Wildlife identification and species population statistics method and system based on drone-photographed image processing

Abstract

The present invention provides a method and system for identifying wild animals and counting species populations based on image processing captured by unmanned aerial vehicles (UAVs), and relates to the technical field of wild animal identification. The present invention significantly improves the accuracy of identification and statistics by fusing image recognition and sound recognition results and dynamically adjusting the shooting parameters of the UAV. By combining the YOLOv5 model, SORT algorithm, deep learning model and short-time Fourier transform for image recognition and sound recognition, and combining the image and sound recognition results, false positives and false negatives are effectively reduced, and the consistency and reliability of the data are improved. In addition, the shooting parameters of the UAV can be dynamically adjusted to find a balance between regional resolution and coverage, ensuring that the system can work effectively in various environments. This not only improves the recognition ability and data quality of the system, but also enhances the robustness and versatility of the system, thereby achieving the effect of improving the application effect and practical value of UAVs in wildlife monitoring.

Description

Technical Field

[0001] The present invention relates to the technical field, and in particular to a method and system for identifying wild animals and counting species populations based on processing images taken by drones. Background Art

[0002] With the development of drone technology, the use of drones for wildlife monitoring has become increasingly common. Traditional methods primarily rely on single-mode image or sound recognition. These methods often suffer from low recognition accuracy, high rates of missed detections, and false alarms when dealing with complex environments and diverse wildlife species. Furthermore, single-modality recognition methods struggle to adapt to varying wildlife distributions and environmental changes, often requiring frequent adjustments to drone imaging parameters, increasing workload and complexity. Existing technologies struggle to maintain high-resolution images while also covering larger areas to improve data comprehensiveness and accuracy, limiting the accuracy of subsequent data analysis and decision-making.

[0003] For example, the method for investigating the number of wild animal populations based on drone-photographed image processing disclosed in Chinese patent application number CN202311830191.X investigates the number of wild animal populations in a region by analyzing aerial images taken by drones. However, it still relies on single image recognition, which is difficult to adapt to different scenarios and reduces the final recognition accuracy.

[0004] Therefore, how to effectively integrate multimodal data in wildlife monitoring, dynamically adjust shooting parameters, and improve the accuracy of recognition and statistics has become a technical problem that needs to be solved urgently.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art. Summary of the Invention

[0006] The purpose of the present invention is to provide a method and system for identifying wild animals and counting species populations based on image processing taken by drones, so as to solve the problems raised in the above background technology.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] The method for identifying wild animals and counting species populations based on drone-photographed image processing includes the following steps:

[0009] S1: Capture an image of wild animals to generate a reference image, and use an image processing algorithm to process the reference image to generate a target ratio coefficient for wild animals;

[0010] S2: Adjust the drone's shooting parameters based on the target ratio coefficient. After the adjustment is completed, perform secondary image and sound collection on the wildlife to generate analysis images and sound sources;

[0011] S3: Use the image processing algorithm to process the analysis image to generate an image recognition result, and then use the sound processing algorithm to process the analysis sound source to generate a sound recognition result;

[0012] S4: Perform set division based on the image recognition results and the sound recognition results, and use the intersection of the image recognition results and the sound recognition results as the final recognition result.

[0013] Preferably, the target proportion coefficient is generated by the following logic:

[0014] The image processing algorithm uses the Yolov5 model. Training images of various wild animal species are collected and divided into a training set and a validation set in an 8:2 ratio. The training set and validation set are used to train and optimize the Yolov5 model respectively.

[0015] Use the optimized Yolov5 model to perform image recognition on the wild animals to be identified in the reference image and generate the identification area corresponding to each wild animal individual;

[0016] Calculate the average area of ​​the identified regions in the reference image using the following formula:

[0017]

[0018] In the formula represents the average area, S k represents the area of ​​the kth recognition area, the subscript k represents the number of the recognition area, and n represents the number of recognition areas;

[0019] The target ratio coefficient is calculated based on the average area of ​​the recognition area. The calculation method is: In the formula represents the target ratio, and Sz represents the total area of ​​the reference image.

