Video-rate environment recognition through depth image plane segmentation for indoor service robot applications on an embedded system
As personal service robots are expected to gain widespread use in the near future there is a need for these robots to function properly in a large number of different environments. In order to acquire such an understanding this thesis focuses on implementing a depth image based planar segmentation me...
Main Authors: | , |
---|---|
Format: | Others |
Language: | English |
Published: |
Mälardalens högskola, Akademin för innovation, design och teknik
2017
|
Subjects: | |
Online Access: | http://urn.kb.se/resolve?urn=urn:nbn:se:mdh:diva-35595 |
id |
ndltd-UPSALLA1-oai-DiVA.org-mdh-35595 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-UPSALLA1-oai-DiVA.org-mdh-355952017-09-13T05:21:55ZVideo-rate environment recognition through depth image plane segmentation for indoor service robot applications on an embedded systemengKarlsson, AhlexanderSkoglund, RobertMälardalens högskola, Akademin för innovation, design och teknikMälardalens högskola, Akademin för innovation, design och teknik2017RoboticsRobotteknik och automationAs personal service robots are expected to gain widespread use in the near future there is a need for these robots to function properly in a large number of different environments. In order to acquire such an understanding this thesis focuses on implementing a depth image based planar segmentation method based on the detection of 3-D edges in video-rate speed on an embedded system. The use of plane segmentation as a mean of understanding an unknown environment was chosen after a thorough literature review that indicated that this was the most promising approach capable of reaching video-rate speeds. The camera used to capture depth images is a Kinect for Xbox One, which makes video-rate speed 30 fps, as it is suitable for use in indoor environments and the embedded system is a Jetson TX1 which is capable of running GPU-accelerated algorithms. The results show that the implemented method is capable of segmenting depth images at video-rate speed at half the original resolution. However, full-scale depth images are only segmented at 10-12 fps depending on the environment which is not a satisfactory result. Student thesisinfo:eu-repo/semantics/bachelorThesistexthttp://urn.kb.se/resolve?urn=urn:nbn:se:mdh:diva-35595application/pdfinfo:eu-repo/semantics/openAccess |
collection |
NDLTD |
language |
English |
format |
Others
|
sources |
NDLTD |
topic |
Robotics Robotteknik och automation |
spellingShingle |
Robotics Robotteknik och automation Karlsson, Ahlexander Skoglund, Robert Video-rate environment recognition through depth image plane segmentation for indoor service robot applications on an embedded system |
description |
As personal service robots are expected to gain widespread use in the near future there is a need for these robots to function properly in a large number of different environments. In order to acquire such an understanding this thesis focuses on implementing a depth image based planar segmentation method based on the detection of 3-D edges in video-rate speed on an embedded system. The use of plane segmentation as a mean of understanding an unknown environment was chosen after a thorough literature review that indicated that this was the most promising approach capable of reaching video-rate speeds. The camera used to capture depth images is a Kinect for Xbox One, which makes video-rate speed 30 fps, as it is suitable for use in indoor environments and the embedded system is a Jetson TX1 which is capable of running GPU-accelerated algorithms. The results show that the implemented method is capable of segmenting depth images at video-rate speed at half the original resolution. However, full-scale depth images are only segmented at 10-12 fps depending on the environment which is not a satisfactory result. |
author |
Karlsson, Ahlexander Skoglund, Robert |
author_facet |
Karlsson, Ahlexander Skoglund, Robert |
author_sort |
Karlsson, Ahlexander |
title |
Video-rate environment recognition through depth image plane segmentation for indoor service robot applications on an embedded system |
title_short |
Video-rate environment recognition through depth image plane segmentation for indoor service robot applications on an embedded system |
title_full |
Video-rate environment recognition through depth image plane segmentation for indoor service robot applications on an embedded system |
title_fullStr |
Video-rate environment recognition through depth image plane segmentation for indoor service robot applications on an embedded system |
title_full_unstemmed |
Video-rate environment recognition through depth image plane segmentation for indoor service robot applications on an embedded system |
title_sort |
video-rate environment recognition through depth image plane segmentation for indoor service robot applications on an embedded system |
publisher |
Mälardalens högskola, Akademin för innovation, design och teknik |
publishDate |
2017 |
url |
http://urn.kb.se/resolve?urn=urn:nbn:se:mdh:diva-35595 |
work_keys_str_mv |
AT karlssonahlexander videorateenvironmentrecognitionthroughdepthimageplanesegmentationforindoorservicerobotapplicationsonanembeddedsystem AT skoglundrobert videorateenvironmentrecognitionthroughdepthimageplanesegmentationforindoorservicerobotapplicationsonanembeddedsystem |
_version_ |
1718532579068477440 |