A multi-source array animal intelligent monitoring and driving method and system based on target identification

Abstract

The application discloses a kind of multi-source array animal intelligent monitoring drive method and system based on target identification, it is related to animal prevention and control technical field, the method includes: based on the acquisition data of multi-source sensor array, extract the distribution behavior parameter of animal individual, obtain individual behavior characteristic data set, and according to the number of back and forth movement of animal individual in monitoring boundary area, single stay duration, the ratio of entry depth and exit frequency, generate animal exploratory behavior determination result;According to animal exploratory behavior determination result and historical drive event record, calculate the adaptability parameter of group to sound and light drive stimulus, and set adaptability critical threshold determination standard, generate animal group drive adaptability evaluation result;Generation includes the drive control signal of starting instruction and adjustment parameter.The application has the advantages of animal exploratory behavior identification and drive adaptability evaluation, solves the problem that prior art long-term prevention and control effect is not good.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of animal prevention and control, in particular to a multi-source array animal intelligent monitoring and driving method and system based on target recognition. BACKGROUND

[0002] With the strengthening of ecological environmental protection and the restorative growth of wild animal population, the loss caused by animals invading human activity areas is becoming increasingly serious, and intelligent animal prevention and control technology is urgently needed. Taking wild boars as an example, their population can expand rapidly and frequently invade agricultural planting areas, causing huge economic losses to crops. Wild boars have strong intelligence and learning ability, can quickly adapt to environmental changes and form complex group behavior patterns, and traditional physical barriers and manual driving methods have limited effect. With the development of artificial intelligence technology and multi-sensor fusion technology, automated animal monitoring and driving technology based on computer vision and intelligent algorithms has gradually become an important development direction in this field, providing a new technical path for solving animal prevention and control.

[0003] Existing animal monitoring and driving technology mainly uses a single sensor node for target detection, collects image data through a camera, identifies animal targets using a deep learning model, and triggers a pre-set driving program after detecting an intrusion. These technologies usually use convolutional neural networks for target classification and combine motion detection algorithms to determine the activity state of animals, and start sound and light driving devices to achieve driving away function when the trigger condition is met. Although this direct trigger method responds quickly, it lacks deep analysis of animal behavior and often causes false triggering and resource waste.

[0004] However, the existing animal monitoring and driving technology has obvious deficiencies. First, it lacks the ability to identify the intelligent behavior patterns of animal groups. Some animal groups often send individuals to conduct reconnaissance, showing complex counter-surveillance behavior, and existing technology cannot identify this behavior pattern, resulting in inaccurate judgment of group size and behavior intention, and affecting the formulation and execution effect of driving strategy. Second, it does not take into account the adaptability of animals to driving measures. After experiencing the same pattern of driving multiple times, animal groups will gradually develop adaptability or even completely ignore the driving measures, and existing technology lacks an evaluation mechanism for this adaptability, making it impossible to determine whether the effectiveness of the current driving strategy is decreasing. This adaptive learning is a natural survival instinct of animals, and existing technology ignores this key factor, resulting in poor long-term protection effect. These two problems cause the existing technology to gradually weaken in long-term application, and when faced with evasive behavior of animals with learning adaptability (such as wild boars), the driving effect decreases and the false judgment rate increases, making it difficult to meet the actual application requirements.

[0005] The prior art has the problems of low accuracy and low efficiency. SUMMARY

[0006] In view of the problems in the prior art, the present application provides a multi-source array animal intelligent monitoring and driving method based on target recognition, which has the advantages of animal exploratory behavior recognition and driving adaptability evaluation, thereby solving the problems of inability to predict animal invasion intention and gradual decrease of driving effect in the prior art.

[0007] To this end, the present application adopts the following specific technical solutions:

[0008] According to one aspect of the present application, a multi-source array animal intelligent monitoring and driving method based on target recognition is provided, which comprises:

[0009] S1, based on the collected data of the multi-source sensor array, extracting the distribution behavior parameters of animal individuals to obtain individual behavior feature data sets, and generating animal exploratory behavior judgment results according to the number of back-and-forth movements, single stay duration, entering depth and exit frequency of animal individuals in the monitoring boundary area;

[0010] S2, according to the animal exploratory behavior judgment results and historical driving event records, using a response threshold reinforcement algorithm to calculate the adaptability parameters of the animal group to the sound and light driving stimulus, and setting adaptability critical threshold judgment criteria to generate animal group driving adaptability evaluation results;

[0011] S3, based on the animal exploratory behavior judgment results and the animal group driving adaptability evaluation results, generating a driving control signal containing a start instruction and adjustment parameters.

[0012] Further, the collected data includes visual, acoustic and thermal imaging data; the distribution behavior parameters include position coordinate sequence, movement speed change rate and stay time distribution; based on the collected data of the multi-source sensor array, the distribution behavior parameters of animal individuals are extracted to obtain individual behavior feature data sets, which include: obtaining the pixel coordinates of animal individuals in the image through visual data, converting the pixel coordinates into visual position coordinates according to a preset camera calibration matrix, and recording the spatial coordinate changes in time sequence to form a position coordinate sequence; identifying the target animal sound based on acoustic data, calculating the time difference of the target animal sound reaching each acoustic sensor to determine the sound source position, associating and matching the sound source position with the position coordinate sequence, and solving the movement speed change rate; marking the animal individual thermal target based on thermal imaging data, counting the centroid coordinate duration of the animal individual thermal target to determine the stay event, calculating the stay time distribution of the animal individuals in the monitoring area, and combining the position coordinate sequence and the movement speed change rate to establish the individual behavior feature data set.

[0013] Further, the animal exploratory behavior judgment result is generated according to the number of back-and-forth movements of the animal individual in the monitoring boundary region, the single stay duration, the entering depth and the exit frequency ratio, including: setting the monitoring boundary line coordinates, counting the entering and exiting events of the animal individual across the monitoring boundary line in the position coordinate sequence, and accumulating the number of back-and-forth movements; determining the stay events of the animal individual in the monitoring region based on the stay time distribution, extracting the start time and end time of each stay event, and calculating the time difference to obtain the single stay duration; calculating the farthest distance of the animal individual from the monitoring boundary line after entering the monitoring region as the entering depth, combining the movement speed change rate to count the exit frequency in a preset time period, and calculating the entering depth and exit frequency ratio; when the number of back-and-forth movements exceeds a first preset threshold, the single stay duration exceeds a second preset threshold, and the entering depth and exit frequency ratio exceeds a third preset threshold, the animal exploratory behavior is judged and output.

[0014] Further, the adaptability parameters of the group to the sound-light driving stimulus include an initial response threshold, a current response threshold and a threshold change rate; the adaptability parameters of the group to the sound-light driving stimulus are calculated by using a response threshold reinforcement algorithm according to the animal exploratory behavior judgment result and the historical driving event record, including: establishing a historical driving event database to record the time, position, driving stimulus type, stimulus intensity and response behavior of the animal group of each driving event; determining the initial response threshold according to the stimulus intensity when the animal group starts to escape in the first driving event; constructing a probability model based on the response threshold, analyzing the adaptability of the animal group to the driving stimulus according to the animal exploratory behavior judgment result and the historical driving event database; analyzing the response change trend of the animal group to the same type of stimulus in the historical driving event, calculating the minimum stimulus intensity causing the escape behavior of the group in each driving event to obtain the current response threshold; calculating the threshold change multiple of the current response threshold and the initial response threshold to obtain the threshold change rate, and calculating the growth rate of the threshold change multiple in unit time to obtain the threshold change rate; multiplying the threshold change multiple by a preset reference coefficient, adding the product of the threshold change rate and a preset weight, to obtain the adaptability parameters of the group to the sound-light driving stimulus.

[0015] According to another aspect of the present application, a multi-source array animal intelligent monitoring and driving system based on target recognition is also provided, which includes:

[0016] The individual exploratory module is used for extracting the distribution behavior parameters of the animal individual based on the collected data of the multi-source sensor array, obtaining the individual behavior feature data set, and generating the animal exploratory behavior judgment result according to the number of back-and-forth movements of the animal individual in the monitoring boundary region, the single stay duration, the entering depth and the exit frequency ratio.

[0017] A group adaptation module is configured to calculate an adaptation parameter of the group to the sound-light driving stimulus by using a response threshold reinforcement algorithm according to the animal exploratory behavior judgment result and the historical driving event record, and set an adaptive critical threshold judgment criterion to generate an animal group driving adaptation evaluation result.

[0018] An adjustment control module is configured to generate a driving control signal containing a start instruction and an adjustment parameter based on the animal exploratory behavior judgment result and the animal group driving adaptation evaluation result.

[0019] The present application has the following advantages:

[0020] (1) The present application successfully solves the technical problem that the exploratory behavior of an animal individual is difficult to identify by using a multi-source sensor array to work cooperatively; the system can capture and analyze the subtle behavior characteristics of the animal in the boundary area, such as back-and-forth movement and staying observation, so as to identify the exploratory behavior of the leading individual before the group invades on a large scale, change the defense measures from passive response to active prevention, and greatly improve the timeliness and accuracy of the prevention and control; compared with the existing single sensor triggering mechanism, the present application can timely find the anti-reconnaissance behavior mode of the leading individual before the group invades on a large scale, so that the management personnel can deploy targeted defense measures in advance, and significantly improve the initiative and effectiveness of animal invasion prevention and control.

[0021] (2) The present application innovatively establishes an adaptation evaluation system of the animal group to the driving measures, can scientifically judge whether the current driving strategy is failing by recording and analyzing the response change trend of the animal in the historical driving event; when detecting the decreasing driving effect, the type, intensity and timing mode of the sound-light stimulus are automatically adjusted, and the adaptability problem of the animal to the single driving mode is effectively overcome; practical application shows that, compared with the traditional fixed mode driving, the present application significantly prolongs the duration of driving effectiveness, and provides a more reliable long-term protection solution for agricultural production and ecological protection. BRIEF DESCRIPTION OF DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments. Obviously, the drawings in the following description only constitute some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor based on these drawings.

[0023] Figure 1 is a flowchart of a multi-source array animal intelligent monitoring and driving method based on target identification according to an embodiment of the present application;

[0024] Figure 2It is a specific implementation diagram for generating animal exploratory behavior judgment result in a target recognition-based multi-source array animal intelligent monitoring and driving method according to an embodiment of the present application.

[0025] Figure 3 It is a principle block diagram of a target recognition-based multi-source array animal intelligent monitoring and driving system according to an embodiment of the present application. DETAILED DESCRIPTION

[0026] To further illustrate the embodiments, the present application provides drawings which are part of the disclosure of the present application, mainly used to illustrate the embodiments, and can explain the operating principle of the embodiments in conjunction with the related description of the specification. Those skilled in the art should understand other possible implementations and advantages of the present application by referring to these contents. The components in the drawings are not drawn to scale, and similar component symbols are generally used to represent similar components.

[0027] According to an embodiment of the present application, a target recognition-based multi-source array animal intelligent monitoring and driving method and system are provided.

[0028] The present application will be further described in conjunction with the drawings and specific embodiments. As shown in the drawings, according to an embodiment of the present application, a target recognition-based multi-source array animal intelligent monitoring and driving method is provided, which comprises: Figure 1

[0029] S1, based on the collected data of the multi-source sensor array, extracting the distribution behavior parameters of the animal individuals to obtain the individual behavior feature data set, and generating an animal exploratory behavior judgment result according to the number of back-and-forth movements of the animal individuals in the monitoring boundary area, the single stay duration, the entering depth and the exit frequency ratio.

[0030] S2, according to the animal exploratory behavior judgment result and the historical driving event record, using a response threshold reinforcement algorithm to calculate the adaptability parameters of the group to the sound and light driving stimulus, and setting the adaptability critical threshold judgment standard to generate an animal group driving adaptability evaluation result;

[0031] S3, based on the animal exploratory behavior judgment result and the animal group driving adaptability evaluation result, generating a driving control signal containing a start instruction and an adjustment parameter.

[0032] In one embodiment, the collected data includes visual, acoustic, and thermal imaging data; the distribution behavior parameters include position coordinate sequence, movement speed change rate, and stay time distribution;

[0033] As shown in Figure 2 the step S1 of collecting data based on the multi-source sensor array, extracting the distribution behavior parameters of the animal individuals to obtain the individual behavior feature data set comprises:​

[0034] acquire the pixel coordinates of the animal individual in the image through the visual data, convert the pixel coordinates into visual position coordinates according to a preset camera calibration matrix, and record the spatial coordinate changes in time sequence to form a position coordinate sequence;

[0035] identify the target animal sound based on the acoustic data, calculate the time difference of the target animal sound reaching each acoustic sensor to determine the sound source position, associate and match the sound source position with the position coordinate sequence, and solve the moving speed change rate;

[0036] mark the thermal target of the animal individual according to the thermal imaging data, count the centroid coordinate duration of the thermal target of the animal individual to determine the stay event, calculate the stay time distribution of the animal individual in the monitoring area, and combine the position coordinate sequence and the moving speed change rate to establish the individual behavior feature dataset.

