Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/66763
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Wang, P. | - |
dc.contributor.author | Shen, C. | - |
dc.contributor.author | Barnes, N. | - |
dc.contributor.author | Zheng, H. | - |
dc.date.issued | 2012 | - |
dc.identifier.citation | IEEE Transactions on Neural Networks and Learning Systems, 2012; 23(1):33-46 | - |
dc.identifier.issn | 2162-237X | - |
dc.identifier.issn | 1045-9227 | - |
dc.identifier.uri | http://hdl.handle.net/2440/66763 | - |
dc.description.abstract | Boosting based object detection has received significant attention recently. In this work, we propose totally-corrective asymmetric boosting algorithms for real-time object detection. Our algorithms differ from Viola-Jones’ detection framework in two folds. Firstly, our boosting algorithms explicitly optimize asymmetric loss of objectives, while AdaBoost used by Viola and Jones optimizes a symmetric loss. Secondly, by carefully deriving the Lagrange duals of the optimization problems, we design more efficient boosting in that the coefficients of the selected weak classifiers are updated in a totally-corrective fashion, in contrast to the stage-wise optimization commonly used by most boosting algorithms. Column generation is employed to solve the proposed optimization problems. Unlike conventional boosting, the proposed boosting algorithms are able to de-select those irrelevant weak classifiers in the ensemble while training a classification cascade. This results in improved detection performance as well as fewer weak classifiers in the learned strong classifier. Compared with AsymBoost of Viola and Jones [1], our proposed asymmetric boosting is non-heuristic and the training procedure is much simpler. Experiments on face and pedestrian detection demonstrate that our methods have superior detection performance than some of the state-of-the-art object detectors. | - |
dc.description.statementofresponsibility | Peng Wang, Chunhua Shen, Nick Barnes, and Hong Zheng | - |
dc.description.uri | http://ieee-cis.org/pubs/tnn/ | - |
dc.language.iso | en | - |
dc.publisher | IEEE | - |
dc.rights | Copyright 2011 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. | - |
dc.source.uri | http://dx.doi.org/10.1109/tnnls.2011.2178324 | - |
dc.subject | Object detection | - |
dc.subject | asymmetric learning | - |
dc.subject | AdaBoost | - |
dc.subject | totally-corrective boosting | - |
dc.subject | column generation | - |
dc.title | Fast and robust object detection using asymmetric totally-corrective boosting | - |
dc.type | Journal article | - |
dc.identifier.doi | 10.1109/TNNLS.2011.2178324 | - |
pubs.publication-status | Published | - |
dc.identifier.orcid | Shen, C. [0000-0002-8648-8718] | - |
Appears in Collections: | Aurora harvest Computer Science publications |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
hdl_66763.pdf | Accepted version | 3.99 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.