JIPS (한국정보처리학회)
Current Result Document :
| 한글제목(Korean Title) |
Dynamic Tracking Aggregation with Transformers for RGB-T Tracking |
| 영문제목(English Title) |
Dynamic Tracking Aggregation with Transformers for RGB-T Tracking |
| 저자(Author) |
Xiaohu Liu
Zhiyong Lei
|
| 원문수록처(Citation) |
VOL 19 NO. 01 PP. 0080 ~ 0088 (2023. 02) |
한글내용
(Korean Abstract) |
|
영문내용
(English Abstract) |
RGB-thermal (RGB-T) tracking using unmanned aerial vehicles (UAVs) involves challenges with regards to the similarity of objects, occlusion, fast motion, and motion blur, among other issues. In this study, we propose dynamic tracking aggregation (DTA) as a unified framework to perform object detection and data association. The proposed approach obtains fused features based a transformer model and an L1-norm strategy. To link the current frame with recent information, a dynamically updated embedding called dynamic tracking identification (DTID) is used to model the iterative tracking process. For object association, we designed a long short-term tracking aggregation module for dynamic feature propagation to match spatial and temporal embeddings. DTA achieved a highly competitive performance in an experimental evaluation on public benchmark datasets. |
| 키워드(Keyword) |
Cross-modal Fusion
Dynamic Tracking Aggregation
RGB-T Tracking
Transformers
|
| 파일첨부 |
PDF 다운로드
|
