PointSeg: Real-Time Semantic Segmentation Based on 3D LiDAR Point Cloud
read the original abstract
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.
This paper has not been read by Pith yet.
Forward citations
Cited by 2 Pith papers
-
ReaLiTy and LADS: A Unified Framework and Dataset Suite for LiDAR Adaptation Across Sensors and Adverse Weather Conditions
ReaLiTy transforms LiDAR data using physics models and learning to simulate sensor and weather changes, backed by the LADS dataset for adaptation studies.
-
Analyzing the Cross-Sensor Portability of Neural Network Architectures for LiDAR-based Semantic Labeling
A new CNN architecture for LiDAR semantic labeling achieves higher cross-sensor portability with a reported 10 percentage point IoU gain over a reference method.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.