Detecting Drivable Area for Self-driving Cars: An Unsupervised Approach
This addresses the limitation of lane-dependent methods for self-driving cars, enabling detection in areas without clear lane marks, though it is an incremental improvement over existing fusion techniques.
The paper tackles the problem of detecting drivable areas for self-driving cars without relying on lane markings, using an unsupervised method that fuses monocular camera images and 3D-LIDAR point clouds, achieving state-of-the-art results on the ROAD-KITTI benchmark.
It has been well recognized that detecting drivable area is central to self-driving cars. Most of existing methods attempt to locate road surface by using lane line, thereby restricting to drivable area on which have a clear lane mark. This paper proposes an unsupervised approach for detecting drivable area utilizing both image data from a monocular camera and point cloud data from a 3D-LIDAR scanner. Our approach locates initial drivable areas based on a "direction ray map" obtained by image-LIDAR data fusion. Besides, a fusion of the feature level is also applied for more robust performance. Once the initial drivable areas are described by different features, the feature fusion problem is formulated as a Markov network and a belief propagation algorithm is developed to perform the model inference. Our approach is unsupervised and avoids common hypothesis, yet gets state-of-the-art results on ROAD-KITTI benchmark. Experiments show that our unsupervised approach is efficient and robust for detecting drivable area for self-driving cars.