Intelligent cattle abnormal sign detection station and cattle abnormal sign detection method

Abstract

The invention provides an intelligent detection station and method for abnormal signs of cattle, and relates to the technical field of agricultural cultivation, and the method comprises the steps: a label sensor is used for obtaining an identification label of a to-be-detected cattle under the condition that the to-be-detected cattle is close to a cattle lick block; the image sensor is used for acquiring a detection image of a cattle to be detected; the infrared sensor is used for acquiring an infrared image of a cattle to be detected; the gas sensor is used for detecting gas exhaled by the to-be-detected cattle and determining respiration characteristics of the to-be-detected cattle; the data processor is used for determining identity information of the cattle to be detected based on the identification tag; based on at least one of the detection image, the infrared image and the breathing feature, determining a physical sign detection result of the cattle to be detected; and associating the physical sign detection result with the identity information. According to the detection station and method provided by the invention, the detection cost of the abnormal signs of the cattle is reduced; the detection accuracy of the abnormal signs of the cattle is improved; and the detection efficiency of the abnormal signs of the cattle is improved.

Description

Technical Field

[0001] The present application relates to the field of agricultural breeding technology, and in particular to an intelligent detection station for abnormal physical signs of cattle and a method for detecting abnormal physical signs of cattle. Background Art

[0002] In traditional cattle breeding practices, the detection of abnormal signs of cattle mostly depends on the experience of farmers and regular manual inspections. This method is not only labor-intensive, but also inefficient, and it is difficult to achieve real-time monitoring of abnormal signs of cattle. Especially in large-scale farms, detailed monitoring of individual cattle is almost an impossible task, which can easily lead to delayed treatment of diseases and low management efficiency. Therefore, real-time monitoring of abnormal signs of cattle is particularly important.

[0003] In the related art, abnormal signs of cattle are detected by installing sensors or detection equipment on cattle. These sensors or detection equipment need to be worn on cattle, which brings inconvenience to cattle's activities and easily causes discomfort. They are also costly and are not suitable for large-scale cattle farms.

[0004] Therefore, how to reduce the cost of detecting abnormal physical signs of cattle and improve the efficiency of detecting abnormal physical signs of cattle has become a technical problem that needs to be urgently solved in the industry. Summary of the invention

[0005] The present application provides an intelligent detection station for abnormal physical signs of cattle and a method for detecting abnormal physical signs of cattle, which are used to solve the technical problem of how to reduce the detection cost of abnormal physical signs of cattle and improve the detection efficiency of abnormal physical signs of cattle.

[0006] The present application provides an intelligent detection station for abnormal physical signs of cattle, comprising a detection station body, and a cattle licking brick, a tag sensor, an image sensor, an infrared sensor, a gas sensor and a data processor arranged in the detection station body; The tag sensor is used to obtain the identification tag of the cattle to be detected when the cattle to be detected are close to the cattle licking brick; The image sensor is used to obtain the detection image of the cattle to be detected; The infrared sensor is used to obtain the infrared image of the cattle to be detected; The gas sensor is used to detect the gas exhaled by the cattle to be detected and determine the breathing characteristics of the cattle to be detected; The data processor is connected to the tag sensor, the image sensor, the infrared sensor and the gas sensor, and is used to determine the identity information of the cattle to be detected based on the identification tag; determine the physical sign detection result of the cattle to be detected based on at least one of the detection image, the infrared image and the respiratory characteristics; and associate the physical sign detection result with the identity information.

[0007] In some embodiments, the data processor is configured to: Recognizing the detection image to determine the facial features of the cattle to be detected; Identify the infrared image to determine the body temperature characteristics of the cattle to be detected; Based on at least one of the facial features, the body temperature features and the respiratory features, the physical sign detection results of the cattle to be detected are determined.

[0008] In some embodiments, the data processor is configured to: When the tag sensor senses identification tags of multiple cattle to be detected, target recognition is performed on the detection image to determine the image area corresponding to each cattle to be detected in the detection image; Perform feature extraction on the image area corresponding to each cow to be detected, and determine the head feature and / or facial feature of each cow to be detected; Based on the head features and / or facial features of each cattle to be detected, the identity information of each cattle to be detected is determined.

