Animal monitoring method and system based on ad hoc network infrared camera

Abstract

The invention relates to the technical field of animal monitoring, in particular to an animal monitoring method and system based on an ad hoc network infrared camera. In the ad-hoc network infrared camera system, a central station and an infrared camera form a wireless local area network, the infrared camera transmits monitoring data to the central station in real time through the wireless local area network, and a central machine establishes network connection with a monitoring center through an optical cable, a microwave network bridge and 4G to gather, store and forward the data to the monitoring center. The problem that no 4G signal coverage exists in a monitoring area is thoroughly solved; meanwhile, the appearance type and the appearance number of the animal individuals are obtained; obtaining each appearance type, likelihood scale and confidence coefficient according to the appearance type, the appearance number, the predicted animal type and the prediction scale thereof; establishing a regional ecological model; and correcting the likelihood scale of each appearance type according to the food chain relationship of the regional ecological model and the confidence coefficient of each appearance type.

Description

Technical Field

[0001] The present application relates to the field of animal monitoring technology, and in particular to an animal monitoring method and system based on a self-organizing network infrared camera. Background Art

[0002] Infrared camera monitoring is an important means of automated animal monitoring. To obtain real-time photos or video footage of animals, the conventional approach is to add a 4G communication module to the infrared camera to transmit the monitoring data back to the monitoring center server in real time via 4G signals. However, in engineering practice, it has been found that areas where animals are active are often relatively remote, sparsely populated, and lack 4G signal coverage. As a result, 4G infrared cameras cannot transmit monitoring data back to the monitoring center server in real time via 4G signals.

[0003] In animal monitoring, animal activities are monitored by sub-machines. However, the animals cannot be fully monitored and tracked due to the living environment factors around them. For example, there may be obstructions from bushes or animal populations. When monitoring animals at a fixed angle, the animals will always be obscured or appear outside the monitoring screen. Setting up multiple sub-machines in animal monitoring will affect the living environment of the animals. Therefore, during animal monitoring, animals may be obscured or lost in the monitoring screen. The types and individuals of animals that appear in the next captured screen cannot be fully counted, so there are certain errors in the animal data obtained after monitoring. Therefore, there is an urgent need for an animal monitoring method and system based on self-organizing network infrared cameras to solve the problems of poor 4G signal coverage and low accuracy of monitored animal data in the monitoring area. Summary of the Invention

[0004] The purpose of the present invention is to propose an animal monitoring method and system based on an ad hoc network infrared camera to solve one or more technical problems existing in the prior art and at least provide a beneficial option or create conditions.

[0005] Front-end infrared camera (referred to as slave, low-power with built-in ultra-long-distance communication module), infrared camera data processing center (referred to as central station, with built-in ultra-long-distance receiving module and data processing micro server), wireless MESH ad hoc network backbone transmission equipment, long-distance bridge, public network base station, application server and AI server.

[0006] The slave units and central station form a local area network, utilizing OFDM and MIMO technologies. A flat system architecture design supports automatic allocation of multiple frequency bands and bandwidths, and boasts strong penetration and diffraction capabilities. In forested areas obstructed by trees and mountains, the coverage radius can reach 1-3 km (with a line-of-sight range of up to 5 km). It also boasts a high 30Mbps bandwidth, strong anti-interference capabilities, and low power consumption.

[0007] The data captured by the slave is transmitted to the central station in real time. After receiving the data, the central station stores it in the hard disk or SD card in the micro server (it can also be forwarded directly to the public network through the server without storage). The central station then transmits it to the wireless MESH self-organizing network backbone transmission equipment, and finally accesses the public network through a bridge or optical fiber (if the 4G signal at a central station is very good, a bridge can be omitted), thereby realizing the transmission of data from areas without public network coverage back to the office.

[0008] The central station integrates a low-power, ultra-long-range communication micro base station, and the slaves integrate low-power, ultra-long-range communication modules. Within the central station's coverage radius of 3-5 km, all slaves can communicate with the central station. Antennas have no directional requirements and do not require elevated installation, making site selection and installation easy. The central station can store and forward data, ensuring data security and saving power. Wireless MESH ad hoc network backbone transmission equipment can be flexibly selected based on customer scenarios and needs, achieving the best cost-effectiveness while meeting requirements.

