3D Fully Convolutional Network for Vehicle Detection in Point Cloud

Abstract

2D fully convolutional network has been recently successfully applied to object detection from images. In this paper, we extend the fully convolutional network based detection techniques to 3D and apply it to point cloud data. The proposed approach is verified on the task of vehicle detection from lidar point cloud for autonomous driving. Experiments on the KITTI dataset shows a significant performance improvement over the previous point cloud based detection approaches.

References in corpus (3)

• Fully Convolutional Networks for Semantic Segmentation
• Vehicle Detection from 3D Lidar Using Fully Convolutional Network
• Learning Rich Features from RGB-D Images for Object Detection and Segmentation

Cited by in corpus (11)

• VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection
• Two-Stream 3D Convolutional Neural Network for Skeleton-Based Action Recognition
• 3DSSD: Point-based 3D Single Stage Object Detector
• Complex-YOLO: Real-time 3D Object Detection on Point Clouds
• A Survey of Deep Network Solutions for Learning Control in Robotics: From Reinforcement to Imitation
• Multi-View 3D Object Detection Network for Autonomous Driving
• PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimation
• Voxel-FPN: multi-scale voxel feature aggregation in 3D object detection from point clouds
• SMOKE: Single-Stage Monocular 3D Object Detection via Keypoint Estimation
• A General Pipeline for 3D Detection of Vehicles
• Points2Pix: 3D Point-Cloud to Image Translation using conditional Generative Adversarial Networks