A neurocomputing approach to the correspondence problem in stereo vision based upon an unsupervised neural network

• Autorzy: El-Henawy I. , Fouda Y. M. , Enab Y. M.
• Języki publikacji: EN

Abstrakty

EN

The stereo matching problem is one of the most widely stidied problems in stereo vision. In this paper we introduce a neurocomputing approach to the local stereo matching problem using edge segments as features with several attributes. Most classical local stereo matching techniques use features representing objects in both images and compute the minimum values of attribute differences. pajares et al ([21]) had verified that the differences in attributes, for the true matches, cluster in a cloud around a center. We used the self-organizing neural network to get the best cluster center. Based on the similarity constraint, we compute the minimum Mahalaobis distances between the differences of the attributes for a new pair of features and the cluster center to classify this new pair as true or false match. Experimental results with two real pairs of images are shown.

Słowa kluczowe

EN

computer vision; stereo vision; matching; unsupervised neural network

• Wydawca: Institute of Information Technology of the Warsaw University of Life Sciences – SGGW
• Czasopismo: Machine Graphics and Vision
• Rocznik: 2001
• Tom: Vol. 10, No. 1
• Strony: 29--46
• Opis fizyczny: Bibliogr. 23 poz.

Twórcy

autor

El-Henawy I.

autor

Fouda Y. M.

autor

Enab Y. M.

• Mathematics Departmnet, Faculty of Science, Manoura University, Mansoura 35516, Egypt