2020/01/27 by Lance Rice, Samual Tate, Rice, Lance +15
Agricultural and Biological Sciences · Computer Science · Environmental Science · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Smart Agriculture and AI #Species Distribution and Climate Change #Video Surveillance and Tracking Methods #Wildlife Ecology and Conservation
paper · pdf · doi:10.48550/arxiv.2001.10072
openalex publication_date 2020/01/27 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Visual multi-object tracking has the potential to accelerate many forms of quantitative analyses, especially in research communities investigating the motion, behavior, or social interactions within groups of animals. Despite its potential for increasing analysis throughput, complications related to accessibility, adaptability, accuracy, or scalable application arise with existing tracking systems. Several iterations of prototyping and testing have led us to a multi-object tracking system -- ABCTracker -- that is: accessible in both system as well as technical knowledge requirements, easily adaptable to new videos, and capable of producing accurate tracking data through a mixture of automatic and semi-automatic tracking features.