UM  > 科技學院  > 電腦及資訊科學系
One sample based feature learning for vehicle identification
XU YANG1; YUAN YAN TANG1; HUI-WU LUO1; TAO WU2; LI SUN1; LEI LI1
2017-03-06
Conference Name2016 International Conference on Machine Learning and Cybernetics (ICMLC)
Source PublicationProceedings of the 2016 International Conference on Machine Learning and Cybernetics
Volume2
Pages1049-1054
Conference Date10-13 July 2016
Conference PlaceJeju
CountrySouth Korea
PublisherIEEE
Abstract

Vehicle identification is one of the frequently studied problems in video surveillance. Commonly, identifying an unknown vehicle object requires a large amount of training instances. Unfortunately, in the large parking scenario, the cost may be prohibitively expensive because of the finitely waiting time from the car owners. In this paper, we show that it is possible to identify a registered vehicle using a single training example. The key insight is that, the human visually representative properties, such as overall appearance and local texture, are described using colors and histogram of oriented gradient (HOG). They are firstly extracted from each patch to form the fundamental representation. After that, the well developed locality-constrained linear coding (LLC) technique is employed to learn a more informative representation. Next, with nearest neighbors (NN) servers as the main classifier, the classical genetic algorithm (GA) is utilized to decide the most informative patches so that the minimum mis-identified error is achieved. The proposed approach is experimentally demonstrated and evaluated on the open Dana36 data set using vehicle images that are taken under an approximate camera pose. Good improvements are obtained with respect to the strategies that do not use LLC encoded features and selectively combined patches.

KeywordFeature Learning Genetic Algorithm Llc One-shot Learning Patches-based Learning Vehicle Identification
DOIhttps://doi.org/10.1109/ICMLC.2016.7873024
URLView the original
Indexed By其他
Language英语
Fulltext Access
Citation statistics
Document TypeConference paper
CollectionDEPARTMENT OF COMPUTER AND INFORMATION SCIENCE
Affiliation1.Faculty of Science and Technology, University of Macau, Macau, China
2.National University of Defense Technology, Changsha, China
First Author AffilicationFaculty of Science and Technology
Recommended Citation
GB/T 7714
XU YANG,YUAN YAN TANG,HUI-WU LUO,et al. One sample based feature learning for vehicle identification[C]:IEEE,2017:1049-1054.
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
[XU YANG]'s Articles
[YUAN YAN TANG]'s Articles
[HUI-WU LUO]'s Articles
Baidu academic
Similar articles in Baidu academic
[XU YANG]'s Articles
[YUAN YAN TANG]'s Articles
[HUI-WU LUO]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[XU YANG]'s Articles
[YUAN YAN TANG]'s Articles
[HUI-WU LUO]'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.