Flea behavior analysis method and related device
Through high-resolution high-frame rate image acquisition and deep learning model, combined with multi-source data analysis, the problem of inaccurate flea behavior monitoring in traditional methods is solved, and accurate and comprehensive analysis of flea behavior is achieved.
Patent Information
- Application Number
- CN202410971690.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-19
- Publication Date
- 2024-11-12
AI Technical Summary
Traditional methods have difficulty monitoring and analyzing flea behavior accurately and efficiently, resulting in inefficiency in research and incomplete data.
High resolution and high frame rate image acquisition equipment are used for image acquisition and preprocessing, combined with image recognition algorithms and deep learning models, extract feature data such as flea position, velocity, acceleration, and posture, and obtain behavioral change patterns through space-time analysis. Further fuse acceleration, pressure and biological data for comprehensive analysis.
It improves the accuracy and accuracy of flea behavior detection and analysis, and has a deep understanding of flea behavior patterns and changing patterns.
Smart Images

Figure CN118941850A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the field of computer technology, and more specifically, relates to a flea behavior analysis method, a flea behavior analysis device, a behavior analysis equipment and a computer-readable storage medium. Background Art
[0002] As a common parasite, fleas have always faced many challenges in studying and monitoring their behavior due to their tiny size and agile movements. Traditional flea research methods mainly rely on manual observation and limited experimental methods, which are not only inefficient but also difficult to obtain comprehensive and accurate behavioral data, resulting in certain defects in research in related fields.
[0003] Therefore, how to improve the accuracy and precision of flea behavior detection and analysis is a key issue that technicians in this field are concerned about. Summary of the invention
[0004] The purpose of this application is to provide a flea behavior analysis method, a flea behavior analysis device, a behavior analysis equipment and a computer-readable storage medium to improve the accuracy and precision of flea behavior detection and analysis.
[0005] In view of the above defects or improvement needs of the prior art, the present invention provides a flea behavior analysis method, comprising:
[0006] The image acquisition device is used to acquire images of the flea activity area to obtain an original image; wherein the image acquisition device is a camera device with high resolution and high frame rate;
[0007] Performing image preprocessing on the original image to obtain a processed image;
[0008] Based on the image recognition algorithm and the flea activity characteristics, the processed image is subjected to multi-feature recognition processing to obtain flea activity feature data; wherein the flea activity feature data includes position data, speed data, acceleration data, posture data, jumping frequency data, jumping height data, and activity range data;
[0009] Based on the flea activity feature data, a deep learning model is trained to obtain a behavior classification model;
[0010] Performing behavior monitoring on fleas in the flea activity area based on the behavior classification model to obtain behavior monitoring data;
[0011] Performing spatiotemporal analysis on the behavior monitoring data based on the location data and corresponding time parameters to obtain the changing rules of flea behavior;
[0012] The flea behavior change patterns and corresponding behavior monitoring data are visualized.
[0013] Optionally, also include:
[0014] Acquire raw acceleration data from an acceleration sensor, acquire raw pressure data from a pressure sensor, and acquire raw biological detection data from a biological detection platform;
[0015] Performing sensor data preprocessing on the acceleration raw data and the pressure raw data to obtain acceleration data and pressure data; wherein the sensor data preprocessing includes noise removal processing, data calibration processing, and unit unification processing;
[0016] Performing experimental data preprocessing on the biological detection raw data to obtain biological detection data; wherein the experimental data preprocessing includes data standardization processing and outlier processing;
[0017] Based on the data acquisition method, time synchronization processing is performed on the acceleration data, the pressure data, the biological detection data, and the processed image to obtain a unified time axis;
[0018] Extracting relevant features from the acceleration data, the pressure data, and the biological detection data to obtain acceleration feature data, pressure feature data, and biological detection feature data;
[0019] The acceleration characteristic data, the pressure characteristic data, and the biological detection characteristic data are added to the flea activity characteristic data based on a data fusion algorithm and the unified time axis.
[0020] Optionally, multi-feature recognition processing is performed on the processed image based on an image recognition algorithm and flea activity characteristics to obtain flea activity feature data, including:
[0021] performing flea individual recognition on the processed image based on a target detection algorithm to obtain a plurality of flea individual images;
[0022] Feature data of the plurality of individual flea images are extracted based on the flea activity characteristics and mathematical statistics to obtain the flea activity feature data.
