Vision & localization module development for nao humanoid robot : robocup standard platform league

• Main Author: Ngo Pham, Hoang Vu
• Other Authors: Chen I-Ming
• Format: Final Year Project
• Language: English
• Published: 2014
• Subjects: DRNTU::Engineering
• Online Access: http://hdl.handle.net/10356/61381
• Institution: Nanyang Technological University

The project involves in developing a vision and localization module for NAO hu- manoid robot - Robocup Standard Platform League (SPL) based on the B-Human open-source software. The goal is to identify a robust and efficient object recogni- tion approach by using segmentation method. This has been done by separating out regions of an image corresponding to objects which will be analyzed further. This separation is based on the variation of intensity between the object pixels and the background pixels. To differentiate the pixels of the object which we are interested in from the rest which will eventually be rejected, a comparison of each pixel in- tensity value with respect to a threshold is performed. Once the important pixels are separated from the rest and are connected together as regions, we can identify the object by comparing the average color shape of the region with the color and shape prototype. A good understanding in how the Particle-based filter especially the Monte-Carlo Localization and the Particle Swarm Optimization has been im- plemented into B-Human self-localization module is also an important requirement for this project.