Sow estrus recognition method and system, and electronic device

Abstract

The application provides a sow estrus recognition method and system and an electronic device, and utilizes image recognition and mechanical automation technology to realize intelligent estrus measurement of sows. The application effectively reduces the workload of workers, lowers the access threshold of the estrus measurement industry, and reduces costs. The application innovatively utilizes an infrared thermal imaging camera to collect image sequences of movements of each part of the body of a target sow, analyzes the image sequences to obtain image sequence data, determines the height of the back of the target sow according to the image sequence data, controls a massage module to apply pressure to the back of the target sow to simulate a boar lying on the back and massaging the udder of the target sow, further analyzes the image sequence data, and outputs a signal about the estrus of the target sow according to a judgment result. The application simplifies the problem of intelligent recognition of sow estrus, does not require complex algorithm modeling, greatly reduces the application cost of the application, improves the intelligent degree of the application, and greatly expands the application scenarios of the application.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of livestock physiological intelligent monitoring and identification, in particular to a sow estrus recognition method and system and an electronic device. BACKGROUND

[0002] Modern pig farming is developing towards large-scale and intensive breeding, and sows are the core group of the pig farm and the key to the success of pig farm management. Normal estrus and timely mating of sows determine the production efficiency of sows. Improving the annual productivity of sows can reduce the amount of feeding, save feed, reduce pig houses and labor, and reduce costs. Sows are often raised in a fixed position, with a small living space. During the feeding process, it is necessary to observe whether the sow has reached the estrus period. If the sow's estrus phenomenon cannot be found in time, it will affect the sow's reproductive performance.

[0003] In current sow feeding, whether the sow is in estrus is mainly determined by artificial back pressure. The sow's standing and ear standing are observed when the back is pressed. Due to the increasing density of large-scale pig farms, the workload of technical personnel is greatly increased, and the experience and technology required for sow estrus recognition are high. Generally, employees need to undergo long-term training before they can work.

[0004] Therefore, the prior art needs to be further developed. SUMMARY

[0005] The present application aims to overcome the above technical deficiencies and provide a sow estrus recognition method and system and an electronic device to solve the problems existing in the prior art.

[0006] To achieve the above technical purpose, according to the first aspect of the present application, a sow estrus recognition method is provided, which comprises:

[0007] The positioning module collects the positioning information of the target sow, obtains the positioning information of the target sow, controls the massage module to move according to the positioning information of the target sow, collects the image sequence of the action of each part of the body of the target sow through the image collection module, analyzes the image sequence to obtain image sequence data, determines the height of the back of the target sow according to the image sequence data, controls the massage module to apply pressure to the back of the target sow to simulate the back of the boar and massage the udder of the target sow, further analyzes and judges the image sequence data, and outputs a signal about the estrus of the target sow according to the judgment result.

[0008] Specifically, the image sequence of the action of each part of the body of the target sow collected by the image collection module comprises:

[0009] The infrared thermal imaging sensor in the image acquisition module includes a first camera, and the first camera is used to acquire an image sequence of the ear of the target sow.

[0010] Specifically, the method further includes:

[0011] If there is a pixel point with a gray value greater than or equal to the first preset threshold in the infrared thermal imaging image data of the ear of the target sow, the pixel point is determined as a target point, a target range is determined according to the target point, the target range needs to include all target points in the current frame of infrared thermal imaging image data, a target search box is established according to the target range, and the left upper corner coordinate and the right lower corner coordinate of the target search box are calculated, and the change amplitudes of the left upper corner coordinate and the right lower corner coordinate of the target search box are calculated respectively according to the left upper corner coordinate and the right lower corner coordinate of the target search box, whether the sum of the change amplitudes of the left upper corner coordinate and the right lower corner coordinate of the target search box is less than or equal to the second preset threshold is judged, and a signal about estrus of the target sow is output according to the judgment result.

[0012] Specifically, the method further includes:

[0013] If the sum of the change amplitudes of the left upper corner coordinate and the right lower corner coordinate of the target search box is less than or equal to the second preset threshold, a signal that the target sow is in estrus is output.

