Unstructured Road Segmentation Based on Road Boundary Enhancement Point-Cylinder Network Using LiDAR Sensor

Abstract

The segmentation of unstructured roads, a key technology in self-driving technology, remains a challenging problem. At present, most unstructured road segmentation algorithms are based on cameras or use LiDAR for projection, which has considerable limitations that the camera will fail at night, and the projection method will lose one-dimensional information. Therefore, this paper proposes a road boundary enhancement Point-Cylinder Network, called BE-PCFCN, which uses Point-Cylinder in order to extract point cloud features directly and integrates the road enhancement module to achieve accurate unstructured road segmentation. Firstly, we use the improved RANSAC-Boundary algorithm to calculate the rough road boundary point set, training in the same parameters with the original point cloud as a submodule. The whole network adopts the encoder and decoder structure, using Point-Cylinder as the basic module, while considering the data locality and the algorithm complexity. Subsequently, we made an unstructured road data set for training and compared it with existing LiDAR(Light Detection And Ranging) semantic segmentation algorithms. Finally, the experiment verified the robustness of BE-PCFCN. The road intersection-over-union (IoU) was increased by 4% when compared with the best existing algorithm, reaching 95.6%. Even on unstructured roads with an extremely irregular shape, BE-PCFCN also currently has the best segmentation results.

Robust 3D Semantic Segmentation Method Based on Multi-Modal Collaborative Learning

“…Voxel-based methods [22][23][24][25][26] transform point clouds into dense voxels and employ 3D convolution to extract and reconstruct the features in each voxel, which achieves superior segmentation results. However, the redundancy in dense voxel representation and the computational inefficiency of 3D convolution contribute to an exponential increase in the complexity of these methods, leading to poor real-time performance.…”

A Rapid Segmentation Method of Highway Surface Point Cloud Data Based on a Supervoxel and Improved Region Growing Algorithm

“…Most of these methods are point-based strategies that directly use point clouds for feature extraction and have achieved promising results in relatively straightforward and structured road extraction scenarios. However, while the accuracy has been improved, a deep learning-based method requires a large sample set and time for training, which reduces the efficiency of the road surface point cloud extraction [36]. Additionally, there is a lack of relevant datasets and experiments established for proving the effectiveness and robustness of these algorithms for the extraction of unstructured road surfaces in complex scenarios.…”

A Novel Real-Time Edge-Guided LiDAR Semantic Segmentation Network for Unstructured Environments

“…Zhu et al [12] proposed a network to enhance the road boundary which uses the RANSAC algorithm to extract the road boundaries of point clouds and fuse them with the features of the original point clouds to segment the road more effectively. There are also some methods that only train for specific unstructured environments.…”

“…Recently, LiDAR-based semantic segmentation of unstructured environments has been developed. On the one hand, most methods use voxel-based [12] or point-based [13] methods for feature extraction, which not only do not design targeted network structures for the edge blurring problems, resulting in poor results when segmenting drivable areas and static obstacles with large areas but also do not guarantee real-time segmentation. On the other hand, some methods are trained only for certain unstructured environments, such as bush segmentation in agricultural scenes [14], and are therefore less adaptable.…”