A Joint 3D-2D based Method for Free Space Detection on Roads
share
In this paper, we address the problem of road segmentation and free space detection in the context of autonomous driving. Traditional methods either use 3D cues such as point clouds obtained from LIDAR, RADAR or stereo cameras or 2D cues such as lane markings, road boundaries, and object detection. Typical 3D point clouds do not have enough resolution to detect fine differences in heights such as between road and pavement. Similarly, image-based cues fail when encountering uneven road textures such as due to shadows, potholes, lane markings or road restoration. Exploiting the rapid advances made in recent years in 2D image segmentation as well as SLAM (Simultaneous Localization and Mapping) problems, we propose a novel free road space detection technique based on the combination of cues from deep convolutional neural networks (CNN) and sparse depth from monocular SLAM. In particular, we use the CNN based road segmentation from 2D images and plane/box fitting on sparse depth data obtained from SLAM as priors to formulate an energy minimization using the conditional random field (CRF) for road pixels classification. While the CNN learns the road texture, the depth information tries to fill in the details for which texture-based classification fails. Finally, we use the obtained road segmentation with the 3D depth data from monocular SLAM to detect the free space for the navigation purposes. Our experiments on KITTI odometry dataset, Camvid dataset as well as videos captured by us validate the superiority of the proposed approach over the state of the art.
READ FULL TEXT