[0037] In one embodiment, acquiring the pixel coordinates of the animal individual in the image through the visual data, converting the pixel coordinates into visual position coordinates according to a preset camera calibration matrix, and recording the spatial coordinate changes in time sequence to form a position coordinate sequence includes:

[0038] Based on the image data collected by different visual sensors (the preset multiple are explained in subsequent embodiments) in the monitoring area, the motion target area is extracted for each visual sensor image by performing inter-frame difference;

[0039] The extracted motion target area is matched and identified by applying an animal body feature template (explained in subsequent embodiments), the animal individual contour area is marked, and the contour barycenter pixel coordinates are extracted;

[0040] The pixel coordinates extracted in each visual sensor are converted into visual position coordinates in a unified three-dimensional coordinate system through the pre-calibrated camera intrinsic and extrinsic matrix;

[0041] The spatial coordinates obtained by different visual sensors at the same time point are fused with weights to eliminate perspective errors, and a timestamp-associated position coordinate sequence is formed.

[0042] In one embodiment, identifying the target animal sound based on the acoustic data, calculating the time difference of the target animal sound reaching each acoustic sensor to determine the sound source position, associating and matching the sound source position with the position coordinate sequence, and solving the moving speed change rate includes:

[0043] Based on the acoustic sensor array (the arrangement of multiple acoustic sensors to form an acoustic array is explained in subsequent embodiments), the sound signal generated by animal activity is collected and preprocessed to eliminate background noise;

[0044] extract time-frequency features of the sound signal, and identify the target animal sound according to a preset animal sound feature library;

[0045] calculate a time difference of arrival of the target animal sound at each acoustic sensor, combine a spatial distribution parameter of the acoustic sensor, and calculate spatial coordinates of the sound source through a sound source positioning algorithm (explained in subsequent embodiments);

[0046] correlate and match the spatial coordinates of the sound source with visual position coordinates at a corresponding time point, calculate displacement distances between adjacent sampling time points through a sequence of position coordinates in a time window, and divide the displacement distances by time intervals to obtain a change rate of moving speed of the animal individual in each time period.

[0047] In one embodiment, a thermal target of the animal individual is labeled according to thermal imaging data, a duration of a centroid coordinate of the thermal target of the animal individual is counted to determine a stay event, and a stay time distribution of the animal individual in the monitoring area is calculated, including:

[0048] based on the collected thermal imaging data of the monitoring area, setting an upper limit and a lower limit of a temperature threshold according to a body temperature feature of the target animal, performing binaryzation processing on the thermal imaging data, and extracting a thermal signal region meeting the temperature threshold interval;

[0049] performing connected domain analysis on the thermal signal region, removing noise regions smaller than a preset area threshold, and labeling the thermal signal region meeting the size condition as a thermal target of the animal individual;

[0050] calculating a centroid coordinate of the thermal target of the animal individual, and establishing a mapping relationship between the centroid coordinate and a sequence of position coordinates;

[0051] based on the mapping relationship, counting a duration of continuous existence of the thermal target of the animal individual in a sequence of continuous frames, and recording corresponding three-dimensional coordinates, when the centroid coordinate is within a preset spatial range and the duration exceeds a preset time threshold, determining as a stay event;

[0052] accumulating a total duration of stay events of each three-dimensional coordinate to form a stay time distribution thermogram of the animal individual in the monitoring area, and extracting the stay time distribution.

[0053] Specifically, the multi-source sensor array in the embodiment includes a plurality of visual sensors, acoustic sensors and thermal imaging sensors arranged around the monitoring area boundary, wherein the visual sensors adopt waterproof high-definition network cameras, which are installed on 3-meter-high poles along the monitoring boundary line at 5-meter intervals, with a field of view angle of 120 degrees and an overlapping area of 30% between adjacent cameras; the acoustic sensors adopt an omnidirectional microphone array, each group containing 6 microphones forming a hexagonal layout, with an adjacent microphone spacing of 2 meters, and a group is arranged every 30 meters on the boundary of the monitoring area; the thermal imaging sensors adopt non-cooled long-wave infrared thermal imagers, which are installed at key monitoring points to cover the blind area of the visual sensors. All sensors are connected to the local computing processing device through wired or wireless network, and a unified time synchronization mechanism is adopted to ensure the accurate alignment of data timestamps, realizing the collaborative collection and processing of multi-source data.

[0054] Specifically, the animal body feature template in the embodiment is an object animal morphological feature recognition model constructed by a deep learning method. For common invasive animals such as wild boars, 1000 sample images containing different walking postures and body sizes are collected, and a target recognition model with a detection accuracy of more than 95% is obtained by using a YOLOv5 algorithm framework; the sound source positioning algorithm adopts a hyperbolic intersection positioning method based on the time difference of arrival (TDOA) principle, combined with a Bayesian filtering algorithm to eliminate environmental noise interference; in thermal imaging data processing, according to the normal temperature range of wild boars (38-39.5°C), the upper limit of the temperature threshold is set to 40°C, and the lower limit is set to 37°C, to adapt to the temperature characteristics of wild boar body surface and consider the influence of environmental temperature; in the connected domain analysis, the area threshold is set to 200 pixels to filter out small heat source interference; for the stay event judgment, the preset spatial range is defined as a spherical region with a radius of 3 meters, and the preset time threshold is set to 15 seconds, that is, when the animal heat target stays within 3 meters for more than 15 seconds, it is judged as an effective stay event, thereby effectively filtering the short passing behavior and actual observation behavior of the animal.

[0055] Specifically, the acquisition of the position coordinate sequence is realized by real-time three-dimensional positioning of the visual sensor array. Each visual sensor collects images and extracts the pixel coordinates (x i ,y i ) of the animal contour barycenter, and through a preset camera intrinsic matrix [f x ,f y ,c x ,c y] and the extrinsic matrix [R, T] converts the pixel coordinates into three-dimensional position coordinates (X, Y, Z) in the world coordinate system. The stereo vision algorithm is used to estimate the depth between adjacent visual sensors to eliminate the depth ambiguity of monocular vision. The final position coordinates are obtained by weighted average fusion of multiple coordinates at the same time point, and the position coordinate sequence {(X(t), Y(t), Z(t)) | t=0, Δt, 2Δt,...} is sorted according to the timestamp t.

