TY - GEN
T1 - A scale adaptive underwater target tracking algorithm
AU - Yan, Zhou
AU - Qingwu, Li
AU - Guanying, Huo
N1 - Publisher Copyright:
© 2017 IEEE.
PY - 2017/7/2
Y1 - 2017/7/2
N2 - A scale adaptive underwater target tracking algorithm based on multi-feature fusion is proposed in this paper. The underwater target tracking task can be divided into two modules: target translation estimation and scale estimation, by using translation correlation filter and scale correlation filter respectively. Meanwhile, a multiple channel features fusion scheme is presented, which employs color attributes and Histogram of Oriented Gradient (HOG) to improve the target feature model. The experimental results show that the proposed algorithm significantly improves the robustness and accuracy of the underwater tracking. Both qualitative and quantitative evaluations show that the proposed algorithm is strongly robust to scale variations, illumination changes, target deformation and background clutter in the underwater environment, while running at real-Time. Compared to the existing tracking approaches, the proposed algorithm obtains better tracking performance.
AB - A scale adaptive underwater target tracking algorithm based on multi-feature fusion is proposed in this paper. The underwater target tracking task can be divided into two modules: target translation estimation and scale estimation, by using translation correlation filter and scale correlation filter respectively. Meanwhile, a multiple channel features fusion scheme is presented, which employs color attributes and Histogram of Oriented Gradient (HOG) to improve the target feature model. The experimental results show that the proposed algorithm significantly improves the robustness and accuracy of the underwater tracking. Both qualitative and quantitative evaluations show that the proposed algorithm is strongly robust to scale variations, illumination changes, target deformation and background clutter in the underwater environment, while running at real-Time. Compared to the existing tracking approaches, the proposed algorithm obtains better tracking performance.
KW - Correlation filter
KW - Multi-feature fusion
KW - Scale estimation
KW - Underwater target tracking
UR - https://www.scopus.com/pages/publications/85047136755
U2 - 10.1109/ICEMI.2017.8265825
DO - 10.1109/ICEMI.2017.8265825
M3 - 会议稿件
AN - SCOPUS:85047136755
T3 - ICEMI 2017 - Proceedings of IEEE 13th International Conference on Electronic Measurement and Instruments
SP - 380
EP - 386
BT - ICEMI 2017 - Proceedings of IEEE 13th International Conference on Electronic Measurement and Instruments
A2 - Juan, Wu
A2 - Jiali, Yin
A2 - Qi, Zhang
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 13th IEEE International Conference on Electronic Measurement and Instruments, ICEMI 2017
Y2 - 20 October 2017 through 22 October 2017
ER -