Detection of doors using a genetic visual fuzzy system for mobile robots
Tóm tắt
Doors are common objects in indoor environments and their detection can be used in robotic tasks such as map-building, navigation and positioning. This work presents a new approach to door-detection in indoor environments using computer vision. Doors are found in gray-level images by detecting the borders of their architraves. A variation of the Hough Transform is used in order to extract the segments in the image after applying the Canny edge detector. Features like length, direction, or distance between segments are used by a fuzzy system to analyze whether the relationship between them reveals the existence of doors. The system has been designed to detect rectangular doors typical of many indoor environments by the use of expert knowledge. Besides, a tuning mechanism based on a genetic algorithm is proposed to improve the performance of the system according to the particularities of the environment in which it is going to be employed. A large database of images containing doors of our building, seen from different angles and distances, has been created to test the performance of the system before and after the tuning process. The system has shown the ability to detect rectangular doors under heavy perspective deformations and it is fast enough to be used for real-time applications in a mobile robot.
Tài liệu tham khảo
Adorni, G., Cagnoni, S., Enderle, S., Kraetzschmar, G.K., Mordonini, M., Plagge, M., Ritter, M., Sablatnög, S., and Zell, A. 2001. Vision-based localization for mobile robots. Robotics and Autonomous Systems, 36(2–3):103–119.
Aguirre, E. and González, A. 2002. Integrating fuzzy topological maps and fuzzy geometric maps for behavior-based robots. International Journal of Intelligent Systems, 17(3):333–368.
Aguirre, E. and González, A. 2003. A fuzzy perceptual model for ultrasound sensors applied to intelligent navigation of mobile robots. Applied Intelligence, 19(3):171–187.
Canny, J. 1986. A computational approach to edge detection. IEEE Transactions on Pattern Analsysis and Machine Intelligence, 8:679–698.
Cha, J., Cofer, R., and Kozaitis, S. 2005. Extended hough transform for linear feature detection. Pattern Recognitiong (Elservier). To appear .
Chan, T. and Yip, R. 1996. Line detection algorithm. 13th International Conference on Pattern Recognition, 2:25–29.
Cicirelli, G., D'orazio, T., and Distante, A. 2003. Target recognition by component for mobile robot navigation. Journal of Experimental and Theoretical Artificial Intelligence, 15(3):281–297.
Cordon, O. and. F. Herrera, F.G., Hoffman, F., and Magdalena, L. 2004. Ten years of genetic fuzzy systems: Current framework and new trends. Fuzzy Sets and Systems, 141:5–31.
Cordon, O., Herrera, F., Hoffman, F., and Magdalena, L. 2001. Genetic Fuzzy Systems: Evolutionary Tuning and Learning of Fuzzy Knwoledge Bases. World Scientific Publishing.
Desouza, G. and Kak, A. 2002. Vision for mobile robot navigation: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24:237– 267.
Eshelman, L. 1991. The chc adaptive search algorithm: How to have safe search when engaging in nontraditional genetic recombination. First Workshop on Foundations of Genetic Algorithms, Morgan Kaufmann, pp. 265–283.
Eshelman, L. and Schaffer, D. 1993. Real-coded genetic algorithms and interval-schemata. Second Workshop on Foundations of Genetic Algorithms, Morgan Kaufmann, pp. 187–202.
Foresti, G. 2000. A real-time hough-based method for segment detection in complex multisensor images. Real-Time Imaging, 6:93–111.
García-Silvente, M., Fdez-Valdivia, J., García, J., and Garrido, A. 1997. A new edge detector integrating scale-spectrum information. Image and Vision Computing, 15(12):913–923.
Gasteratos, A., Beltran, C., Metta, G., and Sandini, G. 2002. Pronto: A system for mobile robot navigation via cad-model guidance. Microprocessors and Microsystems, 26:17–26.
Goldberg, D. 1989. Genetic Algorithms in Search, Optimization, and Machine Learning. Addison- Wesley.
Goldberg, D. 2002. The design of Competent Algorihmts: Steps Towards a Computational Theory of Innovation. Kluwer Academic Publishers.
