A method and system for isolating, observing and monitoring livestock

Abstract

The present invention relates to the field of image communication technology, and in particular to a method and system for isolated observation and monitoring of livestock animals, the method comprising: obtaining the movement time period of each livestock animal in the monitoring video of the monitoring device; determining the movement distance sequence and the first movement speed sequence between adjacent time points of each livestock animal in the movement time period; determining the movement characteristics according to the first movement speed sequence and the movement distance sequence; determining the consistency of the movement characteristics of each livestock animal in the common movement time period according to the movement characteristics, the second movement speed sequence of each livestock animal in the common movement time period, and the first movement distance; determining the image acquisition interval according to the consistency, and acquiring the first target video data in the common movement time period from the monitoring video based on the image acquisition interval; transmitting the first target video data to the target device. In this way, the present invention saves the storage space of the monitoring system and improves the data transmission speed.

Description

Technical Field

[0001] The present invention relates to the technical field of image communication, and in particular to a method and system for isolated observation and monitoring of livestock animals. Background Art

[0002] As an important source of protein, the health of livestock is directly related to food safety and public health. In order to prevent the occurrence and spread of animal diseases and ensure the healthy development of animal husbandry, the isolation of livestock has become an indispensable measure. By placing newly introduced livestock or suspected diseased livestock in an isolation area for isolation and monitoring, the spread of the disease can be effectively prevented, healthy animal herds can be protected from infection, and the risk of introduction and spread of pathogens can be reduced. Isolation monitoring can not only detect abnormal problems of livestock in the isolation area in a timely manner, but also ensure the health and normal life of livestock in the isolation area.

[0003] In some scenarios, when a group of livestock animals need to be monitored for group diseases, they are usually gathered together for observation in an isolated area. For example, a group of livestock animals from the same source may carry the same disease, so they need to be collectively observed in the same isolated area. The camera needs to continuously record the video data of the animals in the isolated area, and then transmit all the real-time monitoring video data to the monitoring system for data processing and analysis. However, the amount of data of these video data is generally large, which will occupy a large amount of storage space in the monitoring system. In addition, a large amount of video data will occupy a lot of bandwidth during the transmission process, resulting in slow transmission speed and affecting the timeliness of data processing and analysis. Summary of the invention

[0004] In order to solve the technical problems of excessive storage space occupation and slow video data transmission speed, the present invention aims to provide a method and system for isolated observation and monitoring of livestock, and the technical solutions adopted are as follows:

[0005] An embodiment of the present invention provides an isolated observation and monitoring method for livestock, comprising: obtaining a movement time period of each livestock in a monitoring video of a monitoring device; determining a movement distance sequence and a first movement speed sequence between adjacent time points of each livestock within the movement time period; determining the movement characteristics of each livestock within the movement time period according to the first movement speed sequence and the movement distance sequence of each livestock; determining the consistency of the movement characteristics of each livestock within the common movement time period according to the movement characteristics, a second movement speed sequence of each livestock within the common movement time period, and a first movement distance between corresponding time points of each livestock within the common movement time period, wherein each livestock moves within the common movement time period; determining an image acquisition interval according to the consistency, and acquiring first target video data within the common movement time period from the monitoring video based on the image acquisition interval; and transmitting the first target video data to a target device.

[0006] Optionally, determining the movement characteristics of each livestock animal within the movement time period based on the first movement speed sequence and movement distance sequence of each livestock animal includes: determining the change characteristics of the movement speed of the livestock animal within the movement time period based on the difference between adjacent first movement speeds in the first movement speed sequence and the variance of the first movement speed in the first movement speed sequence; determining the movement characteristics of the livestock animal within the movement time period based on the sum of the second movement distances between adjacent time points in the movement distance sequence, the movement displacement between the first time point to the last time point in the movement distance sequence, the second movement speed within the movement time period, the angle between adjacent first movement speeds in the first movement speed sequence, and the change characteristics.

[0007] Optionally, determining the changing characteristics of the movement speed of livestock during the movement time period based on the difference between adjacent first movement speeds in the first movement speed sequence and the variance of the first movement speed in the first movement speed sequence includes: superimposing the first difference between adjacent first movement speeds in the first movement speed sequence to obtain a first superimposed value; and determining the first product of the first superimposed value and the variance as the changing characteristics of the movement speed.

[0008] Optionally, determining the movement characteristics of livestock within the movement time period based on the sum of the second movement distances between adjacent time points in the movement distance sequence, the movement displacement between the first time point to the last time point in the movement distance sequence, the second movement speed within the movement time period, the angle between adjacent first movement speeds in the first movement speed sequence, and the change characteristics includes: calculating the second product between the second movement speed within the movement time period and the change characteristics, and the second difference between the sum of the second movement distances between adjacent time points and the movement displacement; superimposing the angles between adjacent first movement speeds in the first movement speed sequence to obtain a second superposition value, and calculating the third product of the second superposition value and the second difference; adding the third product to a preset value to obtain an added value, and determining a first ratio of the second product to the added value as the movement characteristic of livestock within the movement time period.

