Vehicle Detection from 3D Lidar Using Fully Convolutional Network

Abstract

Convolutional network techniques have recently achieved great success in vision based detection tasks. This paper introduces the recent development of our research on transplanting the fully convolutional network technique to the detection tasks on 3D range scan data. Specifically, the scenario is set as the vehicle detection task from the range data of Velodyne 64E lidar. We proposes to present the data in a 2D point map and use a single 2D end-to-end fully convolutional network to predict the objectness confidence and the bounding boxes simultaneously. By carefully design the bounding box encoding, it is able to predict full 3D bounding boxes even using a 2D convolutional network. Experiments on the KITTI dataset shows the state-of-the-art performance of the proposed method.

Robotics: Science and Systems, 2016

References in corpus (1)

• Learning Rich Features from RGB-D Images for Object Detection and Segmentation

Cited by in corpus (22)

• VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection
• Joint Activity Recognition and Indoor Localization with WiFi Fingerprints
• End-to-End Multi-View Fusion for 3D Object Detection in LiDAR Point Clouds
• SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloud
• Spatially-Aware Graph Neural Networks for Relational Behavior Forecasting from Sensor Data
• RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Driving
• Radar-Camera Sensor Fusion for Joint Object Detection and Distance Estimation in Autonomous Vehicles
• TANet: Robust 3D Object Detection from Point Clouds with Triple Attention
• SMOKE: Single-Stage Monocular 3D Object Detection via Keypoint Estimation
• 3D Fully Convolutional Network for Vehicle Detection in Point Cloud
• RST-MODNet: Real-time Spatio-temporal Moving Object Detection for Autonomous Driving
• Triangulation Learning Network: from Monocular to Stereo 3D Object Detection
• LATTE: Accelerating LiDAR Point Cloud Annotation via Sensor Fusion, One-Click Annotation, and Tracking
• Class-specific Anchoring Proposal for 3D Object Recognition in LIDAR and RGB Images
• Dynamic Edge Weights in Graph Neural Networks for 3D Object Detection
• Unsupervised Data Imputation via Variational Inference of Deep Subspaces
• DeepPCO: End-to-End Point Cloud Odometry through Deep Parallel Neural Network
• Learning Orientation-Estimation Convolutional Neural Network for Building Detection in Optical Remote Sensing Image
• Cooperative LIDAR Object Detection via Feature Sharing in Deep Networks
• Range Adaptation for 3D Object Detection in LiDAR
• Depth-Adapted CNN for RGB-D cameras
• 3D Objectness Estimation via Bottom-up Regret Grouping