Description of a visual processing algorithm that supports autonomous road following. The algorithm requires that lane markings be present and attempts to track the lane markings on both boundaries. There are three stages of visual processing computation: extracting edges, matching extracted edge points with a geometric model of the road, and updating the geometric road model. A fourth stage computes a steering command for the vehicle based on the updated road model. All processing is confined to the 2D image plane. No information about the motion of the vehicle is used. This algorithm has been used as part of a complete system to drive an autonomous vehicle, the High Mobility Multipurpose Wheeled Vehicle (HMMWV). The system has been used to successfully drive the vehicle on roads within the grounds of the National Institute of Standards and Technology (NIST) at speeds up to 90 km/h as well as in simulation on a wide variety of video taped road scenes. It performs robustly for video tapes of both highways and rural roads. The algorithm runs at a sampling rate of 15 Hz and has a worst case latency of 139 milliseconds (ms).
Real-time visual processing for autonomous driving
Echtzeit-Bildverarbeitung für autonome Fahrzeugführung
Intelligent Vehicles, Symposium, 1993 ; 373-378
1993
6 Seiten, 3 Bilder, 35 Quellen
Conference paper
English
Real-time Visual Processing For Autonomous Driving
IEEE | 1993
|Real-time Visual Processing for Autonomous Driving
British Library Conference Proceedings | 1993
|Real-time visual processing in support of autonomous driving [2962-16]
British Library Conference Proceedings | 1997
|Real-time autonomous driving sensor calibration apparatus and method during autonomous driving
European Patent Office | 2023
|