[0020] Preferably, the shooting parameters include shooting height and shooting angle, and the logic for adjusting the shooting parameters is:

[0021] Comparing the target proportion coefficient with a preset proportion threshold, generating a first adjustment coefficient according to the comparison result, and then generating a second adjustment coefficient according to the number of recognition areas;

[0022] The first adjustment coefficient and the second adjustment coefficient are weighted to generate a total adjustment coefficient, and the total adjustment coefficient is used to adjust the shooting parameters.

[0023] Preferably, the first adjustment coefficient and the second adjustment coefficient are calculated as follows:

[0024]

[0025] ω2=ln(n+1)

[0026] Where ω1 and ω2 represent the first adjustment coefficient and the second adjustment coefficient respectively. Indicates the preset percentage threshold;

[0027] The total adjustment factor is calculated as follows:

[0028]

[0029] Where ω z represents the total adjustment coefficient, μ1 and μ2 represent the first weight and the second weight respectively, and μ1+μ2=1, δ1 and δ2 represent the preset first adjustment factor and the second adjustment factor respectively.

[0030] Preferably, the shooting parameters are adjusted according to the total adjustment coefficient, and the shooting height and shooting angle are adjusted as follows:

[0031]

[0032]

[0033] Where H and θ represent the shooting height and shooting angle respectively, and c represents the preset adjustment constant.

[0034] Preferably, the logic for processing the analysis image using the image processing algorithm to generate the image recognition result is:

[0035] Load N consecutive frames of analysis images into the optimized Yolov5 model in sequence for image recognition to obtain the corresponding detection results, which are expressed as:

[0036] D i =Yolov5(X i )

[0037] Where D i The detection result of the i-th frame analysis picture is composed of several groups of sub-results. The sub-results correspond to different types of wild animals and include the identified bounding box position, animal category and confidence level. The detection result D i ={d i (1),d i (2),…,d i (j),…d i (m)}, where d i(j) represents the sub-result of the jth animal category in the i-th frame analysis picture, j = 1, 2, 3, ..., m, m represents the number of animal categories, X i Indicates the i-th frame analysis picture;

[0038] The SORT algorithm is used to track the detection results of the Yolov5 model to obtain the position information of each individual in the same animal category in different frames. The tracking results are expressed as:

[0039] T i (j) = SORT[d i (j)]

[0040] Where T i Indicates the tracking result of the i-th frame analysis picture;

[0041] The tracking results of N consecutive frames of analysis images are processed, and the same target detected in consecutive frames is matched to reduce repeated counting. The number of unique individuals of the same animal category appearing in different frames is obtained, and the number of species of each animal is counted. The calculation method is:

[0042]

[0043] Where N z (j) represents the number of species in the jth animal category, T i ′(j) represents the number of unique individuals of the jth animal category appearing in different frames;

[0044] The animal categories are divided into set A1, and the number of species of each animal category is divided into set A2. The elements in set A1 and set A2 correspond one to one, and set A1 and set A2 are taken together as the image recognition result.

[0045] Preferably, the logic for processing the analyzed sound source to generate the sound recognition result is:

[0046] Build a deep learning model, collect a variety of wild animal sounds as training sound sources, divide the training sound sources into training and validation sets in an 8:2 ratio, and use the training and validation sets to train and optimize the deep learning model;

[0047] The frequency domain features of the analyzed sound source are extracted through short-time Fourier transform, and the analyzed sound source is converted into a spectrum. The calculation method is:

[0048] S(f,t)=∫s(τ)·w(t-τ)·e -j′2πfτ dτ

[0049] Where S(f,t) represents the spectrum of the analyzed sound source, s(τ) represents the sound signal of the analyzed sound source at time τ, w(t-τ) represents the time domain window function, f represents the frequency, t represents the reference time, and j′ represents the imaginary unit;

[0050] The spectrum of the analyzed sound source is input into the deep learning model to obtain the animal categories corresponding to different wild animals. The animal categories corresponding to the analyzed sound source are divided into set B and used as the sound recognition results.

