Autonomous positioning using colour based object detection and pose estimation

• Main Author: Hadisaputra, Andika
• Other Authors: Wang Jianliang
• Format: Final Year Project
• Language: English
• Published: 2015
• Subjects: DRNTU::Engineering::Electrical and electronic engineering::Control and instrumentation::Robotics
• Online Access: http://hdl.handle.net/10356/64689
• Institution: Nanyang Technological University

Computer vision discipline has gained popularity for the past few decades. One of the significant applications of computer vision is image-based robot control. The system allows machines to emulate human vision and understand things they see through calculations and processes of image information from the camera. In this project, a vision-guided positioning algorithm was developed by utilising computer vision technology. The system can detect a target object captured by robot’s camera and calculate the position and orientation of the object. The target object specified by a unique pattern of four colour papers was detected using the colour detection method. The centre coordinate of each colour in the image plane was calculated using the image moment theory. Given the object points in 3D coordinate space and the projection in the 2D image plane, the position and the orientation of the target object relative to the robot was estimated using pose estimation algorithm. Robot motional control for autonomous positioning was performed based on the target object’s pose information. This thesis describes main theories used in this project, algorithm development for the system, and recommendations for future work.