Kwik, Darius Budisantosa and Prajogo, Tutuko and Rusyadi, Rusman (2011) Developing a Machine Vision System for Certain-Object's Shape, Orientation, and Location Detection for Sorting Purposes Using a Mitsubishi Industrial Micro-Robot RV-M1 Manipulator. Bachelor thesis, Swiss German University.

Preview	Text Darius Budisantosa 1-1107-006 TOC.pdf Download (122kB) | Preview
	Text Darius Budisantosa 1-1107-006 1.pdf Restricted to Registered users only Download (103kB)
	Text Darius Budisantosa 1-1107-006 2.pdf Restricted to Registered users only Download (877kB)
	Text Darius Budisantosa 1-1107-006 3.pdf Restricted to Registered users only Download (708kB)
	Text Darius Budisantosa 1-1107-006 4.pdf Restricted to Registered users only Download (788kB)
	Text Darius Budisantosa 1-1107-006 5.pdf Restricted to Registered users only Download (104kB)
Preview	Text Darius Budisantosa 1-1107-006 Ref.pdf Download (97kB) | Preview

Abstract

In this thesis, a machine vision system is built for the sorting purpose, which dedicated for pre-assembly process that able to do object recognition, location and orientation detection based on 2D shape image properties of a predefined object. In the process, sorting, orientating, and material handling tasks need to be done. To do such tasks, Diffuse Brick Lighting is applied in the system to produce silhouette image. Computer Vision library, OpenCV, will be used in the image processing process. Freeman Chain Code Feature Extraction method with Least SAD Chain Code Histogram 4-Double Shifting Bins Matching Method is used as the object recognition and orientation detection solution. Minimum Area Bounding Box method is used for location detection solution. An Image to Robot Coordinate System Transformation is applied to transform the object location in the image to the robot coordinate system. Such grabbing determination method is also applied so the robot could grab the object in a proper way. In this system, Robot Arm Mitsubishi Movemaster RV-M1 is used to perform all the works. The performance of the system is 71.4% due to disturbance from environment illumination and 3D object in 2D image perspective effect. In conclusion, by inducing vision capabilities to the robot arm, a smart sorting system is built so that predefined objects with flexible location and orientation could be sorted satisfactorily.

Item Type:	Thesis (Bachelor)
Uncontrolled Keywords:	Machine Vision; Robot Vision; Sorting; Object Recognition; Location Detection
Subjects:	T Technology > TJ Mechanical engineering and machinery T Technology > TJ Mechanical engineering and machinery > TJ1555 Sorting devices T Technology > TJ Mechanical engineering and machinery > TJ210 Robots (General)
Divisions:	Faculty of Engineering and Information Technology > Department of Mechatronics Engineering
Depositing User:	Astuti Kusumaningrum
Date Deposited:	16 Mar 2021 12:49
Last Modified:	16 Mar 2021 12:49
URI:	http://repository.sgu.ac.id/id/eprint/1119

Actions (login required)

View Item