VEHICLE-TYPE MOTION ESTIMATION BY THE FUSION OF IMAGE POINT AND LINE FEATURES

Three-dimensional (3D) motion estimation is a very important topic in machine vision. However, reliability of the estimated 3D motion seems to be the most challenging problem, especially to the linear algorithm s developed for solving a general 3D motion problem (six degrees of fr eedom). In real applications such as the traffic surveillance and auto -vehicle systems, the observed 3D motion has only three degrees of fre edom because of the ground plane constraint (GPC). In this paper, a ne w iterative method is proposed for solving the above problem. Our meth od has several advantages: (1) It can handle both the point and line f eatures as its input image data. (2) It is very suitable for parallel processing. (3) Its cost function is so well-conditioned that the fina l 3D motion estimation is robust and insensitive to noise, which is pr oved by experiments. (4) It can handle the case of missing data to a c ertain degree. The above benefits make our method suitable for a real application. Experiments including simulated and real-world images sho w satisfactory results. (C) 1997 Pattern Recognition Society. Publishe d by Elsevier Science Ltd.