Show simple item record

dc.contributor.authorYe, Zhi-Qinzh_CN
dc.contributor.authorSu, Song-Zhizh_CN
dc.contributor.authorLi, Shao-Zizh_CN
dc.contributor.author苏松志zh_CN
dc.contributor.author李绍滋zh_CN
dc.date.accessioned2015-07-22T02:40:04Z
dc.date.available2015-07-22T02:40:04Z
dc.date.issued2011zh_CN
dc.identifier.citationProceedings - 2011 IEEE International Conference on Computer Science and Automation Engineering, CSAE 2011, 2011,2:366-370zh_CN
dc.identifier.other20113414258605zh_CN
dc.identifier.urihttps://dspace.xmu.edu.cn/handle/2288/86957
dc.descriptionConference Name:2011 IEEE International Conference on Computer Science and Automation Engineering, CSAE 2011. Conference Address: Shanghai, China. Time:June 10, 2011 - June 12, 2011.zh_CN
dc.descriptionIEEE Beijing Section; Pudong New Area Association for Computer; Pudong New Area Science and Technology Development Fund; Tongji University; Xiamen Universityzh_CN
dc.description.abstractObject detection and localization is an important research subject in computer vision. In pedestrian detection, the task of classification is to decide whether an object is present or not in current scanning window, while location focusing on more difficult problem. Sliding window approach is still the main approach now, but its computational cost strongly increases with the image size. In order to perform location as soon as possible, this paper introduce a method for pedestrian detection that relied on branch and bound search proposed by Lampert et al. Compare to sliding window, it can find a globally optimal classifier functions over all candidate subwindows in linear time. For feature vectors, we used HIK(histogram intersection kernel) to calculate the the similarity, and voting according to their values. Compare to others, the approach used few trainging samples, experimental showing the result. ? 2011 IEEE.zh_CN
dc.language.isoen_USzh_CN
dc.publisherIEEE Computer Societyzh_CN
dc.source.urihttp://dx.doi.org/10.1109/CSAE.2011.5952489zh_CN
dc.subjectComputer sciencezh_CN
dc.subjectComputer visionzh_CN
dc.subjectLinear programmingzh_CN
dc.subjectObject recognitionzh_CN
dc.titleResearch on branch and bound for pedestrian detectionzh_CN
dc.typeConferencezh_CN


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record