[0009] In some embodiments, the data processor is configured to: When the tag sensor senses identification tags of multiple cattle to be detected, target recognition is performed on the detection image to determine the image area corresponding to each cattle to be detected in the detection image; Based on the image area corresponding to each to-be-detected cattle and the pixel correspondence relationship between the detection image and the infrared image, determine the image area corresponding to each to-be-detected cattle in the infrared image; Based on the pixel value of each cow to be detected in the image area corresponding to the infrared image, the body temperature characteristics of each cow to be detected are determined.

[0010] In some embodiments, the detection station body is a semi-enclosed structure.

[0011] In some embodiments, an air suction device is further included; the air suction device is arranged above the outside of the detection station body; the gas sensor is arranged above the inside of the detection station body; the air suction port of the air suction device is arranged on the side of the gas sensor.

[0012] The present application provides a method for detecting abnormal physical signs of cattle, which is applied to the intelligent detection station for abnormal physical signs of cattle, comprising: When the identification tag of the cattle to be detected is sensed, the image sensor is controlled to obtain the detection image of the cattle to be detected, the infrared sensor is controlled to obtain the infrared image of the cattle to be detected, and the gas sensor is controlled to obtain the breathing characteristics of the cattle to be detected; Based on the identification tag, determining the identity information of the cattle to be detected; Determine the physical sign detection result of the cattle to be detected based on at least one of the detection image, the infrared image and the breathing characteristics; The physical sign detection result is associated with the identity information.

[0013] In some embodiments, determining the identity information of the cattle to be detected based on the identification tag includes: In the case where there are multiple identification tags, target recognition is performed on the detection image to determine the image area corresponding to each cow to be detected in the detection image; Perform feature extraction on the image area corresponding to each cow to be detected, and determine the head feature and / or facial feature of each cow to be detected; Determine identification features of each cattle to be detected based on head features and / or facial features of each cattle to be detected; Based on the identification features of each cattle to be detected, and the identification features and identity information of multiple identified cattle, the identity information of each cattle to be detected is determined.

[0014] The present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the method for detecting abnormal physical signs of cattle is implemented when the processor executes the computer program.

[0015] The present application provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for detecting abnormal physical signs of cattle is implemented.

[0016] The present application provides an intelligent detection station for abnormal physical signs of cattle and a method for detecting abnormal physical signs of cattle, comprising a detection station body, and a cattle licking brick, a tag sensor, an image sensor, an infrared sensor, a gas sensor and a data processor arranged in the detection station body; the tag sensor is used to obtain the identification tag of the cattle to be detected; the image sensor is used to obtain the detection image of the cattle to be detected; the infrared sensor is used to obtain the infrared image of the cattle to be detected; the gas sensor is used to determine the respiratory characteristics of the cattle to be detected; the data processor is used to determine the identity information of the cattle to be detected; and the detection image, the infrared image and the respiratory characteristics are used to obtain the detection image of the cattle to be detected. at least one, to determine the results of the vital signs test of the cattle to be tested; to associate the vital signs test results with the identity information; because the cattle are attracted to gather near the testing station through the cow licking bricks, a one-stop cattle multi-vital signs test is achieved, and there is no need for the cattle to wear vital signs detection equipment, which not only avoids the discomfort caused by the cattle's activities, but also reduces the cost of detecting abnormal vital signs of cattle in the farm; different types of vital signs detection equipment can be set up in the station, and abnormal vital signs can be determined according to the results of multi-vital signs detection, thereby improving the accuracy of detecting abnormal vital signs of cattle; because there is no need to manually test the cattle one by one, the efficiency of detecting abnormal vital signs of cattle is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0018] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0019] Figure 1 This is one of the structural schematic diagrams of the intelligent detection station for abnormal physical signs of cattle provided in this application.

[0020] Figure 2 This is the second structural schematic diagram of the intelligent detection station for abnormal physical signs of cattle provided in this application.

[0021] Figure 3 It is a schematic diagram of the process of the method for detecting abnormal physical signs of cattle provided in this application.

[0022] Figure 4 It is a structural schematic diagram of the electronic device provided by this application. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0024] It should be noted that the terms "first", "second" etc. in the present application are used to distinguish similar objects, and need not be used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable in appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, the process, method, system, product or equipment comprising a series of steps or units or modules need not be limited to those steps or units or modules clearly listed, but may include other steps or units or modules that are not clearly listed or inherent to these processes, methods, products or equipment.

