Examine vision technology for small object recognition in an industrial robotics application
This thesis explains the development of a computer vision system able to find and orient relatively small objects. The motivations is exchanging a monotonous work done by hand and replace it with an automation system with help of an ABB IRB 140 industrial robot. The vision system runs on a standard...
Main Author: | |
---|---|
Format: | Others |
Language: | English |
Published: |
Mälardalens högskola, Akademin för innovation, design och teknik
2015
|
Subjects: | |
Online Access: | http://urn.kb.se/resolve?urn=urn:nbn:se:mdh:diva-28218 |
id |
ndltd-UPSALLA1-oai-DiVA.org-mdh-28218 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-UPSALLA1-oai-DiVA.org-mdh-282182015-07-01T04:49:27ZExamine vision technology for small object recognition in an industrial robotics applicationengMartinsson, JonasMälardalens högskola, Akademin för innovation, design och teknik2015Computer visionOpenCVAutomationThis thesis explains the development of a computer vision system able to find and orient relatively small objects. The motivations is exchanging a monotonous work done by hand and replace it with an automation system with help of an ABB IRB 140 industrial robot. The vision system runs on a standard PC and is developed using the OpenCV environment, originally made by Intel in Russia. The algorithms of the system is written in C++ and the user interface in C++/CLI. With a derived test case, multiple vision algorithms is tested and evaluated for this kind of application. The result shows that SIFT/SURF works poorly with multiple instances of the search object and HAAR classifiers produces many false positives. Template matching with image moment calculation gave a satisfying result regarding multiple object in the scene and produces no false positives. Drawbacks of the selected algorithm developed where sensibility to light invariance and lack of performance in a skewed scene. The report also contains suggestions on how to precede with further improvements or research. Student thesisinfo:eu-repo/semantics/bachelorThesistexthttp://urn.kb.se/resolve?urn=urn:nbn:se:mdh:diva-28218application/pdfinfo:eu-repo/semantics/openAccess |
collection |
NDLTD |
language |
English |
format |
Others
|
sources |
NDLTD |
topic |
Computer vision OpenCV Automation |
spellingShingle |
Computer vision OpenCV Automation Martinsson, Jonas Examine vision technology for small object recognition in an industrial robotics application |
description |
This thesis explains the development of a computer vision system able to find and orient relatively small objects. The motivations is exchanging a monotonous work done by hand and replace it with an automation system with help of an ABB IRB 140 industrial robot. The vision system runs on a standard PC and is developed using the OpenCV environment, originally made by Intel in Russia. The algorithms of the system is written in C++ and the user interface in C++/CLI. With a derived test case, multiple vision algorithms is tested and evaluated for this kind of application. The result shows that SIFT/SURF works poorly with multiple instances of the search object and HAAR classifiers produces many false positives. Template matching with image moment calculation gave a satisfying result regarding multiple object in the scene and produces no false positives. Drawbacks of the selected algorithm developed where sensibility to light invariance and lack of performance in a skewed scene. The report also contains suggestions on how to precede with further improvements or research. |
author |
Martinsson, Jonas |
author_facet |
Martinsson, Jonas |
author_sort |
Martinsson, Jonas |
title |
Examine vision technology for small object recognition in an industrial robotics application |
title_short |
Examine vision technology for small object recognition in an industrial robotics application |
title_full |
Examine vision technology for small object recognition in an industrial robotics application |
title_fullStr |
Examine vision technology for small object recognition in an industrial robotics application |
title_full_unstemmed |
Examine vision technology for small object recognition in an industrial robotics application |
title_sort |
examine vision technology for small object recognition in an industrial robotics application |
publisher |
Mälardalens högskola, Akademin för innovation, design och teknik |
publishDate |
2015 |
url |
http://urn.kb.se/resolve?urn=urn:nbn:se:mdh:diva-28218 |
work_keys_str_mv |
AT martinssonjonas examinevisiontechnologyforsmallobjectrecognitioninanindustrialroboticsapplication |
_version_ |
1716806993245634560 |