Learning Deformable Network for 3D Object Detection on Point Clouds

Wanyi Zhang,Xiuhua Fu,Wei Li,Sang-Bing Tsai

doi:10.1155/2021/3163470

Abstract

3D object detection based on point cloud data in the unmanned driving scene has always been a research hotspot in unmanned driving sensing technology. With the development and maturity of deep neural networks technology, the method of using neural network to detect three-dimensional object target begins to show great advantages. The experimental results show that the mismatch between anchor and training samples would affect the detection accuracy, but it has not been well solved. The contributions of this paper are as follows. For the first time, deformable convolution is introduced into the point cloud object detection network, which enhances the adaptability of the network to vehicles with different directions and shapes. Secondly, a new generation method of anchor in RPN is proposed, which can effectively prevent the mismatching between the anchor and ground truth and remove the angle classification loss in the loss function. Compared with the state-of-the-art method, the AP and AOS of the detection results are improved.

Highlights

Introduction e3D object detection methods mainly solve the problem of locating and identifying targets from both 2D and 3D data, including image, LiDAR data, and point cloud data. 3D object detection acts as a more and more important role in real-world applications, such as autonomous driving cars [1, 2], housekeeping equipment [3], and augmented reality [4]
Various ways have been proposed for dealing with 3D object detection problem by extracting features in image and point cloud
MV3D extract features from both front view’s RGB image and LiDAR point cloud which is projected to the bird eye view. 3D bounding boxes are proposed by a trained RPN on the bird eye view

Summary

Related Work

Various ways have been proposed for dealing with 3D object detection problem by extracting features in image and point cloud. 3D bounding boxes are proposed by a trained RPN on the bird eye view This method is a little weak to detect the object which is far away or small such as pedestrians and cyclists, and it is difficult to deal with overlap between objects too. Representation learning from point clouds: there exist many deep network architectures which are proposed to deal with point clouds and gain great performance on the task of 3D object detection and object segmentation. Some of these point cloud-based 3D detection techniques introduce a way to extract features by representing the point cloud in form of voxel (divide the point clouds into many cuboids). PointNet is used to generate 3D objects in a frustum point cloud corresponding to a 2D object proposal in [34]

Architecture for 3D Object Detection

Findings

Experiments