A mouse gait analysis method based on follow-up filming

Abstract

The present invention discloses a mouse gait analysis method based on follow-up shooting, comprising: acquiring an initial video image of the mouse's activity area, separating the mouse's movement area through a preset background model, and obtaining a first image; calculating the mouse's motion vector based on the first image, and obtaining motion trend data; adjusting the camera's shooting angle and focal length based on the motion trend data, and obtaining a second image; adjusting the image brightness distribution based on the second image, eliminating the influence of uneven illumination, and obtaining a third image; extracting the mouse's contour features based on the third image, and obtaining gait feature data in combination with a pre-established gait model; updating the camera's tracking path based on the gait feature data, and obtaining a fourth image; enhancing the image clarity based on the fourth image, and obtaining a fifth image; based on the fifth image, identifying the mouse's key joint positions through a deep learning model, and generating a gait analysis report in combination with the gait feature data.

Description

Technical Field

[0001] The present invention belongs to the fields of machine vision and deep learning technology, and in particular relates to a mouse gait analysis method based on follow-up shooting. Background Art

[0002] In the mouse gait analysis method based on follow-up shooting, a key technical problem is how to continuously and stably capture video images of the mouse walking or running when the mouse is free to move. Due to the small size of mice, fast movement speed, and unpredictable movement paths, the traditional fixed-position shooting method is difficult to meet the needs of continuous tracking shooting. In addition, in the environment where mice move freely, the background is complex and changeable, and the lighting conditions are uneven, which will have an adverse effect on the quality of the video image, and thus affect the accuracy of subsequent image processing and gait analysis. At the same time, due to the large range of mouse activities, how to achieve large-scale tracking and shooting of mice while ensuring the quality of video images is also an urgent problem to be solved. Therefore, how to design a flexible and intelligent follow-up shooting system that can adapt to the characteristics of free movement of mice and achieve stable, clear, and comprehensive video image acquisition is a key technical challenge faced by the mouse gait analysis method based on follow-up shooting. Summary of the Invention

[0003] To solve the above technical problems, the present invention proposes a mouse gait analysis method based on follow-up shooting, which realizes accurate analysis and long-term monitoring of mouse behavior.

[0004] To achieve the above object, the present invention provides a mouse gait analysis method based on follow-up shooting, comprising: acquiring an initial video image of the mouse activity area, separating the mouse movement area using a preset background model, and obtaining a first image;

[0005] Calculating the mouse's motion vector based on the first image, determining the mouse's moving direction and speed, and obtaining motion trend data;

[0006] Adjusting the camera's shooting angle and focal length based on the motion trend data, and activating a fast tracking mode to obtain a second image if the mouse's movement speed exceeds a preset threshold;

[0007] Adjusting the brightness distribution of the image according to the second image to eliminate the influence of uneven illumination, thereby obtaining a third image;

[0008] Extracting the outline features of the mouse based on the third image, and determining the gait state of the mouse in combination with a pre-established gait model to obtain gait feature data;

[0009] updating the tracking path of the camera according to the gait feature data, and replanning the shooting area if the mouse's activity path deviates from a preset range to obtain a fourth image;

[0010] According to the fourth image, enhancing image clarity and eliminating background noise to obtain a fifth image;

[0011] Based on the fifth image, the key joint positions of the mouse are identified through a deep learning model, and a gait analysis report is generated in combination with the gait feature data.

[0012] Technical effect of the present invention: The present invention discloses a mouse gait analysis method based on follow-up shooting, which analyzes the mouse movement trend through background separation and optical flow method, and adjusts the camera parameters in real time to maintain stable tracking. Adaptive illumination compensation and multi-frame fusion technology are used to improve image quality, and edge detection and deep learning models are combined to extract mouse gait characteristics. The present invention can continuously and stably capture mouse activities in complex environments, automatically adjust the shooting range and parameters, and effectively solve the problems of traditional methods such as tracking difficulties and unstable image quality in free-movement environments. Through the coordinated application of intelligent algorithms and multiple image processing technologies, the present invention realizes accurate analysis and long-term monitoring of mouse behavior, providing reliable data support and technical guarantees for related research. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The accompanying drawings, which constitute part of this application, are intended to provide a further understanding of this application. The exemplary embodiments and descriptions of this application are intended to explain this application and do not constitute an improper limitation on this application. In the accompanying drawings:

[0014] Figure 1 Schematic diagram of the process of a mouse gait analysis method based on follow-up shooting according to an embodiment of the present invention;

[0015] Figure 2 A schematic diagram of a process for obtaining a first image according to an embodiment of the present invention;

[0016] Figure 3 A schematic diagram of a process for obtaining motion trend data according to an embodiment of the present invention;

[0017] Figure 4 A schematic diagram of a process for obtaining a second image according to an embodiment of the present invention;

[0018] Figure 5 A schematic diagram of a process for obtaining gait feature data according to an embodiment of the present invention;

[0019] Figure 6 A schematic diagram of the process of generating a gait analysis report according to an embodiment of the present invention. DETAILED DESCRIPTION

[0020] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in this application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0021] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0022] like Figure 1 As shown, this embodiment provides a mouse gait analysis method based on follow-up shooting, including: acquiring an initial video image of the mouse activity area, separating the mouse movement area through a preset background model, and obtaining a first image;

[0023] Calculating the mouse's motion vector based on the first image, determining the mouse's moving direction and speed, and obtaining motion trend data;

[0024] Adjusting the camera's shooting angle and focal length based on the motion trend data, and activating a fast tracking mode to obtain a second image if the mouse's movement speed exceeds a preset threshold;

[0025] Adjusting the brightness distribution of the image according to the second image to eliminate the influence of uneven illumination, thereby obtaining a third image;

[0026] Extracting the outline features of the mouse based on the third image, and determining the gait state of the mouse in combination with a pre-established gait model to obtain gait feature data;

[0027] updating the tracking path of the camera according to the gait feature data, and replanning the shooting area if the mouse's activity path deviates from a preset range to obtain a fourth image;

[0028] According to the fourth image, enhancing image clarity and eliminating background noise to obtain a fifth image;

[0029] Based on the fifth image, the key joint positions of the mouse are identified through a deep learning model, and a gait analysis report is generated in combination with the gait feature data.

[0030] Further, such as Figure 2 As shown, obtaining the first image includes:

[0031] S1. Obtain an initial video image sequence of the mouse activity area, and perform background separation processing on each frame image in the initial video image sequence using a preset background model to obtain a binary image sequence of the mouse movement area;

[0032] S2. Based on the binary image sequence of the motion region, removing the noise region in the image to obtain a first denoised image sequence;

[0033] S3. Extracting the complete motion area of ​​the mouse based on the first image sequence to obtain a second image sequence;

[0034] S4. Based on the second image sequence, using a convolutional neural network model to identify and classify the mouse's motion posture to obtain a mouse motion posture category sequence;

[0035] S5. Based on the mouse motion posture category sequence, modeling the mouse behavior pattern using a hidden Markov model to obtain a state transition matrix of the mouse behavior pattern;

[0036] S6, collecting the target mouse activity video image, repeating the processing from S1 to S4, and obtaining the target mouse movement posture category sequence;

[0037] S7. Input the target mouse motion posture category sequence into the hidden Markov model of S5 for decoding to obtain a first image.

[0038] Further, such as Figure 3 As shown, obtaining motion trend data includes:

[0039] Based on the first image, preprocessing the first image to obtain a preprocessed image;

[0040] Based on the preprocessed image, calculating the motion vectors of pixels between adjacent frames to obtain pixel-level motion information;

[0041] Identifying a mouse target in the image based on the pixel-level motion information and determining the position and size of the mouse;

[0042] Track the mouse target in multiple consecutive frames of images, obtain the mouse's motion trajectory, and calculate the mouse's motion trajectory and speed information;

[0043] The movement trend of the mouse is predicted based on the movement trajectory and speed information of the mouse, and the movement trend data of the mouse in the future period is obtained. The movement trend data includes position coordinates and movement speed.