[0051] Preferably, a set Q of wild animal species finally identified is generated based on the set A1 in the image recognition results and the set B in the sound recognition results. The set Q is expressed as:

[0052] Q=A1∩B

[0053] Based on the elements in set Q, corresponding elements are selected from set A2 to re-form a new set A3. The elements in set A3 correspond one-to-one with the elements in set Q, and set A3 and set Q are used as the final recognition results.

[0054] Compared with the prior art, the present invention has the following beneficial effects:

[0055] The present invention significantly improves the accuracy of recognition and statistics by fusing image recognition and sound recognition results and dynamically adjusting the shooting parameters of the drone. Combining the YOLOv5 model and the SORT algorithm for image recognition, and combining the deep learning model and short-time Fourier transform for sound recognition, ensures the accuracy of the image and sound recognition results. Combining the image and sound recognition results effectively reduces false positives and false negatives, and improves the consistency and reliability of the data. Furthermore, the drone's shooting parameters can be dynamically adjusted to find a balance between regional resolution and coverage, ensuring that the system can work effectively in various environments and complex scenarios. This not only improves the system's recognition capabilities and data quality, but also enhances the system's robustness and versatility, achieving the effect of improving the application effect and practical value of drones in wildlife monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 Schematic diagram of the overall method of the present invention. DETAILED DESCRIPTION

[0057] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below with reference to specific embodiments.

[0058] It should be noted that, unless otherwise defined, the technical or scientific terms used in the present invention should have the usual meanings understood by people with ordinary skills in the field to which the present invention belongs. The "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative position relationships. When the absolute position of the object being described changes, the relative position relationship may also change accordingly.

[0059] Example:

[0060] See also Figure 1 , the present invention provides a technical solution:

[0061] The method for identifying wild animals and counting species populations based on drone-photographed image processing includes the following steps:

[0062] S1: Capture an image of wild animals to generate a reference image, and use an image processing algorithm to process the reference image to generate a target ratio coefficient for wild animals.

[0063] The logic for generating the target proportion coefficient is:

[0064] The image processing algorithm uses the Yolov5 model. Training images of various wild animal species are collected and divided into a training set and a validation set in an 8:2 ratio. The training set and validation set are used to train and optimize the Yolov5 model respectively.

[0065] Use the optimized Yolov5 model to perform image recognition on the wild animals to be identified in the reference image and generate the identification area corresponding to each wild animal individual;

[0066] Calculate the average area of ​​the identified regions in the reference image using the following formula:

[0067]

[0068] In the formula represents the average area, S k represents the area of ​​the kth recognition area, the subscript k represents the number of the recognition area, and n represents the number of recognition areas;

[0069] The target ratio coefficient is calculated based on the average area of ​​the recognition area. The calculation method is: In the formula The target ratio is the target share coefficient, and Sz represents the total area of ​​the reference image. The target ratio coefficient is proportional to the size of the identification area and reflects the area ratio of the wild animal in the reference image. It is understandable that if the target ratio coefficient is too small, the area ratio of the wild animal in the reference image is considered too small, and the image features cannot be accurately identified, which may lead to a decrease in the accuracy of subsequent wild animal species identification. Conversely, if the target ratio coefficient is too large, the area ratio of the wild animal in the reference image is considered too large, and the overall image of the entire population cannot be collected, which may lead to a decrease in the accuracy of subsequent wild animal species identification.

[0070] In this step, the drone's imaging parameters are precisely adjusted by calculating the target coverage factor. If the coverage factor is too low, the parameters are readjusted to improve the resolution of the recognition area. If the coverage factor is too high, the parameters are adjusted to expand the field of view to ensure that the entire group is captured. This dynamic adjustment mechanism ensures that the collected image and sound data has optimal quality and coverage, which not only improves subsequent recognition accuracy but also enhances the system's versatility and adaptability, enabling it to operate effectively in different scenarios.

