Vision-based object’s shape determination for robot alignment

• Main Authors: Farah Adiba, Azman, Mohd Razali, Daud, Amir Izzani, Mohamed, Addie Irawan, Hashim, Raja Mohd Taufika, Raja Ismail
• Format: Article
• Language: English
• Published: UTeM 2018
• Subjects: TK Electrical engineering. Electronics Nuclear engineering
• Online Access: http://umpir.ump.edu.my/id/eprint/19462/1/Vision-Based%20Object%E2%80%99s%20Shape%20Determination%20for%20Robot%20Alignment.pdf; http://umpir.ump.edu.my/id/eprint/19462/; http://journal.utem.edu.my/index.php/jtec/article/view/3330

This study provides vision-based system solutions to a peg-in-hole problem facing by a fork lift like robot used to transport copper wire spools from a rack in which the spools are arranged side by side, to a specified place. The copper wire spool is held by 3 round cylindrical shafts; one through the center hole of the spool and another 2 shafts hold at the bottom of the spool. The aim of this development of vision-based system is to make the robot operating autonomously. However, this study scope is limited to copper wire spool detection and confirmation of its alignment compared to camera orientation using a Logitech Webcam C525 which has an autofocus camera and have HD view with lower price. By integrating the Logitech webcam for windows with MATLAB R2016a, all computations, programming and processing of this project are done using the MATLAB. The proposed system uses Circular Hough Transform (CHT) and image processing methods for binarization, morphology and edge detection of the sampled images from real-time video recording. Several simulations have been carried out and from the result obtained, the system is able to detect the copper wire spool with estimated radius in pixel and the alignment of the spool.