In this paper we describe a method for detecting situations where a vehicle moves along a highway in the wrong direction. The first step of the algorithm is to build a pattern using Gaussian mixture model based on the optical flow calculated with the Lucas-Kanade method. The second stage concerns the detection of objects as a potential road hazard. The optical flow calculated on-line during the second stage is compared with the traffic pattern used in the first stage. Then the difference in movement direction is detected using predefined thresholds.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.