A Computational Approach to Edge Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence
Distance transformations in digital images
Computer Vision, Graphics, and Image Processing
ASSET-2: Real-Time Motion Segmentation and Shape Tracking
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Real-time Computer Vision System for Measuring Traffic Parameters
CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
| Hi-index | 0.00 |
The detection of approaching vehicles in traffic lanes is an essential processing step for a driver assistant or a visual traffic monitoring system. For this task a new motion based approach is presented, which allows processing in real-time without the need of special hardware. Motion estimation was processed along contours and restricted to the observed lane(s). Due to the lane based computation vehicles were segmented by evaluation of the motion direction only. The contour tracking algorithm allows a robust motion estimation and a temporal stabilisation of the motion based segmentation. The capabilities of our approach are demonstrated in two applications: a overtake checker for highways and a visual traffic monitoring system.