Title :
Active safety and collision alerts using Contextual Visual Dataspace
Author :
Kim, Kyungnam ; Owechko, Yuri ; Medasani, Swarup
Author_Institution :
HRL Labs., LLC, Malibu, CA, USA
Abstract :
The Contextual Visual Dataspace (CVD) is a real-time representation of an automotive environment that combines automated 3D modeling and semantic labeling of a scene with dynamic object detection using infrastructure cameras. Our automotive active safety concept uses CVD to detect and track dynamic objects of interest, geo-register them into the semantically labeled 3D world space, analyze the paths of vehicles and pedestrians, infer intent and therefore make more accurate predictions of potential collisions, and finally give alerts to drivers and pedestrians and provide them with real-time situational awareness. The CVD system was demonstrated in a blind curve collision warning scenario.
Keywords :
collision avoidance; object detection; safety systems; semantic networks; solid modelling; target tracking; traffic engineering computing; ubiquitous computing; CVD; automated 3D modeling; automotive active safety; collisions alerts; contextual visual dataspace; drivers; dynamic object detection; infrastructure cameras; objects track; pedestrians; semantic labeling; Automotive engineering; Cameras; Context modeling; Labeling; Layout; Object detection; Space vehicles; Vehicle detection; Vehicle dynamics; Vehicle safety;
Conference_Titel :
Intelligent Vehicles Symposium (IV), 2010 IEEE
Conference_Location :
San Diego, CA
Print_ISBN :
978-1-4244-7866-8
DOI :
10.1109/IVS.2010.5548001