中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 三维可视计算
KGSNet: Key-Point-Guided Super-Resolution Network for Pedestrian Detection in the Wild

文献类型：期刊论文

作者Zhang, Yongqiang3; Bai, Yancheng4; Ding, Mingli3; Xu, Shibiao1; Ghanem, Bernard2
刊名IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
出版日期2021-05-01
卷号32期号:5页码:2251-2265
关键词Feature extraction Semantics Object detection Proposals Data mining Visualization Pedestrian detection real-world scenarios small-scale and heavily occluded superresolution network
ISSN号2162-237X
DOI10.1109/TNNLS.2020.3004819
通讯作者Ding, Mingli(mingli.ding.hit@gmail.com) ; Xu, Shibiao(shibiao.xu@nlpr.ia.ac.cn)
英文摘要In real-world scenarios (i.e., in the wild), pedestrians are often far from the camera (i.e., small scale), and they often gather together and occlude with each other (i.e., heavily occluded). However, detecting these small-scale and heavily occluded pedestrians remains a challenging problem for the existing pedestrian detection methods. We argue that these problems arise because of two factors: 1) insufficient resolution of feature maps for handling small-scale pedestrians and 2) lack of an effective strategy for extracting body part information that can directly deal with occlusion. To solve the above-mentioned problems, in this article, we propose a key-point-guided super-resolution network (coined KGSNet) for detecting these small-scale and heavily occluded pedestrians in the wild. Specifically, to address factor 1), a super-resolution network is first trained to generate a clear super-resolution pedestrian image from a small-scale one. In the super-resolution network, we exploit key points of the human body to guide the super-resolution network to recover fine details of the human body region for easier pedestrian detection. To address factor 2), a part estimation module is proposed to encode the semantic information of different human body parts where four semantic body parts (i.e., head and upper/middle/bottom body) are extracted based on the key points. Finally, based on the generated clear super-resolved pedestrian patches padded with the extracted semantic body part images at the image level, a classification network is trained to further distinguish pedestrians/backgrounds from the inputted proposal regions. Both proposed networks (i.e., super-resolution network and classification network) are optimized in an alternating manner and trained in an end-to-end fashion. Extensive experiments on the challenging CityPersons data set demonstrate the effectiveness of the proposed method, which achieves superior performance over previous state-of-the-art methods, especially for those small-scale and heavily occluded instances. Beyond this, we also achieve state-of-the-art performance (i.e., 3.89% MR-2 on the reasonable subset) on the Caltech data set.
WOS关键词DEEP
资助项目Natural Science Foundation of China[61603372]
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:000647397200035
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构Natural Science Foundation of China
源URL[http://ir.ia.ac.cn/handle/173211/44669]  
专题模式识别国家重点实验室_三维可视计算
通讯作者Ding, Mingli; Xu, Shibiao
作者单位1.Chinese Acad Sci, Inst Automat, Beijing 100864, Peoples R China
2.King Abdullah Univ Sci & Technol, Visual Comp Ctr, Thuwal 239556900, Saudi Arabia
3.Harbin Inst Technol, Sch Instrumentat Sci & Engn, Harbin 150001, Peoples R China
4.Chinese Acad Sci, Inst Software, Beijing 100864, Peoples R China
推荐引用方式
GB/T 7714		 Zhang, Yongqiang,Bai, Yancheng,Ding, Mingli,et al. KGSNet: Key-Point-Guided Super-Resolution Network for Pedestrian Detection in the Wild[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2021,32(5):2251-2265.
APA Zhang, Yongqiang,Bai, Yancheng,Ding, Mingli,Xu, Shibiao,&Ghanem, Bernard.(2021).KGSNet: Key-Point-Guided Super-Resolution Network for Pedestrian Detection in the Wild.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,32(5),2251-2265.
MLA Zhang, Yongqiang,et al."KGSNet: Key-Point-Guided Super-Resolution Network for Pedestrian Detection in the Wild".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 32.5(2021):2251-2265.

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。