Object Detection by Spatial Salience Region Features

This paper addresses the challenging problem of detecting objects in still images. A new approach of object detection based on spatial salience region features is introduced. The features consist of marginal distributions of an image over local and global patches. It can preserve shape and contour of an object, and discriminates between object and non-object classes. There are three main contributions in this paper. First of all, we expand the histogram of oriented gradients which can capture local and global compact features of object automatically by extracting features in salience regions only. Secondly, we employ feature similarity and fisher criterion to measure discriminability of features and select some discriminative features to identify the object. Thirdly, a sparse Bayesian classifier, the relevance vector machine, is constructed to train the selected features from target and surrounding background. The proposed algorithm is tested by some public database and pictures which obtained from surveillance video. Experimental results show that the proposed approach is efficient and accurate in object detection.