[0009] Optionally, determining the consistency of the motion characteristics of each livestock animal within the common motion time period based on the motion characteristics, the second motion speed sequence of each livestock animal within the common motion time period, and the first motion distance between corresponding time points of each livestock animal within the common motion time period includes: determining a target motion time period in which the motion characteristics of each livestock animal are greater than a threshold; determining the intersection of the target motion time periods of each livestock animal as the common motion time period; determining the second similarity of the motion speed sequences of all livestock animals within the common motion time period based on the first similarity between the second motion speed sequences within the common motion time period of any two livestock animals; obtaining a first fitting curve of the time and the first motion distance of the livestock animals within the common motion time period by using the least squares method; obtaining a second fitting curve of the time and the position of all livestock animals within the common motion time period by using the least squares method; and determining the consistency of the motion characteristics of each livestock animal within the common motion time period based on the second similarity, the first fitting curve, and the second fitting curve.

[0010] Optionally, determining the consistency of the movement characteristics of each livestock animal within the common movement time period based on the second similarity, the first fitting curve and the second fitting curve includes: obtaining the slope and the mean square error of the first fitting curve, and the average value of the cosine similarities between the second fitting curves; calculating the second ratio of the absolute value of the slope to the second similarity; and determining the fourth product of the average value, the second ratio and the inverse of the mean square error as the consistency of the movement characteristics within the common movement time period.

[0011] Optionally, determining the image acquisition interval according to the consistency includes: normalizing the inverse of the consistency to obtain a normalized value; and determining the image acquisition interval according to the normalized value.

[0012] In a second aspect, an embodiment of the present invention provides an isolated observation and monitoring system for livestock, comprising: an acquisition module, used to acquire the movement time period of each livestock in the monitoring video of the monitoring device; a determination module, used to determine the movement distance sequence and the first movement speed sequence between adjacent time points of each livestock within the movement time period; the determination module is also used to determine the movement characteristics of each livestock within the movement time period according to the first movement speed sequence and the movement distance sequence of each livestock; the determination module is also used to determine the consistency of the movement characteristics of each livestock within the common movement time period according to the movement characteristics, the second movement speed sequence of each livestock within the common movement time period, and the first movement distance between corresponding time points of each livestock within the common movement time period, wherein each livestock moves within the common movement time period; the acquisition module is also used to determine the image acquisition interval according to the consistency, and acquire the first target video data within the common movement time period from the monitoring video based on the image acquisition interval; the transmission module is used to transmit the first target video data to the target device.

[0013] In a third aspect, an embodiment of the present invention provides an isolation, observation and monitoring system for livestock animals, comprising: a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, the steps of the isolation, observation and monitoring method for livestock animals as mentioned in the first aspect are implemented.

[0014] The present invention has the following beneficial effects: firstly, the movement time period of each livestock animal in the monitoring video of the monitoring device is obtained; then the movement distance sequence and the first movement speed sequence between adjacent time points of each livestock animal in the movement time period are determined; then the movement characteristics of each livestock animal in the movement time period are determined according to the first movement speed sequence and the movement distance sequence of each livestock animal; secondly, according to the movement characteristics, the second movement speed sequence of each livestock animal in the common movement time period and the first movement distance between corresponding time points of each livestock animal in the common movement time period, the consistency of the movement characteristics of each livestock animal in the common movement time period is determined, and each livestock animal moves in the common movement time period; and the image acquisition interval is determined according to the consistency, and the first target video data in the common movement time period is acquired from the monitoring video based on the image acquisition interval; finally, the first target video data is transmitted to the target device.

[0015] Thus, in the embodiment of the present invention, by determining the common movement time period of each livestock animal, analyzing the consistency of the movement characteristics of each livestock animal in the common movement time period, abnormal changes of livestock animals are discovered in time. Based on the consistency, the image acquisition interval is determined, and the target video data is acquired from the monitoring video of the monitoring device according to the image acquisition interval, thereby reducing the frequency of data acquisition. Further, only the target video data is transmitted to the target device, thereby avoiding all the monitoring videos monitored by the monitoring device from being transmitted to the monitoring system, avoiding occupying the storage space of the monitoring system, and saving the storage space of the monitoring system. In addition, only the target video data is transmitted to the monitoring system, thereby reducing the bandwidth occupied by the video data during the transmission process, and improving the transmission speed and the timeliness of data processing and analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 A flowchart of a method for isolating, observing and monitoring livestock animals provided by one embodiment of the present invention;

[0018] Figure 2 A schematic diagram of the module composition of a livestock isolation observation and monitoring system provided by one embodiment of the present invention;

[0019] Figure 3 A schematic diagram of the structure of a livestock isolation observation and monitoring system provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0020] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the isolation observation and monitoring method and system for livestock animals proposed by the present invention, its specific implementation method, structure, characteristics and effects, in conjunction with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0021] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0022] The specific scheme of the isolation observation and monitoring method and system for livestock animals provided by the present invention is described in detail below in conjunction with the accompanying drawings.

[0023] Embodiment 1:

[0024] See also Figure 1 , which shows a flow chart of a method for isolated observation and monitoring of livestock animals provided by an embodiment of the present invention, comprising:

[0025] S101, obtaining the movement time period of each livestock animal in the monitoring video of the monitoring device.

[0026] Specifically, the monitoring device can be a camera, which can be installed on the top of the isolation area to monitor the livestock in the isolation area. The camera can also record the activity video of each livestock in the isolation area in real time. The monitoring video consists of different video frames, each of which is an image, and a part of the video frame consists of a background area and livestock.

