Moving obstacle detection and recognition by optical flow pattern analysisfor mobile robots

This paper presents a new idea for an obstacle recognition method for mobil e robots by analyzing optical flow information acquired from dynamic images . First, the optical flow field is detected in image sequences from a camer a on a moving observer and moving object candidates are extracted by using a normalized square residual error [focus of expansion (FOE) residual error ] value that is calculated in the process of estimating the FOE. Next, the optical flow directions and intensity values are stored for the pixels invo lved in each candidate region to calculate the distribution width values ar ound the principal axes of inertia and the direction of the principal axes. Finally, each candidate is classified into an object category that is expe cted to appear in the scene by comparing the proportion and the direction v alues with standard data ranges for the objects which are determined by pre liminary experiments. Experimental results of car/bicycle/pedestrian recogn ition in real outdoor scenes have shown the effectiveness of the proposed m ethod.