[0014] Specifically, the method further includes:

[0015] If the sum of the change amplitudes of the left upper corner coordinate and the right lower corner coordinate of the target search box is greater than the second preset threshold, a signal that the target sow is not in estrus is output.

[0016] Specifically, the method further includes:

[0017] If there is a pixel point with a gray value greater than or equal to the third preset threshold in the infrared thermal imaging image data of the hip of the target sow, the pixel point is determined as a target point, a target range is determined according to the target point, the target range needs to include all target points in the current frame of infrared thermal imaging image data, a target search box is established according to the target range, and the left upper corner coordinate and the right lower corner coordinate of the target search box are calculated, and the change amplitudes of the left upper corner coordinate and the right lower corner coordinate of the target search box are calculated respectively according to the left upper corner coordinate and the right lower corner coordinate of the target search box, whether the sum of the change amplitudes of the left upper corner coordinate and the right lower corner coordinate of the target search box is less than or equal to the fourth preset threshold is judged, and a signal about estrus of the target sow is output according to the judgment result.

[0018] Specifically, the method includes:

[0019] If the sum of the change amplitudes of the left upper corner coordinate and the right lower corner coordinate of the target search frame is less than or equal to a fourth preset threshold, a signal about estrus of the target sow is output.

[0020] Specifically, the method comprises:

[0021] If the sum of the change amplitudes of the left upper corner coordinate and the right lower corner coordinate of the target search frame is greater than the fourth preset threshold, a signal about non-estrus of the target sow is output.

[0022] According to a second aspect of the present application, a sow estrus recognition system is provided, comprising:

[0023] An image acquisition module 100 is configured to acquire an image sequence of movements of each part of the body of the target sow;

[0024] A massage module 400 is configured to apply pressure to the back of the target sow to simulate a boar lying on the back and massage the udder of the target sow;

[0025] A positioning module is configured to acquire positioning information of the target sow;

[0026] The control module acquires the positioning information of the target sow through the positioning module, controls the movement of the massage module according to the positioning information of the target sow, acquires the image sequence of movements of each part of the body of the target sow through the image acquisition module 100, obtains image sequence data by analyzing the image sequence, determines the height of the back of the target sow according to the image sequence data, controls the massage module to apply pressure to the back of the target sow to simulate a boar lying on the back and massage the udder of the target sow, and further analyzes the image sequence data, judges according to the result, and outputs a signal about estrus of the target sow.

[0027] According to a third aspect of the present application, an electronic device is provided, comprising:

[0028] A memory and a processor, wherein computer readable instructions are stored on the memory, and the computer readable instructions are executed by the processor to implement the sow estrus recognition method according to any one of claims 1 to 8.

[0029] The present application has the following beneficial effects:

[0030] The application is based on the traditional experience of sow estrus, uses image recognition and mechanical automation technology, constructs a sow estrus recognition method and system and an electronic device, realizes intelligent estrus measurement of sows, effectively reduces the workload of workers, reduces the access threshold of the estrus measurement industry, and reduces the cost. Through ingenious design, the infrared thermal imaging camera is used to collect image sequences of the movements of each part of the target sow's body, the image sequence data is obtained by analyzing the image sequences, the height of the back of the target sow is determined according to the image sequence data, the massage module is controlled to apply pressure to the back of the target sow to simulate the sow lying on the back of the boar and massaging the udder of the target sow, the image sequence data is further analyzed and judged, and a signal about the estrus of the target sow is output according to the judgment result, the problem of complex sow estrus intelligent recognition is simplified, complex algorithm modeling is not required, the application cost of the application is greatly reduced, the intelligent degree of the application is improved, and the application scenarios of the application are greatly expanded. BRIEF DESCRIPTION OF DRAWINGS

[0031] Figure 1 is a flowchart of the sow estrus recognition method provided in the embodiments of the application;

[0032] Figure 2 is a schematic diagram of the sow estrus recognition system provided in the embodiments of the application;

