Object Segmentation and Classification of Point Cloud

Kanokphan LERTNIPHONPHAN; Satoshi KOMORITA; Kazuyuki TASAKA; Hiromasa YANAGIHARA

doi:10.11485/iteac.2017.0_33B-4

2017

DOI https://doi.org/10.11485/iteac.2017.0_33B-4

Conference information

Host: The Institute of Image Information and Television Engineers

Name : THE 2017 ITE ANNUAL CONVENTION

Location : [in Japanese]

Date : August 30, 2017 - September 01, 2017

Object Segmentation and Classification of Point Cloud

*Kanokphan LERTNIPHONPHAN, Satoshi KOMORITA, Kazuyuki TASAKA, Hiromasa YANAGIHARA

Author information

CONFERENCE PROCEEDINGS FREE ACCESS

Pages 33B-4-

Details

Abstract

Object segmentation and Classification from Point cloud LiDAR are challenging due to its sparseness and lacking of detailed information. In this work, data association between point cloud and RGB image is used to automatically segment objects, which consist of car, cyclist, and pedestrian, for effective making point cloud dataset.

Corresponding author

Register with J-STAGE for free!