[0023] Optionally, a deep learning model is trained based on the flea activity feature data to obtain a behavior classification model, including:
[0024] The initial convolutional neural network is trained based on the flea activity feature data to obtain the behavior classification model.
[0025] The present application also provides a flea behavior analysis device, comprising:
[0026] An image acquisition module is used to acquire images of the flea activity area through an image acquisition device to obtain an original image; wherein the image acquisition device is a camera device with high resolution and high frame rate;
[0027] An image preprocessing module, used for performing image preprocessing on the original image to obtain a processed image;
[0028] A feature processing module, used for performing multi-feature recognition processing on the processed image based on an image recognition algorithm and flea activity characteristics to obtain flea activity feature data; wherein the flea activity feature data includes position data, speed data, acceleration data, posture data, jumping frequency data, jumping height data, and activity range data;
[0029] A model training module, used to train a deep learning model based on the flea activity feature data to obtain a behavior classification model;
[0030] A behavior monitoring module, used for performing behavior monitoring on fleas in the flea activity area based on the behavior classification model to obtain behavior monitoring data;
[0031] A spatiotemporal analysis module, for performing spatiotemporal analysis on the behavior monitoring data based on the position data and corresponding time parameters to obtain the changing rules of flea behavior;
[0032] The analysis result display module is used to visualize the flea behavior change rules and corresponding behavior monitoring data.
[0033] Optionally, also include:
[0034] A fusion data acquisition module is used to acquire raw acceleration data from an acceleration sensor, raw pressure data from a pressure sensor, and raw biological detection data from a biological detection platform;
[0035] A sensor data preprocessing module, used for performing sensor data preprocessing on the acceleration raw data and the pressure raw data to obtain acceleration data and pressure data; wherein the sensor data preprocessing includes noise removal processing, data calibration processing, and unit unification processing;
[0036] An experimental data preprocessing module, used to perform experimental data preprocessing on the biological detection raw data to obtain biological detection data; wherein the experimental data preprocessing includes data standardization processing and outlier processing;
[0037] A time synchronization processing module, used for performing time synchronization processing on the acceleration data, the pressure data, the biological detection data, and the processed image based on a data acquisition method to obtain a unified time axis;
[0038] A fusion feature extraction module, used to extract relevant features from the acceleration data, the pressure data, and the biological detection data to obtain acceleration feature data, pressure feature data, and biological detection feature data;
[0039] A feature fusion module is used to add the acceleration feature data, pressure feature data, and biological detection feature data to the flea activity feature data based on a data fusion algorithm and the unified time axis.
[0040] Optionally, the feature processing module includes:
[0041] An individual identification unit, used for performing flea individual identification on the processed image based on a target detection algorithm to obtain a plurality of flea individual images;
[0042] The feature data extraction unit is used to extract feature data from the plurality of individual flea images based on the flea activity characteristics and mathematical statistics to obtain the flea activity feature data.
[0043] Optionally, the model training module is specifically used to train the initial convolutional neural network based on the flea activity feature data to obtain the behavior classification model.
[0044] The present application also provides a behavior analysis device, comprising:
[0045] Memory for storing computer programs;
[0046] A processor is used to implement the steps of the flea behavior analysis method as described above when executing the computer program.
[0047] The present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the flea behavior analysis method described above are implemented.
[0048] A flea behavior analysis method provided in the present application includes: acquiring images of a flea activity area through an image acquisition device to obtain an original image; wherein the image acquisition device is a high-resolution and high-frame-rate camera device; performing image preprocessing on the original image to obtain a processed image; performing multi-feature recognition processing on the processed image based on an image recognition algorithm and flea activity characteristics to obtain flea activity feature data; wherein the flea activity feature data includes position data, speed data, acceleration data, posture data, jump frequency data, jump height data, and activity range data; training a deep learning model based on the flea activity feature data to obtain a behavior classification model; performing behavior monitoring on fleas in the flea activity area based on the behavior classification model to obtain behavior monitoring data; performing spatiotemporal analysis on the behavior monitoring data based on the position data and corresponding time parameters to obtain flea behavior change patterns; and visually displaying the flea behavior change patterns and the corresponding behavior monitoring data.