[0027] Furthermore, when obtaining the movement time period of each livestock animal from the surveillance video, each video frame in the surveillance video is first subjected to image enhancement processing, and then a segmentation neural network is used to identify and segment the background area and livestock animals in the enhanced video frame. In the embodiment of the present invention, the segmentation neural network adopts a mask region convolutional neural network (Mask Region-based Convolutional Neural Network, Mask R-CNN). When using Mask R-CNN to segment the background area and livestock animals in the enhanced video frame, the pixels to be segmented are first determined, which are divided into 2 categories. The pixels belonging to the background area are marked as 0, and the pixels belonging to the livestock animals are marked as 1. Then the loss function is determined, and the loss function adopts a cross entropy loss function. Finally, the enhanced video frame is segmented using Mask R-CNN to obtain the background area and livestock animals. It is worth noting that the use of Mask R-CNN to segment images can refer to the prior art, and the embodiment of the present invention will not be repeated here.

[0028] Furthermore, after obtaining the background area and livestock, the continuously adaptive mean-shift (CamShift) algorithm is used to obtain the position coordinates of the livestock in the ith video frame in each video frame after the ith video frame. If the position of the livestock changes in a certain continuous video frame, the time period corresponding to the continuous video frame where the position changes is recorded as the movement time period. A livestock can correspond to multiple movement time periods, and the time outside the movement time period can be recorded as relatively static time, such as resting or eating.

[0029] S102, determining a movement distance sequence and a first movement speed sequence between adjacent time points of each livestock animal within a movement time period.

[0030] Specifically, the multiple movement time periods of livestock may be normal activities of livestock, or they may be rapid running caused by sudden disturbance of livestock. Therefore, it is necessary to distinguish the movement characteristics of livestock in multiple movement time periods.

[0031] Furthermore, when distinguishing the movement characteristics of livestock animals in multiple movement time periods, first, for each livestock animal, a sequence of its position coordinates at each time point in the movement time period is recorded as the position sequence of the livestock animal in the movement time period. Then, the movement distance between two adjacent position coordinates in the position sequence is calculated to obtain the movement distance sequence of the livestock animal in the movement time period. Finally, a movement distance-time curve of the livestock animal in the movement time period is drawn. The slope of the curve represents the movement speed of the livestock animal in the movement time period. The slope between adjacent position coordinates in the curve is the movement speed between adjacent position coordinates of the livestock animal. In this way, the first movement speed sequence of the livestock animal in the movement time period is obtained. .in, is the speed of movement between the first position coordinate and the second position coordinate, is the speed of movement between the second position coordinate and the third position coordinate, is the speed of movement between the third position coordinate and the fourth position coordinate, For the The position coordinates and The speed of movement between position coordinates.

[0032] S103, determining the movement characteristics of each livestock animal in the movement time period according to the first movement speed sequence and the movement distance sequence of each livestock animal.

[0033] Specifically, when livestock animals are moving normally, their movement speed is usually kept uniform, that is, the movement speed of livestock animals is basically unchanged. If they are suddenly disturbed or frightened at a certain moment, the livestock animals will suddenly run, that is, the movement speed of livestock animals will suddenly increase and maintain for a period of time. Therefore, the movement characteristics of livestock animals can be determined according to the first movement speed sequence and movement distance sequence of livestock animals. Among them, the movement characteristics can reflect the changes in the movement speed of livestock animals, including the changes in the magnitude of the movement speed and the changes in the direction of the movement speed.

[0034] Furthermore, when determining the movement characteristics of each livestock animal within the movement time period, as an optional embodiment of the present invention, first, based on the difference between adjacent first movement speeds in the first movement speed sequence and the variance of the first movement speed in the first movement speed sequence, the change characteristics of the movement speed of the livestock animal within the movement time period are determined; then, based on the sum of the second movement distances between adjacent time points in the movement distance sequence, the movement displacement between the first time point to the last time point in the movement distance sequence, the second movement speed within the movement time period, the angle between adjacent first movement speeds in the first movement speed sequence, and the change characteristics, the movement characteristics of the livestock animal within the movement time period are determined.

[0035] Specifically, the calculation method of the variance can refer to the prior art, and the embodiments of the present invention will not be repeated here. The sum of the second movement distances between adjacent time points in the movement distance sequence refers to the superposition value of the second movement distances between each adjacent time point. When determining the change characteristics of the movement speed of livestock during the movement time period, firstly, the first difference values ​​of each adjacent first movement speed in the first movement speed sequence are superimposed to obtain a first superposition value; then the first product of the first superposition value and the variance is determined as the change characteristics of the movement speed.

[0036] Specifically, the change characteristics of the motion speed can be calculated using the following formula:

[0037]

[0038] In the above formula, Represents the change characteristics of the first movement speed of the first movement speed sequence in the cth movement time period of the ath livestock animal. Represents the number of first movement speeds in the first movement speed sequence of the cth movement time period of the ath livestock animal. Represents the i-th first movement speed in the first movement speed sequence of the c-th movement time period of the a-th livestock animal. Represents the i+1th first motion speed in the first motion speed sequence of the cth motion time period of the ath livestock animal. Represents the variance of the first movement speed in the first movement speed sequence of the cth movement time period of the ath livestock animal.

[0039] Furthermore, Indicates the difference between two adjacent first motion speeds in the first motion speed sequence. The smaller the value of , the smaller the difference between the two adjacent first motion speeds. The larger the value of , the greater the difference between the two adjacent first motion speeds, indicating that there may be a sudden change in motion speed. The larger the value of The larger the value is, the more unstable the first motion speed sequence is.

