CAMERA-BASED CLEAR PATH DETECTION

Abstract

In using image analysis to assist a driver to avoid obstacles on the road, traditional approaches rely on various detectors to detect all types of objects. We propose a framework that is different from traditional approaches in that it focuses on finding a clear path ahead. We assume that a video camera is calibrated offline (with known intrinsic and extrinsic parameters) and vehicle information (vehicle speed and yaw angle) is known. We first generate perspective patches for feature extraction in the image. Then, after extracting and selecting features of each patch, we estimate an initial probability that the patch corresponds to clear path using an SVM probability estimator based on the selected features. We finally perform probabilistic patch smoothing based on spatial and temporal constraints to improve the initial estimation, thereby enhancing detection performance. We show that the proposed framework performs well even in some challenging situations with shadows and illumination changes.

System overview:

Result: