Boosting part-sense multi-feature learners toward effective object detection

被引:3
作者
Chen, Shi [1 ]
Wang, Jinqiao [1 ]
Ouyang, Yi [1 ]
Wang, Bo [1 ]
Xu, Changsheng [1 ]
Lu, Hanqing [1 ]
机构
[1] Chinese Acad Sci, Inst Automat, Beijing, Peoples R China
基金
中国国家自然科学基金;
关键词
AdaBoost; Object detection; Multi-feature learners; L-1-regularized gradient boosting;
D O I
10.1016/j.cviu.2010.11.006
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
AdaBoost has been applied to object detection to construct the detectors with high performance of discrimination and generalization by single-feature learner. However, the poor discriminative power of extremely weak single-feature learners limits its application for general object detection. In this paper, we propose a novel comprehensive learner design mechanism toward effective object detection in terms of both discrimination and generalization abilities. Firstly, the part-sense multi-feature learners are designed to linearly combine the multiple local features to improve the descriptive and discriminative capacity of the learner. Secondly, we formulate the feature selection in part-sense multi-feature learner as a weighted LASSO regression. Using Least Angle Regression (LARS) method, our approach can choose features adaptively, efficiently and as few as possible to guarantee generalization performance. Finally, a robust L1-regularized gradient boosting is proposed to integrate our part-sense sparse features learner into an object classifier. Extensive experiments and comparisons on the face dataset and the human dataset show the proposed approach outperforms the traditional single-feature learner and other multi-feature learners in discriminative and generalization abilities. (C) 2010 Elsevier Inc. All rights reserved.
引用
收藏
页码:364 / 374
页数:11
相关论文
共 29 条
[1]   Histograms of oriented gradients for human detection [J].
Dalal, N ;
Triggs, B .
2005 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOL 1, PROCEEDINGS, 2005, :886-893
[2]  
DALAL N, 2006, ECCV, V2, P428
[3]   A Sparsity-Enforcing Method for Learning Face Features [J].
Destrero, Augusto ;
De Mol, Christine ;
Odone, Francesca ;
Verri, Alessandro .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2009, 18 (01) :188-201
[4]  
EFRON B, 2003, ANN STAT, P407
[5]   A decision-theoretic generalization of on-line learning and an application to boosting [J].
Freund, Y ;
Schapire, RE .
JOURNAL OF COMPUTER AND SYSTEM SCIENCES, 1997, 55 (01) :119-139
[6]  
FRIEDMAN J, 1999, REITZ LECT, V29, P1189
[7]  
Georghiades A. S., 2000, Proceedings Fourth IEEE International Conference on Automatic Face and Gesture Recognition (Cat. No. PR00580), P277, DOI 10.1109/AFGR.2000.840647
[8]   Fast algorithms for frequent itemset mining using FP-trees [J].
Grahne, G ;
Zhu, JF .
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2005, 17 (10) :1347-1362
[9]  
Huang Yongzhen, 2008, CVPR
[10]   Improving object detection with boosted histograms [J].
Laptev, Ivan .
IMAGE AND VISION COMPUTING, 2009, 27 (05) :535-544