Title: | Kinect based 3D scene reconstruction |
Authors: | Zeller, Niclas Quint, Franz Guan, Ling |
Citation: | WSCG 2014: communication papers proceedings: 22st International Conference in Central Europeon Computer Graphics, Visualization and Computer Visionin co-operation with EUROGRAPHICS Association, p. 73-81. |
Issue Date: | 2014 |
Publisher: | Václav Skala - UNION Agency |
Document type: | konferenční příspěvek conferenceObject |
URI: | wscg.zcu.cz/WSCG2014/!!_2014-WSCG-Communication.pdf http://hdl.handle.net/11025/26380 |
ISBN: | 978-80-86943-71-8 |
Keywords: | 3D rekonstrukce scény;elektronická cestovní pomůcka;Microsoft Kinect;detekce překážek;RANSAC segmentace roviny |
Keywords in different language: | 3D scene reconstruction;electronic travel aid;Microsoft Kinect;obstacle detection;RANSAC plane segmentation |
Abstract in different language: | This paper presents a novel system for 3D scene reconstruction and obstacle detection for visually impaired people, which is based on Microsoft Kinect. From the depth image of Kinect a 3D point cloud is calculated. By using both, the depth image and the point cloud a gradient and RANSAC based plane segmentation algorithm is applied. After the segmentation the planes are combined to objects based on their intersecting edges. For each object a cuboid shaped bounding box is calculated. Based on experiments the accuracy of the presented system is evaluated. The achieved accuracy is in the range of few centimeters and thus sufficient for obstacle detection. Besides, the paper gives an overview about already existing navigation aids for visually impaired people and the presented system is compared to a state of the art system. |
Rights: | @ Václav Skala - UNION Agency |
Appears in Collections: | WSCG 2014: Communication Papers Proceedings |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Zeller.pdf | Plný text | 2,38 MB | Adobe PDF | View/Open |
Please use this identifier to cite or link to this item:
http://hdl.handle.net/11025/26380
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.