Publication:
DirectTracker: 3D Multi-Object Tracking using Direct Image Alignment and Photometric Bundle Adjustment
Authors:
Mariia Gladkova, Nikita Korobov, Nikolaus Demmel, Aljosa Osep, Laura Leal-Taixe and Daniel Cremers
Conference:
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2022
arXiv:
https://arxiv.org/abs/2209.14965
Project Page:
https://vision.in.tum.de/research/vslam/directtracker
Abstract:
Direct methods have shown excellent performance in the applications of visual odometry and SLAM. In this work we propose to leverage their effectiveness for the task of 3D multi-object tracking. To this end, we propose DirectTracker, a framework that effectively combines direct image alignment for the short-term tracking and sliding-window photometric bundle adjustment for 3D object detection. Object proposals are estimated based on the sparse sliding-window pointcloud and further refined using an optimization-based cost function that carefully combines 3D and 2D cues to ensure consistency in image and world space. We propose to evaluate 3D tracking using the recently introduced higher-order tracking accuracy (HOTA) metric and the generalized intersection over union similarity measure to mitigate the limitations of the conventional use of intersection over union for the evaluation of vision-based trackers. We perform evaluation on the KITTI Tracking benchmark for the Car class and show competitive performance in tracking objects both in 2D and 3D.