[0033] Figure 3 is a structural schematic diagram of the sow estrus recognition system provided in the embodiments of the application. DETAILED DESCRIPTION

[0034] In order for those skilled in the art to better understand the technical solutions of the application, the technical solutions of the application will be described clearly and completely below in combination with the drawings of the application. Based on the embodiments in the present application, other similar embodiments obtained by those skilled in the art without making creative efforts should belong to the protection scope of the present application. In addition, the direction words mentioned in the following embodiments, such as “up”, “down”, “left”, “right”, etc., are only the directions of the drawings, therefore, the direction words used are used for illustration but not for limitation of the present application.

[0035] The application will be further described below in combination with the drawings and preferred embodiments.

[0036] Please refer to Figure 1 The present embodiment provides a sow estrus recognition method, which comprises the following steps.

[0037] S100, collect the positioning information of the target sow through the positioning module, the control module obtains the positioning information of the target sow, and controls the massage module to move according to the positioning information of the target sow.

[0038] It should be noted that step S100 includes the following:

[0039] The system presets a first preset threshold, a second preset threshold, a third preset threshold, and a fourth preset threshold.

[0040] S200: The image acquisition module acquires image sequences of the movements of various parts of the target sow's body, and parses the image sequences to obtain image sequence data.

[0041] Specifically, the image sequence of movements of various parts of the target sow's body acquired by the image acquisition module includes:

[0042] The image acquisition module uses an infrared thermal imaging camera group to acquire infrared thermal imaging image sequences of various parts of the target sow's body. The infrared thermal imaging camera group includes a first infrared thermal imaging camera, which is used to acquire image sequences of the target sow's ears. The image acquisition module also includes a second infrared thermal imaging camera, which is used to acquire image sequences of the target sow's rump.

[0043] S300: Determine the back height of the target sow based on the image sequence data, and control the massage module to apply pressure to the back of the target sow to simulate a boar lying on its back and massaging the udder of the target sow.

[0044] S400: Further analyze and judge the image sequence data, and output a signal about the estrus of the target sow based on the judgment result.

[0045] Specifically, the method further includes:

[0046] If there is a pixel in the infrared thermal imaging image data of the target sow's ear with a grayscale value greater than or equal to a first preset threshold, then that pixel is determined as a target point. The target range is determined based on the target point, and the target range needs to include all target points in the current frame of infrared thermal imaging image data. A target search box is established based on the target range, and the coordinates of the upper left and lower right corners of the target search box are calculated. The change amplitude of the upper left and lower right corner coordinates of the target search box is calculated based on the upper left and lower right corner coordinates, respectively. It is determined whether the sum of the change amplitudes of the upper left and lower right corner coordinates of the target search box is less than or equal to a second preset threshold, and a signal related to the estrus of the target sow is output based on the determination result.

[0047] It should be noted that if there are pixels in the infrared thermal imaging data of the target sow's ear with a grayscale value greater than or equal to the first preset threshold, it proves that the pixel is a pixel of the target sow's ear; otherwise, the pixel is an environmental pixel.

[0048] Specifically, the method further includes:

[0049] If the sum of the changes in the upper left and lower right corner coordinates of the target search box is less than or equal to the second preset threshold, the target sow's estrus signal will be output.

[0050] It should be noted that if the sum of the changes in the upper left and lower right corner coordinates of the target search box is less than or equal to the second preset threshold, it proves that the target sow's ears have a standing reaction. At this time, the estrus signal of the target sow is output, realizing intelligent estrus detection of the sow, simplifying the complex problem of intelligent estrus identification of sows, and improving the intelligence level of the present invention.

[0051] Specifically, the method further includes:

[0052] If the sum of the changes in the upper left and lower right corner coordinates of the target search box is greater than the second preset threshold, output a signal that the target sow has not come into estrus.

[0053] It should be noted that if the sum of the changes in the upper left and lower right corner coordinates of the target search box is greater than the second preset threshold, it proves that the target sow's ears do not show a standing response, and a signal that the target sow is not in estrus is output.

