Visual tracking based on stacked Denoising Autoencoder network with genetic algorithm optimization
Visual tracking based on stacked Denoising Autoencoder network with genetic algorithm optimization
复制标题
基于遗传算法优化的堆叠式去噪自动编码器网络的视觉跟踪
DOI：
10.1007/s11042-017-4702-1
复制
发表时间：
2017-11
影响因子：
3.6
通讯作者：
Guo Dawei
中科院分区：
文献类型：
--
作者：
Hua Weixin;Mu Dejun（慕德俊）;Guo Dawei
Visual object tracking in dynamic environments with severe appearance variations is a significant problem in the computer vision field. This paper proposes a novel visual tracking algorithm that exploits the multiple level features learning ability of SDAE. There are two training stages for the SDAE network: Layer-wise pre-training and fine-tuning. In the pre-training stage, a two-layer sparse-coded method is used to represent the input image, then a multi-level image feature descriptor is obtained. In the fine-tuning stage, the connection weights and bias terms for back propagation are gathered via genetic algorithm. A logistic classification layer is added at the top of the encoder network to enable tracking within the well-established particle filter network. Experimental results confirm, both qualitatively and quantitatively, that the proposed method performs well in comparison against eight other state-of-the-art methods.
登录
查看更多内容
DOI：
--
发表时间：
2005
期刊：
Mining and Metallurgy
影响因子：
--
作者：
Hua-chang Li
通讯作者：
Hua-chang Li
DOI：
10.1007/978-3-540-24671-8_37
发表时间：
2004
期刊：
--
影响因子：
--
作者：
David A. Ross;Jongwoo Lim;Ming-Hsuan Yang
通讯作者：
David A. Ross;Jongwoo Lim;Ming-Hsuan Yang
DOI：
10.5555/1756006.1953039
发表时间：
2010-03
期刊：
J. Mach. Learn. Res.
影响因子：
--
作者：
Pascal Vincent;H. Larochelle;Isabelle Lajoie;Yoshua Bengio;Pierre-Antoine Manzagol
通讯作者：
Pascal Vincent;H. Larochelle;Isabelle Lajoie;Yoshua Bengio;Pierre-Antoine Manzagol
影响因子：
10.6
作者：
Kaihua Zhang;Lei Zhang;Ming-Hsuan Yang
通讯作者：
Kaihua Zhang;Lei Zhang;Ming-Hsuan Yang
DOI：
--
发表时间：
2013-12
期刊：
--
影响因子：
--
作者：
Naiyan Wang;D. Yeung
通讯作者：
Naiyan Wang;D. Yeung