[0025] As the scale of cattle breeding continues to expand, the degree of automation in dairy farms continues to improve. If each cow needs to be equipped with detection equipment to detect abnormal characteristics, the cost is still very high; the detection equipment fixed on the cow is likely to cause discomfort to the cow; the number and types of detection equipment worn by cows are also relatively limited, and it is impossible to accurately detect abnormal signs of cows.

[0026] In order to solve the shortcomings of related technologies, Figure 1 This is one of the structural schematic diagrams of the intelligent detection station for abnormal physical signs of cattle provided in this application, such as Figure 1 As shown, the intelligent detection station 100 for abnormal vital signs of cattle includes a detection station body 110 , and a cattle licking brick 120 , a tag sensor 130 , an image sensor 140 , an infrared sensor 150 , a gas sensor 160 and a data processor 170 arranged in the detection station body 110 .

[0027] A tag sensor is used to obtain the identification tag of the cattle to be detected when the cattle to be detected are close to the cattle licking brick; An image sensor, used for acquiring a detection image of the cattle to be detected; Infrared sensor, used to obtain infrared images of the cattle to be detected; A gas sensor is used to detect the gas exhaled by the cattle to be tested and determine the breathing characteristics of the cattle to be tested; The data processor is connected to the tag sensor, the image sensor, the infrared sensor and the gas sensor, and is used to determine the identity information of the cattle to be detected based on the identification tag; determine the physical sign detection result of the cattle to be detected based on at least one of the detection image, the infrared image and the respiratory characteristics; and associate the physical sign detection result with the identity information.

[0028] Specifically, the intelligent detection station for abnormal vital signs of cattle provided in the embodiment of the present application is suitable for both large-scale farms and small and medium-sized farms.

[0029] Cow lick bricks refer to salt bricks containing minerals and trace elements. Cows can supplement salt and mineral nutrients by licking cow lick bricks. The intelligent detection station for abnormal signs of cattle provided in the embodiment of the present application, also called an intelligent detection station, utilizes the tendency of cattle to lick bricks to attract and gather breeding cattle. When licking cow lick bricks, various data of the cattle's body are obtained at close range for the detection of abnormal signs. Physical signs refer to vital signs, which can be used to indicate the health status of cattle. Abnormal signs may include facial disease characteristics, abnormal body temperature, abnormal ketone bodies, etc.

[0030] In a farm, cattle are usually equipped with identification tags on their ears. The identification tags can be radio frequency identification (RFID) tags. The tag sensor is set near the cattle licking brick in the intelligent detection station, and the height from the ground is set according to the height of the cattle's ears from the ground to increase the success rate of sensing the identification tag. When the cattle to be detected enter the intelligent detection station and approach the cattle licking brick, the tag sensor can obtain the identification tag by induction. The identification tag can be used to record the identity information of the cattle to be detected, such as age and gender.

[0031] The image sensor may be a red green blue (RGB) camera or a video camera, which is used to obtain the detection image of the cattle to be detected. In order to obtain a better acquisition field of view, the image sensor may be set at an upper position inside the intelligent detection station.

[0032] The infrared sensor can use an infrared camera to capture the infrared radiation emitted by the cattle to form an image, thereby obtaining an infrared image of the cattle to be tested. In order to obtain a better collection field of view, the infrared sensor can be set at the upper position inside the intelligent testing station.

[0033] The gas sensor is used to detect the gas exhaled by the cow to be tested and determine the respiratory characteristics of the cow to be tested. Respiratory characteristics refer to the physical signs of the cow when breathing air. For example, if it is necessary to detect whether the cow has ketosis, the gas sensor can be configured as an acetone gas sensor. The gas exhaled by the cow to be tested when licking the brick is tested to detect the acetone component.

[0034] The intelligent detection station is also provided with a data processor. The tag sensor, image sensor, infrared sensor and gas sensor are all connected to the data sensor to send the identification tag, detection image, infrared image and breathing characteristics of the cattle to be detected to the data processor.

[0035] The data processor can determine the identity information of the cattle to be detected based on the identification tag. For example, the data processor can match the identification tag of the cattle to be detected with the identification tags of cattle with known identity information stored in the database, and determine the identity information of the cattle to be detected based on the matching result.

