More about HKUST
A Search-Classify Approach for Cluttered Indoor Scene Understanding
************************************************************************ Joint Seminars by Dr. Yunhai WANG and Dr. Liangliang NAN Date: Monday, 24 September 2012 Venue: Lecture Theatre F (near lifts 25/26), HKUST ************************************************************************ Speaker: Liangliang NAN Shenzhen Institutes of Advanced Technology (SIAT) Chinese Academy of Sciences (CAS) Title: "A Search-Classify Approach for Cluttered Indoor Scene Understanding" Time: 4:30pm - 5:00pm Abstract: We present an algorithm for recognition and reconstruction of scanned 3D indoor scenes. 3D indoor reconstruction is particularly challenging due to object interferences, occlusions and overlapping which yield incomplete yet very complex scene arrangements. Since it is hard to assemble scanned segments into complete models, traditional methods for object recognition and reconstruction would be inefficient. We present a search-classify approach which interleaves segmentation and classification in an iterative manner. Using a robust classifier we traverse the scene and gradually propagate classification information. We reinforce classification by a template fitting step which yields a scene reconstruction. We deform-to-fit templates to classified objects to resolve classification ambiguities. The resulting reconstruction is an approximation which captures the general scene arrangement. Our results demonstrate successful classification and reconstruction of cluttered indoor scenes, captured in just few minutes. ***************** Biography: Liangliang Nan is an Associate Professor at the Shenzhen Institutes of Advanced Technology (SIAT), Chinese Academy of Sciences (CAS). He received his Ph.D. degree from Shenyang Institute of Automation, Chinese Academy of Sciences in Feb.2009. His research interests mostly focus on computer graphics, computer vision and human-computer interaction with an emphasis on processing and reconstruction from point cloud, detecting structure semantic information from point cloud, 3D models and images.