SECOND: Sparsely Embedded Convolutional Detection

Clicks: 171
ID: 111488
2018
Free PDF
Article Quality & Performance Metrics
Overall Quality Improving Quality
0.0 /100
Combines engagement data with AI-assessed academic quality
AI Quality Assessment
Not analyzed
Abstract
LiDAR-based or RGB-D-based object detection is used in numerous applications, ranging from autonomous driving to robot vision. Voxel-based 3D convolutional networks have been used for some time to enhance the retention of information when processing point cloud LiDAR data. However, problems remain, including a slow inference speed and low orientation estimation performance. We therefore investigate an improved sparse convolution method for such networks, which significantly increases the speed of both training and inference. We also introduce a new form of angle loss regression to improve the orientation estimation performance and a new data augmentation approach that can enhance the convergence speed and performance. The proposed network produces state-of-the-art results on the KITTI 3D object detection benchmarks while maintaining a fast inference speed.
Reference Key
yan2018sensorssecond: Use this key to autocite in the manuscript while using SciMatic Manuscript Manager or Thesis Manager
Authors Yan Yan;Yuxing Mao;Bo Li;Yan, Yan;Mao, Yuxing;Li, Bo;
Journal sensors
Year 2018
DOI
10.3390/s18103337
URL
https://www.mdpi.com/1424-8220/18/10/3337#viewedby
Keywords
convolutional neural networks lidar autonomous driving 3d object detection

Citations

No citations found. To add a citation, contact the admin at info@scimatic.org

Comments

No comments yet. Be the first to comment on this article.