[0009] In terms of power supply, the slave machine can use 12 alkaline batteries or large-capacity disposable lithium iron batteries, or a large-capacity rechargeable 18650 battery with a small power solar panel of about 5W. The central station uses a large-capacity rechargeable 18650 battery or a large-capacity lead-acid battery and a solar panel of more than 20W for charging. The bridge part connecting to the external network is not necessary. If the 4G signal at a certain central station is very good, you can also use the 4G network of the central station to transmit to the public network directly without a bridge. If you want to use a bridge, you must choose a bridge model of different power according to the distance you want to transmit. To be safe,

[0010] Prepare a 200Ah large-capacity lead-acid battery and a solar panel with a power of about 200-400W or connect to the mains.

[0011] Preferably, the system includes an animal monitoring method based on a wireless infrared camera in an ad hoc network, the method comprising the following steps:

[0012] Identify plant populations within the area based on images captured by the slave device, and obtain predicted animal species and their predicted size based on the plant populations;

[0013] Identify individual animals that appear in the images captured by the slave device and the infrared camera image, and obtain the type and number of individual animals that appear;

[0014] Obtaining each occurrence type, likelihood scale, and confidence level based on the occurrence type, occurrence number, predicted animal type, and predicted scale;

[0015] Establish a regional ecological model based on the likelihood scale of all the described species;

[0016] Correct the likelihood scale of each occurring species based on the food chain relationships of the regional ecological model and the confidence level of each occurring species;

[0017] Based on the plant populations and the regional ecological model after correcting the likelihood scale, regional biodiversity monitoring results are obtained.

[0018] Furthermore, the method for identifying plant populations in an area based on images captured by the slave unit includes: acquiring a plurality of images captured by the slave unit, and performing brightness and color correction on the images captured by the slave unit;

[0019] Aligning the positions of the multiple images taken by the slave units to obtain position annotations of the images taken by the slave units;

[0020] Dividing the stitched image into multiple sub-regions, and obtaining multiple images corresponding to each sub-region according to the position annotations, which are recorded as sub-region images;

[0021] Using a pre-connected image recognition model, respectively identifying plants in a plurality of sub-region images corresponding to each sub-region, and obtaining plant position annotations according to the position annotations;

[0022] The plants identified by fusing multiple sub-region images are labeled according to the plant positions to obtain the plant identification results for each sub-region;

[0023] According to the plant identification results of all sub-regions, the plant population in the region is obtained.

[0024] Furthermore, the method of obtaining the predicted animal species and the predicted size thereof according to the plant population includes: obtaining the type and population size of each plant population respectively, wherein the population size is expressed in terms of number or coverage area;

[0025] Read pre-imported food chain data and list the animal types and population sizes of herbivores or omnivores that can be supported based on the type and size of the plant population;

[0026] Obtaining the animal type and population size of carnivores based on the animal type and population size of the herbivores or omnivores in combination with the food chain data;

[0027] According to the animal types and population sizes of the herbivores, the omnivores, and the carnivores, predicted animal species and predicted sizes are obtained.

[0028] The method for identifying individual animals that appear in the images taken by the slave unit and the infrared camera and obtaining the types and numbers of the individual animals includes: aligning the positions of a plurality of images taken by the slave unit and the infrared camera to obtain position annotations of the images taken by the slave unit and the infrared camera;

[0029] Obtain the location of the individual animal based on the image captured by the infrared camera and the location annotation, and obtain an image captured by the slave device corresponding to the location, which is recorded as a captured image;

[0030] Obtaining the type and location of the individual animal based on a response of a pre-connected image recognition model to the captured image;

[0031] The individual animals identified by the images taken by all the sub-machines and the images taken by the infrared camera are fused according to their positions, the number of individual animals of each type is counted, and the types and numbers of individual animals are obtained.

