SIA OpenIR  > 光电信息技术研究室
Learning Model for Object Detection Based on Local Edge Features
Tang XS(唐旭晟); Shi ZL(史泽林); Li DQ(李德强); Ma L(马龙); Chen D(陈丹)
Department光电信息研究室
Conference NameIEEE International Conference on Information and Automation (ICIA 2009)
Conference DateJune 22-24, 2009
Conference PlaceZhuhai, China
Author of SourceIEEE
Source PublicationICIA: 2009 INTERNATIONAL CONFERENCE ON INFORMATION AND AUTOMATION, VOLS 1-3
PublisherIEEE
Publication PlaceNEW YORK
2009
Pages551-555
Indexed ByEI ; CPCI(ISTP)
EI Accession number20094812499015
WOS IDWOS:000277076800102
Contribution Rank1
ISBN978-1-4244-3607-1
Abstract

We present a learning model for object detection that uses a novel local edge features. The novel features are motivated by the scheme that use the chamfer distance as a shape comparison measure. The features can be calculated very quickly using a look-up table. Adaboost algorithm is used to select a discriminative edge features set from an over-complete local edge features pool and combine them to form an object detector. To demonstrate our method we trained a system to detect car in complex natural scenes using a single shape model. Experimental results show that our system can extremely rapidly detect objects in varying conditions (translation, scaling, occlusion and illumination) with high detection rate. The results are very competitive with other published object detection schemes. The learning techniques can be extended to detect other objects such as airplanes or pedestrian.

Language英语
Citation statistics
Document Type会议论文
Identifierhttp://ir.sia.cn/handle/173321/7991
Collection光电信息技术研究室
Corresponding AuthorTang XS(唐旭晟)
AffiliationShenyang Institute of Automation, The Chinese Academy of Sciences, Shenyang, 110016, China
Recommended Citation
GB/T 7714
Tang XS,Shi ZL,Li DQ,et al. Learning Model for Object Detection Based on Local Edge Features[C]//IEEE. NEW YORK:IEEE,2009:551-555.
Files in This Item:
File Name/Size DocType Version Access License
HYQW000708.pdf(265KB)会议论文 开放获取CC BY-NC-SAView Application Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Tang XS(唐旭晟)]'s Articles
[Shi ZL(史泽林)]'s Articles
[Li DQ(李德强)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Tang XS(唐旭晟)]'s Articles
[Shi ZL(史泽林)]'s Articles
[Li DQ(李德强)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Tang XS(唐旭晟)]'s Articles
[Shi ZL(史泽林)]'s Articles
[Li DQ(李德强)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: HYQW000708.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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