[0071] S2: Adjust the drone's shooting parameters based on the target ratio coefficient. After the adjustment is completed, perform secondary image and sound collection on the wild animals to generate analysis pictures and analysis sound sources.

[0072] Shooting parameters include shooting height and shooting angle. The logic for adjusting shooting parameters is as follows:

[0073] Comparing the target proportion coefficient with a preset proportion threshold, generating a first adjustment coefficient according to the comparison result, and then generating a second adjustment coefficient according to the number of recognition areas;

[0074] The first adjustment coefficient and the second adjustment coefficient are weighted to generate a total adjustment coefficient, and the total adjustment coefficient is used to adjust the shooting parameters.

[0075] The calculation methods of the first adjustment coefficient and the second adjustment coefficient are:

[0076]

[0077] ω2=ln(n+1)

[0078] Where ω1 and ω2 represent the first adjustment coefficient and the second adjustment coefficient respectively. Indicates the preset percentage threshold.

[0079] The total adjustment factor is calculated as follows:

[0080]

[0081] Where ω z Represents the total adjustment coefficient, μ1 and μ2 represent the first weight and the second weight respectively, and μ1+μ2=1, δ1 and δ2 represent the preset first adjustment factor and the second adjustment factor respectively. The first adjustment factor and the second adjustment factor are used to fine-tune the total adjustment coefficient and can be adjusted in a user-preset manner.

[0082] Adjust the shooting parameters according to the total adjustment coefficient. The adjustment methods of shooting height and shooting angle are as follows:

[0083]

[0084] Where H and θ represent the shooting height and shooting angle respectively, and c represents the preset adjustment constant.

[0085] As can be seen, the first adjustment coefficient is inversely proportional to the target share coefficient and directly proportional to the total adjustment coefficient. A larger first adjustment coefficient results in a larger total adjustment coefficient and a smaller target share coefficient, meaning the drone's shooting altitude needs to be lowered and the field of view narrowed to achieve higher regional resolution. Similarly, a smaller first adjustment coefficient means the drone's shooting altitude needs to be raised and the field of view widened to cover a larger area. The second adjustment coefficient is directly proportional to the number of recognition zones and inversely proportional to the total adjustment coefficient. That is, a larger second adjustment coefficient results in a smaller total adjustment coefficient, resulting in a larger number of recognition zones, meaning a greater number of wildlife in the image. Therefore, the drone's shooting altitude needs to be raised and the field of view widened to cover a larger area. Similarly, a smaller number of recognition zones results in a smaller number of wildlife in the image, meaning a lower shooting altitude and a narrower field of view needed to achieve higher regional resolution. The specific values ​​and relationship between the first and second weights can be adjusted according to the user's actual needs.

[0086] In this step, by setting the total adjustment coefficient obtained by the first adjustment coefficient and the second adjustment coefficient, a balance can be found between regional resolution and coverage, ensuring that the image has sufficient details while covering a larger area, adapting to the distribution of different wild animals, and adaptively adjusting shooting parameters in different environments and conditions, thereby enhancing the universality and robustness of the system and enabling it to work effectively in various complex scenarios. Compared with existing technologies, this dynamic adjustment mechanism not only improves the accuracy of recognition and statistics, but also reduces the system's errors and workload, effectively improving the performance and application effect of the overall solution.

[0087] S3: Use the image processing algorithm to process the analysis image to generate an image recognition result, and then use the sound processing algorithm to process the analysis sound source to generate a sound recognition result.

