Title :
Integrate multi-modal cues for category-independent object detection and localization
Author :
Zhang, Jianhua ; Xiao, Junhao ; Zhang, Jianwei ; Zhang, Houxiang ; Chen, Shengyong
Author_Institution :
TAMS group, Dept. Informatics, Hamburg University. Vogt-Koelln-Strasse 30, 22527, Germany
Abstract :
To detect and localize objects is an indispensable step for many computer vision tasks. Most of the state-of-the-art methods of object detection and localization are category-dependent. These methods can achieve a significant performance. However, they are useless for detecting and localizing objects belonging to an unknown category when applying them to an unknown environment. In this paper, a method is proposed for detecting and localizing generic objects without specifying their categories. The proposed method combines diverse cues, including multi-scale saliency, superpixels straddling, intensity, depth and global information, into a uniform Bayesian framework to obtain accurate detection and localization. By comparison to state-of-the-art methods, our experiments show the promising performance of the proposed method based on the PASCAL VOC 08 dataset and our indoor scene dataset.
Keywords :
Bayesian methods; Detectors; Educational institutions; Feature extraction; Histograms; Object detection; Training;
Conference_Titel :
Intelligent Robots and Systems (IROS), 2011 IEEE/RSJ International Conference on
Conference_Location :
San Francisco, CA
Print_ISBN :
978-1-61284-454-1
DOI :
10.1109/IROS.2011.6094960