AN APPROACH TO BEACONS DETECTION FOR A MOBILE ROBOT USING A NEURAL NETWORK MODEL
Mots-clés :
Neural network classifier, image processing, back-propagation network, detection and object extraction, Hough TransformerRésumé
In this paper we propose a neuro-mimetic technique relating to the detection of beacons in mobile robotics. The objective is to bring a robot moving in an unspecified environment to acquire attributes for recognition. We develop a practical approach for the segmentation of images ofobjects of a scene and evaluatethe performances in real time of them. The neuronal classifier used is a window of a network Multi-layer Perceptron MLP (9-6-3-1) using the algorithm of retro-propagation of the gradient,
where the distributed central pixel uses information in gray level. The originality of the work lies in the use of the association of an enhanced neural network configuration and Standard Hough Transform. The results obtained with a momentum of 0.3 and one coefficient of training equal to 0.02 shows that our system is robust with an extremely appreciable computing time.
Références
A. Ghosh and K. P. Sankar, "Neural Network, self
organization, an object extraction", Pattern Recognition
Letters, volume 13, n°5, May (1992).
Resa Nekovei and Ying Sun,"Back-propagation network
audits configuration for blood vessel detection in angiograms" .IEEE Transactions on Neural Networks, Volume 6, N°1, January (1995).
Atiquzzaman M. Multiresolution Hough transforms—an
efficient method of detecting pattern in images. IEEE
Transactions on Pattern Analysis and Machine Intelligence
(1992); 14(11):1090-5.
Koshimizu H, Numada M.FIHT2 algorithm: a fast
incremental Hough transform. IEICE Transactions (1991);
E74 (10).
Philip KP, Dove EL, McPherson DD, Gotteiner NL, Stanford
W, Chandran KB. The fuzzy Hough transforms feature
extraction in medical images. IEEE Transactions on Medical
Imaging (1994); 13(2):235-40.
Choudhary AN, Ponnusarry R. Implementation and evaluation of Hough transform algorithm on a shared—memory
multiprocessor. Journal of Parallel and Distributed Computing (1991); 12:178–88.
Lotufo RA, Dagless EL, Milford DJ, Morgan AD, Morrissey
JF, Thomas BT. Hough transform for transputer arrays. In:
Proceedings of the third international conference on image
processing and its applications, IEEE proceedings, London,
(1994), pp. 122–33.
Tagzout S, Achour K, Djekoune O. Hough transform for
FPGA implementation. Elsevier Journal, Signal Processing
(2001); 81(6):1295–301.
Rumelhart D. E., J. McClelland and PDP Research group,
"Parallel Distributed Processing", Explorations in the Microstructure of recognition, volume 1, MIT Press, Cambridge, MA (1986).
Fnaiech F., M. Sayadi, et M. Najim, "Factored and fast
algorithms for training feed forward neural networks", ESST
de Tunis (1997).
Caplier A., F. Luthon et C. Dumantier, "Real time
implementations of an mrf-based motion detection algorithm, special issue on real-time motion analysis", Journal of real time imaging, vol. 4, n°1, February (1998), pp. 41-54.
T.Tuytelaars and L.Van Gool, “Matching Widely Separated
Views based on affinity Invariant Neighbourhoods”,
International Journal on Computer Vision, July (2003).
Kohonen T, "An introduction to neural networks", Neural
Networks 1, 3-16, (1988).
Qing Song, Jizhong Xiao and Yeng Chai Soh, "Robust back
propagation training algorithm for multilayered neural tracking controller", IEEE Transactions on Robotics and Automation, vol. 10, n°5, September (1999).
S.Baluja, , Evolution of an artificial neural network based
autonomous land vehicle controller, ALVINN, IEEE Transactions on Systems, Man and Cybernetics, Part B, Vol. 26, No. 3, June (1996), pp. 450-463
L. Paletta, E Rome and A. Pinz, "Visual object detection for autonomous sewer robots", IROS'99, Proceeding of the 1999 IEEE/RSJ, International Conference on Intelligent Robots
and automated Systems, Kyougju, South Korea, October
-21, (1999), pp. 1087-1093.
-Oualid A. Djekoune AO, AchourK, Zoubiri H. Segments
matching using a neural network approach. ACS/IEEE
International conference on computer systems and applications, AICCSA’ 01, June 25-29, (2001), Beirut,
Lebanon. pp. 103-105.
K. Achour, O. Djekoune, “Localisation and guidance with an embarked camera on a mobile robot”. Advanced Robotics,
(2002), (16:1).
Passold F., M.R Stemmer, "Feedback error learning neural
network applied to a Scara robot'', RoMoCo’04, Proceedings
of the fourth international workshop on robot motion and
control, June 17-20 (2004), Puszczykowo, Poland, pp. 197-202.
-K. Achour, O. Djekoune, “Incremental Hough transform: an improved algorithm for digital device implementation” Real
Time Imaging, Elsevier, (2004).
Téléchargements
Publié-e
Comment citer
Numéro
Rubrique
Licence
Les auteurs publiant dans cette revue acceptent les termes suivants :- Les auteurs détiennent le droit d'auteurs et accordent à la revue
le droit de première publication, avec l’ouvrage disponible simultanément [SPÉCIFIER LA PÉRIODE DE TEMPS] après publication, sous la licence Licence d’attribution Creative Commons qui permet à d'autres de partager l'ouvrage en en reconnaissant la paternité et la publication initiale dans cette revue. - Les auteurs peuvent conclure des ententes contractuelles additionnelles et séparées pour la diffusion non exclusive de la version imprimée de l'ouvrage par la revue (par ex., le dépôt institutionnel ou la publication dans un livre), accompagné d'une mention reconnaissant sa publication initiale dans cette revue.
- Les auteurs ont le droit et sont encouragés à publier leur ouvrage en ligne (par ex., dans un dépôt institutionnel ou sur le site Web d'une institution) avant et pendant le processus de soumission, car cela peut mener à des échanges fructueux ainsi qu'à un nombre plus important, plus rapidement, de références à l’ouvrage publié (Consulter The Effect of Open Access).
