Abstract:Pigs’ motion data, such as daily motion duration, distance, speed, etc., are important bases for analysis of pigs’ health and performance. Manual monitoring is real-timely difficult, low accuracy, time-consuming and also easy missing for human fatigue. It can not meet the requirement of large-scale farming. Comparing with RFID (radio frequency identification technology) and sensor technology, video technology for development of animal husbandry had a profound influence without physical contact with animals. It was low cost with simple hardware deployment, which can monitor and manage large-scale farms. A scheme for pigs’ motion detection was designed based on video tracking for capturing and detecting a variety of motion information of farm pigs quickly and accurately. Firstly, color channel was selected adaptively to identify field pigs. A target segment method was provided based on characteristics of color and contour. Then each pig was fitted by an ellipse based on minimizing the cost function and tracks of pigs based on the shortest distance matching algorithm. Extraction algorithm for four motion parameters was proposed, which were displacement, velocity, acceleration and angular velocity. Finally, experiments related pigs’ motion detection, such as pigs’ daily activity, daily activity patterns and pigs daily behavior recognition, were carried out. Experimental results showed that the proposed channel selection method could identify a variety of solid colors pigs;the success rate of adhered pigs’ segmentation was 926%. The real-time video in Guangzhou Lizhi male pig farms was tested from November 21, 2015 to November 24, 2015 from 09:00 to 17:00. It showed that the characteristics of pigs daily activity, daily activity patterns and pigs daily behavior recognition could be manifested by the motion information. Therefore, this scheme was effective for pigs’ motion detection dynamically, and it provided a basic support for pigs’ health, behavior analysis and performance analysis.