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 (41)

• 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
• Towards Robust LiDAR-based Perception in Autonomous Driving: General Black-box Adversarial Sensor Attack and Countermeasures
• SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloud
• RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Driving
• Spatially-Aware Graph Neural Networks for Relational Behavior Forecasting from Sensor Data
• 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
• Deep Learning for LiDAR Point Clouds in Autonomous Driving: A Review
• 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
• An LSTM Approach to Temporal 3D Object Detection in LiDAR Point Clouds
• Improving 3D Object Detection with Channel-wise Transformer
• LATTE: Accelerating LiDAR Point Cloud Annotation via Sensor Fusion, One-Click Annotation, and Tracking
• Feature Sharing and Integration for Cooperative Cognition and Perception with Volumetric Sensors
• A Spike Learning System for Event-driven Object Recognition
• An Overview Of 3D Object Detection
• Dynamic Edge Weights in Graph Neural Networks for 3D Object Detection
• Class-specific Anchoring Proposal for 3D Object Recognition in LIDAR and RGB Images
• 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
• LiDAR R-CNN: An Efficient and Universal 3D Object Detector
• Novel Perception Algorithmic Framework For Object Identification and Tracking In Autonomous Navigation
• Range Adaptation for 3D Object Detection in LiDAR
• Cirrus: A Long-range Bi-pattern LiDAR Dataset
• Unsupervised Object Detection with LiDAR Clues
• Joint Spatial-Temporal Optimization for Stereo 3D Object Tracking
• S3Net: 3D LiDAR Sparse Semantic Segmentation Network
• Know Your Surroundings: Panoramic Multi-Object Tracking by Multimodality Collaboration
• 3D Lidar Mapping Relative Accuracy Automatic Evaluation Algorithm
• Non-parametric Memory for Spatio-Temporal Segmentation of Construction Zones for Self-Driving
• 3D Objectness Estimation via Bottom-up Regret Grouping
• All-Weather Object Recognition Using Radar and Infrared Sensing
• Empowering cyberphysical systems of systems with intelligence
• To the Point: Efficient 3D Object Detection in the Range Image with Graph Convolution Kernels
• Depth-Adapted CNN for RGB-D cameras