[0088] The logic of using image processing algorithms to process analysis images and generate image recognition results is as follows:

[0089] Load N consecutive frames of analysis images into the optimized Yolov5 model in sequence for image recognition to obtain the corresponding detection results, which are expressed as:

[0090] D i =Yolov5(X i )

[0091] Where D i The detection result of the i-th frame analysis picture is composed of several groups of sub-results. The sub-results correspond to different types of wild animals and include the identified bounding box position, animal category and confidence level. The detection result D i ={d i (1),d i (2),…,d i (j),…d i (m)}, where d i (j) represents the sub-result of the jth animal category in the i-th frame analysis picture, j = 1, 2, 3, ..., m, m represents the number of animal categories, X i Indicates the i-th frame analysis picture;

[0092] The SORT algorithm is used to track the detection results of the Yolov5 model to obtain the position information of each individual in the same animal category in different frames. The tracking results are expressed as:

[0093] T i (j) = SORT[d i (j)]

[0094] Where T i Represents the tracking result of the i-th frame analysis image. The SORT algorithm can accurately track the position information of each individual in the same animal category in different frames, reduce repeated counting, and ensure the accuracy of target tracking.

[0095] The tracking results of N consecutive frames of analysis images are processed, and the same target detected in consecutive frames is matched to reduce repeated counting. The number of unique individuals of the same animal category appearing in different frames is obtained, and the number of species of each animal is counted. The calculation method is:

[0096]

[0097] Where Nz (j) represents the number of species in the jth animal category, T i ′(j) represents the number of unique individuals of the jth animal category appearing in different frames;

[0098] The animal categories are divided into set A1, and the number of species of each animal category is divided into set A2. The elements in set A1 and set A2 correspond one to one, and set A1 and set A2 are taken together as the image recognition result.

[0099] In this step, the Yolov5 model, with its high efficiency and accuracy, can quickly detect wildlife in the image and generate corresponding detection results. The SORT algorithm can track the detection results, accurately tracking the position information of each individual of the same animal category across different frames, reducing double counting and ensuring accurate target tracking. By combining the efficient target detection of the YOLOv5 model and the precise target tracking of the SORT algorithm, accurate image recognition results can be generated, improving the accuracy of recognition and statistics, reducing double counting and errors. The Yolov5 model and SORT algorithm are existing technologies, so their specific working steps are not detailed here.

[0100] The logic for processing the analyzed sound source and generating the sound recognition result is as follows:

[0101] Build a deep learning model, collect a variety of wild animal sounds as training sound sources, divide the training sound sources into training and validation sets in an 8:2 ratio, and use the training and validation sets to train and optimize the deep learning model;

[0102] The frequency domain features of the analyzed sound source are extracted through short-time Fourier transform, and the analyzed sound source is converted into a spectrum. The calculation method is:

[0103] S(f,t)=∫s(τ)·w(t-τ)·e -j′2πfτ dτ

[0104] Where S(f,t) represents the spectrum of the analyzed sound source, s(τ) represents the sound signal of the analyzed sound source at time τ, w(t-τ) represents the time domain window function, f represents the frequency, t represents the reference time, and j′ represents the imaginary unit;

[0105] The spectrum of the analyzed sound source is input into the deep learning model to obtain the animal categories corresponding to different wild animals. The animal categories corresponding to the analyzed sound source are divided into set B and used as the sound recognition results.

[0106] In this step, deep learning models and short-time Fourier transforms are used to extract frequency domain features, analyze the sound source, and generate sound recognition results. This allows the system to more accurately identify the sounds of different wildlife species. This, combined with image recognition results, improves overall recognition and statistical accuracy. This step not only enhances the system's recognition capabilities and data quality, but also strengthens its robustness and adaptability, significantly boosting the performance and application value of the overall solution.

[0107] S4: Perform set division based on the image recognition results and the sound recognition results, and use the intersection of the image recognition results and the sound recognition results as the final recognition result.

[0108] Based on the set A1 in the image recognition results and the set B in the sound recognition results, the set Q of the finally identified wild animal species is generated. The set Q is expressed as:

[0109] q=A1∩B

[0110] Based on the elements in set Q, corresponding elements are selected from set A2 to re-form a new set A3. The elements in set A3 correspond one-to-one with the elements in set Q, and set A3 and set Q are used as the final recognition results.