[0049] It has the following beneficial effects:
[0050] Through high-resolution and high-frame-rate image acquisition equipment, image preprocessing, multi-feature recognition, and deep learning model training, we can comprehensively and accurately obtain the activity characteristic data of fleas, improve the accuracy and precision of flea behavior detection and analysis, and thus gain a deeper understanding of the flea behavior patterns and changing patterns. BRIEF DESCRIPTION OF THE DRAWINGS
[0051] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.
[0052] Figure 1 A flow chart of a flea behavior analysis method provided in an embodiment of the present application;
[0053] Figure 2 A schematic diagram of the structure of a flea behavior analysis device provided in an embodiment of the present application;
[0054] Figure 3 A schematic diagram of the structure of the behavior analysis device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0055] The core of this application is to provide a flea behavior analysis method, a flea behavior analysis device, a behavior analysis equipment and a computer-readable storage medium to improve the accuracy and precision of flea behavior detection and analysis.
[0056] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.
[0057] The following is an example to illustrate a flea behavior analysis method provided by the present application.
[0058] Please refer to Figure 1 , Figure 1 A flow chart of a flea behavior analysis method provided in an embodiment of the present application.
[0059] In this embodiment, the method may include:
[0060] S101, collecting images of the flea activity area by an image collection device to obtain an original image; wherein the image collection device is a camera device with high resolution and high frame rate;
[0061] This step aims to acquire images of the flea activity area through an image acquisition device to obtain an original image; wherein the image acquisition device is a camera device with high resolution and high frame rate. In particular, since fleas move at a relatively fast speed, in order to effectively acquire the original image of fleas and avoid blurring or failure to capture, this step mainly uses a camera device with high resolution and high frame rate for image acquisition.
[0062] S102, performing image preprocessing on the original image to obtain a processed image;
[0063] Based on S101, this step aims to perform image preprocessing on the original image to obtain a processed image. The image preprocessing may include operations such as denoising, contrast enhancement, and image correction to improve image quality and clarity. Improving the image quality makes subsequent feature recognition and analysis more accurate.
[0064] S103, performing multi-feature recognition processing on the processed image based on the image recognition algorithm and the flea activity characteristics to obtain flea activity feature data; wherein the flea activity feature data includes position data, speed data, acceleration data, posture data, jumping frequency data, jumping height data, and activity range data;
[0065] On the basis of S102, this step aims to perform multi-feature recognition processing on the processed image based on the image recognition algorithm and the flea activity characteristics to obtain flea activity feature data; wherein the flea activity feature data includes position data, speed data, acceleration data, posture data, jumping frequency data, jumping height data, and activity range data;
[0066] Among them, the flea activity characteristics include jumping, moving and other characteristics. Therefore, it is necessary to extract corresponding feature data for the jumping and moving characteristics. Correspondingly, it can include position data, speed data, acceleration data, posture data, jumping frequency data, jumping height data, and activity range data. It can be seen that comprehensive acquisition of various activity feature data of fleas is helpful to deeply understand the behavior patterns of fleas.
[0067] Furthermore, this step may include:
[0068] Step 1, performing flea individual recognition on the processed image based on the target detection algorithm to obtain multiple flea individual images;
[0069] Step 2: extract feature data from multiple flea individual images based on flea activity characteristics and mathematical statistics to obtain flea activity feature data.
[0070] It can be seen that this optional solution mainly explains how to extract feature data. In this optional solution, flea individual recognition is performed on the processed image based on the target detection algorithm to obtain multiple flea individual images. The flea individual can be accurately identified, providing a targeted object for subsequent feature extraction. Based on flea activity characteristics and mathematical statistics, feature data of multiple flea individual images are extracted to obtain flea activity feature data. The ability to accurately obtain feature data related to flea activity provides strong support for in-depth analysis of flea behavior.
[0071] S104, training the deep learning model based on the flea activity feature data to obtain a behavior classification model;
[0072] Based on S103, this step aims to train the deep learning model based on the flea activity feature data to obtain a behavior classification model. The behavior classification model obtained through training can more accurately classify and predict the behavior of fleas.
[0073] Furthermore, this step may include:
[0074] The initial convolutional neural network is trained based on the flea activity feature data to obtain a behavior classification model.
[0075] S105, performing behavior monitoring on fleas in the flea activity area based on the behavior classification model to obtain behavior monitoring data;
[0076] Based on S104, this step aims to monitor the behavior of fleas in the flea activity area based on the behavior classification model to obtain behavior monitoring data, thereby achieving real-time monitoring of flea behavior and timely grasping the behavioral dynamics of fleas.