[0054] Specifically, the method may further include:

[0055] If there is a pixel in the infrared thermal imaging image data of the target sow's rump with a grayscale value greater than or equal to a third preset threshold, then that pixel is determined as a target point. The target range is determined based on the target point, and the target range needs to include all target points in the current frame of infrared thermal imaging image data. A target search box is established based on the target range, and the coordinates of the upper left and lower right corners of the target search box are calculated. The change amplitude of the upper left and lower right corner coordinates of the target search box is calculated based on the upper left and lower right corner coordinates, respectively. It is determined whether the sum of the change amplitudes of the upper left and lower right corner coordinates of the target search box is less than or equal to a fourth preset threshold, and a signal related to the estrus of the target sow is output based on the determination result.

[0056] It should be noted that if there are pixels with a grayscale value greater than or equal to the third preset threshold in the infrared thermal imaging data of the target sow's rump, it proves that the pixel is a pixel of the target sow's rump; otherwise, the pixel is an environmental pixel.

[0057] Specifically, the method includes:

[0058] If the sum of the changes in the upper left and lower right corner coordinates of the target search box is less than or equal to the fourth preset threshold, the target sow's estrus signal will be output.

[0059] It should be noted that if the sum of the changes in the upper left and lower right corner coordinates of the target search box is less than or equal to the fourth preset threshold, a signal indicating estrus in the target sow is output. This confirms that the target sow exhibits a standing reflex, and the output of the estrus signal enables intelligent estrus detection in sows, simplifying the complex problem of intelligent estrus identification and improving the overall intelligence level of the invention.

[0060] Specifically, the method includes:

[0061] If the sum of the changes in the upper left and lower right corner coordinates of the target search box is greater than the fourth preset threshold, output a signal that the target sow has not come into estrus.

[0062] It should be noted that if the sum of the changes in the upper left and lower right corner coordinates of the target search box is greater than the fourth preset threshold, it proves that the target sow's rump does not show a standing reaction. At this time, a signal indicating that the target sow is not in estrus is output, realizing intelligent estrus detection for sows, simplifying the complex problem of intelligent estrus identification for sows, and improving the level of intelligence of the present invention.

[0063] Understandably, this invention, based on traditional experience with sow estrus, utilizes image recognition and mechanical automation technologies to construct a sow estrus detection method, system, and electronic equipment, achieving intelligent estrus detection in sows. This effectively reduces the workload of workers, lowers the entry barrier to the estrus detection industry, and reduces costs. Through ingenious design, this invention innovatively utilizes an infrared thermal imaging camera to collect image sequences of the target sow's body movements, analyzes the image sequences to obtain image sequence data, determines the height of the target sow's back based on the image sequence data, controls a massage module to apply pressure to the target sow's back to simulate a boar lying on its back and massaging the target sow's udder, further analyzes and judges the image sequence data, and outputs signals related to the target sow's estrus based on the judgment results. This simplifies the complex problem of intelligent sow estrus detection, eliminating the need for complex algorithm modeling, significantly reducing the application cost of this invention, improving its intelligence level, and greatly expanding its application scenarios.

[0064] Please see Figures 2-3 The present invention provides another specific embodiment, which provides a sow estrus detection system, the system comprising:

[0065] Image acquisition module 100 is used to acquire image sequences of the movements of various parts of the target sow's body;

[0066] Massage module 400 is used to apply pressure to the back of the target sow to simulate a boar lying on its back and massaging the udder of the target sow.

[0067] The positioning module 200 is used to collect the positioning information of the target sow;

[0068] The control module 300 acquires the positioning information of the target sow through the positioning module 200, controls the movement of the massage module based on the positioning information of the target sow, acquires image sequences of the movements of various parts of the target sow's body through the image acquisition module 100, parses the image sequences to obtain image sequence data, determines the height of the target sow's back based on the image sequence data, controls the massage module 400 to apply pressure to the target sow's back to simulate a boar lying on its back and massaging the target sow's udder, further analyzes and judges the image sequence data, and outputs a signal about the target sow's estrus based on the judgment result.