[0044] As a specific application example, assume that the mouse's position at time t is (100, 150) and its velocity is (5, 3). The Kalman filter can predict its position at time t+1 and make corrections based on actual observations, resulting in a more accurate trajectory estimate. Based on the acquired trajectory data, the mouse's movement direction and velocity can be calculated. For example, the instantaneous velocity can be obtained by calculating the difference between adjacent positions, while the direction can be determined by the angle of the displacement vector. This information provides the basis for subsequent behavioral analysis. The Kalman filter is not only used for tracking but also for predicting future movement trends. By establishing motion models, such as uniform velocity or uniform acceleration, the filter can extrapolate the mouse's likely position over the next few frames. This prediction is particularly useful for handling occlusion or rapid motion scenes. Statistical analysis of the acquired motion data can yield features such as average velocity and acceleration. For example, calculating the mean and standard deviation of velocity over a period of time can reflect the overall intensity and fluctuation of the mouse's activity. These statistical features provide quantitative indicators for studying mouse behavioral patterns. Finally, comparing the analysis results with prior knowledge can promptly detect anomalies. For example, if a mouse is observed to maintain high-speed movements for a long time or repeatedly wander around the same location, it may indicate abnormal behavior or problems with the experimental environment. This abnormality detection mechanism helps ensure the reliability of experimental data and timely intervention for potential health problems.

[0045] Further, such as Figure 4 As shown, obtaining the second image includes:

[0046] Based on the position coordinates in the obtained motion trend data, the motion trajectory of the mouse is predicted to obtain the predicted position of the mouse at the next moment;

[0047] Based on the predicted mouse position, the camera's shooting angle is controlled by a servo motor so that the camera's shooting center coincides with the predicted mouse position. The mouse's displacement between consecutive frames is calculated to obtain the mouse's real-time movement speed.

[0048] A video frame in a fast tracking mode is acquired through a camera, and image enhancement and denoising are performed on the video frame to obtain a second image.

[0049] In a specific application example, obtaining mouse movement trend data is fundamental to behavioral analysis. Position coordinates are typically expressed in pixels, such as (320, 240) indicating the mouse is at the center of the image. Movement speed can be expressed in pixels per second, for example, 10 pixels per second. This data provides important information for subsequent analysis. The Kalman filter algorithm plays a key role in predicting mouse movement trajectories. This algorithm combines previous states with current measurements to estimate the optimal prediction. For example, if the mouse's current position is (100, 100) and its speed is 5 pixels per second, the algorithm might predict its position to be (105, 105) in the next second. This prediction helps the camera adjust in time to keep the mouse centered in the frame. The servo motor controlling the camera's shooting angle is key to achieving accurate tracking. Based on the predicted position, the motor may need to adjust the angle by approximately 0.5 degrees. This small adjustment ensures image stability while keeping the mouse centered in the field of view. Calculating mouse displacement using the optical flow method is a core technology for real-time tracking. By comparing pixel changes in consecutive frames, the direction and speed of the mouse's movement can be determined. If a horizontal displacement of 20 pixels is detected at a frame rate of 30 fps, the mouse's horizontal velocity can be calculated to be approximately 600 pixels per second. Setting the threshold for initiating fast tracking mode is crucial. Assuming a normal movement speed of 5 pixels per frame, the threshold can be set to 15 pixels per frame. Once a speed exceeding this threshold is detected, the system immediately switches to fast tracking mode, improving the sampling rate and tracking accuracy. Dynamic adjustment of the camera's focal length is crucial for maintaining image clarity. During rapid movement, the focal length may need to be adjusted from 50mm to 35mm to expand the field of view. This adjustment not only ensures the mouse remains centered in the frame but also captures more information about its surroundings, facilitating comprehensive analysis of its behavior. Image enhancement and denoising are crucial for obtaining a high-quality second image. Gaussian filtering can be used to remove noise, followed by histogram equalization to increase contrast. These processes create a clearer outline of the mouse, facilitating subsequent behavioral analysis, such as posture recognition or specific action detection. The combined application of this suite of techniques enables precise capture of the mouse's movement trajectory and behavioral characteristics.

[0050] Furthermore, obtaining the third image includes:

[0051] determining, based on the brightness distribution information of the second image, an area in the image where uneven illumination exists;

[0052] Dynamically adjust the brightness compensation coefficient of the area according to the uneven lighting area;

[0053] Adaptively adjusting the pixel brightness values ​​in the unevenly illuminated area according to the compensation coefficient to eliminate the influence of the uneven illumination;

[0054] Smoothing the adjusted pixel brightness values ​​to eliminate sudden brightness changes and obtain an image area with uniform lighting;

[0055] The processed uneven illumination area is fused with the uniform illumination area in the original image to obtain an image with overall uniform illumination, and the image with overall uniform illumination is subjected to contrast enhancement processing to obtain a third image.

