Accurate Color Classification and Segmentation for Mobile Robots

Abstract

Visual perception systems are fundamental for robotic systems, as they represent an affordable interface to obtain information on different objects in the environment for a robot, and because they emulate the most commonly used sense in humans for world perception. M a n y t e c h n i q u e s c a n b e u s e d t o i d e n t i f y a n o b j e c t w i t h i n a n i m a g e . S o m e o f t h e s e techniques are color object identification, shape detection and pattern matching. Each one of these techniques has different advantages; however, color based techniques are usually preferred in real-time systems, as they require less computing power than other approaches. Color object identification is composed by two phases: image segmentation, and object identification. The goal of the first phase is to identify all regions of the image that belong to the same object of interest. These regions are analyzed by the second phase in order to extract features of interest from these objects like geometry and relative distances and to infer the presence of a specific object. Color image segmentation relies highly in the identification of a set of colors. Hence, color classification, which consists on identifying a pixel as a member of a color class, is essential for this process. In this chapter a technique for color image classification and its application for color segmentation will be explained in detail. This chapter will start by presenting a set of general concepts on image processing, which will simplify the understanding of the rest of the chapter. Then, in Section 3, some of the existing approaches used for color image classification, as well as some of their advantages and drawbacks, will be described. Section 4 will describe an efficient technique for accurate color classification of images using implicit surfaces. In Section 5, it will be explained a color segmentation technique based on custom tolerance of color classification. Finally some applications will be presented in Section 6, and conclusions and future work will be discussed in Section 7.