To move around the environment, human beings depend on sight more than their other senses, because provides information about the size, shape, color and position of an object. The increasing interest in building autonomous mobile systems makes the detection and recognition of objects in natural environments is a very important and challenging task. In this chapter, a vision system to detect objects considering natural environments, able to work on real mobile robot is developed. This system is based on supervised algorithms of classification and as input, RGB and depth images are used. Different segmentation and feature extraction methods have been applied. The proposed system has been tested in a real mobile robot and the experimental results have demonstrated the usefulness of the system for detection and location of the objects in natural environments as well as to support navigation tasks in mobile robots.