[0056] Specifically, the moving speed change rate is calculated by data fusion of acoustic positioning and visual positioning. When the acoustic sensor array detects the sound of the target animal, the system calculates the sound source coordinates using the hyperbolic intersection algorithm through the following steps: first, record the timestamp t i of the arrival of the sound signal at each microphone ij , select a reference microphone as the reference point, calculate the time difference Δt j of other microphones and the reference microphone i ; then, according to the sound speed v and the position coordinates (x i , y i , z i ) of each microphone, establish the equation set |R-R i |-|R-R j |=v×Δt ij , where R is the position vector of the sound source, R i and R j are the position vectors of the i-th and j-th microphones respectively; then, the sound source coordinates (X s , Y s , Z s ) are obtained by solving the nonlinear equation set by the least square method; finally, the sound source coordinates are matched and verified with the visual position coordinates corresponding to the time, and the displacement change is calculated within a continuous time window, thereby obtaining the moving speed change rate of the animal.

[0057] Specifically, the residence time distribution is obtained by spatiotemporal statistical analysis of thermal imaging data. The thermal imaging sensor collects temperature distribution images of the monitoring area, sets the temperature threshold range 37℃~40℃ to extract the animal heat target area, and calculates the centroid coordinates (x c , y c ) of the heat target area in consecutive frames. When the centroid coordinates fluctuate within a radius R=3 meters in N consecutive frames (N≥150, i.e. 15 seconds), it is recorded as a residence event. The residence duration calculation formula is T stay =N×0.1 seconds. The monitoring area is divided into 10m×10m grid cells, and the cumulative residence time T total in each grid cell is counted. The residence time distribution thermogram is generated by an interpolation algorithm, and the distribution feature parameters including the maximum residence time Tmax , average stay duration T avg and stay event frequency F stay , combined with spatial trajectory information in the sequence of position coordinates and motion state parameters in the moving speed change rate, to construct an individual behavior feature dataset containing spatio-temporal behavior features {sequence of position coordinates, moving speed change rate, stay time distribution} to support subsequent exploratory behavior recognition analysis.

[0058] In one embodiment, as shown in Figure 2 , the animal exploratory behavior determination result generated in step S1 according to the number of back-and-forth movements of the animal individual in the monitoring boundary area, the single stay duration, the ratio of the entry depth to the exit frequency includes:

[0059] Set the monitoring boundary line coordinates, count the entry and exit events of the animal individual across the monitoring boundary line in the sequence of position coordinates, and accumulate the number of back-and-forth movements;

[0060] Determine the stay event of the animal individual in the monitoring area based on the stay time distribution, extract the start time and end time of each stay event, and calculate the time difference to obtain the single stay duration;

[0061] Calculate the ratio of the entry depth to the exit frequency using the sequence of position coordinates to calculate the farthest distance of the animal individual from the monitoring boundary line after entering the monitoring area as the entry depth, and combining the moving speed change rate to count the exit frequency in a preset time period;

[0062] When the number of back-and-forth movements exceeds the first preset threshold, the single stay duration exceeds the second preset threshold, and the ratio of the entry depth to the exit frequency exceeds the third preset threshold, the animal exploratory behavior is determined and output.

[0063] In one embodiment, setting the monitoring boundary line coordinates, counting the entry and exit events of the animal individual across the monitoring boundary line in the sequence of position coordinates, and accumulating the number of back-and-forth movements includes:

[0064] According to the protection requirements, set the spatial coordinate range of the monitoring boundary line in the monitoring area, and represent the monitoring boundary line as a set of consecutive line segments;

[0065] Determine the relative position relationship of each coordinate point in the sequence of position coordinates with the monitoring boundary line, and when two consecutive coordinate points are located on both sides of the monitoring boundary line, mark it as a boundary line crossing event;

[0066] Classify the boundary line crossing event into entry event and exit event according to the crossing direction, and record the timestamp of each event;

[0067] Set a fixed time window length, calculate the absolute value of the difference between the number of entry events and the number of exit events within the window, and when the absolute value of the difference is less than a preset threshold and the total number of entry and exit events is greater than zero, it is considered a valid back-and-forth movement, and the number of back-and-forth movements within different time windows is accumulated.

[0068] Specifically, in this embodiment, the monitoring boundary line is a closed area boundary composed of multiple broken lines, defined by the GPS coordinate point sequence {(X1,Y1),(X2,Y2),...,(X... n ,Y n The diagram shows that each pair of adjacent points forms a boundary line segment. The ray method is used to determine whether the animal's position coordinates are inside the boundary. When performing boundary crossing detection on the position coordinate sequence, the vector cross product method is used to calculate the distance between two consecutive coordinate points P1(X1,Y1,Z1) and P2(X2,Y2,Z2) and the endpoint A(X1,Y1,Z2) of the boundary line segment. a ,Y a ) and B(X b ,Y b The sign of the cross product of the two vectors formed by (P1-A)×(BA) and (P2-A)×(BA) is changed to determine whether a crossing has occurred. When the product of (P1-A)×(BA) and (P2-A)×(BA) is less than zero, it is determined as a crossing event. A fixed time window length of 5 minutes is set. When the absolute value of the difference between the entry event and the exit event within the window is less than 2 and the sum is greater than 4, it is determined as frequent back-and-forth movement behavior. The number of back-and-forth movements is accumulated within 24 hours. When the number exceeds the first preset threshold of 15 times, the first condition for determining the trial behavior is triggered.

[0069] Specifically, in this embodiment, the calculation of a single stay duration is based on stay time distribution data. The system records the start time t of each stay event identified within the monitoring area. start and end time t end Duration of a single stay T stay =t end -t start The unit is seconds; when the spatial location of a dwelling event is no more than 20 meters from the monitoring boundary line, the system marks the dwelling event as a boundary dwelling event; the system calculates the entry depth parameter D. in The vertical distance between the farthest point reached by an individual animal during a complete invasion process (from entry to final exit) and the monitoring boundary line is calculated using the shortest distance between the spatial extreme point in the location coordinate sequence and the boundary line; the exit frequency F out Defined as the number of times an animal exits the monitoring area within a 1-hour observation period, the system calculates the ratio R=D (entry depth to exit frequency). in / F outAs a key indicator of exploratory behavior; set the second preset threshold value to 120 seconds, when the single stay duration exceeds this threshold, trigger the second condition of exploratory behavior judgment; set the third preset threshold value to 5.0, when the entry depth and exit frequency ratio exceeds this threshold, trigger the third condition of exploratory behavior judgment; when the three conditions are met at the same time, the system outputs the animal exploratory behavior judgment result, and triggers the warning signal.

