Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Track to Detect and Segment: An Online Multi-Object Tracker

About

Most online multi-object trackers perform object detection stand-alone in a neural net without any input from tracking. In this paper, we present a new online joint detection and tracking model, TraDeS (TRAck to DEtect and Segment), exploiting tracking clues to assist detection end-to-end. TraDeS infers object tracking offset by a cost volume, which is used to propagate previous object features for improving current object detection and segmentation. Effectiveness and superiority of TraDeS are shown on 4 datasets, including MOT (2D tracking), nuScenes (3D tracking), MOTS and Youtube-VIS (instance segmentation tracking). Project page: https://jialianwu.com/projects/TraDeS.html.

Jialian Wu, Jiale Cao, Liangchen Song, Yu Wang, Ming Yang, Junsong Yuan• 2021

Related benchmarks

TaskDatasetResultRank
Multiple Object TrackingMOT17 (test)
MOTA69.1
921
Video Instance SegmentationYouTube-VIS 2019 (val)
AP32.6
567
Multi-Object TrackingDanceTrack (test)
HOTA0.48
355
Multi-Object TrackingMOT16 (test)
MOTA70.1
228
Video Instance SegmentationYouTube-VIS (val)
AP32.6
118
3D Multi-Object TrackingnuScenes (val)
AMOTA11.8
115
Multi-Object TrackingMOT 2016 (test)
MOTA70.1
59
Multi-Object TrackingMOT17 1.0 (test)
MOTA69.1
48
Multi-Object TrackingMOT 2017 (test)
MOTA69.1
34
3D Object TrackingnuScenes (test)--
28
Showing 10 of 15 rows

Other info

Code

Follow for update