A Color Segmentation Algorithm for Real-Time Object Localization on Small Embedded Systems
We present an approach to color segmentation and object localization for small-embedded systems. The algorithm defines sub-spaces in the main color space (RGB), each sub-space being a color class. A look-up table is used to speed up pixel classification in color classes. A binary image is computed for every color class. After noise reduction, we obtain a color class pixel list; after each object’s image coordinates are found and transformed to world-coordinates depending on the camera position.
Unable to display preview. Download preview PDF.
- 2.J. Bruce, T. Balch, M. Veloso: Fast and inexpensive color image segmentation for in-teractive robots. In: Proceed. of the IEEE/RSJ Internat. Conf. on Intelligent Robots and Systems, (2000). 69, 70Google Scholar
- 3.R. C. Gonzalez, R. E. Woods: Digital Image Processing. Addison Wesley, (1992). 70, 72Google Scholar
- 4.J. Brusey, L. Padgham: Techniques for obtaining robust, real-time, color-based vi-sion for robotics. In: IJCAI-99: Proceed. of the 3rd Internat. Workshop on RoboCup, M. Veloso, E. Pagello, H. Kitano, eds., (July 1999). 70Google Scholar
- 5.D. Comaniciu, P. Meer: Robust analysis of feature spaces: color image segmen-tation. In: IEEE-Proceed. of the Internat. Conf. on Computer Vision and Pattern Recognition, (June 1997) 750–755. 76Google Scholar
- 6.C. Amoroso, A. Chella, V. Morreale, P. Storniolo: A segmentation system for soc-cer robot based on neural networks. In: IJCAI-99: Proceed. of the 3rd Internat. Workshop on RoboCup, M. Veloso, E. Pagello, H. Kitano, eds., (July 1999). 76Google Scholar