[0070] In one embodiment, the adaptability parameters of the group to the sound-light driving stimulus include an initial response threshold, a current response threshold, and a threshold change rate.

[0071] In step S2, according to the animal exploratory behavior judgment result and the historical driving event record, the adaptability parameters of the group to the sound-light driving stimulus are calculated using a response threshold reinforcement algorithm, including:

[0072] A historical driving event database is established to record the time, location, driving stimulus type, stimulus intensity, and animal group response behavior of each driving event;

[0073] According to the stimulus intensity when the animal group starts to escape behavior in the first driving event, the initial response threshold is determined;

[0074] A probability model based on the response threshold is constructed to analyze the adaptability of the animal group to the driving stimulus according to the animal exploratory behavior judgment result and the historical driving event database;

[0075] The response change trend of the animal group to the same type of stimulus in the historical driving event is analyzed, the minimum stimulus intensity causing the group to escape behavior in each driving event is calculated, and the current response threshold is obtained;

[0076] The ratio of the current response threshold to the initial response threshold is calculated to obtain the threshold change multiple, and the growth rate of the threshold change multiple per unit time is calculated to obtain the threshold change rate;

[0077] The threshold change multiple is multiplied by a preset reference coefficient, and the product of the threshold change rate and a preset weight is added to obtain the adaptability parameters of the group to the sound-light driving stimulus.

[0078] It should be noted that the response threshold reinforcement model algorithm, namely RTR algorithm (RTR, Response Threshold Reinforcement), is an adaptive learning algorithm based on the principle of biological population behavior, and the core idea comes from the task allocation mechanism of social insects. The response threshold change law of individual to environmental stimulus is applied to the animal driving system. The algorithm dynamically tracks and quantifies the adaptation process of the animal group to the repeated driving stimulus by establishing a mathematical mapping relationship between the stimulus intensity and the group behavior response. The algorithm first determines the baseline response threshold according to the initial driving event, then analyzes the stimulus-response pairs in the historical driving data to construct a probability distribution model of the evolution of the response threshold with time, describes the adaptability change of the group using Markov process, and optimizes the model parameters using Bayesian updating method. The algorithm can not only accurately evaluate the adaptability of the current group to the driving stimulus, but also predict the attenuation trend of the future driving effect, providing a scientific basis for the dynamic adjustment of the driving strategy, and effectively solving the adaptability problem faced by the traditional fixed parameter driving method.

[0079] Specifically, a probability model based on response threshold is constructed, and the adaptability of the animal group to the driving stimulus is determined according to the animal exploratory behavior judgment result and the historical driving event database, including:

[0080] Assign an initial response threshold θ to each individual in the animal group i , establish an individual response probability function P(θ i ,s), where s represents the driving stimulus intensity, and when s≥θ i , the individual i responds to the stimulus;

[0081] According to the time, location and driving stimulus type records in the historical driving event database, a stimulus-response pairing matrix is constructed, and the response behavior pattern of the animal group under different stimulus intensities is counted;

[0082] Establish a dynamic updating mechanism of the response threshold, when the individual executes the escape behavior, according to the feedback reinforcement principle, reduce the response threshold of the individual, so that it is more sensitive to the same type of stimulus in the future;

[0083] The response probability distribution of the group is calculated by the Monte Carlo simulation method, and the animal exploratory behavior judgment result is taken as the input parameter to adjust the proportion of active individuals in the group;

[0084] The maximum likelihood estimation method is used to fit the response threshold probability density function, and the sensitivity difference of the group to different driving stimulus types is analyzed;

[0085] Based on Bayesian inference, the individual response threshold parameters are updated, and the prediction accuracy of the probability model is corrected by using the newly observed animal group response behavior data;

[0086] The time evolution trajectory of the group average response threshold is calculated to quantify the change of the overall adaptability of the animal group to the driving stimulus.

[0087] In one embodiment, the adaptive critical threshold determination criterion is set in step S2, and the generation of the animal group driving adaptability evaluation result comprises:

[0088] The adaptive critical threshold determination criterion includes a threshold change multiple upper limit and a threshold change rate upper limit;

[0089] The threshold change multiple is compared with the threshold change multiple upper limit, and the threshold change rate is compared with the threshold change rate upper limit;

[0090] When the threshold change multiple exceeds the threshold change multiple upper limit, or the threshold change rate exceeds the threshold change rate upper limit, it is determined that the animal group has produced adaptability to the current driving mode, and the adaptability state is marked as adapted, otherwise it is marked as not adapted;

[0091] Based on the marked adaptability state, the percentage of the group adaptability degree is calculated according to the threshold change multiple and the threshold change rate, and the animal group driving adaptability evaluation result is obtained.

[0092] Specifically, the historical driving event database in the embodiment adopts a relational data structure design, including fields such as event ID, timestamp, geographic position coordinates, driving stimulus type (sound / light / odor), stimulus intensity (decibel value / light flux / concentration), and response behavior (escape / stasis / ignore); In the first driving, a gradient increasing stimulus intensity strategy is adopted, starting from the lowest stimulus intensity, increasing by one level every 10 seconds, until the stimulus intensity value when more than 70% of the individuals in the animal group begin to escape behavior is recorded as the initial response threshold θ0; For sound stimulus, the initial response threshold is set in the range of 85-95 decibels, and for light stimulus, the initial response threshold is set to 2000-3000 lumens; By analyzing the minimum stimulus intensity change trend that causes the group to escape behavior in the historical driving event, when the minimum stimulus intensity required for the nth driving event is recorded as θn, the ratio κ=θn / θ0 of the current response threshold to the initial response threshold is calculated to obtain the threshold change multiple, and the growth rate μ=dκ / dt of the threshold change multiple per unit time is calculated as the threshold change rate; The system multiplies the threshold change multiple κ by a preset reference coefficient α (default value 1.5), and adds the product of the threshold change rate μ and a preset weight β (default value 2.0), that is, S=α×κ+β×μ, to obtain the adaptability parameter of the group to the sound and light driving stimulus. n n

