Complex-YOLO: Real-time 3D Object Detection on Point Clouds

Abstract

Lidar based 3D object detection is inevitable for autonomous driving, because it directly links to environmental understanding and therefore builds the base for prediction and motion planning. The capacity of inferencing highly sparse 3D data in real-time is an ill-posed problem for lots of other application areas besides automated vehicles, e.g. augmented reality, personal robotics or industrial automation. We introduce Complex-YOLO, a state of the art real-time 3D object detection network on point clouds only. In this work, we describe a network that expands YOLOv2, a fast 2D standard object detector for RGB images, by a specific complex regression strategy to estimate multi-class 3D boxes in Cartesian space. Thus, we propose a specific Euler-Region-Proposal Network (E-RPN) to estimate the pose of the object by adding an imaginary and a real fraction to the regression network. This ends up in a closed complex space and avoids singularities, which occur by single angle estimations. The E-RPN supports to generalize well during training. Our experiments on the KITTI benchmark suite show that we outperform current leading methods for 3D object detection specifically in terms of efficiency. We achieve state of the art results for cars, pedestrians and cyclists by being more than five times faster than the fastest competitor. Further, our model is capable of estimating all eight KITTI-classes, including Vans, Trucks or sitting pedestrians simultaneously with high accuracy.

References in corpus (10)

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Deep Residual Learning for Image Recognition
• Rich feature hierarchies for accurate object detection and semantic segmentation
• YOLO9000: Better, Faster, Stronger
• VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection
• Vehicle Detection from 3D Lidar Using Fully Convolutional Network
• Joint 3D Proposal Generation and Object Detection from View Aggregation
• 3D Object Proposals using Stereo Imagery for Accurate Object Class Detection
• Accurate Single Stage Detector Using Recurrent Rolling Convolution
• 3D Fully Convolutional Network for Vehicle Detection in Point Cloud

Cited by in corpus (20)

• Multimodal End-to-End Autonomous Driving
• Recent Advances in Object Detection in the Age of Deep Convolutional Neural Networks
• How much real data do we actually need: Analyzing object detection performance using synthetic and real data
• 3D-BEVIS: Bird's-Eye-View Instance Segmentation
• Deep SCNN-based Real-time Object Detection for Self-driving Vehicles Using LiDAR Temporal Data
• Spatially-Aware Graph Neural Networks for Relational Behavior Forecasting from Sensor Data
• Object DGCNN: 3D Object Detection using Dynamic Graphs
• Pillar-based Object Detection for Autonomous Driving
• Attention-based Context Aggregation Network for Monocular Depth Estimation
• Reconfigurable Voxels: A New Representation for LiDAR-Based Point Clouds
• Points2Pix: 3D Point-Cloud to Image Translation using conditional Generative Adversarial Networks
• PolarStream: Streaming Lidar Object Detection and Segmentation with Polar Pillars
• RSN: Range Sparse Net for Efficient, Accurate LiDAR 3D Object Detection
• Class-specific Anchoring Proposal for 3D Object Recognition in LIDAR and RGB Images
• Tranquil Clouds: Neural Networks for Learning Temporally Coherent Features in Point Clouds
• PanoNet3D: Combining Semantic and Geometric Understanding for LiDARPoint Cloud Detection
• S3Net: 3D LiDAR Sparse Semantic Segmentation Network
• Hierarchy Denoising Recursive Autoencoders for 3D Scene Layout Prediction
• Real-time Dynamic Object Detection for Autonomous Driving using Prior 3D-Maps
• LiDAR point-cloud processing based on projection methods: a comparison