[0056] Further, such as Figure 5 As shown, obtaining gait feature data includes:

[0057] Preprocessing the third image to obtain a preprocessed image;

[0058] Analyze the preprocessed image, extract the contour features of the mouse in the image, and obtain a binary image of the mouse contour;

[0059] According to the pre-established gait model, the extracted mouse contour features are analyzed, and the current mouse gait state is determined through model matching and feature comparison;

[0060] If the mouse's gait state conforms to the preset gait pattern, the current gait feature data is saved as input for subsequent analysis; otherwise, the next frame of image processing is performed;

[0061] According to the stored gait feature data, similar gait features are grouped into one category to obtain feature sets under different gait states;

[0062] The feature sets under different gait states are trained to establish a gait state classifier, and the gait state of mice is tracked and analyzed in real time to obtain continuous gait feature data.

[0063] Furthermore, obtaining the fourth image includes:

[0064] Based on the gait feature data, the next movement trajectory of the mouse is predicted and the tracking path of the camera is updated in real time;

[0065] Compare the mouse's activity path with the preset range to determine whether the mouse has deviated from the preset range. If the mouse deviates from the preset range, the camera is triggered to re-plan the shooting area;

[0066] Perform semantic segmentation on the mouse's activity area to determine the optimal shooting area;

[0067] Pass the optimal shooting area parameters to the camera, adjust the camera parameters, and re-acquire the shooting area;

[0068] A fourth image is acquired based on the reacquired parameters of the photographing area.

[0069] Specifically, through image preprocessing, edge detection, and feature extraction, the mouse's outline and posture information can be obtained. For example, the Canny edge detection algorithm can accurately depict the mouse's body contour, while the skeleton extraction algorithm can identify the locations of joints. This feature data lays the foundation for subsequent analysis. The Kalman filter algorithm performs well in predicting mouse motion trajectories. By combining historical position data with current observations, this algorithm can effectively estimate the mouse's position and velocity at the next moment. For example, if the mouse's current position is (10, 15) and its velocity is (2, 1), the Kalman filter might predict its next position to be (12, 16). This predictive ability enables the camera to adjust in advance to ensure that the mouse is always kept in the center of the field of view. Setting a preset range is crucial for experimental control. The experimental area can be divided into multiple sub-areas, such as a central area and an edge area. When the mouse's position coordinates exceed the preset range, the system triggers an alarm. For example, if the preset range is a 20×20 cm square area, and the mouse moves to (22, 18), the system will determine that it has deviated from the preset range. Deep learning algorithms play an important role in optimizing the capture area. Using semantic segmentation networks such as U-Net, the system can accurately identify mice, background, and other objects in an image. By analyzing the segmentation results, the system can determine the mouse's primary activity area and adjust camera parameters accordingly. For example, if a mouse is frequently active in the upper right corner of the image, the system will automatically adjust the camera focus and angle to center that area. Camera parameter adjustment is crucial for accurate tracking. Based on the calculated optimal capture area, the system may need to adjust parameters such as focus, aperture, and shutter speed. For example, when a mouse moves quickly, the shutter speed may need to be increased to 1 / 500 second to capture a clear image; in low light conditions, the aperture may need to be increased to f / 2.8 to achieve adequate exposure. The strength of this system lies in its adaptability and precision. Through real-time analysis and adjustments, it consistently tracks and records mouse behavior. This not only improves the quality and efficiency of data acquisition, but also captures subtle behavioral changes that might be overlooked by manual observation.

[0070] Furthermore, obtaining the fifth image includes:

[0071] Extracting feature information of each frame of the image according to the fourth image and constructing a feature matrix;

[0072] According to the characteristic matrix, determining the main characteristic components and removing the secondary components and background noise;

[0073] Reconstructing an image matrix according to the main characteristic components to obtain a preliminary fused image;

[0074] performing image enhancement processing in the frequency domain using wavelet transform on the preliminarily fused image to obtain an enhanced frequency domain image;

[0075] Reconstructing the enhanced frequency domain image using inverse wavelet transform to obtain a reconstructed time domain image;

[0076] According to the reconstructed time domain image, residual noise is removed to obtain a fifth image.

