Person Reidentification Based on Elastic Projections | |
Li, Xuelong; Liu, Lina; Lu, Xiaoqiang; Li, XL (reprint author), Chinese Acad Sci, Inst Opt & Precis Mech, Ctr OPTical IMagery Anal & Learning OPTIMAL, State Key Lab Transient Opt & Photon, Xian 710119, Shaanxi, Peoples R China. | |
作者部门 | 光学影像学习与分析中心 |
2018-04-01 | |
发表期刊 | IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS |
ISSN | 2162-237X |
卷号 | 29期号:4页码:1314-1327 |
产权排序 | 1 |
摘要 | Person reidentification usually refers to matching people in different camera views in nonoverlapping multicamera networks. Many existing methods learn a similarity measure by projecting the raw feature to a latent subspace to make the same target's distance smaller than different targets' distances. However, the same targets captured in different camera views should hold the same intrinsic attributes while different targets should hold different intrinsic attributes. Projecting all the data to the same subspace would cause loss of such an information and comparably poor discriminability. To address this problem, in this paper, a method based on elastic projections is proposed to learn a pairwise similarity measure for person reidentification. The proposed model learns two projections, positive projection and negative projection, which are both representative and discriminative. The representability refers to: for the same targets captured in two camera views, the positive projection can bridge the corresponding appearance variation and represent the intrinsic attributes of the same targets, while for the different targets captured in two camera views, the negative projection can explore and utilize the different attributes of different targets. The discriminability means that the intraclass distance should become smaller than its original distance after projection, while the interclass distance becomes larger on the contrary, which is the elastic property of the proposed model. In this case, prior information of the original data space is used to give guidance for the learning phase; more importantly, similar targets (but not the same) are effectively reduced by forcing the same targets to become more similar and different targets to become more distinct. The proposed model is evaluated on three benchmark data sets, including VIPeR, GRID, and CUHK, and achieves better performance than other methods. |
文章类型 | Article |
关键词 | Machine Learning Person Reidentification Representative And Discriminative Video Surveillance |
学科领域 | Computer Science, Artificial Intelligence |
WOS标题词 | Science & Technology ; Technology |
DOI | 10.1109/TNNLS.2016.2602855 |
收录类别 | SCI ; EI |
关键词[WOS] | RECOGNITION ; CLASSIFICATION ; FEATURES ; TRACKING ; RANKING |
语种 | 英语 |
WOS研究方向 | Computer Science ; Engineering |
WOS类目 | Computer Science, Artificial Intelligence ; Computer Science, Hardware & Architecture ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic |
WOS记录号 | WOS:000427859600044 |
EI入藏号 | 20171703591766 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.opt.ac.cn/handle/181661/30017 |
专题 | 光谱成像技术研究室 |
通讯作者 | Li, XL (reprint author), Chinese Acad Sci, Inst Opt & Precis Mech, Ctr OPTical IMagery Anal & Learning OPTIMAL, State Key Lab Transient Opt & Photon, Xian 710119, Shaanxi, Peoples R China. |
作者单位 | Chinese Acad Sci, Inst Opt & Precis Mech, Ctr OPTical IMagery Anal & Learning OPTIMAL, State Key Lab Transient Opt & Photon, Xian 710119, Shaanxi, Peoples R China |
推荐引用方式 GB/T 7714 | Li, Xuelong,Liu, Lina,Lu, Xiaoqiang,et al. Person Reidentification Based on Elastic Projections[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2018,29(4):1314-1327. |
APA | Li, Xuelong,Liu, Lina,Lu, Xiaoqiang,&Li, XL .(2018).Person Reidentification Based on Elastic Projections.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,29(4),1314-1327. |
MLA | Li, Xuelong,et al."Person Reidentification Based on Elastic Projections".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 29.4(2018):1314-1327. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Person Reidentificat(2236KB) | 期刊论文 | 作者接受稿 | 限制开放 | CC BY-NC-SA | 请求全文 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论