标题:Supervised Hash Coding With Deep Neural Network for Environment Perception of Intelligent Vehicles
作者:Yan, Chenggang; Xie, Hongtao; Yang, Dongbao; Yin, Jian; Zhang, Yongdong; Dai, Qionghai
作者机构:[Yan, Chenggang] Hangzhou Dianzi Univ, Inst Informat & Control, Hangzhou, Zhejiang, Peoples R China.; [Xie, Hongtao; Zhang, Yongdong] Univ Sci & Tec 更多
通讯作者:Xie, Hongtao
通讯作者地址:[Xie, HT]Univ Sci & Technol China, Sch Informat Sci & Technol, Hefei 230026, Anhui, Peoples R China.
来源:IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
出版年:2018
卷:19
期:1
页码:284-295
DOI:10.1109/TITS.2017.2749965
关键词:Intelligent vehicles; binary codes; supervised hashing; image retrieval;; deep learning
摘要:Image content analysis is an important surround perception modality of intelligent vehicles. In order to efficiently recognize the on-road environment based on image content analysis from the large-scale scene database, relevant images retrieval becomes one of the fundamental problems. To improve the efficiency of calculating similarities between images, hashing techniques have received increasing attentions. For most existing hash methods, the suboptimal binary codes are generated, as the hand-crafted feature representation is not optimally compatible with the binary codes. In this paper, a one-stage supervised deep hashing framework (SDHP) is proposed to learn high-quality binary codes. A deep convolutional neural network is implemented, and we enforce the learned codes to meet the following criterions: 1) similar images should be encoded into similar binary codes, and vice versa; 2) the quantization loss from Euclidean space to Hamming space should be minimized; and 3) the learned codes should be evenly distributed. The method is further extended into SDHP+ to improve the discriminative power of binary codes. Extensive experimental comparisons with state-of-the-art hashing algorithms are conducted on CIFAR-10 and NUS-WIDE, the MAP of SDHP reaches to 87.67% and 77.48% with 48 b, respectively, and the MAP of SDHP+ reaches to 91.16%, 81.08% with 12 b, 48 b on CIFAR-10 and NUS-WIDE, respectively. It illustrates that the proposed method can obviously improve the search accuracy.
收录类别:EI;SCIE
WOS核心被引频次:37
资源类型:期刊论文
TOP