ANN implementation of stereo vision using a multi-layer feedback architecture

Mousavi, M.S.; Schalkoff, Robert J.

doi:10.1109/21.299703

Cited by 19 publications

(17 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nevertheless, we have also verified that the best performance in stereovision matching is achieved under global matching strategies [6][7][8]. One of the most relevant approaches used for finding the best global matches is relaxation; it refers to a computational mechanism involving unary and binary measurements [18][19][20][21][22][23][24][25][26][27][28][29] with the purpose of computing and improving any image unit value. Under the stereovision matching framework, the image units are the pairs of features to be matched and the values determine the strength of the correspondences.…”

Section: Techniques In Stereovision Matchingmentioning

confidence: 68%

See 1 more Smart Citation

Fuzzy Cognitive Maps for stereovision matching

Pajares¹,

Cruz

2006

Pattern Recognition

View full text Add to dashboard Cite

This paper outlines a method for solving the stereovision matching problem using edge segments as the primitives. In stereovision matching the following constraints are commonly used: epipolar, similarity, smoothness, ordering and uniqueness. We propose a new matching strategy under a fuzzy context in which such constraints are mapped. The fuzzy context integrates both Fuzzy Clustering and Fuzzy Cognitive Maps. With such purpose a network of concepts (nodes) is designed, each concept represents a pair of primitives to be matched. Each concept has associated a fuzzy value which determines the degree of the correspondence. The goal is to achieve high performance in terms of correct matches. The main findings of this paper are reflected in the use of the fuzzy context that allows building the network of concepts where the matching constraints are mapped. Initially, each concept value is loaded via the Fuzzy Clustering and then updated by the Fuzzy Cognitive Maps framework. This updating is achieved through the influence of the remainder neighboring concepts until a good global matching solution is achieved. Under this fuzzy approach we gain quantitative and qualitative matching correspondences. This method works as a relaxation matching approach and its performance is illustrated by comparative analysis against some existing global matching methods.

show abstract

Section: Techniques In Stereovision Matchingmentioning

confidence: 68%

“…The following papers use a global relaxation technique based on probabilistic/merit [8,[17][18][19][20][21][22][23][24][25] and optimization through a Hopfield neural network [4,6,28,29].…”

Section: Techniques In Stereovision Matchingmentioning

confidence: 99%

Fuzzy Cognitive Maps for stereovision matching

Pajares¹,

Cruz

2006

Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…(1) Let Xmn represent the grey-scale intensity at location (m,n) of an image. G(i,j) and G(i,j) are commonly obtained by convolving the grey-scale intensities about pixel location (i,j) with the 3x3 masks A and B given by Gy(i,i) = bX (5) m=i1 nj-1 enable one to evaluate the components of Eq. 1 and consequently, G(i,j).…”

Section: The Sobel Algorithmmentioning

confidence: 99%

<title>Neural network approach to edge detection and noise reduction in low-contrast images</title>

Johnson

Page

Tagliarini

1995

Applications and Science of Artificial Neural Networks

View full text Add to dashboard Cite

Numerous vision applications rely upon efficient techniques for detecting edges in an image. Edge detection is especially difficu't in low-contrast images which are characterized by the general hck of sharp variations in the grey-scale intensity values between objects of interest and their backgrounds. In low-contrast images, the application of commonly employed edge detection algorithms may result in excessive noise. This paper presents a neural network model which enhances edges and reduces noise in low-contrast grey-scak images. A neural element is associated with each pixel in an image. Each neuron receives weighted grey-scale inputs from its immediate neighbors. The weights associated with the grey-scale inputs are determined through a fuzzy compatibility function that grades the degree of similarity between the grey-scale intensity values of neighboring pixels. The neural element sums its weighted inputs and subjects the weighted sum to a sigmoid function that produces grey-scale outputs ranging between 0 and 255. The slope of the sigmoid function is chosen to force resulting pixel values away from mid-range values and closer to either 0 or 255. The resulting image is then subjected to the Sobel edge detection algorithm. The technique is illustrated by applying it to several low-contrast infrared images containing military vehicles. The results show significant noise reduction and edge enhancement.

show abstract

“…This computational model is massively parallel, which is very important as far as real-time working systems are concerned. This kind of system was used in stereo-matching problem [ 41 – 43 ]. In [ 44 ] and [ 45 ], the authors described a driving support system based on stereoscopy and Hopfield-like analog neural nets.…”

Section: Introductionmentioning

confidence: 99%

A novel hybrid-maximum neural network in stereo-matching process

Laskowski

2012

Neural Comput & Applic

View full text Add to dashboard Cite

In the present paper, the completely innovative architecture of artificial neural network based on Hopfield structure for solving a stereo-matching problem—hybrid neural network, consisting of the classical analog Hopfield neural network and the Maximum Neural Network—is described. The application of this kind of structure as a part of assistive device for visually impaired individuals is considered. The role of the analog Hopfield network is to find the attraction area of the global minimum, whereas Maximum Neural Network is finding accurate location of this minimum. The network presented here is characterized by an extremely high rate of work performance with the same accuracy as a classical Hopfield-like network, which makes it possible to use this kind of structure as a part of systems working in real time. The network considered here underwent experimental tests with the use of real stereo pictures as well as simulated stereo images. This enables error calculation and direct comparison with the classic analog Hopfield neural network as well as other networks proposed in the literature.

show abstract

ANN implementation of stereo vision using a multi-layer feedback architecture

Cited by 19 publications

References 20 publications

Fuzzy Cognitive Maps for stereovision matching

Fuzzy Cognitive Maps for stereovision matching

<title>Neural network approach to edge detection and noise reduction in low-contrast images</title>

A novel hybrid-maximum neural network in stereo-matching process

Contact Info

Product

Resources

About