DocumentCode :
2832412
Title :
Nonlinear L1-norm minimization learning for human detection
Author :
Xu, Ran ; Jiao, Jianbin ; Ye, Qixiang
Author_Institution :
Grad. Univ. of Chinese Acad. of Sci., Beijing, China
fYear :
2011
fDate :
11-14 Sept. 2011
Firstpage :
3573
Lastpage :
3576
Abstract :
View, appearance and pose variations make it difficult to detect human objects only by using linear classification methods. Inspired by the successful applications of L1-norm minimization learning (LML) for human detection, we propose a new nonlinear L1-norm minimization learning method (NL-LML). It integrates a nonlinear transformation with an LML optimization model for human detection. The NL-LML method first maps the samples into a space based on the kernel function, and then combines the reformulated samples in the transformed space with the LML model to learn a classifier. Histograms of orientated gradient (HOG) features are used as the feature descriptors, and the sliding window scheme is adopted to detect humans in images. Experiments on two human datasets validate the efficiency and effectiveness of the proposed method.
Keywords :
gradient methods; image classification; learning (artificial intelligence); object detection; pose estimation; HOG; L1-norm minimization learning method; LML optimization model; NL-LML; histograms of orientated gradient; human detection; human object detection; kernel function; linear classification methods; nonlinear L1-norm minimization learning; nonlinear transformation; pose variations; reformulated samples; Feature extraction; Humans; Kernel; Minimization; Optimization; Support vector machines; Training; Human detection; Kernel function; L1-norm minimization; Nonlinear classification;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Image Processing (ICIP), 2011 18th IEEE International Conference on
Conference_Location :
Brussels
ISSN :
1522-4880
Print_ISBN :
978-1-4577-1304-0
Electronic_ISBN :
1522-4880
Type :
conf
DOI :
10.1109/ICIP.2011.6116488
Filename :
6116488
Link To Document :
بازگشت