[0032] The method for obtaining the probability scale and confidence level of each occurrence species based on the occurrence species, the occurrence number, the predicted animal species and the predicted scale includes: dividing a single day into a number of time periods, and obtaining the equivalent number of outings of a single animal in each time period based on the predicted animal species and the animal's living habits;

[0033] Obtaining the total equivalent number of outings for each animal type in the area during each time period according to the equivalent number of outings and the predicted scale;

[0034] Obtaining the total equivalent number of outings of each animal type in the corresponding period according to the shooting time of the image;

[0035] Calculating the ratio of the number of appearances to the total number of outbound equivalent times;

[0036] The predicted scale is multiplied by the ratio as the likelihood scale, and the closeness of the ratio to 1 is calculated as the confidence.

[0037] The method of correcting the likelihood scale of each occurrence species according to the food chain relationship of the regional ecological model and the confidence of each occurrence species includes: obtaining the scale ratio between all occurrence species according to the food chain relationship of the regional ecological model;

[0038] Select an occurrence category, and calculate the revised scales of other occurrence categories based on the likelihood scale of the selected occurrence category and the scale ratio;

[0039] Calculating the closeness between the corrected scale and the likelihood scale of each occurrence category, and using the closeness to correct the confidence of the occurrence category;

[0040] The sum of the confidence scores of all occurring species is used as the confidence score of the regional ecological model;

[0041] The likelihood scale of each occurrence species was revised based on the regional ecological model with the highest confidence.

[0042] The beneficial effects of the present invention are:

[0043] In the self-organizing infrared camera system, the central station and the infrared camera form a wireless local area network. The infrared camera transmits the monitoring data to the central station in real time through the wireless local area network. The central computer establishes a network connection with the monitoring center through optical cables, microwave bridges, and 4G, and aggregates, stores, and forwards the data to the monitoring center, completely solving the problem of no 4G signal coverage in the monitoring area.

[0044] The proposed regional biodiversity monitoring method can identify plant populations based on images, as well as predict and correct animal species and likelihood sizes. This method addresses industry challenges such as low accuracy of animal data and the tendency for animals to be missed in images captured by drones, enabling the monitoring of regional biodiversity and obtaining accurate results. Correlating calculations using the number of occurrences, predicted size, and likelihood size ultimately yield the size and confidence level of animal populations, making population size monitoring more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The above and other features of the present invention will become more apparent through a detailed description of the embodiments shown in conjunction with the accompanying drawings. In the drawings of the present invention, the same reference numerals represent the same or similar elements. Obviously, the drawings described below are only some embodiments of the present invention. It is possible for a person skilled in the art to derive other drawings based on these drawings without inventive effort. In the drawings:

[0046] Figure 1 This is a structural diagram of an animal monitoring system based on ad hoc network infrared cameras;

[0047] Figure 2 The flowchart of an animal monitoring method based on ad hoc network infrared camera. DETAILED DESCRIPTION

[0048] The embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.

[0049] In the description of the present invention, "several" means one or more, "many" means more than two, "greater than," "less than," and "exceed" are understood to exclude the number itself, while "above," "below," and "within" are understood to include the number itself. The use of "first" and "second" in the description is solely for the purpose of distinguishing technical features and should not be construed as indicating or implying relative importance, implicitly specifying the number of the indicated technical features, or implicitly specifying the order of the indicated technical features.

[0050] The following describes the embodiments of the present disclosure through specific examples, and those skilled in the art can easily understand the advantages and effects of the present disclosure from the contents disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all of the embodiments. The present disclosure can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present disclosure. It should be noted that, in the absence of conflict, the following embodiments and features in the embodiments can be combined with each other. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present disclosure.

[0051] The purpose of the present invention is to propose an animal monitoring method and system based on an ad hoc network infrared camera to solve one or more technical problems existing in the prior art and at least provide a beneficial option or create conditions.

[0052] Front-end infrared camera (referred to as slave, low-power with built-in ultra-long-distance communication module), infrared camera data processing center (referred to as central station, with built-in ultra-long-distance receiving module and data processing micro server), wireless MESH ad hoc network backbone transmission equipment, long-distance bridge, public network base station, application server and AI server.

[0053] The slave units and central station form a local area network, utilizing OFDM and MIMO technologies. A flat system architecture design supports automatic allocation of multiple frequency bands and bandwidths, and boasts strong penetration and diffraction capabilities. In forested areas obstructed by trees and mountains, the coverage radius can reach 1-3 km (with a line-of-sight range of up to 5 km). It also boasts a high 30Mbps bandwidth, strong anti-interference capabilities, and low power consumption.

