Title :
Vision-Based Drivable Surface Detection in Autonomous Ground Vehicles
Author :
Guo, Ying ; Gerasimov, Vadim ; Poulton, Geoff
Author_Institution :
ICT Centre, CSIRO, Sydney, NSW
Abstract :
One of the primary tasks for most autonomous ground vehicles is road following. For safe maneuvering the vehicle needs to correctly identify the drivable surface. Our work is focused on the use of simple video cameras as the sensor devices. We describe a new machine learning approach to drivable surface detection that automatically combines a set of rectangular features and histogram backprojection based image segmentation algorithms to produce superior results. The machine learning algorithm is based on the AdaBoost method, one of a class of boosting techniques which are applicable to many image processing tasks such as object and face recognition or image segmentation. The algorithm is trained and tested on video data obtained from video cameras mounted on an autonomous tractor at our Queensland site. The algorithm approach, together with the simple feature-based weak classifiers used, produces significantly improved drivable surface detection results
Keywords :
face recognition; image classification; image segmentation; learning (artificial intelligence); mobile robots; object recognition; road vehicles; robot vision; video cameras; AdaBoost method; autonomous ground vehicles; autonomous tractor; boosting techniques; face recognition; feature-based weak classifiers; histogram backprojection; image processing; image segmentation; machine learning; object recognition; road following; video cameras; vision-based drivable surface detection; Cameras; Image segmentation; Land vehicles; Machine learning; Machine learning algorithms; Remotely operated vehicles; Roads; Vehicle detection; Vehicle driving; Vehicle safety; AdaBoost; autonomous vehicles; back projection; image segmentation; road detection;
Conference_Titel :
Intelligent Robots and Systems, 2006 IEEE/RSJ International Conference on
Conference_Location :
Beijing
Print_ISBN :
1-4244-0258-1
Electronic_ISBN :
1-4244-0259-X
DOI :
10.1109/IROS.2006.282437