[0040] Furthermore, when determining the movement characteristics of livestock within the movement time period, as an optional embodiment of the present invention, first, the second product between the second movement speed and the change characteristic within the movement time period, and the second difference between the sum of the second movement distances between adjacent time points and the movement displacement are calculated; then, the angles between each adjacent first movement speed in the first movement speed sequence are superimposed to obtain a second superposition value, and a third product of the second superposition value and the second difference is calculated; the third product is added to a preset value to obtain an addition value, and finally, a first ratio of the second product to the addition value is determined as the movement characteristic of the livestock within the movement time period.

[0041] Specifically, when livestock animals are moving normally, they often do not have a fixed movement route and direction. They just keep a stable normal speed and walk around at will without a certain goal. However, when they are suddenly disturbed, they will run quickly in one direction towards an exit or a corner under the leadership of a leader, and the running route is obvious. In the embodiment of the present invention, the direction and distance from the position coordinates of the livestock animals at the previous moment to the position coordinates at the next moment in any movement time period constitute the movement vector of the livestock animals, and the movement vector sequence of the livestock animals in any movement time period is obtained. The difference between the angles of adjacent vectors in the movement vector sequence can represent the change of the movement direction of the livestock animals in the movement time period. Therefore, the second movement speed, the change characteristics and the change of the movement direction in the movement time period can be used to determine the movement characteristics of the livestock animals.

[0042] Furthermore, the angle between adjacent first movement speeds in the first movement speed sequence can be determined by: the direction and distance from the position coordinates of the livestock animal at the previous moment to the position coordinates at the next moment in any movement time period constitutes the movement vector of the livestock animal, and the movement vector sequence of the livestock animal in any movement time period is obtained, and the angle between adjacent vectors in the movement vector sequence is the angle between adjacent first movement speeds. The second movement speed in the movement time period can be the ratio of the distance between the start time and the end time of the movement time period to the duration of the movement time period.

[0043] Furthermore, the preset value can be set according to actual conditions. In the embodiment of the present invention, the preset value can be set to 1. The movement characteristics of livestock animals in the movement time period can be expressed by the following formula:

[0044]

[0045] In the above formula, Represents the movement characteristics of the ath livestock animal in the cth movement time period. Represents the change characteristics of the first movement speed of the first movement speed sequence in the cth movement time period of the ath livestock animal. It represents the second movement speed of the a-th livestock animal in the c-th movement time period, that is, the ratio of the movement distance of the livestock animal in the c-th movement time period to the duration of the movement time period. It represents the number of the first movement speeds in the first movement speed sequence of the a-th livestock animal in the c-th movement time period. Represents the angle between adjacent first movement speeds of the a-th livestock animal in the c-th movement time period. It represents the sum of the second movement distances of the ath livestock animal between adjacent time points in the cth movement time period. It represents the movement displacement between the first time point and the last time point in the movement distance sequence of the ath livestock animal in the cth movement time period.

[0046] Furthermore, when livestock are disturbed, their movement speed will increase, and the movement route is obvious, that is, the movement direction is consistent, so their movement speed Will be larger. It represents the difference between the movement distance and movement displacement of livestock animals during this movement period. When the movement route of livestock animals is a straight line, their movement distance and movement displacement are equal. The less the movement route is close to a straight line, the greater the difference between the movement distance and movement displacement. Indicates the change in the movement direction of livestock animals during this movement period. The smaller the value, the smaller the change in the direction of movement, and the closer it is to the same direction. Therefore, when the change in the direction of movement is smaller and the direction is closer to the same direction, the difference between the movement distance and the movement displacement is also smaller. If disturbed, the movement speeds up, the change characteristics of the first movement speed sequence become larger, and the movement distance is also larger, corresponding to The larger the value is, that is, the greater the motion feature is, the greater the possibility of being disturbed during the motion period is.

[0047] S104, determining the consistency of the motion characteristics of each livestock animal in the common motion time period according to the motion characteristics, the second motion speed sequence of each livestock animal in the common motion time period, and the first motion distance between corresponding time points of each livestock animal in the common motion time period.

[0048] Among them, all livestock animals exercise during the common exercise time period.

[0049] Specifically, the larger the motion feature, the greater the possibility of being disturbed during the motion time period. Therefore, the target motion time period with a motion feature greater than a threshold can be selected as the time period when the livestock is disturbed. If the livestock are disturbed, the livestock in the pen will usually run quickly in a certain direction at the same time and gather in a certain place. The distribution changes from scattered to gathered. Therefore, it is necessary to analyze the consistency of the motion features of all livestock in the pen. When determining the common time period, all target motion time periods of each livestock are obtained to form its motion time period set, and the intersection of the motion time period sets of all animals is obtained. Several continuous time periods in the obtained intersection are recorded as the common motion time period of all livestock. For any common motion time period, the consistency of the motion features of all livestock in the common motion time period is determined.

[0050] Furthermore, when determining the consistency of the motion characteristics of each livestock within a common motion time period, as an optional embodiment of the present invention, first determine the target motion time period in which the motion characteristics of each livestock are greater than a threshold; then determine the intersection of the target motion time periods of each livestock as the common motion time period; then determine the second similarity of the motion speed sequences of all livestock within the common motion time period based on the first similarity between the second motion speed sequences within the common motion time period of any two livestock; secondly, use the least squares method to fit a first fitting curve of the time and the first motion distance of the livestock within the common motion time period; and use the least squares method to fit a second fitting curve of the time and position of all livestock within the common motion time period; finally, determine the consistency of the motion characteristics of each livestock within the common motion time period based on the second similarity, the first fitting curve, and the second fitting curve.

