izpis_h1_title_alt

Razvoj sistema za določanje lege objektov na osnovi globinske kamere
ID Burger, Aljoša (Author), ID Vrabič, Rok (Mentor) More about this mentor... This link opens in a new window, ID Bračun, Drago (Co-mentor)

.pdfPDF - Presentation file, Download (4,49 MB)
MD5: D98AB48F400DB975B411BDE7E2469E46

Abstract
Sodobni industrijski roboti so pogosto uporabljeni za manipulacijo različnih objektov. Za uspešno delovanje pa potrebujejo informacije iz okolice. En od pristopov za zbiranje podatkov in njihovo procesiranje v takem sistem je računalniški vid. V diplomskem delu je zasnovan sistem za prepoznavanje oblike, velikosti in pozicije objekta, ki se premika po tekočem traku, s pomočjo globinske kamere. Predstavljena je teorija zapisa 2D slike, globinske slike, pridobljene s pomočjo stereo vida, ter osnovna predstavitev programskega ogrodja ROS. Razvito je programje, ki je povezano v delovnem okolju ROS. Programska oprema deluje v simulatorju Gazebo ter v realnem okolju s pomočjo Intel D435 globinske kamere. Narejena je primerjava med rezultati v simuliranem in realnem okolju, kjer se vidi pomanjkljivost globinskih podatkov če kamera ni pravilno postavljena glede na delovno območje, in če vplivi okolice niso pravilno upoštevani. Največja težava za procesiranje dvodimenzionalnih podatkov pa je razmerje med ločljivostjo kamere ter območjem interesa. Na koncu so podani še napotki za nadaljnje delo.

Language:Slovenian
Keywords:robotika, slikovni sistemi, OpenCV, zaznavanje oblike objektov, Robotski operacijski sistem, C++
Work type:Bachelor thesis/paper
Typology:2.11 - Undergraduate Thesis
Organization:FS - Faculty of Mechanical Engineering
Place of publishing:Ljubljana
Publisher:[A. Burger]
Year:2021
Number of pages:XXIV, 46 str.
PID:20.500.12556/RUL-130064 This link opens in a new window
UDC:007.52:004.93(043.2)
COBISS.SI-ID:76678147 This link opens in a new window
Publication date in RUL:10.09.2021
Views:769
Downloads:115
Metadata:XML RDF-CHPDL DC-XML DC-RDF
:
Copy citation
Share:Bookmark and Share

Secondary language

Language:English
Title:Development of a system for object pose estimation using a depth camera
Abstract:
Modern industrial robots are often used for manipulation of various objects. For a system to work, however, the robot needs information from its environment. An often used approach for collecting and processing of data in such systems is computer vision. In the thesis, a system was designed for recognition of the general shape, height, and position of an object, moving on a conveyor belt, with the use of an RGBD camera. The presented theory explains how 2D and depth images collected with stereo vision are formed as well as the fundamentals of the Robot Operating System (ROS). The software is developed within a ROS workspace. The software is tested in a simulated enviroment based on Gazebo and in real life using an Intel D435 RGBD camera. A comparison is made between the results from the simulated and recorded data. It is evident that the depth information is susceptible to errors from incorrect camera placement and other negative impacts from the environment. Meanwhile, the largest issue when processing 2D data is the ratio between the camera resolution and the size of the region of interest. In the end further work and system optimisation is proposed.

Keywords:robotics, computer vision, OpenCV, object shape recognition, Robot operating system, C++

Similar documents

Similar works from RUL:
Similar works from other Slovenian collections:

Back