Two algorithms for vehicular obstacle detection in sparse pointcloud
This work addresses cost and processing challenges for autonomous vehicles by enabling obstacle detection with cheaper, low-resolution lidars, though it is incremental as it builds on existing methods for sparse data.
The paper tackles the problem of obstacle detection for autonomous vehicles using low-resolution lidars, proposing two algorithms based on occupancy grid and geometric refinement to retrieve 3D bounding boxes with 16 and 8 planes, validated on a custom dataset.
One of the main components of an autonomous vehicle is the obstacle detection pipeline. Most prototypes, both from research and industry, rely on lidars for this task. Pointcloud information from lidar is usually combined with data from cameras and radars, but the backbone of the architecture is mainly based on 3D bounding boxes computed from lidar data. To retrieve an accurate representation, sensors with many planes, e.g., greater than 32 planes, are usually employed. The returned pointcloud is indeed dense and well defined, but high-resolution sensors are still expensive and often require powerful GPUs to be processed. Lidars with fewer planes are cheaper, but the returned data are not dense enough to be processed with state of the art deep learning approaches to retrieve 3D bounding boxes. In this paper, we propose two solutions based on occupancy grid and geometric refinement to retrieve a list of 3D bounding boxes employing lidar with a low number of planes (i.e., 16 and 8 planes). Our solutions have been validated on a custom acquired dataset with accurate ground truth to prove its feasibility and accuracy.