[0077] S106, performing spatiotemporal analysis on the behavior monitoring data based on the position data and the corresponding time parameters to obtain the changing pattern of flea behavior;
[0078] On the basis of S105, this step aims to perform spatiotemporal analysis on the behavior monitoring data based on the position data and the corresponding time parameters to obtain the behavior change pattern of fleas. On the basis of the effective monitoring of the behavior of fleas, the behavior change pattern of fleas in time and space can be studied. For example, the behavior pattern of fleas in different spaces at a certain time, or the behavior pattern of fleas in a certain space at different times.
[0079] S107, visually displaying the changing patterns of flea behavior and the corresponding behavior monitoring data.
[0080] Based on S106, this step aims to visualize the flea behavior change patterns and the corresponding behavior monitoring data. The flea behavior change patterns and related behavior monitoring data are displayed in an intuitive manner, such as through charts, images, etc. This enables researchers to more intuitively understand the flea behavior patterns and patterns, which is convenient for analysis and research.
[0081] Furthermore, this embodiment may also include:
[0082] Step 1, obtaining raw acceleration data from an acceleration sensor, raw pressure data from a pressure sensor, and raw biological detection data from a biological detection platform;
[0083] Step 2, performing sensor data preprocessing on the acceleration raw data and the pressure raw data to obtain acceleration data and pressure data; wherein the sensor data preprocessing includes noise removal processing, data calibration processing, and unit unification processing;
[0084] Step 3, performing experimental data preprocessing on the biological detection raw data to obtain biological detection data; wherein the experimental data preprocessing includes data standardization processing and outlier processing;
[0085] Step 4, based on the data acquisition method, time synchronization processing is performed on the acceleration data, pressure data, biological detection data, and processed images to obtain a unified time axis;
[0086] Step 5, extracting relevant features from the acceleration data, the pressure data, and the biological detection data to obtain acceleration feature data, pressure feature data, and biological detection feature data;
[0087] Step 6: Add the acceleration feature data, pressure feature data, and biological detection feature data to the flea activity feature data based on the data fusion algorithm and the unified time axis.
[0088] It can be seen that in this embodiment, the features corresponding to the sensor data and the experimental data can also be fused with the flea activity feature data to obtain new flea activity feature data. That is, it is added to the flea activity feature data. Obviously, this optional solution integrates multi-source data, further improving the comprehensiveness and accuracy of the analysis. By obtaining relevant data from the acceleration sensor, pressure sensor and biological detection platform, and performing data preprocessing, time synchronization and feature fusion, the physical characteristics and biological characteristics of fleas can be comprehensively considered, thereby more comprehensively analyzing the behavior of fleas and improving the reliability and scientificity of the analysis results.
[0089] In summary, this embodiment can comprehensively and accurately obtain the activity characteristic data of fleas through high-resolution and high-frame rate image acquisition equipment, image preprocessing, multi-feature recognition and deep learning model training, thereby improving the accuracy and precision of flea behavior detection and analysis, thereby gaining an in-depth understanding of the behavior patterns and changing laws of fleas.
[0090] The following is another specific example to further illustrate the flea behavior analysis method provided by the present application.
[0091] Step 1: Use a high-resolution, high-frame-rate camera or other imaging device to continuously capture images from multiple angles of the area where fleas are active. These devices can clearly record the tiny movements of fleas under different lighting conditions.
[0092] Step 2: Preprocess the acquired images, including denoising, contrast enhancement, image correction and other operations, to improve image quality and clarity.
[0093] Step 3: Use target detection algorithms, such as deep learning-based object detection models, to accurately identify individual fleas in the image. Then, extract features related to flea behavior from the processed image, such as the flea's position, speed, acceleration, posture, jumping frequency and height, and activity range.
[0094] Step 4: Use machine learning or deep learning algorithms to analyze and classify the extracted features and establish a flea behavior model. For example, use support vector machines, decision trees, artificial neural networks and other methods to classify flea behaviors into different categories such as jumping, stationary, exploring, and eating.
[0095] Step 5: Use a large amount of labeled flea behavior data to train the established model, and continuously optimize the model parameters to improve the accuracy of behavior classification and prediction.
