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 旨在讓多目標追蹤（MOT）更具魯棒性，特別是在目標以非線性模式移動的擁擠場景中。它解決了傳統卡爾曼濾波器與原始 SORT 演算法的限制，避免在目標被遮擋或運動不可預測時發生追蹤失敗。

How it works

此專案實作了一個純粹基於運動模型的追蹤器。它使用「觀測中心再更新」(Observation-centric Re-Update, ORU) 機制來修正運動模型預測的錯誤。設計上具備彈性，能與各種目標偵測器與匹配模組（例如外觀相似度）整合，維持即時、線上追蹤流程。

Who it’s for

此工具適合從事電腦視覺與多目標追蹤的開發者與研究者，特別是需要即時系統以處理複雜、擁擠環境的使用者。

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.