[0093] Specifically, the adaptive critical threshold determination criterion in the embodiment sets a clear numerical boundary, including a threshold change multiple upper limit κ max ​​is set to 2.5, indicating that when the response threshold of the animal population to a specific stimulus reaches 2.5 times the initial value, it is considered that significant adaptation has occurred; the upper limit of the threshold rate μ max is set to 0.25 / day, indicating that when the daily growth rate of the response threshold of the animal population to a specific stimulus exceeds 25%, it is determined to be in a state of rapid adaptation; when the system calculates the real-time adaptability evaluation, the adaptability degree P=(κ / κ max )×70%+(μ / μ max )×30% is used to divide the adaptability degree into three levels: low adaptation (P<50%), moderate adaptation (50%≤P<80%), and high adaptation (P≥80%); when P≥80%, the system automatically generates a suggestion for adjusting the driving strategy, including changing the type of driving stimulus, increasing the stimulus intensity, or adjusting the stimulus frequency pattern.

[0094] In order to facilitate the understanding of the above technical solutions of the present application, the following will be described in detail as follows taking a wild boar invasion prevention and control system of a certain national nature reserve as an example:

[0095] At the intersection of the protection zone and the surrounding farmland, due to the frequent invasion of wild boars into farmland causing crop losses, the local agricultural department decides to implement the intelligent monitoring and driving technology of the present application. First, the staff installs a waterproof high-definition network camera every 5 meters along the intersection line of the protection zone and the farmland, and arranges a set of omnidirectional microphone array (6 microphones in a hexagonal distribution) every 30 meters, and installs a non-cooled long-wave infrared thermal imager at the key monitoring point, and sets the temperature threshold to identify the wild boar heat target.

[0096] In the first month of system operation, the local computing and processing equipment processes these data and extracts the distribution behavior parameters of the wild boar population. Through the analysis of the sequence of position coordinates, it is found that the wild boar population mainly moves at night from 22:00 to 4:00 in the morning, and frequently moves back and forth at the intersection of the southeast corner of the protection zone. The system counts the events of wild boars crossing the monitoring boundary line, and the record shows that the number of back-and-forth movements within 24 hours reaches 18 times. At the same time, through the analysis of the thermal imaging data, the system detects that the wild boar stays in the grass 15 meters away from the boundary for a duration of 180 seconds, and combined with the position data, it calculates that the maximum penetration depth of the wild boar is 25 meters, and the exit frequency within 1 hour is 3 times, and the ratio of penetration depth to exit frequency is 8.33, which exceeds the preset threshold value of 5.0. Based on these three indicators, the system generates a judgment result of the wild boar's exploratory behavior, confirming that the wild boar population is exploring the farmland purposefully.

[0097] Subsequently, the system initiates the driving control process. At the first driving, the system starts from the lowest stimulation intensity, uses 85 decibels of wolf calls as the sound stimulation, and observes that more than 70% of the wild boar individuals start to escape, and this intensity is recorded as the initial response threshold. After two weeks of continuous driving, the system finds that the minimum sound stimulation intensity that causes the wild boar group to escape has risen to 105 decibels, and the adaptive assessment P = 36.76% is calculated, determining that the current wild boar group is in a "low adaptation" state.

[0098] Based on the above trial behavior judgment result and the adaptive assessment result, the system generates a corresponding driving control signal. The control signal mainly includes two parts: start instruction and adjustment parameter. The start instruction determines the driving device number to be activated (E15-E20 six devices at the southeast corner of the protection zone), the device activation sequence (starting from the closest device E17 of the wild boar group, extending outward to E15, E16, E18, E19, E20), and the scheduled execution time (22:30, before the peak period of wild boar activity). The adjustment parameter includes sound stimulation parameters (selecting wolf calls as the sound type, sound pressure level set to 95 decibels, higher than the initial response threshold but lower than the current response threshold) and light stimulation parameters (white light, brightness 2000 lumens, flicker frequency 3Hz). Since the adaptive assessment shows that the wild boar group is in a "low adaptation" state, the system selects a combined stimulation mode instead of a single sound stimulation to avoid rapid adaptation of the wild boar group to a single stimulation type. The driving control signal is sent to the controllers of the driving devices on site in the form of an encrypted data packet through the communication module of the system, and the controllers execute the driving operation according to the specified parameters after receiving the signal. This adaptive control strategy based on animal behavior characteristic analysis and adaptive assessment enables the system to dynamically adjust the driving method according to the behavior changes of the wild boar group, effectively avoiding the adaptability problems caused by traditional fixed mode driving, and significantly improving the effectiveness and durability of animal intrusion prevention and control.

[0099] After three months of system operation, the wild boar intrusion events in the southeast corner of the protection zone were reduced by 87%, and the crop loss was reduced by 92%. This successful case proves that the present application realizes intelligent, efficient, and durable prevention and control of wild animal intrusion by combining animal behavior characteristic analysis, adaptive assessment, and adaptive control technology.

[0100] As Figure 3 shown, according to another embodiment of the present application, a multi-source array animal intelligent monitoring and driving system based on target recognition is also provided, which comprises:

[0101] The individual exploration module 1 is used for extracting the distribution behavior parameters of the animal individuals based on the collected data of the multi-source sensor array, obtaining the individual behavior characteristic data set, and generating the animal exploration behavior judgment result according to the number of back-and-forth movements of the animal individuals in the monitoring boundary region, the single stay duration, the ratio of the entering depth to the exiting frequency.

[0102] The group adaptation module 2 is used for calculating the adaptability parameters of the group to the sound-light driving stimulation by using a response threshold reinforcement algorithm according to the animal exploration behavior judgment result and the historical driving event record, setting the adaptability critical threshold judgment standard, and generating the animal group driving adaptability evaluation result.

[0103] The adjustment control module 3 is used for generating the driving control signal containing the start instruction and the adjustment parameter based on the animal exploration behavior judgment result and the animal group driving adaptability evaluation result.

