WormSORT: A detection-based multiple object tracking model for individual silkworms in breeding environments

Variety breeding has long been a cornerstone of high-quality agriculture, and recent advances in artificial intelligence have opened new avenues for accelerating biological breeding. In this study, we applied multiple object tracking (MOT) technology to silkworm breeding to achieve efficient, non-invasive, and dynamic individual monitoring. Unlike pedestrian or vehicle tracking, silkworms pose unique challenges for MOT due to their small size, dense distribution, and high inter-individual similarity, which complicate accurate tracking and behavioral analysis. To address these issues, we propose WormSORT, an enhanced tracking method based on a tracking-by-detection framework with an optimized data association strategy. A pre-trained detection model identifies silkworms in each frame, and deep feature vectors are extracted using a re-identification network. Identity association is first performed using Intersection over Union (IoU) matching, followed by deep feature similarity for unmatched cases, improving both tracking accuracy and reliability. To further enhance tracking stability, we introduce a candidate input padding mechanism, including IoU padding and feature padding, ensuring that high-confidence unmatched trajectories and detections remain involved in the matching process. To validate the proposed tracking strategy, we constructed two multiple silkworm tracking (MST) datasets: MST-50, containing approximately 50 individuals over 1000 frames, and MST-100, containing approximately 100 individuals over 1200 frames. Experimental results demonstrate that WormSORT outperforms existing methods, including DeepSORT, StrongSORT, OCSORT, ByteTrack, and BotSORT, achieving superior tracking performance. This study provides a valuable reference for silkworm tracking and behavioral analysis, contributing to the advancement of high-quality silkworm rearing and management.Author summary: Artificial intelligence (AI) has achieved remarkable progress in computational biology, with notable success in tasks such as protein structure prediction, molecular property modeling, and drug discovery. In the field of silkworm breeding, AI also shows great potential to accelerate research and production processes, enabling large-scale counting, behavior recognition, and health condition assessment. This study focuses on leveraging deep learning techniques to extract crawling trajectories of silkworms through multiple object tracking. Accurate trajectory information provides essential support for analyzing individual movement patterns, modeling group interactions, and evaluating traits related to growth and health conditions. Therefore, it serves as a fundamental tool that bridges counting, behavior analysis, and health assessment tasks. However, most existing multiple object tracking methods are designed for pedestrians or vehicles. In contrast, silkworm tracking presents unique challenges, including dense distributions, highly non-linear motion patterns, and strong visual similarity among individuals, which limit the direct applicability of existing approaches. To address these challenges, this work proposes a multiple object tracking method tailored for silkworm scenarios and constructs a dedicated silkworm tracking dataset to validate its effectiveness.