Improvement of Auto-Tracking Mobile Robot based on HSI Color Model

• Main Authors: Sundarajoo, Suresh, Ahmad Shahrizan, Abdul Ghani
• Format: Article
• Language: English
• Published: Institute of Advanced Engineering and Science 2018
• Subjects: Q Science (General); QC Physics; TC Hydraulic engineering. Ocean engineering; TD Environmental technology. Sanitary engineering; TF Railroad engineering and operation; TJ Mechanical engineering and machinery; TK Electrical engineering. Electronics Nuclear engineering; TL Motor vehicles. Aeronautics. Astronautics; TS Manufactures
• Online Access: http://umpir.ump.edu.my/id/eprint/23969/1/2018%20Improvement%20of%20Auto-Tracking%20Mobile%20Robot%2015266-28154-1-PB.pdf; http://umpir.ump.edu.my/id/eprint/23969/; http://dx.doi.org/10.11591/ijeecs.v12.i3.pp1349-1357; http://dx.doi.org/10.11591/ijeecs.v12.i3.pp1349-1357

Auto tracking mobile robot is a device that able to detect and track a target. For an auto tracking device, the most crucial part of the system is the object identification and tracking of the moving targets. In order to improve the accuracy of identification of object in different illumination and background conditions, the implementation of HSI color model is used in image processing algorithm. In this project HSI-based color enhancement algorithm were used for object identification. This is because HSI parameter are more stable in different light and background conditions, so it is selected as the main parameters of this system. Pixy CMUcam5 is used as the vision sensor while Arduino Uno as the main microcontroller that controls all the input and output of the device. Moreover, two servo motors were used to control the pan-tilt movement of the vision sensor. Experimental results demonstrate that when HSI color-based filtering algorithm is applied to visual tracking it improves the accuracy and stability of tracking under the condition of varying brightness, or even in the low-light-level environment. Besides that, this algorithm also prevents tracking loss due to object color appears in the background.