Journal
IMAGE AND VISION COMPUTING
Volume 106, Issue -, Pages -Publisher
ELSEVIER
DOI: 10.1016/j.imavis.2020.104091
Keywords
Multiple object tracking; refinement
Categories
Funding
- JSPS KAKENHI [JP17H06101]
- MSRA Collaborative Research 2019 Grant - Microsoft Research Asia
Ask authors/readers for more resources
The refinement method was studied for Multiple Object Tracking (MOT) tasks, defining Mix-up Error and Cut-off Error in imperfect tracklets, proposing the ReMOT framework to improve appearance features by splitting and merging tracklets, significantly improving MOT results, and assisting semi-automatic MOT data annotation.
Although refinement is commonly used in visual tasks to improve pre-obtained results, it has not been studied for Multiple Object Tracking (MOT) tasks. This could be attributed to two reasons: i) it has not been explored what kinds of errors should - and could - be reduced in MOT refinement; ii) the refinement target, namely, the tracklets, are intertwined and interactive in a 3D spatio-temporal space, and therefore changing one tracklet may affect the others. To tackle these issues, i) we define two types of errors in imperfect tracklets, as Mix-up Error and Cut-off Error, to clarify the refinement goal; ii) we propose a Refining MOT Framework (ReMOT), which first splits imperfect tracklets and then merges the split tracklets with appearance features improved by self-supervised learning. Experiments demonstrate that ReMOT can make significant improvements to state-of-the-art MOT results as powerful post-processing. As a new application, we demonstrate that ReMOT has the potential of being used to assist semi-automatic MOT data annotation and partially release humans from the tedious work. (C) 2020 Elsevier B.V. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available