skip to main content
Language:
Search Limited to: Search Limited to: Resource type Show Results with: Show Results with: Search type Index

SECOND: Sparsely Embedded Convolutional Detection

Sensors (Basel, Switzerland), 2018-10, Vol.18 (10), p.3337 [Peer Reviewed Journal]

2018 by the authors. 2018 ;ISSN: 1424-8220 ;EISSN: 1424-8220 ;DOI: 10.3390/s18103337 ;PMID: 30301196

Full text available

Citations Cited by
  • Title:
    SECOND: Sparsely Embedded Convolutional Detection
  • Author: Yan, Yan ; Mao, Yuxing ; Li, Bo
  • Subjects: 3D object detection ; autonomous driving ; convolutional neural networks ; LIDAR
  • Is Part Of: Sensors (Basel, Switzerland), 2018-10, Vol.18 (10), p.3337
  • Description: 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.
  • Publisher: Switzerland: MDPI
  • Language: English
  • Identifier: ISSN: 1424-8220
    EISSN: 1424-8220
    DOI: 10.3390/s18103337
    PMID: 30301196
  • Source: DOAJ Directory of Open Access Journals
    Geneva Foundation Free Medical Journals at publisher websites
    AUTh Library subscriptions: ProQuest Central
    PubMed Central
    ROAD: Directory of Open Access Scholarly Resources
Back to results list
INSPIRE LIBRARY - TON DUC THANG UNIVERSITY (84-028) 37 755 057 Feedback
19 Nguyen Huu Tho St. Dist.7, HCM thuvien@tdtu.edu.vn

Copyright © 2017 INSPIRE LIBRARY - TON DUC THANG UNIVERSITY

Searching Remote Databases, Please Wait