Guil, N., Villalba, J., and Zapata, E. 1995. A fast hough transform for segment detection. IEEE Transactions on Image Processing, 11:1541 – 1548.
Herrera, F., Lozano, M., and Verdegay, J. 1995. Tuning of fuzzy controllers by genetic algorithms. International Journal of Approximate Reasoning, 12:299–315.
Holland, J. 1975. Adaptation in Natural and Artificial Systems. University of Michigan Press.
Huber, E. and Kortenkamp, D. 1998. A behavior-based approach to active stereo vision for mobile robots. Engineering Applications of Artificial Intelligence, 11(2):229–243.
Ishibuchi, H., Nakashima, T., and Nii, M. 2004. Classification and Modeling with Linguistic Information Granules: Advances Approaches to Linguistic Data Mining. Springer.
Karr, C. 1991. Genetic algorithms for fuzzy controllers. AI Expert, 6(2):26–33.
Katsuki, R., Ota, J., Mizuta, T., Kito, T., Arai, T., Ueyama, T., and Nishiyama, T. 2003. Design of an Artificial mark to determine 3d pose by monocular vision. IEEE International Conference on Robotics and Automation, 2003. Proceedings ICRA’ 03, vol. 114–19), pp. 995–1000.
Kim, D. and Nevatia, R. 1998. Recognition and localization of generic objects for indoor navigation using functionality. Image and Vision Computing, 16(11):729–743.
Li, H. and Yang, S. 2003. A behavior-based mobile robot with a visual landmark-recognition system. IEEE/ASME Transactions on Mechatronics, 8:390–400.
Monasterio, I., Lazkano, E., Rañó, I., and Sierra, B. 2002. Learning to traverse door using visual information. Mathematics and Computer in Simulation, 60:347–356.
Moreno-Velo, F., Baturone, I., Senhadji, R., and Sanchez-Solano, S. 2003. Tuning complex fuzzy systems by supervised learning algorithms. The 12th IEEE International Conference on Fuzzy Systems, vol. 1, pp. 226–231.
Muñoz-Salinas, R., Aguirre, E., García-Silvente, M., and Gómez, M. 2004. A multi-agent system architecture for mobile robot navigation based on fuzzy and visual behaviours. To appear in Robotica. Cambridge University Press.
Paulino, A., Batista, J., and Araújo, H. 2001. Maintaining the relative positions and orientations of multiple robots using vision. Pattern Recognition Letters, 22(12):1331–1335.
Scharstein, D. and Briggs, A.J. 2001. Real-time recognition of self-similar landmarks. Image and Vision Computing, 19:763–772.
Srinivasan, M.V., Chahl, J.S., Weber, K., Venkatesh, S., Nagle, M.G., and Zhang, S.W. 1999. Robot navigation inspired by principles of insect vision. Robotics and Autonomous Systems, 26(2--3):203–216.
Stevens, M. and Beveridge, J. 2000. Localized scene interpretation from 3d models, range, and optical data. Computer Vision and Image Understanding, 80:111–129.
Stoeter, S.A., Mauff, F.L., and Papanikolopoulos, N.P. 2000. Real-time door detection in cluttered enviroments. Proceeding of the 15th IEEE International Symposium on Intelligent Control (ISIC 200), pp. 187–191.
Tashiro, K., Ota, J., Lin, Y., and Arai, T. 1995. Design of the optimal arrangement of Artificial landmarks. IEEE International Conference on Robotics and Automation, pp. 407–413.
Technologies, N. 1995. User's Manual.
Wells, G., Venaille, C., and Torras, C. 1996. Vision-based robot positioning using neural networks. Image and Vision Computing, 14(10):715–732.
Zadeh, L. 1975. The concept of linguistic variable and its applications to approximate reasoning. Parte I Information Sciences vol. 8, pp. 199–249, Parte II Information Sciences vol. 8, pp. 301–357, Parte III Information Sciences vol. 9, pp. 43–80.
Zheng, N., Fu, X.-D., and Liu, H. 1993. 3 cad-based 3d robot vision. Intelligent Robots and Systems′93, IROS′93. Proceedings of the 1993 IEEE/RSJ International Conference on, 3:1905–1910.