Improving Robot Vision by Color Information
نویسنده
چکیده
Robot vision tasks often use stereo methods to obtain 3-d information on the environment. This paper shows how color information can be utilized to improve the results of dense stereo matching as well as the results of edge-based stereo matching. A hierarchical chromatic Block Matching technique to obtain dense stereo correspondence is presented. The results have been compared to the results of the gray value algorithm. The precision of the matching results always improved by 25 to 30 % when color information instead of gray value information was used. Furthermore, it will be shown how the results of edge-based stereo matching can be improved in quantity and in quality when using color information. This improvement is based on the higher number of edges that can be detected in color images as compared to intensity images. Moreover, the idea of edge classification for edge-based stereo correspondence is outlined.
منابع مشابه
An Intelligent Vision System on a Mobile Manipulator
This article will introduce a robust vision system which was implemented on a mobile manipulator. This robot has to find objects and deliver them to pre specified locations. In the first stage, a method which is named color adjacency method was employed. However, this method needs a large amount of memory and the process is very slow on computers with small memories. Therefore since the previou...
متن کاملRobot Motion Vision Pait I: Theory
A direct method called fixation is introduced for solving the general motion vision problem, arbitrary motion relative to an arbitrary environment. This method results in a linear constraint equation which explicitly expresses the rotational velocity in terms of the translational velocity. The combination of this constraint equation with the Brightness-Change Constraint Equation solves the gene...
متن کاملQuantitative Comparison of Color Systems for Robot Soccer Applications
Robot soccer has evolved into a very dynamic and competitive field within the last few years, many different robot soccer leagues now exist. Most of the leagues rely on computer vision in one form or another to gather information about the game situation – the position of a team's robots, the position of the opponent's robots and the ball. While some problems robot soccer vision posed have been...
متن کاملEye Spy: Improving Vision through Dialog
Despite efforts to build robust vision systems, robots in new environments inevitably encounter new objects. Traditional supervised learning requires gathering and annotating sample images in the environment, usually in the form of bounding boxes or segmentations. This training interface takes some experience to do correctly and is quite tedious. We report work in progress on a robotic dialog s...
متن کاملSelf-localization of Indoor Mobile Robots Based on Artificial Landmarks and Binocular Stereo Vision
For the self-localization problem of the indoor mobile robots, a self-localization method of indoor mobile robots based on artificial landmarks and binocular stereo vision was proposed in this paper. First, a color scalable artificial landmark model is designed to give position information of the environment. Second, using the color segmentation, invariance of cross-ratio and self-adaptive wind...
متن کامل