A General Pipeline for 3D Detection of Vehicles

Abstract

Autonomous driving requires 3D perception of vehicles and other objects in the in environment. Much of the current methods support 2D vehicle detection. This paper proposes a flexible pipeline to adopt any 2D detection network and fuse it with a 3D point cloud to generate 3D information with minimum changes of the 2D detection networks. To identify the 3D box, an effective model fitting algorithm is developed based on generalised car models and score maps. A two-stage convolutional neural network (CNN) is proposed to refine the detected 3D box. This pipeline is tested on the KITTI dataset using two different 2D detection networks. The 3D detection results based on these two networks are similar, demonstrating the flexibility of the proposed pipeline. The results rank second among the 3D detection algorithms, indicating its competencies in 3D detection.

arXiv commentAccepted at ICRA 2018

References in corpus (5)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
• Vehicle Detection from 3D Lidar Using Fully Convolutional Network
• 3D Fully Convolutional Network for Vehicle Detection in Point Cloud
• 3D Bounding Box Estimation Using Deep Learning and Geometry

Cited by in corpus (3)

• Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Driving
• Orthographic Feature Transform for Monocular 3D Object Detection
• TANet: Robust 3D Object Detection from Point Clouds with Triple Attention