Bootstrapping Labelled Dataset Construction for Cow Tracking and Behavior Analysis
This work addresses the challenge of monitoring cow behavior for precision agriculture, specifically aiming for early lameness detection, but it is incremental as it builds on existing tracking methods for a specific domain.
The paper tackles the problem of long-term tracking of cows in a cluttered enclosure by developing a multi-stage approach involving object localization, instance segmentation, learning, and tracking, showing strong performance compared to semi-supervised algorithms.
This paper introduces a new approach to the long-term tracking of an object in a challenging environment. The object is a cow and the environment is an enclosure in a cowshed. Some of the key challenges in this domain are a cluttered background, low contrast and high similarity between moving objects which greatly reduces the efficiency of most existing approaches, including those based on background subtraction. Our approach is split into object localization, instance segmentation, learning and tracking stages. Our solution is compared to a range of semi-supervised object tracking algorithms and we show that the performance is strong and well suited to subsequent analysis. We present our solution as a first step towards broader tracking and behavior monitoring for cows in precision agriculture with the ultimate objective of early detection of lameness.