[0051] Specifically, the threshold value can be determined according to actual conditions, and the embodiment of the present invention does not limit it here. When obtaining the first similarity, the second motion speed sequence of any two livestock animals in the mth common motion time period is obtained, and the Manhattan distance between the second motion speed sequences of any two livestock animals in the mth common motion time period is obtained. The Manhattan distance is used to represent the first similarity between the second motion speed sequences of any two livestock animals in the common motion time period, and several Manhattan distances are obtained. The average of all Manhattan distances is used as the second similarity of the second motion speed sequences of all livestock animals in the common motion time period. In the embodiment of the present invention, the second similarity is recorded as It is worth noting that the calculation method of Manhattan distance can refer to the prior art, and the embodiment of the present invention will not be repeated here.

[0052] Further, the first movement distance between any two livestock animals at the first time point in the mth common movement time period is obtained, and the sum of the first movement distances between all livestock animals at the first time point in the common movement time period is used to represent the dispersion degree of all livestock animals at the first time point, which is recorded as in the embodiment of the present invention: . According to this method, the dispersion degree of all livestock animals at all time points in the mth common movement time period is obtained, and the dispersion degree sequence in the mth common movement time period is obtained. If the flock is disturbed, the dispersion degree will decrease over time. The time-dispersion degree curve of the mth common movement time period is obtained by least square fitting, that is, the first fitting curve, and the slope and mean square error MSE of the first fitting curve are obtained, and the fitting error of the curve is represented by the mean square error. It is worth noting that the slope and mean square error MSE of the first fitting curve can be referred to the prior art, and the embodiments of the present invention will not be repeated here.

[0053] Furthermore, the time-position curve of all livestock animals in the mth common movement period is fitted using the least squares method, that is, the second fitting curve, and the average value of the cosine similarity between all the second fitting curves is obtained, which represents the similarity of the time-position curves of all livestock animals in the mth common movement period, denoted as .

[0054] Furthermore, when determining the consistency of the movement characteristics of each livestock animal within the common movement time period based on the second similarity, the first fitting curve and the second fitting curve, as an optional embodiment of the present invention, first obtain the slope and the mean square error of the first fitting curve, and the average value of the cosine similarity between the second fitting curves; then calculate the second ratio of the absolute value of the slope to the second similarity; finally, determine that the fourth product of the average value, the second ratio and the inverse of the mean square error is the consistency of the movement characteristics within the common movement time period.

[0055] Specifically, the consistency of motion characteristics within the common motion time period can be calculated using the following formula:

[0056]

[0057] In the above formula, It represents the consistency of the movement characteristics of all livestock animals in the mth common movement time period. The second similarity of the second movement speed sequence of all livestock animals in the mth common movement time period, The smaller it is, the more similar the second movement speed sequences of all livestock animals are in the mth common movement time period. Represents the slope of the first fitting curve for the mth common motion time period. It may be negative, so take its absolute value. The larger the value of , the faster the dispersion degree changes over time during the mth common movement period, and the greater the possibility that the flock is disturbed. represents the mean square error of the first fitting curve for the mth common motion period. The larger it is, the closer it is to 1, the more similar the second fitting curve is, corresponding to The larger it is, the more consistent the movement characteristics of all livestock animals in the mth common movement time period are.

[0058] S105, determining an image acquisition interval according to the consistency, and acquiring first target video data within a common motion time period from the surveillance video based on the image acquisition interval.

[0059] Specifically, the higher the consistency, the more it is believed that the livestock animals are moving due to being disturbed, and a smaller image acquisition interval is assigned to the video images of the common movement period. The lower the consistency, the larger the image acquisition interval is assigned. Acquiring the first target video data in the common movement period from the monitoring video based on the image acquisition interval means acquiring data from the monitoring video once every time corresponding to the image acquisition interval, and using the acquired data as the first target video data. For example, if the image acquisition interval is 3 seconds, data is acquired every 3 seconds in the common movement period.

[0060] Furthermore, when determining the image acquisition interval according to consistency, as an optional embodiment of the present invention, the inverse of the consistency is first normalized to obtain a normalized value; and then the image acquisition interval is determined according to the normalized value.

[0061] Specifically, after obtaining the consistency, the reciprocal is obtained and normalized to a range of 0 to 1. The normalized value is obtained, and after obtaining the normalized value, it can be magnified N times to obtain the image acquisition interval, and the unit of the image acquisition interval can be seconds. For example, if a normalized value is 0.3, it can be magnified 10 times, that is, 3, and the image acquisition interval is determined to be 3 seconds.

[0062] S106, transmitting the first target video data to the target device.

[0063] Specifically, the first target video data may be compressed and then transmitted to the target device, or the first target video data may be directly transmitted to the target device. The target device may be an electronic device such as a mobile phone or a computer, which is not limited in the embodiment of the present invention.

[0064] Furthermore, for non-common motion time periods, second target video data at the first time point and the second time point within the non-common motion time period can be determined from the surveillance video, and the non-common motion time period is other motion time periods except the common motion time period; and then the second target video data is transmitted to the target device.

[0065] Specifically, the non-common motion time period indicates that the animal may be in a state of eating or sleeping, and the state of the livestock is relatively stable, so the second target video data of the first time point and the second time point in the non-common motion time period can be obtained. After the second target video data is obtained, the second target video data can be compressed and transmitted to the target device, or the second target video data can be directly transmitted to the target device. The embodiment of the present invention is not limited here.

