CASIA OpenIR  > 09年以前成果
A low-cost pedestrian-detection system with a single optical camera
Cao, Xian-Bin1,2; Qiao, Hong3,4; Keane, John5
Source PublicationIEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
2008-03-01
Volume9Issue:1Pages:58-67
SubtypeArticle
AbstractThe ultimate purpose of a pedestrian-detection system (PDS) is to reduce pedestrian-vehicle-related injury. Most such systems tend to adopt expensive sensors, such as infrared devices, in expectation of better performance. In comparison low-cost optical-camera-based system has much potential practical value, including a greater detection range, and can easily be trained to detect other objects. However, such low-cost systems are difficult to design (e.g., little original information can be collected, and the scene is very complex). To address these problems, an effective and reliable classifier is needed. The classifier should have a proper structure, its features need to be well selected, and a large number of high-quality samples are necessary for training. In this paper, we present a low-cost PDS which only uses a single optical camera. We design a cascade classifier to achieve an effective and reliable detection. First, our system scans two sequential frames at each zoom scale with a sliding window. Second, with each window, both appearance and motion features are extracted. A well-trained cascade classifier, combining statistical learning with a decomposed support-vector-machine classifier, then determines whether the window contains a human body. At the same time, to provide as much information as possible about the pedestrian, a small-scale weighted template tree trained by a coevolutionary algorithm is adopted to identify each pedestrian's direction, and the distance of each from the vehicle is also provided using an estimation algorithm. During the training procedure, we select key features by using the AdaBoost algorithm and a large number of high-quality samples. Experimental results demonstrate that the system is suitable for pedestrian detection in city traffic: The detection speed is more than 10 ft/s, the detection rate reaches 80%, and the false positive rate is no more than 0.3 parts per thousand.
KeywordCascade Classifier Coevolutionary Algorithm Decomposed Support Vector Machines (Svms) Pedestrian-detection System (Pds) Small-scale Weighted Template Tree Statistical Learning
WOS HeadingsScience & Technology ; Technology
WOS KeywordNIGHT-VISION ; TRACKING
Indexed BySCI
Language英语
WOS Research AreaEngineering ; Transportation
WOS SubjectEngineering, Civil ; Engineering, Electrical & Electronic ; Transportation Science & Technology
WOS IDWOS:000253790100007
Citation statistics
Cited Times:45[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/9516
Collection09年以前成果
Corresponding AuthorCao, Xian-Bin
Affiliation1.Univ Sci & Technol China, Dept Comp Sci & Technol, Anhua 230026, Peoples R China
2.Anhui Prov Key Lab Software Comp & Commun, Anhua 230026, Peoples R China
3.Chinese Acad Sci, Inst Automat, Lab Comp Syst & Intelligent Sci, Beijing 100080, Peoples R China
4.Univ Manchester, Sch Informat, Manchester M60 1QD, Lancs, England
5.Univ Manchester, Manchester M13 9PL, Lancs, England
Recommended Citation
GB/T 7714
Cao, Xian-Bin,Qiao, Hong,Keane, John. A low-cost pedestrian-detection system with a single optical camera[J]. IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS,2008,9(1):58-67.
APA Cao, Xian-Bin,Qiao, Hong,&Keane, John.(2008).A low-cost pedestrian-detection system with a single optical camera.IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS,9(1),58-67.
MLA Cao, Xian-Bin,et al."A low-cost pedestrian-detection system with a single optical camera".IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 9.1(2008):58-67.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Cao, Xian-Bin]'s Articles
[Qiao, Hong]'s Articles
[Keane, John]'s Articles
Baidu academic
Similar articles in Baidu academic
[Cao, Xian-Bin]'s Articles
[Qiao, Hong]'s Articles
[Keane, John]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Cao, Xian-Bin]'s Articles
[Qiao, Hong]'s Articles
[Keane, John]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.