Using Optical Flow with Principal Divection Screen Strategy for Road Navigation

Abstract

In this paper, a monocular vision navigation algorithm using optical flow with Principal Direction Screen Strategy is proposed. Firstly, we present an optical flow extraction and adjusting method based on Speed-up robust features (SURF), which makes the distribution of optical flow vectors more well-distributed and increases the accuracy of optical flow. Secondly, we constructive a complete ego-motion parameter estimation algorithm on the basis of the adjusted optical flow. There is a problem of depth information absence and scale drift in monocular vision. So we adopt a variety of strategies to reduce scale drift, which include normalized eight-points algorithm and Random sample consensus (RANSAC) Strategy. The RANSAC based Eight-points algorithm contributes to mitigate the impact of noise in the process of computing fundamental matrix. Then we estimate the translation and rotation motion parameters of the camera. Eventually we utilize three-points based ground plane estimation algorithm to calculate the absolute scale of camera motion.