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. 中科院工业视觉智能装备工程实验室
  5. 精密感知与控制
A fast fused part-based model with new deep feature for pedestrian detection and security monitoring

文献类型：期刊论文

作者Cheng, Eric Juwei4; Prasad, Mukesh3; Yang, Jie3; Khanna, Pritee2; Chen, Bing-Hong4; Tao, Xian1; Young, Ku-Young4; Lin, Chin-Teng3
刊名MEASUREMENT
出版日期2020-02-01
卷号151页码:12
关键词Pedestrian detection Haar-like feature Deep fused feature Deformable partmodel Security monitoring
ISSN号0263-2241
DOI10.1016/j.measurement.2019.107081
通讯作者Prasad, Mukesh(mukesh.prasad@uts.edu.au)
英文摘要In recent years, pedestrian detection based on computer vision has been widely used in intelligent transportation, security monitoring, assistance driving and other related applications. However, one of the remaining open challenges is that pedestrians are partially obscured and their posture changes. To address this problem, deformable part model (DPM) uses a mixture of part filters to capture variation in view point and appearance and achieves success for challenging datasets. Nevertheless, the expensive computation cost of DPM limits its ability in the real-time application. This study propose a fast fused part-based model (FFPM) for pedestrian detection to detect the pedestrians efficiently and accurately in the crowded environment. The first step of the proposed method trains six Adaboost classifiers with Haar-like feature for different body parts (e.g., head, shoulders, and knees) to build the response feature maps. These six response feature maps are combined with full-body model to produce spatial deep features. The second step of the proposed method uses the deep features as an input to support vector machine (SVM) to detect pedestrian. A variety of strategies is introduced in the proposed model, including part-based to full-body method, spatial filtering, and multi-ratios combination. Experiment results show that the proposed FFPM method improves the computation speed of DPM and maintains the performance in detection. (C) 2019 Elsevier Ltd. All rights reserved.
资助项目Australian Re-search Council (ARC)[DP180100670] ; Australian Re-search Council (ARC)[DP180100656] ; Army Research Laboratory ; Taiwan Ministry of Science and Technology MOST[106-2218-E-009-027-MY3] ; [W911NF-10-2-0022] ; [W911NF-10-D-0 0 02/TO 0 023]
WOS研究方向Engineering ; Instruments & Instrumentation
语种英语
WOS记录号WOS:000500942200046
出版者ELSEVIER SCI LTD
资助机构Australian Re-search Council (ARC) ; Army Research Laboratory ; Taiwan Ministry of Science and Technology MOST
源URL[http://ir.ia.ac.cn/handle/173211/29373]  
专题精密感知与控制研究中心_精密感知与控制
通讯作者Prasad, Mukesh
作者单位1.Chinese Acad Sci, Inst Automat, Res Ctr Precis Sensing & Control, Beijing, Peoples R China
2.Indian Inst Informat Technol Design & Mfg Jabalpu, Comp Sci & Engn Discipline, Jabalpur, India
3.Univ Technol Sydney, FEIT, Sch Comp Sci, Ctr Artificial Intelligence, Sydney, NSW, Australia
4.Natl Chaio Tung Univ, Dept Elect Engn, Hsinchu, Taiwan
推荐引用方式
GB/T 7714		 Cheng, Eric Juwei,Prasad, Mukesh,Yang, Jie,et al. A fast fused part-based model with new deep feature for pedestrian detection and security monitoring[J]. MEASUREMENT,2020,151:12.
APA Cheng, Eric Juwei.,Prasad, Mukesh.,Yang, Jie.,Khanna, Pritee.,Chen, Bing-Hong.,...&Lin, Chin-Teng.(2020).A fast fused part-based model with new deep feature for pedestrian detection and security monitoring.MEASUREMENT,151,12.
MLA Cheng, Eric Juwei,et al."A fast fused part-based model with new deep feature for pedestrian detection and security monitoring".MEASUREMENT 151(2020):12.

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。