Automatic individual pig detection and tracking in pig farms

Zhang, Lei and Gray, Helen and Ye, Xujiong and Collins, lisa and Allinson, Nigel (2019) Automatic individual pig detection and tracking in pig farms. Sensors, 19 (5). p. 1188. ISSN 1424-8220

Full content URL: https://doi.org/10.3390/s19051188

Documents
Automatic individual pig detection and tracking in pig farms
author's accepted manuscript

Request a copy
Automatic individual pig detection and tracking in pig farms
publisher's pdf
[img]
[Download]
[img] PDF
automatic pig tracking- sensors.pdf - Whole Document
Restricted to Repository staff only

8MB
[img] PDF
sensors-final.pdf - Whole Document
Available under License Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International.

4MB
Item Type:Article
Item Status:Live Archive

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. In order to tackle these problems, we propose a robust on-line 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 (nighttime) light conditions. Our method couples a CNN-based detector and a correlation filter-based tracker via a novel hierarchical data association algorithm. In our method, 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, from which features with a more local scope are extracted for learning, 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:Computer vision, object detection, multiple objects tracking, surveillance system
Subjects:G Mathematical and Computer Sciences > G400 Computer Science
Divisions:College of Science > School of Computer Science
ID Code:35275
Deposited On:08 Mar 2019 10:09

Repository Staff Only: item control page