[0054] The data captured by the slave is transmitted to the central station in real time. After receiving the data, the central station stores it in the hard disk or SD card in the micro server (it can also be forwarded directly to the public network through the server without storage). The central station then transmits it to the wireless MESH self-organizing network backbone transmission equipment, and finally accesses the public network through a bridge or optical fiber (if the 4G signal at a central station is very good, a bridge can be omitted), thereby realizing the transmission of data from areas without public network coverage back to the office.

[0055] The central station integrates a low-power, ultra-long-range communication micro base station, and the slaves integrate low-power, ultra-long-range communication modules. Within the central station's coverage radius of 3-5 km, all slaves can communicate with the central station. Antennas have no directional requirements and do not require elevated installation, making site selection and installation easy. The central station can store and forward data, ensuring data security and saving power. Wireless MESH ad hoc network backbone transmission equipment can be flexibly selected based on customer scenarios and needs, achieving the best cost-effectiveness while meeting requirements.

[0056] For power, the slave units can be powered by 12 alkaline batteries or high-capacity disposable lithium-ion batteries, or by large-capacity rechargeable 18650 batteries paired with a low-power solar panel of approximately 5W. The central station uses a large-capacity rechargeable 18650 battery or a large-capacity lead-acid battery and a solar panel with a power output of 20W or more. The bridge connecting to the external network is optional. If the 4G signal at a central station is strong, a bridge can be omitted and data can be transmitted directly to the public network using the central station's 4G network. If a bridge is required, select a model with different power ratings based on the desired transmission distance. For added security, a large-capacity 200Ah lead-acid battery and a 200-400W solar panel or a mains connection are recommended.

[0057] Preferably, the main parameters of the wireless ad hoc network central processing station (abbreviated as central station) are

[0058] The central station integrates a low-power long-distance communication micro base station and a micro server, and is connected to an external high-gain fiberglass omnidirectional antenna. It is small in size, low in power consumption, and has strong diffraction capability. It can be installed using a pole, which is convenient for construction and installation, with small engineering workload, low cost, and little impact on the environment. The main parameters are as follows:

[0059] Support frequency hopping to avoid co-frequency interference;

[0060] Support multiple networking modes: point-to-point, point-to-multipoint;

[0061] Support multiple frequency bands

[0062] Support multiple bandwidth allocation schemes

[0063] The highest sensitivity can reach: -106dBm@3M

[0064] Dual antenna design, supports two-way communication, supports single-transmit single-receive, single-transmit dual-receive

[0065] Low power consumption design, the whole machine power consumption is no more than 3.5W

[0066] Support automatic power control and automatically adjust the power

[0067] Non-line-of-sight low-power long-distance transmission, line-of-sight > 5km, 1-3km in mountainous and forested areas;

[0068] The maximum number of concurrent connections is no less than 16.

[0069] The maximum rate is no less than 30Mbps, and the original image, original video and real-time video stream can be directly transmitted back

[0070] Comes with 256G storage

[0071] Supports breakpoint resume and transit cache. When the backbone network is interrupted or the speed is slow, the infrared camera data can be automatically saved and uploaded when the network is restored, thus saving the power consumption of the infrared camera.

[0072] Support multi-time appointment working to save power consumption

[0073] Waterproof and dustproof rating: IP67

[0074] Multiple interface input and output, support network port, RS485, etc.

[0075] Support OTA remote upgrade

[0076] Support webUI to remotely view device status and control device parameters

[0077] Support 6-18V wide voltage power supply

[0078] Multiple lightning protection design

[0079] Support GPS automatic positioning and timing

[0080] The operating temperature is -40 to +80 degrees Celsius, the maximum working humidity is 98%, and it can withstand repeated impacts of high temperature, low temperature and high humidity for a long time.

