Binocular stereo vision based indoor scene perception
Hong Liu, Jiexin Pu, Qinghua Zhang · 2011
Scene perception aims to build a semantic context for various tasks of visual processing, especially for object recognition. Binocular vision system is now widely equipped with mobile intelligent robots,however, monocular images are currently mostly used for scene perception task. One can obtain lower classification performance by using features extracted from monocular image as the complexity of natural scene. In this paper a binocular stereo vision based approach for scene perception is developed. A feature descriptor of indoor scene is proposed, that is a vector extracted from planes fitting parameters in several specified regions. First step, scene is classified as empty space and close space classes using feature extracted from disparity map with nearest neighbor method. In following step, both empty space and close space scene are classified into some subclasses using Gist and proposed feature descriptor. To test our approach we created a dataset of 4 indoor scenes categories. The experiments show that our approach got excellent classification performance.