A system for obstacle detection by real-time evaluation of image sequences

In this contribution we present a system for the detection of stationary obstacles and moving objects in front of a moving vehicle. The detection of obstacles and other objects is based on the evaluation of optical flow vectors calculated in real-time from image sequences. The optical flow vectors are calculated with a local analytical approach. The necessary second order spatio-temporal derivatives are computed in real-time with our second generation custom designed image sequence analysis system MiniVISTA. At all image locations it is tested whether the structure of the gray value distribution is sufficient for a local optical flow vector calculation or not. Only those sets of spatio- temporal derivatives which passed the structure test are transmitted to subsequent processes being executed on a transputer network. These processes calculate the optical flow vectors, compare the calculated optical flow vectors with the corresponding model vectors, and perform the obstacle test. Experi mental results obtained from image sequences recorded on our experimental vehicles MB 609D and BMW 735 iL are presented.