期刊
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
卷 32, 期 3, 页码 1418-1430出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TCSVT.2021.3072171
关键词
Gray-scale; Image color analysis; Image synthesis; Generative adversarial networks; Training; Gallium nitride; Feature extraction; Person re-identification; visible-infrared; colorization; cross-modality; grayscale enhancement
资金
- Department of Science and Technology, Hubei Provincial People's Government [2017CFA012]
- Fundamental Research Funds for the Central Universities of China [191010001]
- Hubei Key Laboratory of Transportation Internet of Things [2018IOT003, 2020III026GX]
- National Natural Science Foundation of China [62066021]
- Ministry of Science and Technology, Taiwan [MOST 109-2634-F-007-013]
Visible-infrared person re-identification (VI-ReID) is a challenging cross-modality image matching problem in night-time surveillance applications. This study addresses the problem by learning the correspondence between infrared and visible images using intermediate grayscale images as auxiliary information, and proposes a grayscale enhancement colorization network (GECNet) to bridge the modality gap.
Visible-infrared person re-identification (VI-ReID) is an emerging and challenging cross-modality image matching problem because of the explosive surveillance data in night-time surveillance applications. To handle the large modality gap, various generative adversarial network models have been developed to eliminate the cross-modality variations based on a cross-modal image generation framework. However, the lack of point-wise cross-modality ground-truths makes it extremely challenging to learn such a cross-modal image generator. To address these problems, we learn the correspondence between single-channel infrared images and three-channel visible images by generating intermediate grayscale images as auxiliary information to colorize the single-modality infrared images. We propose a grayscale enhancement colorization network (GECNet) to bridge the modality gap by retaining the structure of the colored image which contains rich information. To simulate the infrared-to-visible transformation, the point-wise transformed grayscale images greatly enhance the colorization process. Our experiments conducted on two visible-infrared cross-modality person re-identification datasets demonstrate the superiority of the proposed method over the state-of-the-arts.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据