Title | Adaptive Feature Selection Based on Local Descriptor Distinctive Degree for Vehicle Retrieval Application |
Authors | Zhu, Chuang Jia, Huizhu Lu, Tao Tao, Li Song, Jiawen Xiang, Guoqing Li, Yuan Xie, Xiaodong |
Affiliation | Peking Univ, Beijing, Peoples R China. Cooperat Medianet Innovat Ctr, Beijing, Peoples R China. Beida Binhai Informat Res, Tianjin, Peoples R China. |
Issue Date | 2017 |
Publisher | IEEE International Conference on Consumer Electronics (ICCE) |
Citation | IEEE International Conference on Consumer Electronics (ICCE).2017. |
Abstract | Performing image retrieval in large image database is becoming popular with the development of multimedia technology. Recently, ISO/IEC moving pictures experts group (MPEG) drafts compact descriptors for visual search (CDVS) to support the related applications. The state-of-the-art feature selection strategy in CDVS adopts a priori relevance measure to guide the selection. However, this method ignores the gradient information of the described feature. In this paper, we adopt CDVS to address traffic vehicle search in large database. After detailedly analyzing to the local descriptor, we firstly define local descriptor distinctive degree based on the gradient quantity and the spatial gradient distribution energy of the feature. Then we propose our adaptive feature selection method by combing feature distinctive degree and the priori information. The proposed method is proven to be better than the standard algorithm in CDVS and it almost introduces 10% mean average precision (MAP) and top match rate increase in low bit rate mode. |
URI | http://hdl.handle.net/20.500.11897/469900 |
Indexed | CPCI-S(ISTP) |
Appears in Collections: | 待认领 |