[0069] Specifically, the image acquisition module 100 includes a first infrared thermal imaging camera 3, which is used to acquire image sequences of the ears of the target sow 7.

[0070] Specifically, the image acquisition module 100 further includes a second infrared thermal imaging camera 5, which is used to acquire image sequences of the rump of the target sow 7.

[0071] Understandably, the image acquisition module 100 acquires image sequences of the ears and rump of the target sow 7 and sends them to the control module 300. The control module 300 determines whether the target sow 7 is in estrus based on the movement of its ears and rump. The measurement results are accurate and greatly reduce the workload of the staff.

[0072] Specifically, the image acquisition module 100 also includes a depth camera 4, which is used to determine the height of the sow's back. The control module 300 moves the massage module 400 according to the height of the sow's back and fixes the massage module 400 on the back of the target sow 7.

[0073] Understandably, using depth camera 4 to determine the height of the sow's back results in accurate measurements, greatly improving the reliability and practicality of the invention and further expanding its application scope.

[0074] Specifically, the massage module 400 includes a guide rail 1, a guide rail clamp 2, and a sow fixing device. The guide rail clamp 2 is disposed on the guide rail 1. The control module 300 is connected to the guide rail clamp 2 and controls the guide rail clamp 2 to move on the guide rail 1.

[0075] Specifically, the sow restraint device includes a massage pad 6 and an electric telescopic device. The massage pad 6 is fixedly connected to one end of the electric telescopic device, and the other end of the electric telescopic device is fixedly connected to the guide rail clamp 2. The control module 300 is connected to the electric telescopic device and controls the extension and retraction of the electric telescopic device.

[0076] Specifically, the massage pad 6 includes a carrying mechanism, which includes a first carrying mechanism 9 and a second carrying mechanism. One end of the first carrying mechanism 9 and the second carrying mechanism are fixedly connected to one end of the electric telescopic device to form a claw-shaped structure for fixing the sow. The second carrying mechanism and the first carrying mechanism 9 are electrically connected to the control module 300, which can control the opening and closing of the first carrying mechanism 9 and the second carrying mechanism.

[0077] It should be noted that the first and second harness mechanisms are made of metal. After the control module 300 controls the first and second harness mechanisms to close, the control module 300 controls the electric telescopic rod to extend one end to apply pressure to the back of the target sow 7, simulating a boar lying on its back, which better enables the identification of the sow's estrus. This further improves the practicality and reliability of the invention, eliminates the need for manual back pressing, greatly reduces the workload of staff, and saves a significant amount of labor costs.

[0078] Specifically, the other end of the first shoulder strap mechanism 9 and the second shoulder strap structure are provided with an adhesive structure 12 for bonding to each other after the first shoulder strap mechanism 9 and the second shoulder strap mechanism are closed.

[0079] Understandably, this arrangement can further improve the stability and robustness of the first shoulder strap mechanism 9 and the second shoulder strap mechanism after they are closed, thereby further improving the reliability of the present invention.

[0080] Specifically, an abdominal belt 8 is provided on the first carrying strap mechanism 9 and / or near the adhesive structure 12, and a massage device 10 is provided on the abdominal belt 8. After the first carrying strap mechanism 9 and the second carrying strap mechanism are bonded together, the massage device 10 is located at the udder of the sow.

[0081] Specifically, the abdominal belt 8 is also provided with an elastic switch 11, which is electrically connected to the massage device 10. When the first carrying belt mechanism 9 and the second carrying belt mechanism are bonded together, the elastic switch 11 is turned on by the tightening pressure from the sow, and the massage device 10 is turned on. When the first carrying belt mechanism 9 and the second carrying belt mechanism are opened, the pressure disappears, the elastic switch 11 is turned off, and the massage device 10 stops.

[0082] Understandably, this setting enables the massage device 10 to start and stop automatically without manual intervention, further reducing the workload of staff and further improving the usability and practicality of the invention.

