CAMOT: Camera Angle-aware Multi-Object Tracking

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Limanta, Felix, Uto, Kuniaki, Shinoda, Koichi
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913846243885056
author Limanta, Felix
Uto, Kuniaki
Shinoda, Koichi
author_facet Limanta, Felix
Uto, Kuniaki
Shinoda, Koichi
contents This paper proposes CAMOT, a simple camera angle estimator for multi-object tracking to tackle two problems: 1) occlusion and 2) inaccurate distance estimation in the depth direction. Under the assumption that multiple objects are located on a flat plane in each video frame, CAMOT estimates the camera angle using object detection. In addition, it gives the depth of each object, enabling pseudo-3D MOT. We evaluated its performance by adding it to various 2D MOT methods on the MOT17 and MOT20 datasets and confirmed its effectiveness. Applying CAMOT to ByteTrack, we obtained 63.8% HOTA, 80.6% MOTA, and 78.5% IDF1 in MOT17, which are state-of-the-art results. Its computational cost is significantly lower than the existing deep-learning-based depth estimators for tracking.
format Preprint
id arxiv_https___arxiv_org_abs_2409_17533
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle CAMOT: Camera Angle-aware Multi-Object Tracking
Limanta, Felix
Uto, Kuniaki
Shinoda, Koichi
Computer Vision and Pattern Recognition
This paper proposes CAMOT, a simple camera angle estimator for multi-object tracking to tackle two problems: 1) occlusion and 2) inaccurate distance estimation in the depth direction. Under the assumption that multiple objects are located on a flat plane in each video frame, CAMOT estimates the camera angle using object detection. In addition, it gives the depth of each object, enabling pseudo-3D MOT. We evaluated its performance by adding it to various 2D MOT methods on the MOT17 and MOT20 datasets and confirmed its effectiveness. Applying CAMOT to ByteTrack, we obtained 63.8% HOTA, 80.6% MOTA, and 78.5% IDF1 in MOT17, which are state-of-the-art results. Its computational cost is significantly lower than the existing deep-learning-based depth estimators for tracking.
title CAMOT: Camera Angle-aware Multi-Object Tracking
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2409.17533