[0081] Preferably, 3. Main parameters of wireless ad hoc network infrared camera (referred to as slave)

[0082] The handset integrates a broadband, high-speed, long-distance, and strong diffraction communication module, resulting in a high degree of integration, more stable operation, a smaller size, easier portability and installation, and lower power consumption. The handset can communicate with the central station within its coverage radius. The handset antenna has no directional requirements and does not need to be specially elevated, making site selection and installation easy. The main parameters of the handset are as follows:

[0083] The camera has a built-in ad hoc network communication module that supports multiple frequency bands.

[0084] The maximum transmission rate is not less than 30Mbps;

[0085] Support uploading original files, compressed videos, and optional thumbnails;

[0086] Support live streaming in real time;

[0087] Dual antenna design supports two-way communication, single transmit and single receive, single transmit and dual receive;

[0088] Support frequency hopping to avoid co-frequency interference;

[0089] Support GPS automatic positioning and timing;

[0090] Supports 4K (3840*2160) / 3K (2560*1920) audio and video, and 32 million photo pixels;

[0091] The 2.0-inch high-definition front-facing omnidirectional screen makes it easy to view the monitoring area during installation. After replacing the battery, the camera housing can be left open to prevent it from accidentally falling into rainwater when opened in rainy days.

[0092] The camera starts recording and taking photos simultaneously, with a startup time of 0.2 seconds, which perfectly solves the problem of no animals in the video.

[0093] The camera can take photos while recording video, which saves the time of taking photos and shortens the working time of each camera startup, thus saving power consumption.

[0094] Built-in intelligent image algorithm, adapting to various ambient light conditions and automatically adjusting exposure at near and far distances;

[0095] Supports magazine-like overall installation and battery replacement, regardless of installation height or angle. Battery replacement does not require lying on the ground or loosening straps, nor does it require disassembling and installing batteries one by one outdoors, making battery replacement quick and easy.

[0096] The two-position switch design automatically enters monitoring mode without any operation after power on, so as to avoid forgetting to manually enter monitoring mode in the field and causing the camera to not enter monitoring mode;

[0097] Adopt multi-zone large sensing surface, high sensitivity, strong anti-interference PIR, multi-stage signal amplification and filtering design to effectively avoid false triggering;

[0098] Compatible with 8AA batteries and 7.5Ah@12V battery packs, supports solar charging;

[0099] Supports photo taking, video recording, and photo taking + video recording working modes;

[0100] Strong resistance to cold and heat shock, super stability, IP68 waterproof and dustproof design;

[0101] Lens F = 1.6 large aperture lens, FOV = 65 degrees;

[0102] Built-in low-temperature resistant button battery ensures that the time is not lost when the power is off or the temperature is low;

[0103] Ultra-low power consumption design, 100ua ultra-low standby current, the whole machine working current is less than 180ma during the day;

[0104] 4 high-efficiency fill lights, 850nm, 940nm;

[0105] High shutter speed to effectively suppress motion blur;

[0106] PIR sensitivity can be adjusted: high, normal, low;

[0107] Integrated high-stability IR-CUT day and night switcher to improve color and black and white image quality;

[0108] Supports up to 512GB SD memory card and is compatible with various brands;

[0109] High-quality recording design, -38dB sensitivity MIC;

[0110] Can display rich photo information, including shooting date, time, temperature, moon phase, device name, longitude and latitude, etc.

[0111] Compact size design, 135*108*96mm;

[0112] Operating temperature -40 to +80 degrees Celsius.

[0113] Preferably, the system includes an animal monitoring method based on an ad hoc network infrared camera, the method comprising the following steps:

[0114] Identify plant populations within the area based on images captured by the slave device, and obtain predicted animal species and their predicted size based on the plant populations;

[0115] Identify individual animals that appear in the images captured by the slave device and the infrared camera image, and obtain the type and number of individual animals that appear;

[0116] Obtaining each occurrence type, likelihood scale, and confidence level based on the occurrence type, occurrence number, predicted animal type, and predicted scale;

[0117] Establish a regional ecological model based on the likelihood scale of all the described species;

[0118] Correct the likelihood scale of each occurring species based on the food chain relationships of the regional ecological model and the confidence level of each occurring species;

[0119] Based on the plant populations and the regional ecological model after correcting the likelihood scale, regional biodiversity monitoring results are obtained.