[0036] The data processor can store relevant algorithms, process the detection images, infrared images and respiratory characteristics, and determine the physical sign detection results of the cattle to be detected. The physical sign detection results can include normal or abnormal. For example, the facial features of the cattle in the detection image can be identified to determine whether there are secretions in the mouth of the cattle, whether there are secretions such as snot in the nose, whether there are sunken eyes, etc., so as to determine whether the cattle to be detected have abnormal signs such as diseases; the pixel values ​​in the infrared image can be analyzed to determine whether the cattle to be detected have abnormal signs such as high body temperature; the respiratory characteristics can be analyzed to determine whether some gases exceed normal values, so as to determine whether the cattle to be detected have abnormal signs such as respiratory diseases.

[0037] The data processor can associate the vital sign detection results with the identity information, thereby realizing the abnormal vital sign detection of each cattle in the farm.

[0038] The embodiment of the present application provides an intelligent detection station for abnormal signs of cattle, including a detection station body, and a cattle licking brick, a tag sensor, an image sensor, an infrared sensor, a gas sensor and a data processor arranged in the detection station body; the tag sensor is used to obtain the identification tag of the cattle to be detected; the image sensor is used to obtain the detection image of the cattle to be detected; the infrared sensor is used to obtain the infrared image of the cattle to be detected; the gas sensor is used to determine the respiratory characteristics of the cattle to be detected; the data processor is used to determine the identity information of the cattle to be detected; according to at least one of the detection image, the infrared image and the respiratory characteristics, Determine the results of the physical sign detection of the cattle to be detected; associate the physical sign detection results with the identity information; because the cattle are attracted to gather near the detection station through cattle licking bricks, a one-stop cattle multi-physical sign detection is achieved, and there is no need for the cattle to wear physical sign detection equipment, which not only avoids discomfort to the cattle's activities, but also reduces the cost of detecting abnormal physical signs of cattle in the farm; different types of physical sign detection equipment can be set up in the station, and abnormal physical signs can be determined according to the results of multi-physical sign detection, thereby improving the accuracy of detecting abnormal physical signs of cattle; because there is no need to manually detect cattle one by one, the efficiency of detecting abnormal physical signs of cattle is improved.

[0039] In some embodiments, the data processor is configured to: Identify the detection image and determine the facial features of the cattle to be detected; Identify infrared images and determine the body temperature characteristics of the cattle to be tested; Based on at least one of facial features, body temperature features and respiratory features, the physical sign detection results of the cattle to be detected are determined.

[0040] Specifically, facial features refer to the signs shown on the face of the cattle. The data processor can identify the detection image, determine whether there are secretions in the mouth of the cattle, whether there are secretions such as snot in the nose, whether there are sunken eyes and other facial features, so as to determine whether the cattle to be detected have abnormal signs such as diseases. For example, the data processor can detect the key points of the cattle's face in the detection image, and determine the regional images of the cattle's mouth, nose and eyes based on the key points obtained by identification. Then the detection image is segmented, and the segmented mouth area image, nose area image and eye area image are respectively input into the pre-trained neural network model, and abnormal signs are detected by the neural network model. These neural network models can be obtained by pre-training with sample images and abnormal sign labels corresponding to the sample images.

[0041] Body temperature characteristics refer to physical signs manifested by the body temperature of cattle. The data processor can identify the infrared image and determine the body temperature characteristics of the cattle to be detected through the correspondence between the pixel values ​​of each pixel point in the infrared image and the body temperature value of the cattle. For example, if the pixel values ​​of multiple pixels in a region of the infrared image exceed the pixel values ​​of the pixels corresponding to the normal body temperature, it can be determined that the body temperature of the cattle to be detected is abnormal.

[0042] The data processor can determine the physical sign detection result of the cattle to be detected based on at least one of the facial features, body temperature features and respiratory features. In order to improve the accuracy of the detection, the data processor sets a credibility weight for each feature, and determines the physical sign detection result based on the weighted sum of each feature and the credibility weight.

[0043] The intelligent detection station for abnormal physical signs of cattle provided in the embodiment of the present application determines the physical sign detection results of the cattle to be detected based on at least one of facial features, body temperature characteristics and respiratory characteristics, thereby improving the detection accuracy of abnormal physical signs of cattle.