[0066] In the embodiment of the present invention, by determining the common movement time period of each livestock animal, analyzing the consistency of the movement characteristics of each livestock animal in the common movement time period, abnormal changes of livestock animals are discovered in time. Based on the consistency, the image acquisition interval is determined, and the target video data is acquired from the monitoring video of the monitoring device according to the image acquisition interval, thereby reducing the frequency of data acquisition. Further, only the target video data is transmitted to the target device, avoiding the transmission of all the monitoring videos monitored by the monitoring device to the monitoring system, avoiding occupying the storage space of the monitoring system, and saving the storage space of the monitoring system. In addition, only the target video data is transmitted to the monitoring system, reducing the bandwidth occupied by the video data during the transmission process, improving the transmission speed and the timeliness of data processing and analysis.

[0067] Embodiment 2:

[0068] The isolation observation and monitoring method for livestock provided in the above-mentioned embodiment is based on the same technical concept, such as Figure 2As shown, the embodiment of the present invention also provides an isolated observation monitoring system 200 for animal husbandry, including: an acquisition module 201, used to acquire the movement time period of each animal husbandry in the monitoring video of the monitoring device; a determination module 202, used to determine the movement distance sequence and the first movement speed sequence of each animal husbandry between adjacent time points in the movement time period; the determination module 202 is also used to determine the movement characteristics of each animal husbandry in the movement time period according to the first movement speed sequence and the movement distance sequence of each animal husbandry; the determination module 202 is also used to determine the consistency of the movement characteristics of each animal husbandry in the common movement time period according to the movement characteristics, the second movement speed sequence of each animal husbandry in the common movement time period, and the first movement distance between the corresponding time points of each animal husbandry in the common movement time period, and each animal husbandry moves in the common movement time period; the acquisition module 201 is also used to determine the image acquisition interval according to the consistency, and acquire the first target video data in the common movement time period from the monitoring video based on the image acquisition interval; the transmission module 203 is used to transmit the first target video data to the target device.

[0069] Optionally, the determination module 202 is also used to determine the second target video data at the first time point and the second time point within the non-common motion time period from the surveillance video, where the non-common motion time period is other motion time period except the common motion time period; and transmit the second target video data to the target device.

[0070] Optionally, the determination module 202 is also used to determine the change characteristics of the movement speed of livestock within the movement time period based on the difference between adjacent first movement speeds in the first movement speed sequence and the variance of the first movement speed in the first movement speed sequence; determine the movement characteristics of livestock within the movement time period based on the sum of the second movement distances between adjacent time points in the movement distance sequence, the movement displacement between the first time point to the last time point in the movement distance sequence, the second movement speed within the movement time period, the angle between adjacent first movement speeds in the first movement speed sequence, and the change characteristics.

[0071] Optionally, the determination module 202 is further configured to superimpose first differences of adjacent first motion speeds in the first motion speed sequence to obtain a first superposition value; and determine a first product of the first superposition value and the variance as a motion speed variation feature.

[0072] Optionally, the determination module 202 is also used to calculate the second product between the second movement speed and the change characteristic within the movement time period, the second difference between the sum of the second movement distances between adjacent time points and the movement displacement; superimpose the angles between each adjacent first movement speed in the first movement speed sequence to obtain a second superposition value, and calculate the third product of the second superposition value and the second difference; add the third product to a preset value to obtain an addition value, and determine the first ratio of the second product to the addition value as the movement characteristic of the livestock within the movement time period.

[0073] Optionally, the determination module 202 is also used to determine a target movement time period in which the movement characteristics of each livestock animal are greater than a threshold; determine the intersection of the target movement time periods of each livestock animal as a common movement time period; determine the second similarity of the movement speed sequences of all livestock animals in the common movement time period based on the first similarity between the second movement speed sequences in the common movement time period of any two livestock animals; use the least squares method to fit a first fitting curve of the time and the first movement distance of the livestock animals in the common movement time period; use the least squares method to fit a second fitting curve of the time and position of all livestock animals in the common movement time period; and determine the consistency of the movement characteristics of each livestock animal in the common movement time period based on the second similarity, the first fitting curve, and the second fitting curve.

[0074] Optionally, the determination module 202 is also used to obtain the slope and mean square error of the first fitting curve, and the average value of the cosine similarity between each second fitting curve; calculate the second ratio of the absolute value of the slope to the second similarity; and determine that the fourth product of the average value, the second ratio and the inverse of the mean square error is the consistency of the motion features within the common motion time period.

[0075] Optionally, the determination module 202 is further configured to normalize the inverse of the consistency to obtain a normalized value; and determine the image acquisition interval according to the normalized value.

[0076] Embodiment three:

[0077] Corresponding to the isolation observation and monitoring method for livestock animals provided in the above embodiment, based on the same technical concept, an embodiment of the present invention further provides an isolation observation and monitoring system for livestock animals, and the isolation observation and monitoring system for livestock animals is used to execute the isolation observation and monitoring method for livestock animals. Figure 3 A schematic diagram of a livestock isolation observation and monitoring system for implementing various embodiments of the present invention is shown in FIG. Figure 3As shown in the hardware level, the isolated observation and monitoring system for animal husbandry includes a processor, and optionally, an internal bus, a network interface, and a memory. The memory may include a memory, such as a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage, etc. Of course, the isolated observation and monitoring system for animal husbandry may also include hardware required for other services.