[0096] In step 6, if there are multiple data sources, such as different types of sensor data (e.g., accelerometer, pressure sensor) or other relevant biological data, these data are fused to obtain more comprehensive and accurate behavioral information.
[0097] Step 7, considering time and space factors, analyze the changing patterns of flea behavior in time series, as well as its distribution and preference in different spatial locations.
[0098] Step 8: The system can process the newly acquired image data in real time, quickly analyze the current behavior of the fleas, and provide real-time feedback to the user.
[0099] Step 9: Present the analysis results in the form of intuitive charts, animations, reports, etc.
[0100] It can be seen that this embodiment can comprehensively and accurately obtain the activity characteristic data of fleas through high-resolution and high-frame rate image acquisition equipment, image preprocessing, multi-feature recognition and deep learning model training, thereby improving the accuracy and precision of flea behavior detection and analysis, thereby gaining an in-depth understanding of the behavior patterns and changing laws of fleas.
[0101] The flea behavior analysis device provided in the embodiment of the present application is introduced below. The flea behavior analysis device and the flea behavior analysis method described below can be referenced to each other.
[0102] Please refer to Figure 2 , Figure 2 A schematic diagram of the structure of a flea behavior analysis device provided in an embodiment of the present application.
[0103] In this embodiment, the device may include:
[0104] The image acquisition module 100 is used to acquire images of the flea activity area through an image acquisition device to obtain an original image; wherein the image acquisition device is a camera device with high resolution and high frame rate;
[0105] The image preprocessing module 200 is used to perform image preprocessing on the original image to obtain a processed image;
[0106] The feature processing module 300 is used to perform multi-feature recognition processing on the processed image based on the image recognition algorithm and the flea activity characteristics to obtain flea activity feature data; wherein the flea activity feature data includes position data, speed data, acceleration data, posture data, jumping frequency data, jumping height data, and activity range data;
[0107] A model training module 400 is used to train a deep learning model based on flea activity feature data to obtain a behavior classification model;
[0108] A behavior monitoring module 500 is used to perform behavior monitoring on fleas in the flea activity area based on a behavior classification model to obtain behavior monitoring data;
[0109] The spatiotemporal analysis module 600 is used to perform spatiotemporal analysis on the behavior monitoring data based on the position data and the corresponding time parameters to obtain the changing rules of flea behavior;
[0110] The analysis result display module 700 is used to visualize the changing patterns of flea behavior and the corresponding behavior monitoring data.
[0111] Optionally, the device in this embodiment may further include:
[0112] A fusion data acquisition module is used to acquire raw acceleration data from an acceleration sensor, raw pressure data from a pressure sensor, and raw biological detection data from a biological detection platform;
[0113] A sensor data preprocessing module is used to perform sensor data preprocessing on the acceleration raw data and the pressure raw data to obtain acceleration data and pressure data; wherein the sensor data preprocessing includes noise removal processing, data calibration processing, and unit unification processing;
[0114] The experimental data preprocessing module is used to perform experimental data preprocessing on the biological detection raw data to obtain biological detection data; wherein the experimental data preprocessing includes data standardization processing and outlier processing;
[0115] A time synchronization processing module is used to perform time synchronization processing on acceleration data, pressure data, biological detection data, and processed images based on the data acquisition method to obtain a unified time axis;
[0116] A fusion feature extraction module is used to extract relevant features from acceleration data, pressure data, and biological detection data to obtain acceleration feature data, pressure feature data, and biological detection feature data;
[0117] The feature fusion module is used to add acceleration feature data, pressure feature data, and biological detection feature data to flea activity feature data based on a data fusion algorithm and a unified time axis.
[0118] Optionally, the feature processing module 300 includes:
[0119] An individual identification unit, used for performing flea individual identification on the processed image based on a target detection algorithm to obtain a plurality of flea individual images;
[0120] The feature data extraction unit is used to extract feature data from multiple flea individual images based on flea activity characteristics and mathematical statistics to obtain flea activity feature data.
[0121] Optionally, the model training module 400 is specifically used to train the initial convolutional neural network based on the flea activity feature data to obtain a behavior classification model.
[0122] This application also provides behavioral analysis equipment, please refer to Figure 3 , Figure 3 This is a schematic diagram of the structure of a behavior analysis device provided in an embodiment of the present application. The behavior analysis device may include:
[0123] Memory for storing computer programs;
[0124] A processor, when used to execute a computer program, can implement the steps of any of the above-mentioned flea behavior analysis methods.
