If the target monitoring area is larger than the area threshold, a kilometer grid is used; if the target monitoring area is not larger than the area threshold, a hectare grid is used.
3. The method for predicting animal migration routes based on infrared camera monitoring data according to claim 1, characterized in that, Specifically, the clustering algorithm used to calculate the number of monitored target animal species is the k-means clustering algorithm.
4. An animal migration route prediction device based on infrared camera monitoring data, characterized in that, include: The monitoring grid division module is used to divide the target monitoring area into multiple monitoring grids based on the monitoring range of the infrared camera, and configure an infrared camera in each monitoring grid; For each season, for any monitoring grid, The image processing module is used to acquire image data captured by its infrared camera, and to obtain the types and quantities of animals monitored by the monitoring grid based on the image data. The monitoring quantity statistics module is used to obtain the target animal species and the selected time range, and to count the monitoring quantity of the target animal species in the seasons included in the selected time range; For each season within a selected time range, where the season is either a month or a quarter, The high-density grid search module is used to perform cluster calculations on the monitoring quantity of target animal species, obtain multiple classifications based on the monitoring quantity, find the classification with the most monitoring quantity, search for the minimum monitoring quantity value R in the classification, find the monitoring grid with a monitoring quantity greater than R, and define such monitoring grids as high-density grids for the target animal species. The high-density region division module is used to merge adjacent high-density grids into multiple high-density regions for the target animal species. The migration route calculation module is used to obtain the migration route of the target animal based on high-density areas; Specifically, the migration routes of target animals obtained based on high-density areas include: Assume there are a total of I time periods within the selected time period, where i is a certain time period, Zone(Ji) is the high-density region with the largest sequence number in the i-th time period, and Zone(ji) is the j-th high-density region in the i-th time period. Let i be cyclically executed from 1 to I to perform steps 140-150, resulting in multiple high-density regions; For instruction i, perform the following steps from i=2 to i=1: Step 210: Calculate the high-density regions in time i-1 as Zone(j(i-1))~Zone(J(i-1)), and calculate the high-density regions in time i as Zone(ji)~Zone(Ji). Step 220: Search for the high-density region in Zone (j(i-1)) whose geographical location is closest to the high-density region in current time i. Assume that the high-density region in current time i is Zone (Mi), and the high-density region in time i-1 whose geographical location is closest to the high-density region in current time i is Zone (N(i-1)). Then draw a directional connecting line from Zone (N(i-1)) to Zone (Mi), with the arrow of the connecting line pointing to Zone (Mi). Step 230: Perform the operation of step 220 on each high-density region in time period i to obtain the connection map of each high-density region, which is the migration route of the target animal species within the selected time period.
5. The animal migration route prediction device based on infrared camera monitoring data according to claim 4, characterized in that, Specifically, the specifications of the monitoring grid are divided based on the size of the target monitoring area. An area threshold is set. If the target monitoring area is larger than the area threshold, a kilometer grid is used; if the target monitoring area is not larger than the area threshold, a hectare grid is used.
6. The animal migration route prediction device based on infrared camera monitoring data according to claim 4, characterized in that, Specifically, the clustering algorithm used to calculate the number of monitored target animal species is the k-means clustering algorithm.
Citation Information
Patent Citations
Parallel and highly efficient grid-and-density-based multi-dimensional spatial data clustering algorithm (GRIDEN)
CN107908696A
Cross-city interest point distribution data migration prediction method and system
CN115422993A
