SCNet: Subdivision Coding Network for Object Detection Based on 3D Point Cloud
Open Access
- 26 August 2019
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 120449-120462
Abstract
High-precision real-time 3D object detection based on the LiDAR point cloud is an important task for autonomous driving. Most existing methods utilize grid-based convolutional networks to handle sparse and cluttered point clouds. However, the performance of object detection is limited by the coarse grid quantization and expensive computational cost. In this paper, we propose a more efficient representation of 3D point clouds and propose SCNet, a single-stage, end-to-end 3D subdivision coding network that learns finer feature representations for vertical grids. SCNet divides each grid into smaller sub-grids to preserve more point cloud information and converts points in the grid to a uniform feature representation through 2D convolutional neural networks. The 3D point cloud is encoded as the fine 2D sub-grid representation, which helps to reduce the computational cost. We validate our SCNet on the KITTI object benchmark in which we show that the proposed object detector produces state-of-the-art results with more than 20 FPS.Keywords
Funding Information
- National Natural Science Foundation of China (61790565, 61803380)
This publication has 25 references indexed in Scilit:
- 3D Object Proposals Using Stereo Imagery for Accurate Object Class DetectionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- Vehicle Detection from 3D Lidar Using Fully Convolutional Network2016
- Volumetric and Multi-view CNNs for Object Classification on 3D Data2016
- Deep Residual Learning for Image Recognition2016
- Monocular 3D Object Detection for Autonomous Driving2016
- Multi-view Convolutional Neural Networks for 3D Shape Recognition2015
- Fast R-CNN2015
- Fast and Robust Multi-view 3D Object Recognition in Point Clouds2015
- Voting for Voting in Online Point Cloud Object Detection2015
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009