The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
희소 표현이 시각적 추적에 성공적으로 적용되었습니다. 희소 추적의 최근 진전은 주로 입자 필터 프레임워크 내에서 이루어졌습니다. 그러나 대부분의 희소 추적기는 제한된 샘플 공간에서 각 입자에 대한 복잡한 특징 표현을 추출해야 하므로 계산 비용이 많이 들고 추적 성능이 떨어집니다. 위의 문제를 해결하기 위해 순환 역 올가미 모델을 기반으로 하는 새로운 희소 추적 방법을 제안합니다. 순환 행렬의 속성을 활용하여 조밀하게 샘플링된 대상 후보는 기본 특징 설명자를 주기적으로 이동하여 암시적으로 생성된 다음 강력한 모양 템플릿을 인코딩하기 위해 사전으로 역 희소 재구성 모델에 포함됩니다. 역 희소 모델을 해결하기 위해 승산기의 교번 방향 방법을 사용하고 주파수 영역에서 최적화 프로세스를 효율적으로 해결할 수 있으므로 제안된 추적기가 실시간으로 실행될 수 있습니다. 계산된 희소 계수 맵은 템플릿과 원형 이동 샘플 간의 유사성 점수를 나타냅니다. 따라서 피크 계수의 좌표에 따라 목표 위치를 직접 예측할 수 있습니다. 규모 인식 템플릿 업데이트 전략은 모양 변형과 규모 변화를 모두 고려하기 위해 학습하는 상관 필터 템플릿과 결합됩니다. 두 가지 까다로운 추적 벤치마크에 대한 정량적 및 정성적 평가는 모두 제안된 알고리즘이 여러 최첨단 희소 표현 기반 추적 방법에 대해 유리한 성능을 발휘함을 보여줍니다.
Chenggang GUO
University of Electronic Science and Technology of China
Dongyi CHEN
University of Electronic Science and Technology of China
Zhiqi HUANG
University of Electronic Science and Technology of China
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
부
Chenggang GUO, Dongyi CHEN, Zhiqi HUANG, "Real-Time Sparse Visual Tracking Using Circulant Reverse Lasso Model" in IEICE TRANSACTIONS on Information,
vol. E102-D, no. 1, pp. 175-184, January 2019, doi: 10.1587/transinf.2018EDP7248.
Abstract: Sparse representation has been successfully applied to visual tracking. Recent progresses in sparse tracking are mainly made within the particle filter framework. However, most sparse trackers need to extract complex feature representations for each particle in the limited sample space, leading to expensive computation cost and yielding inferior tracking performance. To deal with the above issues, we propose a novel sparse tracking method based on the circulant reverse lasso model. Benefiting from the properties of circulant matrices, densely sampled target candidates are implicitly generated by cyclically shifting the base feature descriptors, and then embedded into a reverse sparse reconstruction model as a dictionary to encode a robust appearance template. The alternating direction method of multipliers is employed for solving the reverse sparse model and the optimization process can be efficiently solved in the frequency domain, which enables the proposed tracker to run in real-time. The calculated sparse coefficient map represents the similarity scores between the template and circular shifted samples. Thus the target location can be directly predicted according to the coordinates of the peak coefficient. A scale-aware template updating strategy is combined with the correlation filter template learning to take into account both appearance deformations and scale variations. Both quantitative and qualitative evaluations on two challenging tracking benchmarks demonstrate that the proposed algorithm performs favorably against several state-of-the-art sparse representation based tracking methods.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2018EDP7248/_p
부
@ARTICLE{e102-d_1_175,
author={Chenggang GUO, Dongyi CHEN, Zhiqi HUANG, },
journal={IEICE TRANSACTIONS on Information},
title={Real-Time Sparse Visual Tracking Using Circulant Reverse Lasso Model},
year={2019},
volume={E102-D},
number={1},
pages={175-184},
abstract={Sparse representation has been successfully applied to visual tracking. Recent progresses in sparse tracking are mainly made within the particle filter framework. However, most sparse trackers need to extract complex feature representations for each particle in the limited sample space, leading to expensive computation cost and yielding inferior tracking performance. To deal with the above issues, we propose a novel sparse tracking method based on the circulant reverse lasso model. Benefiting from the properties of circulant matrices, densely sampled target candidates are implicitly generated by cyclically shifting the base feature descriptors, and then embedded into a reverse sparse reconstruction model as a dictionary to encode a robust appearance template. The alternating direction method of multipliers is employed for solving the reverse sparse model and the optimization process can be efficiently solved in the frequency domain, which enables the proposed tracker to run in real-time. The calculated sparse coefficient map represents the similarity scores between the template and circular shifted samples. Thus the target location can be directly predicted according to the coordinates of the peak coefficient. A scale-aware template updating strategy is combined with the correlation filter template learning to take into account both appearance deformations and scale variations. Both quantitative and qualitative evaluations on two challenging tracking benchmarks demonstrate that the proposed algorithm performs favorably against several state-of-the-art sparse representation based tracking methods.},
keywords={},
doi={10.1587/transinf.2018EDP7248},
ISSN={1745-1361},
month={January},}
부
TY - JOUR
TI - Real-Time Sparse Visual Tracking Using Circulant Reverse Lasso Model
T2 - IEICE TRANSACTIONS on Information
SP - 175
EP - 184
AU - Chenggang GUO
AU - Dongyi CHEN
AU - Zhiqi HUANG
PY - 2019
DO - 10.1587/transinf.2018EDP7248
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E102-D
IS - 1
JA - IEICE TRANSACTIONS on Information
Y1 - January 2019
AB - Sparse representation has been successfully applied to visual tracking. Recent progresses in sparse tracking are mainly made within the particle filter framework. However, most sparse trackers need to extract complex feature representations for each particle in the limited sample space, leading to expensive computation cost and yielding inferior tracking performance. To deal with the above issues, we propose a novel sparse tracking method based on the circulant reverse lasso model. Benefiting from the properties of circulant matrices, densely sampled target candidates are implicitly generated by cyclically shifting the base feature descriptors, and then embedded into a reverse sparse reconstruction model as a dictionary to encode a robust appearance template. The alternating direction method of multipliers is employed for solving the reverse sparse model and the optimization process can be efficiently solved in the frequency domain, which enables the proposed tracker to run in real-time. The calculated sparse coefficient map represents the similarity scores between the template and circular shifted samples. Thus the target location can be directly predicted according to the coordinates of the peak coefficient. A scale-aware template updating strategy is combined with the correlation filter template learning to take into account both appearance deformations and scale variations. Both quantitative and qualitative evaluations on two challenging tracking benchmarks demonstrate that the proposed algorithm performs favorably against several state-of-the-art sparse representation based tracking methods.
ER -