PointSeg: Real-Time Semantic Segmentation Based on 3D LiDAR Point Cloud

July 17, 2018 · Entered Twilight · 🏛 arXiv.org

"Last commit was 7.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: .gitmodules, LICENSE, README.md, SqueezeSeg, data, eval.sh, src, train.sh

Authors Yuan Wang, Tianyue Shi, Peng Yun, Lei Tai, Ming Liu arXiv ID 1807.06288 Category cs.CV: Computer Vision Citations 130 Venue arXiv.org Repository https://github.com/ywangeq/PointSeg ⭐ 66 Last Checked 1 month ago

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.