Title :
Human detection based on Curvelet transform
Author :
Han, Hong ; Fan, Youjian ; Chen, Zhichao
Author_Institution :
Xidian Univ., Xi´´an, China
Abstract :
A method in Curvelet transformation for human detection is proposed in this paper. First, the curvelet coefficient was obtained by conducting the second curvelet transform for images. Then several statistical characteristics were computed from each sub-band coefficient. Finally, according the possibilities of the statistical features chosen by AdaBoost weak classifiers, some reasonable statistical measures were chosen as the final edge feature vector. The experimental results on INRIA and MIT human database showed that CTD increased the detection accuracy comparing to HOG.
Keywords :
curvelet transforms; object detection; statistical analysis; AdaBoost weak classifiers; INRIA human database; MIT human database; final edge feature vector; human detection; second curvelet transform; statistical features; Feature extraction; Humans; Image edge detection; Lighting; Support vector machine classification; Training; Transforms; CTD; Edge Features; human detection;
Conference_Titel :
Multimedia Technology (ICMT), 2011 International Conference on
Conference_Location :
Hangzhou
Print_ISBN :
978-1-61284-771-9
DOI :
10.1109/ICMT.2011.6003080
