Automatic individual pig detection and tracking in surveillance videos
Authors:
- Lei ZhangLZLei Zhang
- Helen GrayHGHelen Gray
- Xujiong YeXYXujiong Ye
- Lisa CollinsLCLisa Collins
- Nigel AllinsonNANigel Allinson
Preprint
Abstract
Individual pig detection and tracking is an important requirement in many video-based pig monitoring applications. However, it still remains a challenging task in complex scenes, due to problems of light fluctuation, similar appearances of pigs, shape deformations and occlusions. To tackle these problems, we propose a robust real time multiple pig detection and tracking method which does not require manual marking or physical identification of the pigs, and works under both daylight and infrared light conditions. Our method couples a CNN-based detector and a correlation filter-based tracker via a novel hierarchical data association algorithm. The detector gains the best accuracy/speed trade-off by using the features derived from multiple layers at different scales in a one-stage prediction network. We define a tag-box for each pig as the tracking target, and the multiple object tracking is conducted in a key-points tracking manner using learned correlation filters. Under challenging conditions, the tracking failures are modelled based on the relations between responses of detector and tracker, and the data association algorithm allows the detection hypotheses to be refined, meanwhile the drifted tracks can be corrected by probing the tracking failures followed by the re-initialization of tracking. As a result, the optimal tracklets can sequentially grow with on-line refined detections, and tracking fragments are correctly integrated into respective tracks while keeping the original identifications. Experiments with a dataset captured from a commercial farm show that our method can robustly detect and track multiple pigs under challenging conditions. The promising performance of the proposed method also demonstrates a feasibility of long-term individual pig tracking in a complex environment and thus promises a commercial potential.Keywords
All Related Versions
This publication has 24 references indexed in Scilit:
- Using machine vision for investigation of changes in pig group lying patternsComputers and Electronics in Agriculture, 2015
- Validity of the Microsoft Kinect sensor for assessment of normal walking patterns in pigsComputers and Electronics in Agriculture, 2015
- Application of 3-D imaging sensor for tracking minipigs in the open field testJournal of Neuroscience Methods, 2014
- Observer bias in animal behaviour research: can we believe what we score, if we score what we believe?Animal Behaviour, 2014
- Foreground detection using loopy belief propagationBiosystems Engineering, 2013
- Selective Search for Object RecognitionInternational Journal of Computer Vision, 2013
- Automatic identification of marked pigs in a pen using image pattern recognitionComputers and Electronics in Agriculture, 2013
- Development of a real-time computer vision system for tracking loose-housed pigsComputers and Electronics in Agriculture, 2011
- The effects of observer presence on the behavior of Cebus capucinus in Costa RicaAmerican Journal of Primatology, 2007
- Segmentation and tracking of piglets in imagesMachine Vision and Applications, 1995