In urban traffic situations - but not only there - image sequence evaluation can provide information about the environment of a car to a driver's warning assistant and thus enables it to give warning meassages if the driver approaches an intersection too quickly. The image sequence evaluation procedure has to detect an intersection in real-time in a sufficiently large distance (i.e. about 30 m) with a camera mounted inside a passenger car at 1.30 m of height. It additionally detects the road borders in order to estimate the pitch angle of the camera and to establish search areas for the intersection detection. The intersection itself is detected by a model-based approach. The model contains information about usual intersection markings such as dashed or solid lines. The system applies search windows for the road borders and for the intersection in order to concentrate the evaluation on the important image parts. The authors start with an initial model of the road and first derive search windows for the borders. Inside these windows, the gradient directions of positions with maximum gray value gradient magnitude are analyzed: edges with appropriate angles are extracted which are then used to estimate the road borders. The search window for the intersection is determined by the estimated borders and two horizontal lines in the image narrowing down the scope to distances of interest. Horizontal structures are extracted, labeled as candidates for upper and lower edges of road markings and assembled so that they match the intersection model as exactly as possible. The extent to which the hypothesis resembles the model determines the value of a scoring function. The best hypothesis is considered as the detected intersection, provided it's scoring function exceeds a threshold.
Real-time vision-based intersection detection for a driver's warning assistant
Echtzeitermittlung von Kreuzungen mit Hilfe des maschinellen Sehens zur Warnung des Fahrers
Intelligent Vehicles, Symposium, 1993 ; 340-344
1993
5 Seiten, 7 Bilder, 4 Quellen
Conference paper
English
Real-time Vision-based Intersection Detection for a Driver's Warning Assistant
British Library Conference Proceedings | 1993
|Realization of a Driver's Warning Assistant for Intersections
British Library Conference Proceedings | 1993
|Realization of a driver's warning assistant for intersections
Tema Archive | 1993
|Real-time driver's eye state detection
IEEE | 2005
|Realization and evaluation of driver's interactions with a warning assistant for collision avoidance
British Library Conference Proceedings | 1993
|