Re-engineering SORT-based algorithms for low-cost small object tracking from omnidirectional footage

2026-09-07

AI Summary

研究解决了低成本全景摄像机中小目标跟踪问题，通过改进SORT算法，提出缝合感知运动模型和关联成本，提高了多目标跟踪性能。

Abstract

Multi-object tracking (MOT) has advanced rapidly in urban surveillance and autonomous driving, yet many trackers rely on ReID- and transformer-based appearance encoders and are designed for standard FoV cameras. These assumptions break down for low-cost omnidirectional deployments, where equirectangular projection introduces seam discontinuities and targets appear to be small and fast-moving. We address multi-object tracking of flying animals captured in remote environments using omnidirectional cameras. We propose a lightweight framework that re-engineers SORT-based tracking for this geometry, including (i) a Seam-Aware Motion Model that keeps the Kalman state continuous across the seam, (ii) a composite seam-aware association cost that pairs a wrapped Euclidean term with GIoU, and (iii) OmniSmall, a new benchmark of omnidirectional wildlife footage. On our new dataset, with ground-truth detections, our modifications improved over OCSORT by +8.51 HOTA, +9.41 MOTA, and +10.17 IDF1; with YOLOX detections the gain narrows to +1.95 HOTA. Our proposed methods improved tracking performance on OmniSmall and remained competitive on JRDB without adding appearance encoders while keeping the tracking stage CPU-only. Our dataset and source code are available at: https://github.com/Xin-Shu/OmniSORT.git.

Problem

• multi-object tracking
• omnidirectional cameras
• low-cost deployment
• seam discontinuities
• small and fast-moving targets

Innovation

• Seam-Aware Motion Model
• composite seam-aware association cost
• OmniSmall