Optical flow and active contour for moving object segmentation and detection in monocular robot

Optical flow is the apparent motion of the brightness pattern in an image. It generally corresponds to the motion field of the captured scene in the image so that we can use it distinguish moving objects. The computation of optical flow is conventionally based on the assumption of uniform brightness, which however does not always hold. Numerous algorithms have been proposed to improve the computation precision of optical flow. In this paper, we propose to incorporate optical flow information into a novel geodesic active contour model for moving-object detection in monocular robots. Specifically, an active contour is formulated by using the level set method, which eliminates the need of a re-initialization procedure. The developed scheme alleviates the effect of optical flow noise, increasing the robustness of the perception of moving objects. The experimental results show that our algorithm can successfully track a moving target, e.g., a human being