[0120] Furthermore, the method for identifying plant populations in an area based on images captured by the slave unit includes: acquiring a plurality of images captured by the slave unit, and performing brightness and color correction on the images captured by the slave unit;

[0121] Aligning the positions of the multiple images taken by the slave units to obtain position annotations of the images taken by the slave units;

[0122] Dividing the stitched image into multiple sub-regions, and obtaining multiple images corresponding to each sub-region according to the position annotations, which are recorded as sub-region images;

[0123] Using a pre-connected image recognition model, respectively identifying plants in a plurality of sub-region images corresponding to each sub-region, and obtaining plant position annotations according to the position annotations;

[0124] The plants identified by fusing multiple sub-region images are labeled according to the plant positions to obtain the plant identification results for each sub-region;

[0125] According to the plant identification results of all sub-regions, the plant population in the region is obtained.

[0126] Furthermore, the method of obtaining the predicted animal species and the predicted size thereof according to the plant population includes: obtaining the type and population size of each plant population respectively, wherein the population size is expressed in terms of number or coverage area;

[0127] Read pre-imported food chain data and list the animal types and population sizes of herbivores or omnivores that can be supported based on the type and size of the plant population;

[0128] Obtaining the animal type and population size of carnivores based on the animal type and population size of the herbivores or omnivores in combination with the food chain data;

[0129] According to the animal types and population sizes of the herbivores, the omnivores, and the carnivores, predicted animal species and predicted sizes are obtained.

[0130] The method for identifying individual animals that appear in the images taken by the slave unit and the infrared camera and obtaining the types and numbers of the individual animals includes: aligning the positions of a plurality of images taken by the slave unit and the infrared camera to obtain position annotations of the images taken by the slave unit and the infrared camera;

[0131] Obtain the location of the individual animal based on the image captured by the infrared camera and the location annotation, and obtain an image captured by the slave device corresponding to the location, which is recorded as a captured image;

[0132] Obtaining the type and location of the individual animal based on a response of a pre-connected image recognition model to the captured image;

[0133] The individual animals identified by the images taken by all the sub-machines and the images taken by the infrared camera are fused according to their positions, the number of individual animals of each type is counted, and the types and numbers of individual animals are obtained.

[0134] The method for obtaining the probability scale and confidence level of each occurrence species based on the occurrence species, the occurrence number, the predicted animal species and the predicted scale includes: dividing a single day into a number of time periods, and obtaining the equivalent number of outings of a single animal in each time period based on the predicted animal species and the animal's living habits;

[0135] Obtaining the total equivalent number of outings for each animal type in the area during each time period according to the equivalent number of outings and the predicted scale;

[0136] Obtaining the total equivalent number of outings of each animal type in the corresponding period according to the shooting time of the image;

[0137] Calculating the ratio of the number of appearances to the total number of outbound equivalent times;

[0138] The predicted scale is multiplied by the ratio as the likelihood scale, and the closeness of the ratio to 1 is calculated as the confidence.

[0139] The method of correcting the likelihood scale of each occurrence species according to the food chain relationship of the regional ecological model and the confidence of each occurrence species includes: obtaining the scale ratio between all occurrence species according to the food chain relationship of the regional ecological model;

[0140] Select an occurrence category, and calculate the revised scales of other occurrence categories based on the likelihood scale of the selected occurrence category and the scale ratio;

[0141] Calculating the closeness between the corrected scale and the likelihood scale of each occurrence category, and using the closeness to correct the confidence of the occurrence category;

[0142] The sum of the confidence scores of all occurring species is used as the confidence score of the regional ecological model;

[0143] The likelihood scale of each occurrence species was revised based on the regional ecological model with the highest confidence.

[0144] Although the present invention has been described in considerable detail and with particularity with respect to several embodiments, it is not intended to limit the present invention to any of these details or embodiments or any particular embodiment, so as to effectively encompass the intended scope of the present invention. In addition, the present invention has been described above with respect to embodiments foreseen by the inventors for the purpose of providing a useful description, and those insubstantial modifications of the present invention that are not currently foreseen may still represent equivalent modifications of the present invention.