[0125] like Figure 3 , which is a schematic diagram of the structure of a behavior analysis device, the behavior analysis device may include: a processor 10, a memory 11, a communication interface 12 and a communication bus 13. The processor 10, the memory 11 and the communication interface 12 all communicate with each other through the communication bus 13.
[0126] In the embodiment of the present application, the processor 10 may be a central processing unit (CPU), an application specific integrated circuit, a digital signal processor, a field programmable gate array or other programmable logic devices.
[0127] The processor 10 may call a program stored in the memory 11. Specifically, the processor 10 may execute operations in an embodiment of the abnormal IP identification method.
[0128] The memory 11 is used to store one or more programs, which may include program codes, and the program codes include computer operation instructions. In the embodiment of the present application, the memory 11 at least stores programs for implementing the following functions:
[0129] The image acquisition device is used to acquire images of the flea activity area to obtain an original image; wherein the image acquisition device is a camera device with high resolution and high frame rate;
[0130] Performing image preprocessing on the original image to obtain a processed image;
[0131] Based on the image recognition algorithm and the flea activity characteristics, the processed image is subjected to multi-feature recognition processing to obtain flea activity feature data; wherein the flea activity feature data includes position data, speed data, acceleration data, posture data, jumping frequency data, jumping height data, and activity range data;
[0132] Based on the flea activity feature data, a deep learning model is trained to obtain a behavior classification model;
[0133] Performing behavior monitoring on fleas in the flea activity area based on the behavior classification model to obtain behavior monitoring data;
[0134] Performing spatiotemporal analysis on the behavior monitoring data based on the location data and corresponding time parameters to obtain the changing rules of flea behavior;
[0135] The flea behavior change patterns and corresponding behavior monitoring data are visualized.
[0136] In a possible implementation, the memory 11 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required for at least one function, etc.; the data storage area may store data created during use.
[0137] In addition, the memory 11 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device or other volatile solid-state storage device.
[0138] The communication interface 12 may be an interface of a communication module, and is used to connect to other devices or systems.
[0139] Of course, it should be noted that Figure 3 The structure shown does not constitute a limitation on the behavior analysis device in the embodiment of the present application. In actual applications, the behavior analysis device may include Figure 3 More or fewer components than shown, or combinations of certain components.
[0140] The present application also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of any of the above-mentioned flea behavior analysis methods can be implemented.
[0141] The computer-readable storage medium may include: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.
[0142] For an introduction to the computer-readable storage medium provided in this application, please refer to the above method embodiment, and this application will not go into details here.
[0143] The various embodiments in the specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.
[0144] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0145] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
[0146] The above is a detailed introduction to a flea behavior analysis method, a flea behavior analysis device, a behavior analysis equipment, and a computer-readable storage medium provided by the present application. Specific examples are used herein to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. It should be pointed out that for ordinary technicians in this technical field, without departing from the principles of the present application, several improvements and modifications can be made to the present application, and these improvements and modifications also fall within the scope of protection of the claims of the present application.
Claims
1. A flea behavior analysis method, characterized in that: include: The image acquisition device is used to acquire images of the flea activity area to obtain an original image; wherein the image acquisition device is a camera device with high resolution and high frame rate; Performing image preprocessing on the original image to obtain a processed image; Based on the image recognition algorithm and the flea activity characteristics, the processed image is subjected to multi-feature recognition processing to obtain flea activity feature data; wherein the flea activity feature data includes position data, speed data, acceleration data, posture data, jumping frequency data, jumping height data, and activity range data; Based on the flea activity feature data, a deep learning model is trained to obtain a behavior classification model; Performing behavior monitoring on fleas in the flea activity area based on the behavior classification model to obtain behavior monitoring data; Performing spatiotemporal analysis on the behavior monitoring data based on the location data and corresponding time parameters to obtain the changing rules of flea behavior; The flea behavior change patterns and corresponding behavior monitoring data are visualized.
