Abstract
Three-dimensional object detection from point cloud data is becoming more and more significant, especially for autonomous driving applications. However, it is difficult for lidar to obtain the complete structure of an object in a real scene due to its scanning characteristics. Although the existing methods have made great progress, most of them ignore the prior information of object structure, such as symmetry. So, in this paper, we use the symmetry of the object to complete the missing part in the point cloud and then detect it. Specifically, we propose a two-stage detection framework. In the first stage, we adopt an encoder–decoder structure to generate the symmetry points of the foreground points and make the symmetry points and the non-empty voxel centers form an enhanced point cloud. In the second stage, the enhanced point cloud is input into the baseline, which is an anchor-based region proposal network, to generate the detection results. Extensive experiments on the challenging KITTI benchmark show the effectiveness of our method, which has better performance on both 3D and BEV (bird’s eye view) object detection compared with some previous state-of-the-art methods.
Highlights
In recent years, 3D object detection has been widely investigated by the industry and academia thanks to its applications in various fields, such as autonomous driving and robotics
We propose a new task to predict the positions of symmetry points, which can complete the missing symmetry part of the object in the point cloud, so as to better detect the objects
We propose a simple method for calculating the symmetry point labels, that is, the position of a symmetry point in the point cloud coordinate system can be calculated indirectly through its relative position in the 3D ground truth box
Summary
3D object detection has been widely investigated by the industry and academia thanks to its applications in various fields, such as autonomous driving and robotics. It is still an open problem to be explored, though deep learning methods have made significant progress in 2D object detection [1,2,3,4,5,6] and have a relatively unified framework. 3D object detection based on point clouds has attracted more attention of researchers due to some characteristics of lidar, such as accurate depth information and high resolution. One is based on multi-sensor fusion [7,8,9,10], mainly cameras and lidar. The images captured by the camera contain rich color and texture information, while the point clouds scanned by lidar contain accurate depth information
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