Claims

1. An animal monitoring system based on a self-organizing network infrared camera, characterized in that: The system includes: a front-end self-organizing wireless infrared camera, a data processing center, a backbone network, a solar energy function system, a central computer room and a command room, and the monitoring system is powered by the solar energy function system; In the system, a local area network is formed by a sub-machine and a central station, wherein the sub-machine is represented by a front-end self-organizing wireless infrared camera, and the central station is a data processing center.

2. The animal monitoring system based on ad hoc network infrared camera according to claim 1, characterized in that: The data captured by the slave is transmitted to the central station in real time. After receiving the data, the central station stores the received data in the memory of the micro server, obtains the received data of the central station in the memory, and transmits the received data to the backbone transmission equipment of the wireless MESH self-organizing network by the central station, and finally accesses the public network through a bridge or optical fiber, so as to realize the data transmission from the area without public network coverage back to the command room; The central station integrates a low-power and ultra-long-distance communication micro base station, and the slave unit integrates a low-power and ultra-long-distance communication module.

3. The animal monitoring system based on ad hoc network infrared camera according to claim 1, characterized in that: The central station integrates a low-power long-distance communication micro base station and a micro server, and is externally connected to a high-gain fiberglass omnidirectional antenna, which is installed in a pole-mounted manner; The central station supports frequency hopping to avoid co-frequency interference; Support multiple networking modes, including point-to-point and point-to-multipoint; support multiple frequency bands to choose from; support multiple bandwidth allocation schemes; The submachine has an integrated broadband, high-speed, long-distance, strong diffraction communication module. The submachine can communicate with the central station within the radius covered by the central station. The submachine antenna has no direction requirements and does not need to be specially elevated. The submachine camera has a built-in self-organizing network communication module that supports multiple frequency bands to choose from; supports frequency hopping to avoid co-frequency interference; supports GPS automatic positioning and timing.

4. The animal monitoring system based on ad hoc network infrared camera according to claim 1, characterized in that: The system includes an animal monitoring method based on a self-organizing network infrared camera, and the method includes the following steps: Identify plant populations in the area based on images taken by the slave unit, and obtain predicted animal species and their predicted sizes based on the plant populations; Identify individual animals that appear in the images taken by the slave and the infrared camera, and obtain the type and number of individual animals that appear; According to the occurrence types, occurrence numbers, predicted animal species and predicted scales, obtaining each occurrence type, likelihood scale and confidence level; Establish regional ecological models based on the likelihood scale of all described species; Correcting the likelihood scale of each occurrence species according to the food chain relationship of the regional ecological model and the confidence of each occurrence species; Based on the plant population and the regional ecological model after correcting the likelihood scale, the regional biodiversity monitoring results are obtained.

5. The animal monitoring method based on a self-organizing network infrared camera according to claim 4, characterized in that: The method for identifying plant populations in an area based on images taken by the slave unit includes: acquiring a plurality of images taken by the slave unit, and performing brightness and color correction on the images taken by the slave unit; Aligning the positions of the multiple images taken by the slave units to obtain position annotations of the images taken by the slave units; Divide the stitched image into multiple sub-regions, and obtain multiple images corresponding to each sub-region according to the position annotations, which are recorded as sub-region images; Using a pre-connected image recognition model, respectively identifying plants in a plurality of sub-region images corresponding to each sub-region, and obtaining plant position annotations according to the position annotations; The plants identified by fusing multiple sub-region images are labeled according to the plant positions to obtain the plant identification results for each sub-region; According to the plant identification results of all sub-areas, the plant population in the area is obtained.

6. The animal monitoring method based on a self-organizing network infrared camera according to claim 4, characterized in that: According to the plant population, the method for obtaining the predicted animal species and the predicted scale thereof comprises: obtaining the type and the scale of each plant population respectively, wherein the scale of the population is expressed by the number or the coverage area; Read the pre-imported food chain data, and list the animal types and population sizes of herbivores or omnivores that can be supported based on the types and population sizes of plant populations; According to the animal type and population size of the herbivores or the omnivores, in combination with the food chain data, the animal type and population size of the carnivores are obtained; According to the animal types and population sizes of the herbivores, the omnivores and the carnivores, predicted animal species and predicted sizes thereof are obtained.

Images