YOLOv8-SMOT: An Efficient and Robust Framework for Real-Time Small Object Tracking via Slice-Assisted Training and Adaptive Association

TL;DR

This paper introduces YOLOv8-SMOT, a real-time small object tracking framework that combines slice-assisted training and adaptive association techniques, achieving state-of-the-art results in challenging UAV-based bird tracking scenarios.

Contribution

The paper presents novel training and tracking innovations, including SliceTrain for small object detection and a motion-based, appearance-independent tracker with adaptive similarity metrics.

Findings

Achieved SO-HOTA score of 55.205 on SMOT4SB benchmark.

Proposed SliceTrain enhances small object detection in high-resolution images.

Developed a robust tracker that handles irregular motion without appearance features.

Abstract

Tracking small, agile multi-objects (SMOT), such as birds, from an Unmanned Aerial Vehicle (UAV) perspective is a highly challenging computer vision task. The difficulty stems from three main sources: the extreme scarcity of target appearance features, the complex motion entanglement caused by the combined dynamics of the camera and the targets themselves, and the frequent occlusions and identity ambiguity arising from dense flocking behavior. This paper details our championship-winning solution in the MVA 2025 "Finding Birds" Small Multi-Object Tracking Challenge (SMOT4SB), which adopts the tracking-by-detection paradigm with targeted innovations at both the detection and association levels. On the detection side, we propose a systematic training enhancement framework named \textbf{SliceTrain}. This framework, through the synergy of 'deterministic full-coverage slicing' and 'slice-level stochastic augmentation, effectively addresses the problem of insufficient learning for small objects in high-resolution image training. On the tracking side, we designed a robust tracker that is completely independent of appearance information. By integrating a \textbf{motion direction maintenance (EMA)} mechanism and an \textbf{adaptive similarity metric} combining \textbf{bounding box expansion and distance penalty} into the OC-SORT framework, our tracker can stably handle irregular motion and maintain target identities. Our method achieves state-of-the-art performance on the SMOT4SB public test set, reaching an SO-HOTA score of \textbf{55.205}, which fully validates the effectiveness and advancement of our framework in solving complex real-world SMOT problems. The source code will be made available at https://github.com/Salvatore-Love/YOLOv8-SMOT.