Name
Abstract | ||
|---|---|---|
Human detection in images is challenged by the view and posture variation problem. In this paper, we propose a piecewise linear support vector machine (PL-SVM) method to tackle this problem. The motivation is to exploit the piecewise discriminative function to construct a nonlinear classification boundary that can discriminate multiview and multiposture human bodies from the backgrounds in a high-dimensional feature space. A PL-SVM training is designed as an iterative procedure of feature space division and linear SVM training, aiming at the margin maximization of local linear SVMs. Each piecewise SVM model is responsible for a subspace, corresponding to a human cluster of a special view or posture. In the PL-SVM, a cascaded detector is proposed with block orientation features and a histogram of oriented gradient features. Extensive experiments show that compared with several recent SVM methods, our method reaches the state of the art in both detection accuracy and computational efficiency, and it performs best when dealing with low-resolution human regions in clutter backgrounds. |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1109/TIP.2012.2222901 | IEEE Transactions on Image Processing |
Keywords | DocType | Volume |
margin maximization,multiview human bodies,local linear svm training,detection accuracy,image detection,cascaded detector,image resolution,computational efficiency,block orientation features,piecewise linear,histogram,feature space division,high-dimensional feature space,iterative procedure,piecewise discriminative function,low-resolution human regions,support vector machine,posture variation problem,gradient methods,multiposture human bodies,object detection,nonlinear classification boundary,classification,piecewise linear support vector machines,pl-svm method,human detection,gradient features,human cluster,clutter backgrounds,support vector machines,iterative methods | Journal | 22 |
Issue | ISSN | Citations |
2 | 1941-0042 | 15 |
PageRank | References | Authors |
0.56 | 32 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Qixiang Ye | 1 | 913 | 64.51 |
| Zhenjun Han | 2 | 176 | 16.40 |
| Jianbin Jiao | 3 | 367 | 32.61 |
| Jianzhuang Liu | 4 | 1614 | 98.72 |