Name
Abstract | ||
|---|---|---|
Systems for automated image analysis are useful for a vari- ety of tasks and their importance is still growing due to technological advances and an increase of social acceptance. Especially in the eld of driver assistance systems the progress in science has reached a level of high performance. Fully or partly autonomously guided vehicles, par- ticularly for road-based trac, pose high demands on the development of reliable algorithms due to the conditions imposed by natural envi- ronments. At the Institut fur Neuroinformatik methods for analyzing driving relevant scenes by computer vision are developed in cooperation with several partners from the automobile industry. We introduce a sys- tem which extracts the important information from an image taken by a CCD camera installed at the rear view mirror in a car. The approach consists of a sequential and a parallel sensor and information processing. Three main tasks namely the initial segmentation (object detection), the object tracking and the object classication are realized by integration in the sequential branch and by fusion in the parallel branch. The main gain of this approach is given by the integrative coupling of dierent algorithms providing partly redundant information. Some systems presented in ref. (4, 23, 3) show the principal feasibility of driver assistance systems based on computer vision. Although exclusively vision based systems and algorithms are not yet powerful enough to solve all driving rele- vant tasks, a large amount of dierent scenarios can be interpreted suciently. Additionally sensors like RADAR and LIDAR extent the contents of sensor in- formation necessary for building a reliable system. The main focus of our system lies in combining various methods for the analysis and interpretation of images and in the fusion of a large spectrum of sensor data to extract most reliable in- formation for the nal planning and for predicting of behavior of other vehicles. The great variety of dierent scenarios as well as the high degree of reliability necessary for the given task require an encompassing and flexible system ar- chitecture. The requirements concerning the reliability of the reached solution, the variety of geometric appearances of involved objects and the environmen- tal constraints of both deterministic as well as statistical nature necessitate a multitude of partial solutions based on dierent representations of the environ- ment. Consequently, complexity and structure of the overall system have to be |
Year | Venue | Keywords |
|---|---|---|
1998 | DAGM-Symposium | driver assistance,object tracking,image processing,image analysis,information processing,automobile industry,computer vision,ccd camera,spectrum |
Field | DocType | ISBN |
Object detection,Computer vision,Rear-view mirror,Information processing,Segmentation,Advanced driver assistance systems,Image processing,Video tracking,Artificial intelligence,Engineering,Automotive industry | Conference | 3-540-64935-2 |
Citations | PageRank | References |
2 | 0.62 | 6 |
Authors | ||
5 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| W von Seelen | 1 | 503 | 140.13 |
| Uwe Handmann | 2 | 139 | 27.63 |
| thomas kalinke | 3 | 134 | 26.81 |
| christos tzomakas | 4 | 123 | 23.55 |
| Martin Werner | 5 | 12 | 2.37 |