1 / 3

Vision-based Object Recognition for Environment Perception (5-1)

Vision-based Object Recognition for Environment Perception (5-1). Background of research. • Vision-based object recognition is a core technology for a human-friendly service robot. ▪ Human-friendly autonomous navigation “Seeing a sofa, this may be a living room.”

jace
Download Presentation

Vision-based Object Recognition for Environment Perception (5-1)

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Vision-based Object Recognition for Environment Perception(5-1) • Background of research • • Vision-based object recognition is a core technology for a human-friendly service robot. • ▪ Human-friendly autonomous navigation • “Seeing a sofa, this may be a living room.” • ▪ Object-centered human-robot interaction • “T-rot! These are my glasses. Remember them!” Door • Research objectives TV • Vision-based object recognition technologies ▪ Specific object recognition (Identification) ▪ Category object recognition ▪Multi-modal based object modeling/learning • Object-based environment perception ▪ Perceptionof spatial relationship between objects ▪ Object-based mapping and global localization Sofa

  2. Vision-based Object Recognition for Environment Perception(5-1) (1-3) 상호작용 Object verification Object Modeler Object Learner • Research contents • Specific/Category object recognition ▪ LIF+Contour Fragment / Spectral Matching • Multi-modal based object modeling/learning ▪SFM/handgesture + voice + category OR • Perception spatial relationship between objects ▪Ontology + Stereo depth + Object recognition • Object-based mapping and global localization ▪object + topology map/ 2-view based localization “Register this pencil sharpener!” Task : Register(PS) Human Detector Object Detector

  3. Project Leader Sung-Kee Park Senior Research Scientist, Center for Cognitive Robotics Research Korea Institute of Science and Technology (KIST) skee@kist.re.kr Research Institutes : KIST Researchers : 12 (KIST)

More Related