Wyniki wyszukiwania - BazTech

Ograniczanie wyników

3 Machine Graphics and Vision

Znaleziono wyników: 3

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: edge tracking

Sortuj według:

Ogranicz wyniki do:

An algorithm for automatic detection of runways in aerial images

Jun Wei H., Lei G.

Machine Graphics and Vision

2001

Vol. 10, No. 4

503-518

This paper presents an automatic algorith to detect runways of the military airport in aerial images. Firstly, we design a model of runway based on its features, Then, we find the runway in a hypothesis and test paradigm. Hypothesis are formed by looing for instances of long rectangular shapes. Runway intensity and intensity contrast between the runway and background are used to verify our hypotheses. Finally, the hypothesis that is supported by verification is believed to be the runway. Many experiments demonstrate that this algorithm can find runway of a military airport effectively.

Accuracy prediction in a 3D active triangulation scanner

Kovacs T.

Machine Graphics and Vision

2001

Vol. 10, No. 1

75-87

An active triangulation 3D scanner was developed at the Budapest University of Technology and Economics, Departament of Automation. In the first part of this paper the configuration of 3D scanner system will be presented. Then the edge tracking part of model extraction algorithm will be described, especially focusing on the handing of noise. Accuracy of the generated CAD model depends of configuration parameters and the noise of the frame buffer image can be taken into consideration. The last part of the paper presents a workflow for the adequate handling of accuracy, as a function of a certain noise model. Since the development is focused on the accuracy of method instead of expensive hardware elements, it is essential to know the theoretical capabilities of the system. The focus of the paper is finding the initial point of edge tracking, the accuracy of angle calculation and the accuracy of line tracking supposing a noise model. Finally some experiment results are demonstrated.

Identification of retinal vessels by color image analysis

Rakotomalala V., Macaire L., Postaire J. G., Valette M.

Machine Graphics and Vision

1998

Vol. 7, No. 4

725-742

A recursive edge tracking of the retinal blood vessel is presented in order to achieve a bidimensionnal reconstruction of the rential vasculature. First, color edge detection is applied on the original angiographic images. Second, from interactive selection of starting points near the papilla, the tracking of the two contours of a vessel is processed. The algorithm validates the next connected pixels to the current ones which satisfy the tracking hypotheses. Problems induced by the curvature of the vessel and the discontinuity of the detected edges will be dealed with. Third, during the tracking procedure is then performed from these branch points until the end of the vessel is reached. Contour and the color of the vessel's body are associated in order to get more accurate extraction. The reconstructed vacular strucures will be used as landmarks for the follow--up of a new retinopathy called CytoMegalo Virus retinitis found on patients with acquired immune deficiency syndrome (AIDS).