AN INTEGRATED SPATIOTEMPORAL APPROACH TO AUTOMATIC VISUAL GUIDANCE OF AUTONOMOUS VEHICLES

The Kaiman filter approach to recursive state estimation exploiting dynamical models for the motion of massive objects has been extended to image sequence processing. This allows to confine image processing to the last frame of the sequence only and to derive a direct spatial interpretation including spatial velocity components by smoothing integrations of prediction errors. Results are presented for road vehicle guidance at high speeds including obstacle detection and monocular relative spatial state estimation. The corresponding data processing architecture is discussed; the system has been implemented on a MIMD parallel processing system. Speeds up to 100 km/h have been demonstrated. © 1990 IEEE