Saved in:
Bibliographic Details
Main Authors: Kim, Vitaliy, Jung, Gunho, Lee, Seong-Whan
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2401.13950
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929223595196416
author Kim, Vitaliy
Jung, Gunho
Lee, Seong-Whan
author_facet Kim, Vitaliy
Jung, Gunho
Lee, Seong-Whan
contents Many multi-object tracking (MOT) approaches, which employ the Kalman Filter as a motion predictor, assume constant velocity and Gaussian-distributed filtering noises. These assumptions render the Kalman Filter-based trackers effective in linear motion scenarios. However, these linear assumptions serve as a key limitation when estimating future object locations within scenarios involving non-linear motion and occlusions. To address this issue, we propose a motion-based MOT approach with an adaptable motion predictor, called AM-SORT, which adapts to estimate non-linear uncertainties. AM-SORT is a novel extension of the SORT-series trackers that supersedes the Kalman Filter with the transformer architecture as a motion predictor. We introduce a historical trajectory embedding that empowers the transformer to extract spatio-temporal features from a sequence of bounding boxes. AM-SORT achieves competitive performance compared to state-of-the-art trackers on DanceTrack, with 56.3 IDF1 and 55.6 HOTA. We conduct extensive experiments to demonstrate the effectiveness of our method in predicting non-linear movement under occlusions.
format Preprint
id arxiv_https___arxiv_org_abs_2401_13950
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle AM-SORT: Adaptable Motion Predictor with Historical Trajectory Embedding for Multi-Object Tracking
Kim, Vitaliy
Jung, Gunho
Lee, Seong-Whan
Computer Vision and Pattern Recognition
Many multi-object tracking (MOT) approaches, which employ the Kalman Filter as a motion predictor, assume constant velocity and Gaussian-distributed filtering noises. These assumptions render the Kalman Filter-based trackers effective in linear motion scenarios. However, these linear assumptions serve as a key limitation when estimating future object locations within scenarios involving non-linear motion and occlusions. To address this issue, we propose a motion-based MOT approach with an adaptable motion predictor, called AM-SORT, which adapts to estimate non-linear uncertainties. AM-SORT is a novel extension of the SORT-series trackers that supersedes the Kalman Filter with the transformer architecture as a motion predictor. We introduce a historical trajectory embedding that empowers the transformer to extract spatio-temporal features from a sequence of bounding boxes. AM-SORT achieves competitive performance compared to state-of-the-art trackers on DanceTrack, with 56.3 IDF1 and 55.6 HOTA. We conduct extensive experiments to demonstrate the effectiveness of our method in predicting non-linear movement under occlusions.
title AM-SORT: Adaptable Motion Predictor with Historical Trajectory Embedding for Multi-Object Tracking
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2401.13950