Paper Title
Image Processing Algorithms For Robotics On Embedded System

Abstract
Vision is the most versatile and efficient sensory system. So, it is not surprising that images contribute an important role in human perception. This is analogous to machine vision such as shape recognition application which is an important field nowadays. This paper describes implementation of image processing on embedded platform and an embedded application, a robot capable of tracking an object in 3-dimensional environment. It is a real time operating system (RTOS) based embedded system which will run the Digital Image Processing Algorithms to extract the information from the images. The camera connected on USB bus is used to capture images on the ARM9 core running RTOS. Depending upon the information extracted, the locomotion is carried out. The camera is a simple CMOS USB-camera module which has a resolution about 0.3MP. Video4Linux API’s provided by kernel are used to capture the image, and then it is decoded, and the required object location is detected using image processing algorithms. The actuations are made so as to track the object. The embedded Linux kernel provides support for multitasking and ensures that the task is performed within the real time constraints. The OS makes system flexible for changes such as interfacing new devices, handling the file system and memory management for storage of data. Keywords- Embedded Linux, ARM, Video4Linux, YUYV, Embedded C, Object detection, CMOS, USB, SOC, Kerne