Home >

news ヘルプ

論文・著書情報


タイトル
和文: 
英文:CAMOT: Camera Angle-aware Multi-Object Tracking 
著者
和文: LIMANTA Felix, 宇都 有昭, 篠田 浩一.  
英文: Felix Limanta, Kuniaki Uto, Koichi Shinoda.  
言語 English 
掲載誌/書名
和文: 
英文:2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 
巻, 号, ページ         pp. 6465-6474
出版年月 2024年1月 
出版者
和文: 
英文:IEEE 
会議名称
和文: 
英文:IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2024 
開催地
和文: 
英文:Hawaii 
ファイル
公式リンク https://wacv2024.thecvf.com/
 
DOI https://doi.org/10.1109/WACV57701.2024.00635
アブストラクト 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.

©2007 Institute of Science Tokyo All rights reserved.