[0083] It should be noted that the control module 300 in this embodiment includes a PC, and the positioning module 200 includes an NFC chip. The PC is used for training the estrus detection model, transmitting commands, storing and summarizing data, recording sow estrus, and notifying farmers of sow mating. The NFC chip is used for pig identification. The estrus detection device includes a massage pad 6 with back pressure, a first infrared thermal imaging camera 3, a second infrared thermal imaging camera 5, a guide rail 1, a guide rail clamp 2, and a depth camera 4. The massage pad 6 with back pressure is positioned on the sow's back, simulating the pressure of a real boar. When the device is running, a command is initiated through the PC, and the massage device 10 is precisely positioned above the sow via the guide rail 1. At the same time, the NFC chip identifies the pig, and the depth camera 4 determines the height of the target sow's back. Then, the height of the pad is automatically adjusted according to the height, automatically clamping the target sow's back, and activating the massage device 10 with the massage pad 6 to massage the target sow's udder. The first infrared thermal imaging camera 3 captures images of changes in the ears of the target sow 7, while the second infrared thermal imaging camera 5 captures images of the sow 7's rump and overall movement from different angles. The captured data is uploaded to a PC for processing to determine whether the sow consistently exhibits erect ears and standing posture over a certain period. If data processing indicates that the target sow 7 is in estrus, as determined by both the first and second infrared thermal imaging cameras, the sow is considered to be in estrus. The sow is then marked as being in estrus on the PC, and the farmer is notified to breed her.

[0084] Image data of the ears and body of the target sow 7 are acquired by the first infrared thermal imaging camera 3 and the second infrared thermal imaging camera 5. The acquired first sample image dataset is input into the estrus detection model, and the estrus detection model is trained and corrected until the estrus detection model reaches the set threshold. The second sample image dataset is input into the estrus detection model for verification. If the verification is successful, the estrus detection model is obtained. If the estrus detection model does not reach the threshold, regression training is performed until the estrus detection model is verified and the final estrus detection model is obtained.

[0085] A massage pad 6 with back pressure is used to simulate the back pressure of a boar and is located between the first infrared thermal imaging camera 3 and the second infrared thermal imaging camera 5. The depth camera 4 is mainly used to identify the height of the sow's back and waist, and then automatically adjust the height of the pad according to the height, automatically clamping the sow's back and waist, and performing the corresponding massage.

[0086] The first infrared thermal imaging camera 3 captures changes in the ears of the target sow 7 to determine whether the sow's ears are erect. The second infrared thermal imaging camera 5 captures changes in the sow's rump to determine whether the sow's rump is still.

[0087] Guide rail 1 and guide rail caliper 2 are made of stainless steel.

[0088] The specific working process of this invention embodiment is as follows:

[0089] like Figures 1-3 As shown, the massage pad 6, the infrared thermal imaging camera, and the second infrared thermal imaging camera 5 of the present invention are fixed to the guide rail 1 by the guide rail clamp 2. The massage pad 6 is located at the sow's back. The depth camera 4 is used to identify the height of the sow's back and then automatically adjust the height of the pad according to the height, so that it automatically clamps the sow's back and performs the corresponding massage. The first infrared thermal imaging camera 3 is aimed at the sow's ear, and the second infrared thermal imaging camera 5 is aimed at the sow's rump.

[0090] (1) When the system starts up, the equipment is automatically powered on, connected to the database and the Internet, and prepares for data storage. The entire system can be controlled through a mobile APP or client.

[0091] (2) Install guide rail clamps 2 on guide rail 1 and install massage pads 6 on guide rail clamps 2. The height of the sow’s back is identified by depth camera 4. Then the height of the pads is automatically adjusted according to the height, automatically clamping the sow’s back and massaging the sow with the massage body. This is used to massage the sow’s udder and simulate the back pressing process of a boar.

