Simple Online and Realtime Tracking with a Deep Association Metric
Nicolai Wojke, Alex Bewley, Dietrich Paulus
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/nwojke/deep_sortOfficialIn papertf★ 0
- github.com/PaddlePaddle/PaddleDetectionpaddle★ 14,132
- github.com/mikel-brostrom/Yolov5_DeepSort_Pytorchpytorch★ 8,069
- github.com/open-mmlab/mmtrackingpytorch★ 3,865
- github.com/linghu8812/tensorrt_trackerpytorch★ 108
- github.com/ZhangwenguangHikvision/YoloV5_JDE_TensorRT_for_Tracknone★ 55
- github.com/oaqoe-DWQ/Yolov5_DeepSort_Pytorchpytorch★ 45
- github.com/sithu31296/simple-object-trackingpytorch★ 34
- github.com/WuPedin/Multi-class_Yolov5_DeepSort_Pytorchpytorch★ 24
- github.com/Robotmurlock/Motracknone★ 16
Abstract
Simple Online and Realtime Tracking (SORT) is a pragmatic approach to multiple object tracking with a focus on simple, effective algorithms. In this paper, we integrate appearance information to improve the performance of SORT. Due to this extension we are able to track objects through longer periods of occlusions, effectively reducing the number of identity switches. In spirit of the original framework we place much of the computational complexity into an offline pre-training stage where we learn a deep association metric on a large-scale person re-identification dataset. During online application, we establish measurement-to-track associations using nearest neighbor queries in visual appearance space. Experimental evaluation shows that our extensions reduce the number of identity switches by 45%, achieving overall competitive performance at high frame rates.
Tasks
Benchmark Results
| Dataset | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| Waymo Open Dataset | CTRL_FSD_TTA | MOTA/L2 | 0.73 | — | Unverified |