[0078] The processor, network interface and memory can be interconnected through an internal bus, which can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one bidirectional arrow is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0079] The memory is used to store programs. Specifically, the program may include program code, and the program code includes computer operation commands. The memory may include internal memory and non-volatile memory, and provide instructions and data to the processor.

[0080] The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming a device for locating the specified user at the logical level. The processor executes the program stored in the memory and is specifically used to execute: Figure 3 The method disclosed in the illustrated embodiment implements the functions and beneficial effects of each method in the previous method embodiments, which will not be described in detail here.

[0081] It should be noted that the isolation, observation and monitoring system for livestock animals provided by the embodiment of the present invention and the isolation, observation and monitoring method for livestock animals provided by the embodiment of the present invention are based on the same inventive concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the aforementioned isolation, observation and monitoring method for livestock animals, and has the same or similar beneficial effects, and the repeated parts will not be repeated.

[0082] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0083] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A method for isolated observation and monitoring of livestock, characterized in that: The isolation observation and monitoring method of livestock and poultry comprises: Obtain the movement time period of each livestock animal in the surveillance video of the monitoring device; Determine a movement distance sequence and a first movement speed sequence of each of the livestock animals between adjacent time points within the movement time period; Determining the movement characteristics of each of the livestock animals in the movement time period according to the first movement speed sequence and the movement distance sequence of each of the livestock animals; Determine the consistency of the movement characteristics of each of the livestock animals in the common movement time period according to the movement characteristics, the second movement speed sequence of each of the livestock animals in the common movement time period, and the first movement distance between each of the livestock animals at the same time point in the common movement time period, wherein each of the livestock animals moves in the common movement time period; Determining an image acquisition interval according to the consistency, and acquiring first target video data within the common motion time period from the monitoring video based on the image acquisition interval; transmitting the first target video data to a target device; The step of determining the movement characteristics of each of the livestock animals in the movement time period according to the first movement speed sequence and the movement distance sequence of each of the livestock animals comprises: Determining a change characteristic of the movement speed of the livestock within the movement time period according to a difference between adjacent first movement speeds in the first movement speed sequence and a variance of the first movement speeds in the first movement speed sequence; Determine the movement characteristics of the livestock in the movement time period according to the sum of the second movement distances between adjacent time points in the movement distance sequence, the movement displacement between the first time point and the last time point in the movement distance sequence, the second movement speed in the movement time period, the angle between adjacent first movement speeds in the first movement speed sequence, and the change characteristics; The second movement speed in the movement time period is the ratio of the distance between the start time and the end time of the movement time period to the duration of the movement time period; Determining the change characteristics of the movement speed of the livestock within the movement time period according to the difference between adjacent first movement speeds in the first movement speed sequence and the variance of the first movement speeds in the first movement speed sequence includes: superimposing first differences of adjacent first motion speeds in the first motion speed sequence to obtain a first superimposed value; Determine a first product of the first superposition value and the variance as a change characteristic of the motion speed; Determining the movement characteristics of the livestock in the movement time period according to the sum of the second movement distances between adjacent time points in the movement distance sequence, the movement displacement between the first time point and the last time point in the movement distance sequence, the second movement speed in the movement time period, the angle between adjacent first movement speeds in the first movement speed sequence, and the change characteristics includes: Calculate a second product of a second movement speed within the movement time period and the change characteristic, and a second difference between a sum of second movement distances between adjacent time points and the movement displacement; superimposing the angles between adjacent first motion speeds in the first motion speed sequence to obtain a second superimposed value, and calculating a third product of the second superimposed value and the second difference; Adding the third product to a preset value to obtain an added value; Determine a first ratio of the second product to the added value as a movement characteristic of the livestock during the movement time period; Determining the consistency of the motion characteristics of each of the livestock animals in the common motion time period according to the motion characteristics, the second motion speed sequence of each of the livestock animals in the common motion time period, and the first motion distance between each of the livestock animals at the same time point in the common motion time period includes: Determine a target movement time period in which the movement characteristics of each of the livestock animals are greater than a threshold value; Determining the intersection of the target movement time periods of the livestock animals as the common movement time period; Determine the second similarity of the movement speed sequences of all the livestock animals in the common movement time period according to the first similarity between the second movement speed sequences in the common movement time period of any two livestock animals; A first fitting curve of the time and the first movement distance of the livestock animals in the common movement time period is obtained by using the least squares method; A second fitting curve of the time and position of all livestock animals in the common movement time period is obtained by fitting using the least square method; Determining the consistency of the movement characteristics of each of the livestock animals during the common movement time period according to the second similarity, the first fitting curve and the second fitting curve; The obtaining of the first fitting curve comprises: Obtaining the first movement distance between any two livestock animals at the same time point in each common movement time period; The sum of the first movement distances of all livestock animals at the same time point in any common movement time period is used as the dispersion degree of all livestock animals at the corresponding time point; the dispersion degree of all livestock animals at each time point in the common movement time period is fitted by the least square method to obtain a first fitting curve; Determining the consistency of the movement characteristics of each of the livestock animals in the common movement time period according to the second similarity, the first fitting curve and the second fitting curve includes: Obtaining the slope and mean square error of the first fitting curve, and the average value of the cosine similarities between the second fitting curves; calculating a second ratio of the absolute value of the slope to the second similarity; The fourth product of the average value, the second ratio and the inverse of the mean square error is determined as the consistency of the motion characteristics within the common motion time period.

