Video-based pig behavior recognition system and method
A recognition method and behavioral technology, applied in neural learning methods, character and pattern recognition, image data processing, etc., can solve the problems of sensor aging and corrosion, poor effect of pig recognition technology, high maintenance and use costs, and achieve accurate recognition Pig behavior, the effect of saving labor costs
Pending Publication Date: 2021-12-07
GUANGZHOU JIANKUN NETWORK TECH DEV +2
View PDF0 Cites 5 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, most of the current pig identification technologies need to install sensors on pigs. The use and installation of sensors can easily cause stress reactions in pigs. At the same time, the sensors also have problems such as aging and corrosion, and the maintenance and use costs are high. The implementation effect of recognition-only technology is poor
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0044] The preferred embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings, so that the advantages and features of the present invention can be more easily understood by those skilled in the art, so as to define the protection scope of the present invention more clearly.
[0045] Such as figure 1 As shown, the present invention discloses a video-based pig behavior recognition method in one embodiment.
[0046] The video-based pig behavior recognition method includes the following steps:
[0047] S1: Obtain video image information of all pigs in the group breeding pen in real time.
[0048] In order to obtain the video image information of all pigs in the group breeding pigsty, a monitoring camera can be installed in the pigsty, and the monitoring camera can be installed on the top of the field of the pigsty, and the monitoring camera can be tilted 15° downwards relative to the horizontal direction, so that Ensure...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a video-based pig behavior recognition system and method. The recognition method comprises the following steps: acquiring video image information of all pigs in a group pig pen in real time; detecting pig target position information in the video frame based on a YOLOv3 pig detection model, and tracking the detected pig target based on a DeepSort multi-target tracking algorithm to obtain a motion trail of the pig target; calling an OpenPose key point detection model, and extracting pig skeleton key point information of the pig target in the video frame; continuously extracted skeleton key point information of multiple frames of pig targets is input into a pig behavior recognition model based on space-time diagram convolution, and pig behavior categories are predicted; and recording and prompting the predicted pig behavior category. The invention is suitable for monitoring the growth process of the pigs in a group pig raising environment, can accurately recognize the behaviors of the pigs, and greatly saves the manual labor cost.
Description
technical field [0001] The invention relates to a video-based pig behavior recognition system and method. Background technique [0002] The abnormal behavior of pigs will have a negative impact on the growth of pigs. At present, the abnormal state monitoring of pig breeding in my country mainly relies on manual observation. Manual observation is time-consuming, laborious and inefficient, which increases the cost of breeding and is not conducive to the high efficiency of pigs. grow. In order to improve the monitoring of abnormal status of pig breeding, pig behavior recognition technology was developed. However, most of the current pig identification technologies need to install sensors on pigs. The use and installation of sensors can easily cause stress reactions in pigs. At the same time, the sensors also have problems such as aging and corrosion, and the maintenance and use costs are high. The implementation effect of only recognition technology is poor. Contents of the ...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More IPC IPC(8): G06T7/246G06T7/277G06T7/73G06K9/62G06N3/04G06N3/08
CPCG06T7/246G06T7/277G06T7/73G06N3/08G06T2207/30241G06T2207/10016G06T2207/20081G06T2207/20084G06N3/045G06F18/241G06F18/214
Inventor 刘红刚潘明陈万云陈艺刘海峰钟林忆谢秋波孟祥宝朱熠
Owner GUANGZHOU JIANKUN NETWORK TECH DEV