noahcao/OC_SORT

[CVPR2023] The official repo for OC-SORT: Observation-Centric SORT on video Multi-Object Tracking. OC-SORT is simple, online and robust to occlusion/non-linear motion.

What it solves

OC-SORT 旨在让多目标跟踪（MOT）更具鲁棒性，特别是在目标以非线性模式移动的拥挤场景中。它解决了传统卡尔曼滤波器和原始 SORT 算法的局限，防止在目标被遮挡或运动不可预测时出现跟踪失败。

How it works

该项目实现了一个纯运动模型的跟踪器。它使用“观测中心再更新”(Observation-centric Re-Update, ORU) 机制来修正运动模型预测的错误。设计上具有灵活性，能够与各种目标检测器和匹配模块（如外观相似度）集成，保持实时、在线的跟踪流水线。

Who it’s for

此工具面向从事计算机视觉和多目标跟踪的开发者与研究者，尤其是需要实时系统来处理复杂、拥挤环境的用户。

Highlights

  • Real-time performance: Achieves high inference speeds (up to 700 FPS for association on a CPU).
  • Robustness: Specifically optimized for non-linear motion and crowded scenes.
  • ** uma flexible integration**: Compatible with with various detectors and cost metrics like GIoU and CIoU.
  • C++ Support: Provides C++ implementation for deployment.
  • Deployment options: Supports ONNX, TensorRT, and ncnn.