[0044] In some embodiments, the data processor is configured to: When the tag sensor senses identification tags of multiple cattle to be detected, target recognition is performed on the detection image to determine the image area corresponding to each cattle to be detected in the detection image; Perform feature extraction on the image area corresponding to each cow to be detected, and determine the head feature and / or facial feature of each cow to be detected; Based on the head features and / or facial features of each cattle to be detected, the identity information of each cattle to be detected is determined.

[0045] Specifically, when multiple cows enter the intelligent detection station, the tag sensor senses the identification tags of multiple cows to be detected. At this time, it is still impossible to distinguish the multiple cows to be detected. Accordingly, the detection image collected by the image sensor may also contain multiple cows to be detected.

[0046] The target recognition algorithm can be run in the data processor to perform target recognition on each detection image to determine the image area corresponding to each to-be-detected cow in the detection image. Feature extraction is performed on the image area corresponding to each to-be-detected cow to determine the head feature and / or facial feature of each to-be-detected cow.

[0047] The head features and facial features here are mainly used to identify the identity of each cow to be detected. Since the head features or facial features of each cow are different, the identity information of the cow to be detected can be identified based on the head features or facial features. For example, first collect multi-angle head images of each cow to construct an independent data set for each cow, establish a cow database, train to form a spatial feature subset of each cow, and after sensing the identification tags of multiple cows, obtain the local head map of each cow from the image obtained by the image sensor, extract the spatial feature subset of each cow in the cow database, and calculate the comparison similarity separately to achieve accurate identification.

[0048] The intelligent detection station for abnormal vital signs of cattle provided in the embodiment of the present application determines the identity information of each cattle through image recognition method when the tag sensor senses the identification tags of multiple cattle to be detected, thereby improving the detection accuracy of abnormal vital signs of cattle.

[0049] In some embodiments, the data processor is configured to: When the tag sensor senses identification tags of multiple cattle to be detected, target recognition is performed on the detection image to determine the image area corresponding to each cattle to be detected in the detection image; Based on the image area corresponding to each cow to be detected and the pixel correspondence relationship between the detection image and the infrared image, determine the image area corresponding to each cow to be detected in the infrared image; The body temperature characteristics of each cow to be detected are determined based on the pixel values ​​in the image areas corresponding to each cow to be detected in the infrared image.

[0050] Specifically, when multiple cows enter the intelligent detection station, the tag sensor senses the identification tags of multiple cows to be detected. At this time, it is still impossible to distinguish the multiple cows to be detected, and it is also impossible to detect the body temperature of each cow to be detected. At this time, the body temperature characteristics of each cow to be detected can be determined by comprehensive analysis of the detection image and the infrared image.

[0051] The detection image may be subjected to target recognition to determine the image area corresponding to each cow to be detected in the detection image, which has been described in the above embodiment and will not be repeated here.

[0052] Since both the image sensor and the infrared sensor are installed in the intelligent detection station, images of the cattle entering the detection are collected. The two have the same field of view, which makes a corresponding relationship between the pixels in the detection image and the pixels in the infrared image. The former represents visible light information through pixel values, and the latter represents infrared information through pixel values.

[0053] According to the pixel correspondence between the detection image and the infrared image, and the image area corresponding to each cow to be detected, the image area corresponding to each cow to be detected in the infrared image can be determined.

[0054] By calculating the pixel values ​​in the image area corresponding to each cow to be detected in the infrared image, the body temperature characteristics of each cow to be detected can be determined.

[0055] The intelligent detection station for abnormal vital signs of cattle provided in the embodiment of the present application can distinguish the cattle to be detected and determine the body temperature characteristics by detecting the pixel correspondence between the image and the infrared image when the tag sensor senses the identification tags of multiple cattle to be detected, thereby improving the detection accuracy of abnormal vital signs of cattle.

[0056] In some embodiments, the detection station body is a semi-enclosed structure.

[0057] Specifically, the semi-enclosed structure can better protect the various sensors installed inside, and on the other hand, it limits the number of cattle entering the intelligent detection station, reduces the amount of data that the data processor needs to process simultaneously, and improves the accuracy of detecting abnormal physical signs of cattle.

[0058] In some embodiments, the intelligent testing station further comprises an air suction device; the air suction device is arranged above the outside of the testing station body; the gas sensor is arranged above the inside of the testing station body; and the air suction port of the air suction device is arranged on the side of the gas sensor.

