Title :
Steering wheel´s angle tracking from camera-car
Author :
Cucchiara, Rita ; Prati, Andrea ; Vigett, Francesca
Author_Institution :
Dipt. di Ingegneria dell´´Informazione, Modena Univ., Italy
Abstract :
This paper proposes a general-purpose method to track the steering wheel´s absolute angle by using a single camera vision system mounted inside the car. The approach is based on the modeling of the motion of the steering wheel, as it appears perspectively distorted by the point of view of the uncalibrated camera. We modified the Lucas-Kanade method for an approximately rotational motion model in order to provide the detection and tracking of significant features on the wheel. The experimental results are compared with ground-truth data obtained with different types of sensors.
Keywords :
automobiles; feature extraction; image sensors; position control; tracking; video cameras; Lucas-Kanade method; automobiles; camera vision system; feature detection; feature selection; feature tracking; ground truth data; rotational motion model; sensors; steering wheel angle tracking; Automatic control; Cameras; Land vehicles; Motion detection; Real time systems; Sensor systems and applications; Tracking; Vehicle driving; Videos; Wheels;
Conference_Titel :
Intelligent Vehicles Symposium, 2003. Proceedings. IEEE
Print_ISBN :
0-7803-7848-2
DOI :
10.1109/IVS.2003.1212945