[0104] The above merely describes the preferred embodiment of the present application and is not used to limit the present application, and any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A multi-source array-based intelligent animal monitoring and deterrence method based on target recognition, characterized in that, include: S1. Based on the data collected by the multi-source sensor array, extract the distribution behavior parameters of individual animals to obtain an individual behavior feature dataset, and generate the animal exploration behavior judgment result according to the number of times the individual animal moves back and forth in the monitoring boundary area, the duration of a single stay, and the ratio of entry depth to exit frequency. Based on the number of times an animal moves back and forth within the monitoring boundary area, the duration of each stay, and the ratio of entry depth to exit frequency, the animal's exploratory behavior is determined. Specifically, this includes: setting the coordinates of the monitoring boundary line; statistically analyzing the entry and exit events of an animal crossing the boundary line in the position coordinate sequence; accumulating the number of back-and-forth movements; determining the stay events of an animal within the monitoring area based on the stay time distribution; extracting the start and end times of each stay event; calculating the time difference to obtain the duration of each stay; using the position coordinate sequence to calculate the farthest distance from the monitoring boundary line after the animal enters the monitoring area as the entry depth; combining the rate of change of movement speed to calculate the exit frequency within a preset time period; and calculating the ratio of entry depth to exit frequency. When the number of back-and-forth movements exceeds a first preset threshold, the duration of each stay exceeds a second preset threshold, and the ratio of entry depth to exit frequency exceeds a third preset threshold, the behavior is determined as exploratory behavior and output. S2. Based on the results of animal trial behavior assessment and historical driving event records, the adaptive parameters of the group to the sound and light driving stimuli are calculated using the response threshold enhancement algorithm, and the adaptive critical threshold judgment criteria are set to generate the animal group driving adaptation assessment results; among which, the adaptive parameters of the group to the sound and light driving stimuli include the initial response threshold, the current response threshold, and the threshold change rate. Based on the animal exploration behavior assessment results and historical drive-away event records, the adaptive parameters of a group to audio-visual drive-away stimuli are calculated using a response threshold enhancement algorithm. Specifically, this includes: establishing a historical drive-away event database, recording the time, location, type of drive-away stimulus, stimulus intensity, and animal group response behavior for each drive-away event; determining the initial response threshold based on the stimulus intensity at which the animal group begins to flee in the first drive-away event; constructing a probabilistic model based on the response threshold, analyzing the animal group's adaptation to drive-away stimuli based on the animal exploration behavior assessment results and the historical drive-away event database; analyzing the trend of animal group response to the same type of stimulus in historical drive-away events, calculating the minimum stimulus intensity that causes the group to flee in each drive-away event, and obtaining the current response threshold; calculating the ratio of the current response threshold to the initial response threshold to obtain the threshold change factor, and calculating the growth rate of the threshold change factor per unit time to obtain the threshold change rate; multiplying the threshold change factor by a preset reference coefficient, and adding the product of the threshold change rate and a preset weight, to obtain the adaptive parameters of the group to audio-visual drive-away stimuli. The process of setting adaptive threshold criteria and generating animal group drive adaptation assessment results includes: setting adaptive threshold criteria, including an upper limit for the threshold change multiple and an upper limit for the threshold change rate; comparing the threshold change multiple with the upper limit for the threshold change multiple and comparing the threshold change rate with the upper limit for the threshold change rate; when the threshold change multiple exceeds the upper limit for the threshold change multiple or the threshold change rate exceeds the upper limit for the threshold change rate, the animal group is determined to have adapted to the current drive method, and the adaptive state is marked as adapted; otherwise, it is marked as unadapted; based on the marked adaptive state, the percentage of the group's degree of adaptation is calculated according to the threshold change multiple and the threshold change rate to obtain the animal group drive adaptation assessment results. S3. Based on the results of animal trial behavior assessment and animal group drive-off adaptability assessment, generate a drive-off control signal containing activation instructions and adjustment parameters.

2. The multi-source array animal intelligent monitoring and repelling method based on target recognition according to claim 1, characterized in that, The collected data includes visual data, acoustic data, and thermal imaging data; the distribution behavior parameters include position coordinate sequences, rate of change of movement speed, and residence time distribution. The data collected based on the multi-source sensor array is used to extract the distribution and behavioral parameters of individual animals, resulting in an individual behavioral feature dataset including: The pixel coordinates of individual animals in the image are obtained through visual data. The pixel coordinates are converted into visual position coordinates according to the preset camera calibration matrix, and the spatial coordinate changes are recorded in time series to form a position coordinate sequence. Based on acoustic data, the sound of the target animal is identified, and the time difference of the sound reaching each acoustic sensor is calculated to determine the location of the sound source. The sound source location is then correlated and matched with the location coordinate sequence to solve for the rate of change of movement speed. Animal thermal targets are marked based on thermal imaging data. The duration of the centroid coordinates of the animal thermal targets is counted to determine dwell events. The dwell time distribution of animal individuals in the monitoring area is calculated. Combined with the position coordinate sequence and the rate of change of movement speed, an individual behavior feature dataset is established.

3. The multi-source array animal intelligent monitoring and repelling method based on target recognition according to claim 2, characterized in that, The process of acquiring the pixel coordinates of an individual animal in an image through visual data, converting the pixel coordinates into visual position coordinates according to a preset camera calibration matrix, and recording the spatial coordinate changes in a time series to form a position coordinate sequence includes: Based on image data collected by different visual sensors within the monitoring area, inter-frame difference is performed on each visual sensor image to extract the moving target region; The extracted moving target region is matched and identified using animal body feature templates, the individual animal contour region is marked, and the pixel coordinates of the contour centroid are extracted. The pixel coordinates extracted from each visual sensor are converted into visual position coordinates in a unified three-dimensional coordinate system through a pre-calibrated camera intrinsic and extrinsic parameter matrix. Spatial coordinates obtained from different visual sensors at the same time point are weighted and fused to eliminate viewpoint errors and form a time-stamped sequence of location coordinates.

4. The multi-source array animal intelligent monitoring and repelling method based on target recognition according to claim 2, characterized in that, The process of identifying target animal sounds based on acoustic data, calculating the time difference between the arrival of the animal's sounds at each acoustic sensor to determine the sound source location, associating and matching the sound source location with the location coordinate sequence, and solving for the rate of change of movement speed includes: Based on an acoustic sensor array, sound signals generated by animal activities are collected and preprocessed to eliminate background noise; Extract the time-frequency features of the sound signal and identify the target animal's sound based on a pre-set animal sound feature database; The time difference between the arrival of the target animal's sound at each acoustic sensor is calculated, and the spatial coordinates of the sound source are calculated using a sound source localization algorithm, taking into account the spatial distribution parameters of the acoustic sensors. The spatial coordinates of the sound source are associated and matched with the visual position coordinates at the corresponding time points. The displacement distance between adjacent sampling time points is calculated by the position coordinate sequence within the time window and divided by the time interval to obtain the rate of change of the animal's movement speed in each time period.