[0059] Specifically, the suction device can generate negative pressure above the interior of the detection station body. The gas exhaled by the cow when licking the brick is affected by the negative pressure, rises and contacts the gas sensor, which can improve the accuracy of respiratory characteristic detection.

[0060] Figure 2 This is the second structural diagram of the intelligent detection station for abnormal physical signs of cattle provided by this application, such as Figure 2 As shown in the figure, the intelligent detection station mainly consists of a cow licking brick containing minerals and trace elements, a semi-enclosed main structure, an RGB camera, a thermal infrared camera, an acetone gas sensor, an RFID receiver, a processor, etc. When the cow approaches the cow licking brick, the RFID obtains the tag information in the cow's ear tag; the processor uses the RGB camera image to instantiate and identify individual cows, as well as abnormalities such as runny nose and sunken eyes, and uses the thermal infrared camera combined with the RGB image to identify individual cows and obtain the body temperature information of the cow at close range; the gas exhaled by the cow when licking the cow licking brick is sucked by the negative pressure formed by the air pump, and the specific components in the gas are detected by the gas sensor, and the above information is associated to detect cow diseases.

[0061] The embodiment of the present application utilizes the preference of cattle for cattle licking bricks to construct a fixed-point cattle multi-sign detection system including multiple sensors. The cattle licking bricks are semi-enclosed, and when cattle actively go to lick the cattle licking bricks, multiple signs such as abnormal body morphological characteristics, abnormal body temperature, and abnormal exhaled gas can be detected.

[0062] The embodiments of the present application address the problem that the difference between individual cattle images is small, and the misidentification rate is likely to increase when there are a large number of individual cattle. At the same time, RFID cannot distinguish the orientation of cattle within the sensing range. The RFID cattle tag information is combined with the cattle feature matching of the image to achieve accurate individual cattle identification. Multi-angle head images of each cow are collected, and an independent data set for each cow is constructed, and training is performed to form a spatial feature subset for each cow. After RFID obtains several cattle tags within the sensing range, the local image of each cow's head is obtained from the image obtained by the RGB camera, and the cattle spatial feature subset corresponding to the RFID-sensed tag in the database is extracted. After calculating and comparing the similarity, accurate identification is achieved.

[0063] The embodiment of the present application has a built-in acetone gas sensor to detect the exhaled gas of the cow. The acetone gas sensor is placed inside the upper part of the device, and a negative pressure outlet connected to an external suction pump is set on the side. The gas exhaled by the cow when licking the brick is affected by the negative pressure, rises and contacts the acetone gas sensor. The acetone component in the exhaled gas of cows with ketosis can be detected by the acetone gas sensor, realizing the early detection of ketosis in dairy cows.

[0064] The intelligent detection station for abnormal vital signs of cattle provided in the embodiment of the present application realizes one-stop observation of multiple vital signs of cattle, reduces detection costs, improves detection efficiency, and has a reliable structure and strong practicality.

[0065] The method provided in the embodiment of the present application is described below. The method described below and the device described above can be referenced to each other.

[0066] Figure 3 is a flow chart of the method for detecting abnormal physical signs of cattle provided in this application, such as Figure 3 As shown, the method is applied to the data processor in the above-mentioned intelligent detection station for abnormal physical signs of cattle, including step 310, step 320, step 330 and step 340.

[0067] Step 310: when the identification tag of the cattle to be detected is sensed, the image sensor is controlled to obtain the detection image of the cattle to be detected, the infrared sensor is controlled to obtain the infrared image of the cattle to be detected, and the gas sensor is controlled to obtain the breathing characteristics of the cattle to be detected; Step 320: Determine the identity information of the cattle to be detected based on the identification tag; Step 330: Determine the physical sign detection result of the cattle to be detected based on at least one of the detection image, the infrared image and the respiratory characteristics; Step 340: Associating the physical sign detection result with the identity information.

