PointSeg: Real-Time Semantic Segmentation Based on 3D LiDAR Point Cloud
This addresses the need for efficient semantic segmentation in autonomous driving applications, though it is incremental as it builds on existing methods like SqueezeNet and spherical projections.
The paper tackles real-time semantic segmentation of road objects from 3D LiDAR point clouds by proposing PointSeg, which transforms point clouds into spherical images and uses a lightweight CNN based on SqueezeNet, achieving competitive accuracy at 90fps on a single GPU.
In this paper, we propose PointSeg, a real-time end-to-end semantic segmentation method for road-objects based on spherical images. We take the spherical image, which is transformed from the 3D LiDAR point clouds, as input of the convolutional neural networks (CNNs) to predict the point-wise semantic map. To make PointSeg applicable on a mobile system, we build the model based on the light-weight network, SqueezeNet, with several improvements. It maintains a good balance between memory cost and prediction performance. Our model is trained on spherical images and label masks projected from the KITTI 3D object detection dataset. Experiments show that PointSeg can achieve competitive accuracy with 90fps on a single GPU 1080ti. which makes it quite compatible for autonomous driving applications.