5. The multi-source array animal intelligent monitoring and repelling method based on target recognition according to claim 2, characterized in that, The process of marking individual animal thermal targets based on thermal imaging data, statistically analyzing the duration of the centroid coordinates of individual animal thermal targets to determine dwell events, and calculating the dwell time distribution of individual animals within the monitoring area includes: Based on the collected thermal imaging data of the monitoring area, upper and lower limits of temperature thresholds are set according to the body temperature characteristics of the target animal. The thermal imaging data is binarized and thermal signal areas that meet the temperature threshold range are extracted. Connectivity analysis is performed on the thermal signal region to remove noise regions smaller than a preset area threshold, and thermal signal regions that meet the size condition are marked as thermal targets of individual animals. Calculate the centroid coordinates of the thermal target of an individual animal and establish a mapping relationship between the centroid coordinates and the position coordinate sequence; Based on the mapping relationship, the duration of the thermal target of an individual animal in a continuous frame sequence is statistically analyzed, and the corresponding three-dimensional coordinates are recorded. When the centroid coordinates are within a preset spatial range and the duration exceeds a preset time threshold, it is determined as a dwell event. The total duration of dwell time for each three-dimensional coordinate is accumulated to form a heat map of the dwell time distribution of individual animals within the monitoring area, and the dwell time distribution is extracted.

6. The multi-source array animal intelligent monitoring and repelling method based on target recognition according to claim 1, characterized in that, The process of setting the coordinates of the monitoring boundary line, counting the entry and exit events of individual animals crossing the monitoring boundary line in the position coordinate sequence, and accumulating the number of back-and-forth movements includes: Based on protection requirements, the spatial coordinate range of the monitoring boundary line within the monitoring area is set, and the monitoring boundary line is represented as a set of continuous line segments; For each coordinate point in the position coordinate sequence, determine its relative positional relationship with the monitoring boundary line. When two consecutive coordinate points are located on opposite sides of the monitoring boundary line, it is marked as a boundary line crossing event. Based on the direction of crossing, boundary line crossing events are classified into entry events and exit events, and the timestamp of each event is recorded. Set a fixed time window length, calculate the absolute value of the difference between the number of entry events and the number of exit events within the window, and when the absolute value of the difference is less than a preset threshold and the total number of entry and exit events is greater than zero, it is considered a valid back-and-forth movement, and the number of back-and-forth movements within different time windows is accumulated.

7. A multi-source array intelligent animal monitoring and deterrence system based on target recognition, used to implement the multi-source array intelligent animal monitoring and deterrence method based on target recognition as described in any one of claims 1-6, characterized in that, The system includes: The individual exploration module is used to extract the distribution behavior parameters of individual animals based on the data collected by the multi-source sensor array, obtain the individual behavior feature dataset, and generate the animal exploration behavior judgment result based on the number of times the individual animal moves back and forth in the monitoring boundary area, the duration of a single stay, and the ratio of entry depth to exit frequency. Based on the number of times an animal moves back and forth within the monitoring boundary area, the duration of each stay, and the ratio of entry depth to exit frequency, the animal's exploratory behavior is determined. Specifically, this includes: setting the coordinates of the monitoring boundary line; statistically analyzing the entry and exit events of an animal crossing the boundary line in the position coordinate sequence; accumulating the number of back-and-forth movements; determining the stay events of an animal within the monitoring area based on the stay time distribution; extracting the start and end times of each stay event; calculating the time difference to obtain the duration of each stay; using the position coordinate sequence to calculate the farthest distance from the monitoring boundary line after the animal enters the monitoring area as the entry depth; combining the rate of change of movement speed to calculate the exit frequency within a preset time period; and calculating the ratio of entry depth to exit frequency. When the number of back-and-forth movements exceeds a first preset threshold, the duration of each stay exceeds a second preset threshold, and the ratio of entry depth to exit frequency exceeds a third preset threshold, the behavior is determined as exploratory behavior and output. The group adaptation module is used to calculate the group's adaptation parameters to the sound and light driving stimuli based on the results of animal trial behavior judgment and historical driving event records, using the response threshold enhancement algorithm, and to set the adaptation critical threshold judgment criteria to generate the animal group driving adaptation assessment results; among which, the group's adaptation parameters to the sound and light driving stimuli include the initial response threshold, the current response threshold, and the threshold change rate. Based on the animal exploration behavior assessment results and historical drive-away event records, the adaptive parameters of a group to audio-visual drive-away stimuli are calculated using a response threshold enhancement algorithm. Specifically, this includes: establishing a historical drive-away event database, recording the time, location, type of drive-away stimulus, stimulus intensity, and animal group response behavior for each drive-away event; determining the initial response threshold based on the stimulus intensity at which the animal group begins to flee in the first drive-away event; constructing a probabilistic model based on the response threshold, analyzing the animal group's adaptation to drive-away stimuli based on the animal exploration behavior assessment results and the historical drive-away event database; analyzing the trend of animal group response to the same type of stimulus in historical drive-away events, calculating the minimum stimulus intensity that causes the group to flee in each drive-away event, and obtaining the current response threshold; calculating the ratio of the current response threshold to the initial response threshold to obtain the threshold change factor, and calculating the growth rate of the threshold change factor per unit time to obtain the threshold change rate; multiplying the threshold change factor by a preset reference coefficient, and adding the product of the threshold change rate and a preset weight, to obtain the adaptive parameters of the group to audio-visual drive-away stimuli. The process of setting adaptive threshold criteria and generating animal group drive adaptation assessment results includes: setting adaptive threshold criteria, including an upper limit for the threshold change multiple and an upper limit for the threshold change rate; comparing the threshold change multiple with the upper limit for the threshold change multiple and comparing the threshold change rate with the upper limit for the threshold change rate; when the threshold change multiple exceeds the upper limit for the threshold change multiple or the threshold change rate exceeds the upper limit for the threshold change rate, the animal group is determined to have adapted to the current drive method, and the adaptive state is marked as adapted; otherwise, it is marked as unadapted; based on the marked adaptive state, the percentage of the group's degree of adaptation is calculated according to the threshold change multiple and the threshold change rate to obtain the animal group drive adaptation assessment results. The regulation and control module is used to generate a deportation control signal containing activation commands and regulation parameters based on the results of animal exploratory behavior judgment and animal group deportation adaptability assessment.

Images