Illumination Distillation Framework for Nighttime Person Re-Identification and a New Benchmark
文献类型：期刊论文
| 作者 | Lu, Andong1,2; Zhang, Zhang2 ; Huang, Yan2; Zhang, Yifan2; Li, Chenglong3; Tang, Jin2; Wang, Liang2
|
| 刊名 | IEEE TRANSACTIONS ON MULTIMEDIA
 |
| 出版日期 | 2024 |
| 卷号 | 26页码:406-419 |
| 关键词 | Bottleneck fusion computer vision illumination distillation image enhancement person re-identification |
| ISSN号 | 1520-9210 |
| DOI | 10.1109/TMM.2023.3266066 |
| 通讯作者 | Li, Chenglong(lcl1314@foxmail.com) |
| 英文摘要 | Nighttime person Re-ID (person re-identification in the nighttime) is a very important and challenging task for visual surveillance but it has not been thoroughly investigated. Under the low illumination condition, the performance of person Re-ID methods usually sharply deteriorates. To address the low illumination challenge in nighttime person Re-ID, this article proposes an Illumination Distillation Framework (IDF), which utilizes illumination enhancement and illumination distillation schemes to promote the learning of Re-ID models. Specifically, IDF consists of a master branch, an illumination enhancement branch, and an illumination distillation module. The master branch is used to extract the features from a nighttime image. The illumination enhancement branch first estimates an enhanced image from the nighttime image using a nonlinear curve mapping method and then extracts the enhanced features. However, nighttime and enhanced features usually contain data noise due to unstable lighting conditions and enhancement failures. To fully exploit the complementary benefits of nighttime and enhanced features while suppressing data noise, we propose an illumination distillation module. In particular, the illumination distillation module fuses the features from two branches through a bottleneck fusion model and then uses the fused features to guide the learning of both branches in a distillation manner. In addition, we build a real-world nighttime person Re-ID dataset, named Night600, which contains 600 identities captured from different viewpoints and nighttime illumination conditions under complex outdoor environments. Experimental results demonstrate that our IDF can achieve state-of-the-art performance on two nighttime person Re-ID datasets (i.e., Night600 and Knight). |
| WOS关键词 | NETWORK |
| 资助项目 | Natural Science Foundation of Anhui Province |
| WOS研究方向 | Computer Science ; Telecommunications |
| 语种 | 英语 |
| WOS记录号 | WOS:001157873000026 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 资助机构 | Natural Science Foundation of Anhui Province |
| 源URL | [http://ir.ia.ac.cn/handle/173211/57825]  |
| 专题 | 多模态人工智能系统全国重点实验室 |
| 通讯作者 | Li, Chenglong |
| 作者单位 | 1.Anhui Univ, Sch Comp Sci & Technol, Anhui Prov Key Lab Multimodal Cognit Computat, Hefei 230601, Peoples R China 2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 3.Anhui Univ, Sch Artificial Intelligence, Informat Mat & Intelligent Sensing Lab Anhui Prov, Anhui Prov Key Lab Multimodal Cognit Computat, Hefei 230601, Peoples R China |
| 推荐引用方式 GB/T 7714 | Lu, Andong,Zhang, Zhang,Huang, Yan,et al. Illumination Distillation Framework for Nighttime Person Re-Identification and a New Benchmark[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2024,26:406-419. |
| APA | Lu, Andong.,Zhang, Zhang.,Huang, Yan.,Zhang, Yifan.,Li, Chenglong.,...&Wang, Liang.(2024).Illumination Distillation Framework for Nighttime Person Re-Identification and a New Benchmark.IEEE TRANSACTIONS ON MULTIMEDIA,26,406-419. |
| MLA | Lu, Andong,et al."Illumination Distillation Framework for Nighttime Person Re-Identification and a New Benchmark".IEEE TRANSACTIONS ON MULTIMEDIA 26(2024):406-419. |
入库方式： OAI收割
来源：自动化研究所
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。