2. The method for isolated observation and monitoring of livestock according to claim 1, characterized in that: The method further comprises: Determine second target video data at a first time point and a second time point within a non-common motion time period from the monitoring video, wherein the non-common motion time period is other motion time periods except the common motion time period; The second target video data is transmitted to the target device.

3. The method for isolated observation and monitoring of livestock according to claim 1, characterized in that: Determining the image acquisition interval according to the consistency comprises: Normalizing the reciprocal of the consistency to obtain a normalized value; The image acquisition interval is determined according to the normalized value.

4. A livestock isolation observation and monitoring system, characterized in that: include: An acquisition module, used to acquire the movement time period of each livestock animal in the monitoring video of the monitoring device; A determination module, used to determine a movement distance sequence and a first movement speed sequence of each of the livestock animals between adjacent time points within the movement time period; The determination module is further used to determine the movement characteristics of each of the livestock animals in the movement time period according to the first movement speed sequence and the movement distance sequence of each of the livestock animals; The determination module is further used to determine the consistency of the movement characteristics of each of the livestock animals in the common movement time period according to the movement characteristics, the second movement speed sequence of each of the livestock animals in the common movement time period, and the first movement distance between each of the livestock animals at the same time point in the common movement time period, wherein each of the livestock animals moves in the common movement time period; The acquisition module is further used to determine an image acquisition interval according to the consistency, and acquire the first target video data within the common motion time period from the monitoring video based on the image acquisition interval; A transmission module, used for transmitting the first target video data to a target device; The step of determining the movement characteristics of each of the livestock animals in the movement time period according to the first movement speed sequence and the movement distance sequence of each of the livestock animals comprises: Determining a change characteristic of the movement speed of the livestock within the movement time period according to a difference between adjacent first movement speeds in the first movement speed sequence and a variance of the first movement speeds in the first movement speed sequence; Determine the movement characteristics of the livestock in the movement time period according to the sum of the second movement distances between adjacent time points in the movement distance sequence, the movement displacement between the first time point and the last time point in the movement distance sequence, the second movement speed in the movement time period, the angle between adjacent first movement speeds in the first movement speed sequence, and the change characteristics; The second movement speed in the movement time period is the ratio of the distance between the start time and the end time of the movement time period to the duration of the movement time period; Determining the change characteristics of the movement speed of the livestock within the movement time period according to the difference between adjacent first movement speeds in the first movement speed sequence and the variance of the first movement speeds in the first movement speed sequence includes: superimposing first differences of adjacent first motion speeds in the first motion speed sequence to obtain a first superimposed value; Determine a first product of the first superposition value and the variance as a change characteristic of the motion speed; Determining the movement characteristics of the livestock in the movement time period according to the sum of the second movement distances between adjacent time points in the movement distance sequence, the movement displacement between the first time point and the last time point in the movement distance sequence, the second movement speed in the movement time period, the angle between adjacent first movement speeds in the first movement speed sequence, and the change characteristics includes: Calculate a second product of a second movement speed within the movement time period and the change characteristic, and a second difference between a sum of second movement distances between adjacent time points and the movement displacement; superimposing the angles between adjacent first motion speeds in the first motion speed sequence to obtain a second superimposed value, and calculating a third product of the second superimposed value and the second difference; Adding the third product to a preset value to obtain an added value; Determine a first ratio of the second product to the added value as a movement characteristic of the livestock during the movement time period; Determining the consistency of the motion characteristics of each of the livestock animals in the common motion time period according to the motion characteristics, the second motion speed sequence of each of the livestock animals in the common motion time period, and the first motion distance between each of the livestock animals at the same time point in the common motion time period includes: Determine a target movement time period in which the movement characteristics of each of the livestock animals are greater than a threshold value; Determining the intersection of the target movement time periods of the livestock animals as the common movement time period; Determine the second similarity of the movement speed sequences of all the livestock animals in the common movement time period according to the first similarity between the second movement speed sequences in the common movement time period of any two livestock animals; A first fitting curve of the time and the first movement distance of the livestock animals in the common movement time period is obtained by using the least squares method; A second fitting curve of the time and position of all livestock animals in the common movement time period is obtained by fitting using the least square method; Determining the consistency of the movement characteristics of each of the livestock animals during the common movement time period according to the second similarity, the first fitting curve and the second fitting curve; The obtaining of the first fitting curve comprises: Obtaining the first movement distance between any two livestock animals at the same time point in each common movement time period; The sum of the first movement distances of all livestock animals at the same time point in any common movement time period is used as the dispersion degree of all livestock animals at the corresponding time point; the dispersion degree of all livestock animals at each time point in the common movement time period is fitted by the least square method to obtain a first fitting curve; Determining the consistency of the movement characteristics of each of the livestock animals in the common movement time period according to the second similarity, the first fitting curve and the second fitting curve includes: Obtaining the slope and mean square error of the first fitting curve, and the average value of the cosine similarities between the second fitting curves; calculating a second ratio of the absolute value of the slope to the second similarity; The fourth product of the average value, the second ratio and the inverse of the mean square error is determined as the consistency of the motion characteristics within the common motion time period.

5. A livestock isolation observation and monitoring system, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, the steps of the method for isolated observation and monitoring of livestock animals as described in any one of claims 1 to 3 are implemented.

Images