상세정보
학술대회
Learning Video Correspondence using Appearance Module for Target Tracking
- 발행일
- 202101
- 출처
- International Conference on Big Data and Smart Computing (BigComp) 2021, pp.287-290
- 협약과제
- 20HR6100, 군내 병영생활 안전 및 인재관리 신뢰성 문제해결, 박상준
- 초록
- We introduce a new method for self-supervised video correspondence matching to effectively track targets in battlefield situations. Specifically, we propose Appearance module that enforces to maintain a target appearance between two consecutive frames in a local window, where an affinity matrix is computed on high-resolution feature maps with a small search window. It has an advantage of mitigating an over-fitting problem of a conventional affinity matrix that only predicts motions by reducing ambiguity of labels in a pretest task. Also the proposed method preserves the detailed shape of an object by handling high resolution information while high computational costs due to the correlation filter is alleviated by a small search window. Our experimental results on the DAVIS2017 dataset showed the significant performance improvement over the baseline.
- KSP 제안 키워드
- Correlation Filter, Correspondence Matching, Feature Map, High-resolution, Search Window, affinity matrix, computational cost, fitting problem, local window, new method, over-fitting