2. The flea behavior analysis method according to claim 1, characterized in that: Also includes: Acquire raw acceleration data from an acceleration sensor, acquire raw pressure data from a pressure sensor, and acquire raw biological detection data from a biological detection platform; Performing sensor data preprocessing on the acceleration raw data and the pressure raw data to obtain acceleration data and pressure data; wherein the sensor data preprocessing includes noise removal processing, data calibration processing, and unit unification processing; Performing experimental data preprocessing on the biological detection raw data to obtain biological detection data; wherein the experimental data preprocessing includes data standardization processing and outlier processing; Based on the data acquisition method, time synchronization processing is performed on the acceleration data, the pressure data, the biological detection data, and the processed image to obtain a unified time axis; Extracting relevant features from the acceleration data, the pressure data, and the biological detection data to obtain acceleration feature data, pressure feature data, and biological detection feature data; The acceleration characteristic data, the pressure characteristic data, and the biological detection characteristic data are added to the flea activity characteristic data based on a data fusion algorithm and the unified time axis.
3. The flea behavior analysis method according to claim 1, characterized in that: Based on the image recognition algorithm and the flea activity characteristics, the processed image is subjected to multi-feature recognition processing to obtain flea activity feature data, including: performing flea individual recognition on the processed image based on a target detection algorithm to obtain a plurality of flea individual images; Feature data of the plurality of individual flea images are extracted based on the flea activity characteristics and mathematical statistics to obtain the flea activity feature data.
4. The flea behavior analysis method according to claim 1, characterized in that: The deep learning model is trained based on the flea activity feature data to obtain a behavior classification model, including: The initial convolutional neural network is trained based on the flea activity feature data to obtain the behavior classification model.
5. A flea behavior analysis device, characterized in that: include: An image acquisition module is used to acquire images of the flea activity area through an image acquisition device to obtain an original image; wherein the image acquisition device is a camera device with high resolution and high frame rate; An image preprocessing module, used for performing image preprocessing on the original image to obtain a processed image; A feature processing module, used for performing multi-feature recognition processing on the processed image based on an image recognition algorithm and flea activity characteristics to obtain flea activity feature data; wherein the flea activity feature data includes position data, speed data, acceleration data, posture data, jumping frequency data, jumping height data, and activity range data; A model training module, used to train a deep learning model based on the flea activity feature data to obtain a behavior classification model; A behavior monitoring module, used for performing behavior monitoring on fleas in the flea activity area based on the behavior classification model to obtain behavior monitoring data; A spatiotemporal analysis module, for performing spatiotemporal analysis on the behavior monitoring data based on the position data and corresponding time parameters to obtain the changing rules of flea behavior; The analysis result display module is used to visualize the flea behavior change rules and corresponding behavior monitoring data.
6. The flea behavior analysis device according to claim 5, characterized in that: Also includes: A fusion data acquisition module is used to acquire raw acceleration data from an acceleration sensor, raw pressure data from a pressure sensor, and raw biological detection data from a biological detection platform; A sensor data preprocessing module, used for performing sensor data preprocessing on the acceleration raw data and the pressure raw data to obtain acceleration data and pressure data; wherein the sensor data preprocessing includes noise removal processing, data calibration processing, and unit unification processing; An experimental data preprocessing module, used to perform experimental data preprocessing on the biological detection raw data to obtain biological detection data; wherein the experimental data preprocessing includes data standardization processing and outlier processing; A time synchronization processing module, used for performing time synchronization processing on the acceleration data, the pressure data, the biological detection data, and the processed image based on a data acquisition method to obtain a unified time axis; A fusion feature extraction module, used to extract relevant features from the acceleration data, the pressure data, and the biological detection data to obtain acceleration feature data, pressure feature data, and biological detection feature data; A feature fusion module is used to add the acceleration feature data, pressure feature data, and biological detection feature data to the flea activity feature data based on a data fusion algorithm and the unified time axis.
7. The flea behavior analysis device according to claim 5, characterized in that: The feature processing module comprises: An individual identification unit, used for performing flea individual identification on the processed image based on a target detection algorithm to obtain a plurality of flea individual images; The feature data extraction unit is used to extract feature data from the plurality of individual flea images based on the flea activity characteristics and mathematical statistics to obtain the flea activity feature data.
8. The flea behavior analysis device according to claim 5, characterized in that: The model training module is specifically used to train the initial convolutional neural network based on the flea activity feature data to obtain the behavior classification model.
9. A behavior analysis device, characterized in that: include: Memory for storing computer programs; A processor, configured to implement the steps of the flea behavior analysis method as described in any one of claims 1 to 4 when executing the computer program.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the flea behavior analysis method as described in any one of claims 1 to 4.
