针对全景相机小目标追踪难题，改造SORT算法实现低资源高效追踪。
Re-engineering SORT-based algorithms for low-cost small object tracking from omnidirectional footage
- 设计无缝运动模型与复合关联代价，解决全景图接缝处目标断裂问题。
- 在新数据集OmniSmall上提升8.51点HOTA，YOLOX检测下仍获1.95点增益。
- 无需外观编码器，纯CPU运行，适合野外小动物追踪场景。
多目标追踪（MOT）在城市监控和自动驾驶中快速发展，但现有方法多依赖ReID与变压器类外观编码器，且针对标准视场相机设计。这些假设在低成本全景部署中失效，因等距柱状投影引入接缝不连续性，目标呈现为小而快速移动。本文聚焦远程环境中全景相机拍摄的飞行动物多目标追踪。提出轻量级框架，对SORT类追踪器进行重构，包括：(i) 无缝运动模型，确保卡尔曼状态跨接缝连续；(ii) 复合无缝关联代价，结合包裹欧氏距离与GIoU；(iii) 新建基准OmniSmall，包含全景野生动物影像。在自有数据集上，使用真值检测时，性能较OCSORT提升+8.51 HOTA、+9.41 MOTA、+10.17 IDF1；使用YOLOX检测时，仍获得+1.95 HOTA增益。所提方法在OmniSmall上表现更优，且在JRDB上保持竞争力，无须添加外观编码器，全程仅需CPU计算。数据集与代码已开源：https://github.com/Xin-Shu/OmniSORT.git。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。