[0077] Specifically, feature extraction from image sequences is the foundation of multi-frame image fusion. By calculating the grayscale histogram and edge detection results for each frame, a feature matrix can be constructed. For example, for a sequence of mouse motion images, features such as the mouse's outline and position are extracted from each frame to form a feature matrix describing the mouse's motion. Principal component analysis is used for dimensionality reduction and denoising. By calculating the covariance matrix of the feature matrix and solving for the eigenvalues ​​and eigenvectors, the principal eigencomponents can be identified. In mouse motion analysis, the first three principal components may account for over 90% of the total variance. These principal components may correspond to key information such as the mouse's position, velocity, and acceleration. Image reconstruction involves projecting the reduced data back into the original space. Reconstructing the image matrix using the principal eigencomponents produces a preliminary fused image that removes minor information and background noise. This step helps highlight key features of mouse motion, such as trajectory and posture changes. Wavelet transforms enhance image clarity in the frequency domain. By decomposing the image into subbands of different scales and orientations, high-frequency details can be specifically enhanced. For images of mouse motion, this can focus on enhancing edge and texture information, improving the clarity of the mouse's outline. The inverse wavelet transform converts the enhanced frequency domain information back to the time domain. This step integrates the enhancement effects at all scales, producing a higher-resolution time domain image. In mouse motion analysis, this may manifest as clearer fur texture and limb outlines. The non-local means filtering algorithm searches for similar regions within the image and uses a weighted average of these regions to reduce noise. This method effectively preserves image details while removing residual noise. For mouse motion images, it can preserve motion details while removing background interference. The final result of multi-frame image fusion is output as the fifth image. This process combines multiple steps, including feature extraction, dimensionality reduction and denoising, frequency domain enhancement, and spatial domain filtering, to produce a clear and low-noise image. For mouse motion analysis, the final fused image should clearly demonstrate the mouse's motion trajectory, posture changes, and subtle behavioral details, providing high-quality data support for subsequent behavioral analysis. The significance of this series of processing steps lies in the synergistic effect of multiple image processing techniques to maximize the extraction and preservation of useful information while effectively suppressing noise and irrelevant information. This not only improves the visual quality of the image but, more importantly, enhances the effective information contained in the image, laying a solid foundation for subsequent image analysis and understanding tasks. In mouse behavior research, this high-quality image processing result can significantly improve the accuracy of behavior recognition, helping researchers to more accurately analyze the movement patterns and behavioral characteristics of mice.

[0078] Further, such as Figure 6 As shown, generating a gait analysis report includes:

[0079] Inputting the fifth image into a pre-established deep learning model, performing feature extraction and key joint position identification on the fifth image, and obtaining coordinate position information of the key joints of the mouse;

[0080] Acquiring pre-collected mouse gait characteristic data and establishing a gait analysis model based on the gait characteristic data;

[0081] The coordinate position information of the key joints of the mouse is input into the gait analysis model, and the gait of the mouse is analyzed in combination with the pre-established gait feature data to generate a gait analysis report of the mouse.

[0082] Specifically, deep learning models play a key role in mouse gait analysis. These models typically employ a convolutional neural network architecture and, after training with a large amount of labeled data, are able to accurately identify key joint locations in mouse images. For example, a typical deep learning model might identify key points on a mouse's head, shoulder, elbow, wrist, hip, knee, and ankle. The coordinates of these key points provide the foundational data for subsequent gait analysis. The collection of gait feature data is a prerequisite for establishing a gait analysis model. Researchers typically collect a large amount of gait data from healthy mice and mice with various diseases. This data includes parameters such as stride length, cadence, gait cycle, and stance phase duration. Statistical analysis of this data allows the establishment of reference models for normal and abnormal gait. Gait analysis models utilize machine learning algorithms, such as support vector machines or random forests, to compare and analyze the joint coordinate information output by the deep learning model with pre-established gait feature data. For example, the model might calculate metrics such as the mouse's stride length ratio (the ratio of stride length between the forelimb and hindlimb) and gait symmetry (the consistency of movement between the left and right limbs). These metrics are compared with a reference model to determine whether the mouse's gait is normal. Preset threshold conditions play a key role in gait analysis. For example, the stride length ratio of a normal mouse is typically between 0.8 and 1.2. If the analysis results show that the stride length ratio exceeds this range, the system may determine that the gait is abnormal. Similarly, a gait symmetry index below 0.9 may be considered abnormal. If multiple metrics exceed the preset thresholds, the system generates a detailed gait analysis report. The gait analysis report typically contains multiple aspects of information. First, basic gait parameters such as stride length and cadence are analyzed. Second, more in-depth analysis results such as the motion trajectory of each joint and changes in joint angles are analyzed. The report may also include a comparative analysis with normal reference values ​​and possible causes of the abnormality. For example, if a mouse's hindlimb stride length is significantly shortened while its forelimbs are normal, the report may suggest a possible connection to spinal cord injury or neurodegenerative disease. This approach, based on deep learning and gait analysis models, offers several technical advantages. First, it improves the accuracy and objectivity of the analysis and reduces human error. Secondly, it can capture subtle gait changes that are imperceptible to the naked eye, aiding in early disease diagnosis. Furthermore, this method is highly efficient and reproducible, enabling rapid processing of large amounts of data, providing strong support for drug screening and disease research. Through continuous data accumulation and model optimization, the accuracy and applicability of this method will be further enhanced, leading to further breakthroughs in mouse-related medical research.