[0092] (3) Two infrared thermal imaging cameras are installed in front of and behind the massage pad 6 respectively. The first infrared thermal imaging camera 3 is aimed at the sow's ear and the second infrared thermal imaging camera 5 is aimed at the sow's buttocks. The information images of the sow when she is being massaged by the massage pad 6 are collected. The images are then transmitted to the database and the database is connected to the Internet so that the recognition results can be viewed through APP and web pages.

[0093] (4) The estrus status of the sow is determined by the first infrared thermal imaging camera 3 and the second infrared thermal imaging camera 5. If the first infrared thermal imaging camera 3 determines that the sow's ears are erect and the second infrared thermal imaging camera 5 determines that the sow's buttocks are still, then the sow being tested is determined to be in estrus.

[0094] (5) Store the measured data on the PC, analyze the estrus cycle of sows, and notify the farmers to mate the sows in estrus.

[0095] In a preferred embodiment, this application also provides an electronic device, the electronic device comprising:

[0096] The computer device includes a memory and a processor, wherein the memory stores computer-readable instructions that, when executed by the processor, implement the sow estrus detection method. The computer device can be broadly categorized as a server, terminal, or any other electronic device with the necessary computing and / or processing capabilities. In one embodiment, the computer device may include a processor, memory, network interface, communication interface, etc., connected via a system bus. The processor of the computer device can be used to provide the necessary computing, processing, and / or control capabilities. The memory of the computer device may include a non-volatile storage medium and internal memory. The non-volatile storage medium may store an operating system, computer programs, etc. The internal memory can provide an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The network interface and communication interface of the computer device can be used to connect and communicate with external devices via a network. When the computer program is executed by the processor, it performs the steps of the method of the present invention.

[0097] This invention can be implemented as a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, causes the steps of the methods of embodiments of the invention to be performed. In one embodiment, the computer program is distributed across multiple network-coupled computer devices or processors, such that the computer program is stored, accessed, and executed in a distributed manner by one or more computer devices or processors. A single method step / operation, or two or more method steps / operations, may be executed by a single computer device or processor or by two or more computer devices or processors. One or more method steps / operations may be executed by one or more computer devices or processors, and one or more other method steps / operations may be executed by one or more other computer devices or processors. One or more computer devices or processors may execute a single method step / operation, or execute two or more method steps / operations.

[0098] Those skilled in the art will understand that the method steps of this invention can be performed by a computer program instructing related hardware, such as a computer device or processor, to perform the steps of this invention when executed. Depending on the context, any references herein to memory, storage, databases, or other media may include non-volatile and / or volatile memory. Examples of non-volatile memory include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, magnetic tape, floppy disk, magneto-optical data storage device, optical data storage device, hard disk, solid-state drive, etc. Examples of volatile memory include random access memory (RAM), external cache memory, etc.

[0099] The technical features described above can be combined arbitrarily. Although not all possible combinations of these technical features are described, any combination of these technical features should be considered to be covered by this specification, provided that such combination does not contain contradictions.

[0100] The specific embodiments of the present invention described above do not constitute a limitation on the scope of protection of the present invention. Any other corresponding changes and modifications made in accordance with the technical concept of the present invention should be included within the scope of protection of the claims of the present invention.

Claims

1. A sow estrus detection method, characterized by, The method comprises the following steps: The positioning information of the target sow is collected by the positioning module, and the positioning information of the target sow is obtained by the control module. The control module controls the massage module to move according to the positioning information of the target sow. The image sequence of the movement of each part of the body of the target sow is collected by the image collection module. The image sequence data is obtained by analyzing the image sequence. The height of the back of the target sow is determined according to the image sequence data. The control module controls the massage module to apply pressure to the back of the target sow to simulate the lying back of a boar and massage the udder of the target sow. The image sequence data is further analyzed and judged, and a signal related to the estrus of the target sow is output according to the judgment result.

2. The sow estrus detection method of claim 1, wherein The image sequence of the movement of each part of the body of the target sow collected by the image collection module comprises: The infrared thermal imaging camera group in the image collection module collects the infrared thermal imaging image sequence of each part of the body of the target sow. The infrared thermal imaging camera group comprises a first infrared thermal imaging camera. The first infrared thermal imaging camera is used to collect the image sequence of the ear of the target sow. The image collection module further comprises a second infrared thermal imaging camera. The second infrared thermal imaging camera is used to collect the image sequence of the hip of the target sow.