[0068] The method for detecting abnormal vital signs of cattle provided in the embodiment of the present application, when sensing the identification tag of the cattle to be detected, controls the image sensor to obtain the detection image of the cattle to be detected, controls the infrared sensor to obtain the infrared image of the cattle to be detected, and controls the gas sensor to obtain the respiratory characteristics of the cattle to be detected; determines the identity information of the cattle to be detected based on the identification tag; determines the vital sign detection result of the cattle to be detected based on at least one of the detection image, the infrared image and the respiratory characteristics; associates the vital sign detection result with the identity information; because the cattle are attracted to gather near the detection station by the cattle licking bricks, a one-stop multi-vital sign detection of cattle is achieved, and there is no need for the cattle to wear vital sign detection equipment, which not only avoids the discomfort caused by the cattle's activities, but also reduces the detection cost of abnormal vital signs of cattle in the farm; different types of vital sign detection equipment can be set in the station, and abnormal vital signs are determined according to the multi-vital sign detection results, thereby improving the detection accuracy of abnormal vital signs of cattle; because there is no need to manually detect the cattle one by one, the detection efficiency of abnormal vital signs of cattle is improved.

[0069] In some embodiments, determining the identity information of the cattle to be detected based on the identification tag includes: In the case where there are multiple identification tags, target recognition is performed on the detection image to determine the image area corresponding to each cow to be detected in the detection image; Perform feature extraction on the image area corresponding to each cow to be detected, and determine the head feature and / or facial feature of each cow to be detected; Determine identification features of each cattle to be detected based on head features and / or facial features of each cattle to be detected; Based on the identification features of each cattle to be detected, as well as the identification features and identity information of multiple identified cattle, the identity information of each cattle to be detected is determined.

[0070] Specifically, when multiple cows enter the intelligent detection station, the tag sensor senses the identification tags of multiple cows to be detected. At this time, it is still impossible to distinguish the multiple cows to be detected. Accordingly, the detection image collected by the image sensor may also contain multiple cows to be detected.

[0071] The target recognition algorithm can be run in the data processor to perform target recognition on each detection image to determine the image area corresponding to each to-be-detected cow in the detection image. Feature extraction is performed on the image area corresponding to each to-be-detected cow to determine the head feature and / or facial feature of each to-be-detected cow.

[0072] The head features and facial features here are mainly used to identify the identities of each cow to be detected. Since the head features or facial features of each cow are different, the identity information of the cow to be detected can be identified based on the head features or facial features. For example, first collect multi-angle head images of each cow to construct an independent data set for each cow, establish a cow database, and train to form a spatial feature subset of each cow. These cows become identified cows. The cow database not only stores identification features (spatial feature subsets), but also stores identity information. After sensing the identification tags of multiple cows, the local head images of each cow are obtained from the images obtained by the image sensor, and the spatial feature subsets of each identified cow in the cow database are extracted. After calculating and comparing the similarity, accurate identity recognition is achieved.

[0073] The method for detecting abnormal physical signs of cattle provided in the embodiment of the present application determines the identity information of each cattle through image recognition when the tag sensor senses the identification tags of multiple cattle to be detected, thereby improving the accuracy of detecting abnormal physical signs of cattle.

[0074] Figure 4 is a schematic diagram of the structure of the electronic device provided by this application, such as Figure 4 As shown, the electronic device may include: a processor (Processor) 410, a communication interface (Communications Interface) 420, a memory (Memory) 430 and a communication bus (Communications Bus) 440, wherein the processor 410, the communication interface 420, and the memory 430 communicate with each other through the communication bus 440. The processor 410 may call the logic command in the memory 430 to execute the method described in the above embodiment, for example: When the identification tag of the cattle to be detected is sensed, the image sensor is controlled to obtain the detection image of the cattle to be detected, the infrared sensor is controlled to obtain the infrared image of the cattle to be detected, and the gas sensor is controlled to obtain the breathing characteristics of the cattle to be detected; based on the identification tag, the identity information of the cattle to be detected is determined; based on at least one of the detection image, the infrared image and the breathing characteristics, the physical sign detection result of the cattle to be detected is determined; and the physical sign detection result is associated with the identity information.

[0075] In addition, the logical commands in the above-mentioned memory can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several commands to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program code.

[0076] The processor in the electronic device provided in the embodiment of the present application can call the logic instructions in the memory to implement the above method. Its specific implementation method is consistent with the implementation method of the aforementioned method and can achieve the same beneficial effects, which will not be repeated here.

[0077] An embodiment of the present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the methods provided in the above embodiments are implemented.

[0078] Its specific implementation is consistent with the aforementioned method implementation and can achieve the same beneficial effects, so it will not be repeated here.

[0079] An embodiment of the present application provides a computer program product, including a computer program, which implements the above method when executed by a processor.