[0111] Here is a simple example to illustrate: suppose that after image recognition, three birds are identified, bird a, bird b and bird c, and the corresponding animal categories are numbered 1, 2, and 3 respectively. The number of the three birds is N. z (1) = 10, N z (2) = 8, N z (3) = 6, then correspondingly, the set A1 in the image recognition result is {bird a, bird b, bird c}, and the set A2 is {N z (1),N z (2),N z (3)}. If three types of birds are identified after sound recognition, namely bird b, bird c and bird d, then the corresponding set B = {bird b, bird c, bird d}. Therefore, the set Q of wild animal species finally identified is the intersection of set A1 and set B, set Q = {bird b, bird c}. Then, according to the elements in set Q, the corresponding elements are selected from set A2 to re-form a new set A3, A3 = {N z (2),N z (3)}, and finally set A3 and set Q are used as the final recognition results to obtain the types and quantities of wild animals.

[0112] In this step, by combining the image recognition results with the sound recognition results, a multimodal data fusion method is provided, which effectively reduces the misidentification caused by single-modality recognition, improves the precision and accuracy of recognition, and thus provides reliable data on the species and quantity of wild animals.

[0113] In summary, the present invention significantly improves the accuracy of recognition and statistics by fusing image recognition and sound recognition results and dynamically adjusting the shooting parameters of the drone. The YOLOv5 model and SORT algorithm are combined for image recognition, and the deep learning model and short-time Fourier transform are combined for sound recognition to ensure the accuracy of the image and sound recognition results. The image and sound recognition results are combined to effectively reduce false positives and false negatives, and improve the consistency and reliability of the data. The shooting parameters of the drone can also be dynamically adjusted to find a balance between regional resolution and coverage, ensuring that the system can work effectively in various environments and complex scenarios. This not only improves the system's recognition ability and data quality, but also enhances the system's robustness and versatility, achieving the effect of improving the application effect and practical value of drones in wildlife monitoring.

[0114] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0115] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software depends on the specific application and design constraints of the technical solution.

[0116] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, and may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment as needed.

[0117] The above is only a specific implementation method of the present application, but the scope of protection of the present application is not limited thereto. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed in this application, which should be covered by the scope of protection of the present application.

Claims

1. A method for identifying wild animals and counting species populations based on image processing captured by drones, characterized in that: The specific steps include: S1: Capture an image of wild animals to generate a reference image, and use an image processing algorithm to process the reference image to generate a target ratio coefficient for wild animals; S2: Adjust the drone's shooting parameters based on the target ratio coefficient. After the adjustment is completed, perform secondary image and sound collection on the wildlife to generate analysis images and sound sources; S3: Use the image processing algorithm to process the analysis image to generate an image recognition result, and then use the sound processing algorithm to process the analysis sound source to generate a sound recognition result; S4: performing set division based on the image recognition results and the sound recognition results, and taking the intersection of the image recognition results and the sound recognition results as the final recognition result; The shooting parameters include shooting height and shooting angle. The logic for adjusting the shooting parameters is as follows: Comparing the target proportion coefficient with a preset proportion threshold, generating a first adjustment coefficient according to the comparison result, and then generating a second adjustment coefficient according to the number of recognition areas; weighting the first adjustment coefficient and the second adjustment coefficient to generate a total adjustment coefficient, and adjusting the shooting parameters using the total adjustment coefficient; The calculation methods of the first adjustment coefficient and the second adjustment coefficient are: ω2=ln(n+1) Where ω1 and ω2 represent the first adjustment coefficient and the second adjustment coefficient respectively. Indicates the preset proportion threshold, represents the target ratio, and n represents the number of recognition areas; The total adjustment factor is calculated as follows: Where ω z represents the total adjustment coefficient, μ1 and μ2 represent the first weight and the second weight respectively, and μ1+μ2=1, δ1 and δ2 represent the preset first adjustment factor and the second adjustment factor respectively.

