中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
Viewpoint Alignment and Discriminative Parts Enhancement in 3D Space for Vehicle ReID

文献类型:期刊论文

作者Meng, Dechao1; Li, Liang1; Liu, Xuejing1; Gao, Lin4; Huang, Qingming2,3
刊名IEEE TRANSACTIONS ON MULTIMEDIA
出版日期2023
卷号25页码:2954-2965
关键词3D reconstruction feature enhancement vehicle ReID viewpoint alignment
ISSN号1520-9210
DOI10.1109/TMM.2022.3154102
英文摘要Vehicle Re-Identification is to find the same vehicle from images captured in different views under cross-camera scenarios. Traditional methods focus on depicting the holistic appearance of a vehicle, but they suffer from the hard samples with the same vehicle type and color. Recent works leverage the discriminative visual cues to solve this problem, where three challenges exist as follows. First, vehicle features are misaligned and distorted because of the viewpoint variance. Second, the discriminative visual cues are usually subtle, which is easy to be diluted by the large area of non-discriminative regions in subsequent average pooling modules. Third, these discriminative visual cues are dynamic for the same image when it compares with different vehicle images. To tackle the above problems, we project the vehicle images from 2D to 3D space and rotate them to the same view, and leverage the viewpoint aligned features to enhance the discriminative parts for vehicle ReID. In detail, our method consists of three sub-modules, 1) The 3D viewpoint alignment module restores the 3D information of the vehicle from a single vehicle image, and then rotates and re-renders it under fixed viewpoints. It enables fine-grained viewpoint alignment and relieves the distortion of the vehicle caused by the viewpoint variation. 2) The discriminative parts enhancement module performs feature enhancement guided by the prior distribution of distinctive parts. 3) The adaptive duplicated parts suppression module guides the network to focus on the most discriminative parts, which not only prevents the dilution of the high responses but also provides explainable evidence. The experimental results reveal our method achieves new state-of-the-art on large scale vehicle ReID dataset.
资助项目National Key Ramp;D Program of China[2018AAA0102000] ; National Natural Science Foundation of China[61732007] ; Youth Innovation Promotion Association of Chinese Academy of Sciences[2020108] ; CCF-Baidu Open Fund[2021PP15002000] ; CAAI-Huawei MindSpore Open Fund
WOS研究方向Computer Science ; Telecommunications
语种英语
WOS记录号WOS:001045742200001
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
源URL[http://119.78.100.204/handle/2XEOYT63/21351]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Li, Liang
作者单位1.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
3.Univ Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China
4.Univ Chinese Acad Sci, Inst Comp Technol, Beijing Key Lab Mobile Comp & Pervas Device, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714
Meng, Dechao,Li, Liang,Liu, Xuejing,et al. Viewpoint Alignment and Discriminative Parts Enhancement in 3D Space for Vehicle ReID[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2023,25:2954-2965.
APA Meng, Dechao,Li, Liang,Liu, Xuejing,Gao, Lin,&Huang, Qingming.(2023).Viewpoint Alignment and Discriminative Parts Enhancement in 3D Space for Vehicle ReID.IEEE TRANSACTIONS ON MULTIMEDIA,25,2954-2965.
MLA Meng, Dechao,et al."Viewpoint Alignment and Discriminative Parts Enhancement in 3D Space for Vehicle ReID".IEEE TRANSACTIONS ON MULTIMEDIA 25(2023):2954-2965.

入库方式: OAI收割

来源:计算技术研究所

浏览0
下载0
收藏0
其他版本

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。