[0080] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0081] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0082] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. An intelligent detection station for abnormal physical signs of cattle, characterized in that: It includes a detection station body, and a cow licking brick, a tag sensor, an image sensor, an infrared sensor, a gas sensor and a data processor arranged in the detection station body; The tag sensor is used to obtain the identification tag of the cattle to be detected when the cattle to be detected are close to the cattle licking brick; The image sensor is used to obtain the detection image of the cattle to be detected; The infrared sensor is used to obtain the infrared image of the cattle to be detected; The gas sensor is used to detect the gas exhaled by the cattle to be detected and determine the breathing characteristics of the cattle to be detected; The data processor is connected to the tag sensor, the image sensor, the infrared sensor and the gas sensor, and is used to determine the identity information of the cattle to be detected based on the identification tag; Based on at least one of the detection image, the infrared image and the respiratory characteristics, the physical sign detection result of the cattle to be detected is determined; and the physical sign detection result is associated with the identity information.

2. The intelligent detection station for abnormal physical signs of cattle according to claim 1, characterized in that: The data processor is used to: Recognizing the detection image to determine the facial features of the cattle to be detected; Identify the infrared image to determine the body temperature characteristics of the cattle to be detected; Based on at least one of the facial features, the body temperature features and the respiratory features, the physical sign detection results of the cattle to be detected are determined.

3. The intelligent detection station for abnormal signs of cattle according to claim 1, characterized in that: The data processor is used to: When the tag sensor senses identification tags of multiple cattle to be detected, target recognition is performed on the detection image to determine the image area corresponding to each cattle to be detected in the detection image; Perform feature extraction on the image area corresponding to each cow to be detected, and determine the head feature and / or facial feature of each cow to be detected; Based on the head features and / or facial features of each cattle to be detected, the identity information of each cattle to be detected is determined.

4. The intelligent detection station for abnormal physical signs of cattle according to claim 1, characterized in that: The data processor is used to: When the tag sensor senses identification tags of multiple cattle to be detected, target recognition is performed on the detection image to determine the image area corresponding to each cattle to be detected in the detection image; Based on the image area corresponding to each to-be-detected cattle and the pixel correspondence relationship between the detection image and the infrared image, determine the image area corresponding to each to-be-detected cattle in the infrared image; Based on the pixel value of each cow to be detected in the image area corresponding to the infrared image, the body temperature characteristics of each cow to be detected are determined.

5. The intelligent detection station for abnormal physical signs of cattle according to any one of claims 1 to 4, characterized in that: The detection station body is a semi-enclosed structure.

6. The intelligent detection station for abnormal physical signs of cattle according to any one of claims 1 to 4, characterized in that: It also includes an air suction device; the air suction device is arranged above the outside of the detection station body; the gas sensor is arranged above the inside of the detection station body; the air suction port of the air suction device is arranged on the side of the gas sensor.

7. A method for detecting abnormal physical signs of cattle, characterized in that: The intelligent detection station for abnormal physical signs of cattle as described in any one of claims 1 to 6 comprises: When the identification tag of the cattle to be detected is sensed, the image sensor is controlled to obtain the detection image of the cattle to be detected, the infrared sensor is controlled to obtain the infrared image of the cattle to be detected, and the gas sensor is controlled to obtain the breathing characteristics of the cattle to be detected; Based on the identification tag, determining the identity information of the cattle to be detected; Determine the physical sign detection result of the cattle to be detected based on at least one of the detection image, the infrared image and the breathing characteristics; The physical sign detection result is associated with the identity information.

8. The method for detecting abnormal physical signs of cattle according to claim 7, characterized in that: The step of determining the identity information of the cattle to be detected based on the identification tag includes: In the case where there are multiple identification tags, target recognition is performed on the detection image to determine the image area corresponding to each cow to be detected in the detection image; Perform feature extraction on the image area corresponding to each cow to be detected, and determine the head feature and / or facial feature of each cow to be detected; Determine identification features of each cattle to be detected based on head features and / or facial features of each cattle to be detected; Based on the identification features of each cattle to be detected, as well as the identification features and identity information of multiple identified cattle, the identity information of each cattle to be detected is determined.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method for detecting abnormal physical signs of cattle as described in claim 7 or 8 is implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for detecting abnormal physical signs of cattle as described in claim 7 or 8 is implemented.

Images