DocumentCode :
3283778
Title :
Disparity map estimation with neural network
Author :
Touzene, Nadia Baha ; Larabi, Slimane
Author_Institution :
Comput. Sci. Dept., USTHB, Algiers, Algeria
fYear :
2010
fDate :
3-5 Oct. 2010
Firstpage :
303
Lastpage :
306
Abstract :
This work aims at defining a new approach for a dense disparity map computing based on the neural networks from a pair of stereo images. Our approach has been divided into two main tasks. The first one deals with computing the initial disparity map using a neuronal method (BP). Whereas the second one presents a simple method to refine the initial disparity map using neural refinement so that an accurate result can be acquired. In the literature, the matching score is based only on the pixel intensities. We introduce in this work two additional features: the gradient magnitude and orientation of the gradient vector of pixels which gives a true degree of similarity between pixels. Experimental results on real data sets were conducted for evaluating the proposed method.
Keywords :
neural nets; stereo image processing; disparity map estimation; neural network; neuronal method; stereo images; Artificial neural networks; Computer architecture; Correlation; Neurons; Pixel; Stereo vision; Training; Neural network; disparity; stereovision;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Machine and Web Intelligence (ICMWI), 2010 International Conference on
Conference_Location :
Algiers
Print_ISBN :
978-1-4244-8608-3
Type :
conf
DOI :
10.1109/ICMWI.2010.5648182
Filename :
5648182
Link To Document :
بازگشت