2. The method for identifying wild animals and counting species populations based on image processing captured by drones according to claim 1, characterized in that: The generation logic of the target proportion coefficient is: The image processing algorithm uses the Yolov5 model. Training images of various wild animal species are collected and divided into a training set and a validation set in an 8:2 ratio. The training set and validation set are used to train and optimize the Yolov5 model respectively. Use the optimized Yolov5 model to perform image recognition on the wild animals to be identified in the reference image and generate the identification area corresponding to each wild animal individual; Calculate the average area of ​​the identified regions in the reference image using the following formula: In the formula represents the average area, S k represents the area of ​​the kth recognition region, and the subscript k represents the number of the recognition region; The target ratio coefficient is calculated based on the average area of ​​the recognition area. The calculation method is: Where Sz represents the total area of ​​the reference image.

3. The method for identifying wild animals and counting species populations based on image processing captured by drones according to claim 2, characterized in that: Adjust the shooting parameters according to the total adjustment coefficient. The adjustment methods of shooting height and shooting angle are as follows: Where H and θ represent the shooting height and shooting angle respectively, and c represents the preset adjustment constant.

4. The method for identifying wild animals and counting species populations based on drone-photographed image processing according to claim 1, characterized in that: The logic of using image processing algorithms to process analysis images and generate image recognition results is as follows: Load N consecutive frames of analysis images into the optimized Yolov5 model in sequence for image recognition to obtain the corresponding detection results, which are expressed as: D i =Yolov5(X i ) Where D i The detection result of the i-th frame analysis picture is composed of several groups of sub-results. The sub-results correspond to different types of wild animals and include the identified bounding box position, animal category and confidence level. The detection result D i ={d i (1),d i (2),…,d i (j),…d i (m)}, where d i (j) represents the sub-result of the jth animal category in the i-th frame analysis picture, j = 1, 2, 3, ..., m, m represents the number of animal categories, X i Indicates the i-th frame analysis picture; The SORT algorithm is used to track the detection results of the Yolov5 model to obtain the position information of each individual in the same animal category in different frames. The tracking results are expressed as: T i (j)=SORT[d i (j)] Where T i Indicates the tracking result of the i-th frame analysis picture; The tracking results of N consecutive frames of analysis images are processed, and the same target detected in consecutive frames is matched to reduce repeated counting. The number of unique individuals of the same animal category appearing in different frames is obtained, and the number of species of each animal is counted. The calculation method is: Where N z (j) represents the number of species in the jth animal category, T i ′(j) represents the number of unique individuals of the jth animal category appearing in different frames; The animal categories are divided into set A1, and the number of species of each animal category is divided into set A2. The elements in set A1 and set A2 correspond one to one, and set A1 and set A2 are taken together as the image recognition result.

5. The method for identifying wild animals and counting species populations based on image processing captured by drones according to claim 4, characterized in that: The logic for processing the analyzed sound source and generating the sound recognition result is as follows: Build a deep learning model, collect a variety of wild animal sounds as training sound sources, divide the training sound sources into training and validation sets in an 8:2 ratio, and use the training and validation sets to train and optimize the deep learning model; The frequency domain features of the analyzed sound source are extracted through short-time Fourier transform, and the analyzed sound source is converted into a spectrum. The calculation method is: S(f,t)=∫s(τ)·w(t-τ)·e -j′2πfτ dτ Where S(f,t) represents the spectrum of the analyzed sound source, s(τ) represents the sound signal of the analyzed sound source at time τ, w(t-τ) represents the time domain window function, f represents the frequency, t represents the reference time, and j′ represents the imaginary unit; The spectrum of the analyzed sound source is input into the deep learning model to obtain the animal categories corresponding to different wild animals. The animal categories corresponding to the analyzed sound source are divided into set B and used as the sound recognition results.

6. The method for identifying wild animals and counting species populations based on drone-photographed image processing according to claim 5, characterized in that: Based on the set A1 in the image recognition results and the set B in the sound recognition results, the set Q of the finally identified wild animal species is generated. The set Q is expressed as: Q=A1∩B Based on the elements in set Q, corresponding elements are selected from set A2 to re-form a new set A3. The elements in set A3 correspond one-to-one with the elements in set Q, and set A3 and set Q are used as the final recognition results.

Images