3. The sow estrus detection method of claim 2, wherein The method further comprises: If there is a pixel point with a gray value greater than or equal to a first preset threshold in the infrared thermal imaging image data of the ear of the target sow, the pixel point is determined as a target point. The target range is determined according to the target point. The target range needs to include all target points in the current frame of infrared thermal imaging image data. The target search box is established according to the target range, and the left upper corner coordinates and the right lower corner coordinates of the target search box are calculated. The change amplitudes of the left upper corner coordinates and the right lower corner coordinates of the target search box are calculated respectively according to the left upper corner coordinates and the right lower corner coordinates of the target search box. It is judged whether the sum of the change amplitudes of the left upper corner coordinates and the right lower corner coordinates of the target search box is less than or equal to a second preset threshold. A signal related to the estrus of the target sow is output according to the judgment result.

4. The sow estrus detection method of claim 3, wherein The method further comprises: If the sum of the change amplitudes of the left upper corner coordinates and the right lower corner coordinates of the target search box is less than or equal to the second preset threshold, the signal that the target sow is in estrus is output.

5. The sow estrus detection method of claim 4, wherein The method further comprises: If the sum of the change amplitudes of the left upper corner coordinates and the right lower corner coordinates of the target search box is greater than the second preset threshold, the signal that the target sow is not in estrus is output.

6. The sow estrus detection method of claim 2, wherein The method further comprises: If there is a pixel point with a gray value greater than or equal to a third preset threshold in the infrared thermal imaging image data of the hip of the target sow, the pixel point is determined as a target point. The target range is determined according to the target point. The target range needs to include all target points in the current frame of infrared thermal imaging image data. The target search box is established according to the target range, and the left upper corner coordinates and the right lower corner coordinates of the target search box are calculated. The change amplitudes of the left upper corner coordinates and the right lower corner coordinates of the target search box are calculated respectively according to the left upper corner coordinates and the right lower corner coordinates of the target search box. It is judged whether the sum of the change amplitudes of the left upper corner coordinates and the right lower corner coordinates of the target search box is less than or equal to a fourth preset threshold. A signal related to the estrus of the target sow is output according to the judgment result.

7. The sow estrus detection method of claim 6, wherein The method comprises: If the sum of the change amplitudes of the top-left corner coordinate and the bottom-right corner coordinate of the target search box is less than or equal to a fourth preset threshold, a signal indicating that the target sow is in estrus is output.

8. The sow estrus detection method of claim 1, wherein The method comprises: If the sum of the change amplitudes of the top-left corner coordinate and the bottom-right corner coordinate of the target search box is greater than the fourth preset threshold, a signal indicating that the target sow is not in estrus is output.

9. A sow estrus detection system characterized by, The method comprises: An image acquisition module is configured to acquire an image sequence of movements of each part of the body of the target sow; A massage module is configured to apply pressure to the back of the target sow to simulate a boar lying on its back and massage the udder of the target sow; A positioning module is configured to acquire positioning information of the target sow; A control module is configured to acquire the positioning information of the target sow by the positioning module, obtain the positioning information of the target sow, control the massage module to move according to the positioning information of the target sow, acquire the image sequence of movements of each part of the body of the target sow by the image acquisition module, analyze the image sequence to obtain image sequence data, determine the height of the back of the target sow according to the image sequence data, control the massage module to apply pressure to the back of the target sow to simulate a boar lying on its back and massage the udder of the target sow, further analyze and judge the image sequence data, and output a signal about estrus of the target sow according to the judgment result.

10. An electronic device, comprising: The method comprises: A memory; and a processor, wherein the memory stores computer readable instructions, and the computer readable instructions are executed by the processor to implement the sow estrus recognition method according to any one of claims 1 to 8.

Images