{"445081":{"#nid":"445081","#data":{"type":"event","title":"IRIM Robotics Seminar\u2013Martial Hebert","body":[{"value":"\u003Cp\u003ECarnegie Mellon\u2019s\u0026nbsp;Martial Hebert, the director of the\u0026nbsp;Robotics Institute\u003Cstrong\u003E,\u0026nbsp;\u003C\/strong\u003Epresents \u201cChallenges in Semantic Perception for Autonomous Systems\u201d as part of the IRIM Robotics Seminar Series.\u0026nbsp;The event will be held in the\u0026nbsp;TSRB Banquet Hall from 12-1 p.m. and is open to the public.\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EAbstract\u003C\/strong\u003E\u003C\/p\u003E\u003Cp\u003EDespite considerable progress in all aspects of machine perception, using machine vision in autonomous systems remains a formidable challenge. This is especially true in applications such as robotics, in which even a small error rate in the perception system can have catastrophic consequences for the overall system.\u003C\/p\u003E\u003Cp\u003EThis talk will review a few ideas that could be used to start formalizing the issues revolving around integrating vision systems. They include a systematic approach to the problem of self-assessment of vision algorithms and predicting quality metrics on the inputs to the vision algorithms, ideas on how to manage multiple hypotheses generated from a vision algorithm rather than relying on a single \u201chard\u201d decision, and methods for using external (non-visual) domain- and task-dependent information. These ideas will be illustrated with examples of recent vision for scene understanding, depth estimation, and object recognition.\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EBio\u003C\/strong\u003E\u003C\/p\u003E\u003Cp\u003EMartial\u0026nbsp;Hebert\u2019s\u0026nbsp;work is in the areas of computer vision and perception for autonomous systems.\u0026nbsp;His interests are in the interpretation of perception data (both 2-D and 3-D), including building models of environments. Current research directions include:\u003C\/p\u003E\u003Cul\u003E\u003Cli\u003EEfficient techniques for object\/category recognition\u003C\/li\u003E\u003Cli\u003EUse of contextual information, in particular 3-D geometry from images, for scene analysis\u003C\/li\u003E\u003Cli\u003ESymbolic knowledge for scene interpretation and reconstruction\u003C\/li\u003E\u003Cli\u003EMotion analysis for feature extraction and event detection in video clips\u003C\/li\u003E\u003Cli\u003EEfficient tools for the analysis of dynamic 3-D point clouds (\u00223-D signal processing\u0022)\u003C\/li\u003E\u003Cli\u003EPerception for autonomous systems\u003C\/li\u003E\u003Cli\u003EDetection, tracking, and prediction in dynamic environments\u003C\/li\u003E\u003C\/ul\u003E","summary":null,"format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003ECarnegie Mellon\u2019s\u0026nbsp;Martial Hebert, the director of the\u0026nbsp;Robotics Institute\u003Cstrong\u003E,\u0026nbsp;\u003C\/strong\u003Epresents \u201cChallenges in Semantic Perception for Autonomous Systems\u201d as part of the IRIM Robotics Seminar Series.\u0026nbsp;The event will be held in the\u0026nbsp;TSRB Banquet Hall from 12-1 p.m. and is open to the public.\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"Martial Hebert presents \u201cChallenges in Semantic Perception for Autonomous Systems\u201d as part of the IRIM Robotics Seminar Series."}],"uid":"27255","created_gmt":"2015-09-04 16:13:02","changed_gmt":"2017-04-13 21:18:23","author":"Josie Giles","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2015-10-07T13:00:00-04:00","event_time_end":"2015-10-07T14:00:00-04:00","event_time_end_last":"2015-10-07T14:00:00-04:00","gmt_time_start":"2015-10-07 17:00:00","gmt_time_end":"2015-10-07 18:00:00","gmt_time_end_last":"2015-10-07 18:00:00","rrule":null,"timezone":"America\/New_York"},"extras":[],"hg_media":{"445091":{"id":"445091","type":"image","title":"Martial Hebert","body":null,"created":"1449256205","gmt_created":"2015-12-04 19:10:05","changed":"1475895184","gmt_changed":"2016-10-08 02:53:04","alt":"Martial Hebert","file":{"fid":"203161","name":"hebert_martial.jpg","image_path":"\/sites\/default\/files\/images\/hebert_martial_0.jpg","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/images\/hebert_martial_0.jpg","mime":"image\/jpeg","size":19606,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/images\/hebert_martial_0.jpg?itok=S5n3l1HH"}}},"media_ids":["445091"],"related_links":[{"url":"http:\/\/www.cs.cmu.edu\/~hebert\/","title":"Martial Hebert"},{"url":"http:\/\/robotics.gatech.edu\/","title":"Center for Robotics \u0026 Intelligent Machines"}],"groups":[{"id":"47223","name":"College of Computing"},{"id":"50876","name":"School of Interactive Computing"},{"id":"142761","name":"IRIM"}],"categories":[],"keywords":[{"id":"1808","name":"graduate students"},{"id":"81491","name":"Institute for Robotics and Intelligent Machines (IRIM)"},{"id":"667","name":"robotics"},{"id":"167194","name":"seminar series"}],"core_research_areas":[],"news_room_topics":[],"event_categories":[{"id":"1795","name":"Seminar\/Lecture\/Colloquium"}],"invited_audience":[{"id":"78751","name":"Undergraduate students"},{"id":"78761","name":"Faculty\/Staff"},{"id":"78771","name":"Public"},{"id":"174045","name":"Graduate students"}],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[{"value":"\u003Cp\u003EJosie Giles\u003Cbr \/\u003EIRIM Marketing Communications Mgr.\u003Cbr \/\u003E\u003Ca href=\u0022mailto:josie@gatech.edu\u0022\u003Ejosie@gatech.edu\u003C\/a\u003E\u003C\/p\u003E","format":"limited_html"}],"email":[],"slides":[],"orientation":[],"userdata":""}}}