tracktor

Tracking without Bells and Whistles

Introduction

[ALGORITHM]

@inproceedings{bergmann2019tracking,
  title={Tracking without bells and whistles},
  author={Bergmann, Philipp and Meinhardt, Tim and Leal-Taixe, Laura},
  booktitle={Proceedings of the IEEE international conference on computer vision},
  pages={941--951},
  year={2019}
}

Results and models on MOT17

We implement Tracktor with independent detector and ReID models. To train a model by yourself, you need to train a detector following here and also train a ReID model following here. The configs in this folder are basiclly for inference.

The implementations of Tracktor follow the offical practices. In the table below, the result marked with * (the last line) is the offical one. Our implementation outperform it by 4.9 points on MOTA and 3.3 points on IDF1.

Detector	ReID	Train Set	Test Set	Public	Inf time (fps)	MOTA	IDF1	FP	FN	IDSw.	Config	Download
R50-FasterRCNN-FPN	R50	half-train	half-val	Y	3.2	57.3	63.4	1254	67091	614	config	detector reid
R50-FasterRCNN-FPN	R50	half-train	half-val	N	3.1	64.1	66.9	11088	45762	1233	config	detector reid
R50-FasterRCNN-FPN	R50	train	train	Y	3.2	69.3	69.4	4010	97918	1540	config	detector reid
R50-FasterRCNN-FPN	R50	train	train	N	3.1	82.1	73.2	12795	44637	3033	config	detector reid
R50-FasterRCNN-FPN	R50	train	test	Y	3.2	61.2	58.4	8609	207627	2634	config	detector reid
R50-FasterRCNN-FPN*	R50	train	test	Y	-	56.3	55.1	8866	235449	1987	-	-