[0083] The present invention discloses a mouse gait analysis method based on follow-up shooting, which analyzes the mouse movement trend through background separation and optical flow method, and adjusts the camera parameters in real time to maintain stable tracking. Adaptive illumination compensation and multi-frame fusion technology are used to improve image quality, and edge detection and deep learning models are combined to extract mouse gait characteristics. The present invention can continuously and stably capture mouse activities in complex environments, automatically adjust the shooting range and parameters, and effectively solve the problems of traditional methods such as tracking difficulties and unstable image quality in free-movement environments. Through the coordinated application of intelligent algorithms and multiple image processing technologies, the present invention realizes accurate analysis and long-term monitoring of mouse behavior, providing reliable data support and technical guarantees for related research.

[0084] The above are merely preferred embodiments of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A mouse gait analysis method based on follow-up shooting, characterized in that: include: Acquire an initial video image of the mouse activity area, separate the mouse movement area using a preset background model, and obtain a first image; Calculating the mouse's motion vector based on the first image, determining the mouse's moving direction and speed, and obtaining motion trend data; Adjusting the camera's shooting angle and focal length based on the motion trend data, and activating a fast tracking mode to obtain a second image if the mouse's movement speed exceeds a preset threshold; Adjusting the brightness distribution of the image according to the second image to eliminate the influence of uneven illumination, thereby obtaining a third image; Extracting the outline features of the mouse based on the third image, and determining the gait state of the mouse in combination with a pre-established gait model to obtain gait feature data; updating the tracking path of the camera according to the gait feature data, and replanning the shooting area if the mouse's activity path deviates from a preset range to obtain a fourth image; According to the fourth image, enhancing image clarity and eliminating background noise to obtain a fifth image; Based on the fifth image, the key joint positions of the mouse are identified through a deep learning model, and a gait analysis report is generated in combination with the gait feature data.

2. The mouse gait analysis method based on follow-up shooting according to claim 1, wherein Obtaining the first image includes: S1. Obtain an initial video image sequence of the mouse activity area, and perform background separation processing on each frame image in the initial video image sequence using a preset background model to obtain a binary image sequence of the mouse movement area; S2. Based on the binary image sequence of the motion region, removing the noise region in the image to obtain a first denoised image sequence; S3. Extracting the complete motion area of ​​the mouse based on the first image sequence to obtain a second image sequence; S4. Based on the second image sequence, using a convolutional neural network model to identify and classify the mouse's motion posture to obtain a mouse motion posture category sequence; S5. Based on the mouse motion posture category sequence, modeling the mouse behavior pattern using a hidden Markov model to obtain a state transition matrix of the mouse behavior pattern; S6, collecting the target mouse activity video image, repeating the processing from S1 to S4, and obtaining the target mouse movement posture category sequence; S7. Input the target mouse motion posture category sequence into the hidden Markov model of S5 for decoding to obtain a first image.

3. The mouse gait analysis method based on follow-up shooting according to claim 1, wherein Obtaining motion trend data includes: Based on the first image, preprocessing the first image to obtain a preprocessed image; Based on the preprocessed image, calculating the motion vectors of pixels between adjacent frames to obtain pixel-level motion information; Identifying a mouse target in the image based on the pixel-level motion information and determining the position and size of the mouse; Track the mouse target in multiple consecutive frames of images, obtain the mouse's motion trajectory, and calculate the mouse's motion trajectory and speed information; The movement trend of the mouse is predicted based on the movement trajectory and speed information of the mouse, and the movement trend data of the mouse in the future period is obtained. The movement trend data includes position coordinates and movement speed.

