期刊名称：International Journal of Multimedia and Ubiquitous Engineering
印刷版ISSN：1975-0080
出版年度：2015
卷号：10
期号：4
页码：325-336
DOI：10.14257/ijmue.2015.10.4.31
出版社：SERSC
摘要：Recent research has been devoted and focused on detecting pedestrians and vehicles in intelligent vehicles except for vulnerable road users (VRUs). Histogram of Oriented Gradients (HOGs) descriptor is one of the state-of-art methods which have been shown to significantly outperform the existing feature set for several objects detection. In this paper we present a method for two-wheelers detection based on the periodicity of the size of spatial regions; cells and blocks. Contrary to concatenating feature vectors using a dense grid of HOG, proposed algorithm storage extracted feature vectors according to the period in each step. Experimental results show that the new approach gives higher detection accuracy than that of the conventional method.
关键词：HOG; two-wheelers; local vectors; spatial regions; Adaboost