4. The mouse gait analysis method based on follow-up shooting according to claim 1, wherein Obtaining the second image includes: Based on the position coordinates in the obtained motion trend data, the motion trajectory of the mouse is predicted to obtain the predicted position of the mouse at the next moment; Based on the predicted mouse position, the camera's shooting angle is controlled by a servo motor so that the camera's shooting center coincides with the predicted mouse position. The mouse's displacement between consecutive frames is calculated to obtain the mouse's real-time movement speed. A video frame in a fast tracking mode is acquired through a camera, and image enhancement and denoising are performed on the video frame to obtain a second image.

5. The mouse gait analysis method based on follow-up shooting according to claim 1, wherein Obtaining the third image includes: determining, based on the brightness distribution information of the second image, an area in the image where uneven illumination exists; Dynamically adjust the brightness compensation coefficient of the area according to the uneven lighting area; Adaptively adjusting the pixel brightness values ​​in the unevenly illuminated area according to the compensation coefficient to eliminate the influence of the uneven illumination; Smoothing the adjusted pixel brightness values ​​to eliminate sudden brightness changes and obtain an image area with uniform lighting; The processed uneven illumination area is fused with the uniform illumination area in the original image to obtain an image with overall uniform illumination, and the image with overall uniform illumination is subjected to contrast enhancement processing to obtain a third image.

6. The mouse gait analysis method based on follow-up shooting according to claim 1, wherein The gait feature data obtained include: Preprocessing the third image to obtain a preprocessed image; Analyze the preprocessed image, extract the contour features of the mouse in the image, and obtain a binary image of the mouse contour; According to the pre-established gait model, the extracted mouse contour features are analyzed, and the current mouse gait state is determined through model matching and feature comparison; If the mouse's gait state conforms to the preset gait pattern, the current gait feature data is saved as input for subsequent analysis; otherwise, the next frame of image processing is performed; According to the stored gait feature data, similar gait features are grouped into one category to obtain feature sets under different gait states; The feature sets under different gait states are trained to establish a gait state classifier, and the gait state of mice is tracked and analyzed in real time to obtain continuous gait feature data.

7. The mouse gait analysis method based on follow-up shooting according to claim 1, wherein Obtaining the fourth image includes: Based on the gait feature data, the next movement trajectory of the mouse is predicted and the tracking path of the camera is updated in real time; Compare the mouse's activity path with the preset range to determine whether the mouse has deviated from the preset range. If the mouse deviates from the preset range, the camera is triggered to re-plan the shooting area; Perform semantic segmentation on the mouse's activity area to determine the optimal shooting area; Pass the optimal shooting area parameters to the camera, adjust the camera parameters, and re-acquire the shooting area; A fourth image is acquired based on the reacquired parameters of the photographing area.

8. The mouse gait analysis method based on follow-up shooting according to claim 1, wherein Obtaining the fifth image includes: Extracting feature information of each frame of the image according to the fourth image and constructing a feature matrix; According to the characteristic matrix, determining the main characteristic components and removing the secondary components and background noise; Reconstructing an image matrix according to the main characteristic components to obtain a preliminary fused image; performing image enhancement processing in the frequency domain using wavelet transform on the preliminarily fused image to obtain an enhanced frequency domain image; Reconstructing the enhanced frequency domain image using inverse wavelet transform to obtain a reconstructed time domain image; According to the reconstructed time domain image, residual noise is removed to obtain a fifth image.

9. The mouse gait analysis method based on follow-up shooting according to claim 1, wherein Generating a gait analysis report includes: Inputting the fifth image into a pre-established deep learning model, performing feature extraction and key joint position identification on the fifth image, and obtaining coordinate position information of the key joints of the mouse; Acquiring pre-collected mouse gait characteristic data and establishing a gait analysis model based on the gait characteristic data; The coordinate position information of the key joints of the mouse is input into the gait analysis model, and the gait of the mouse is analyzed in combination with the pre-established gait feature data to generate a gait analysis report of the mouse.

Images