|
Artificial Intelligence, Intelligent Systems, Neural Networks
The method of comparing a 3D object model with a 2D image based on invariant moments
D. T. Nguyena, M. V. Khacumovb a RUDN University
b Institute for Systems Analysis, FRC "Computer Science and Control" of RAS
Abstract:
The solution of the comparison problem comes down to that of optimizing the orientation of the 3D object model in order to achieve maximum matching of its projection to the presented image.
The closeness measure is the
Euclidean distance between invariant moments of the compared 2D images.
In the presented formulation, the projection of the 3D model is a grayscale image and the brightness of the pixel is determined by the distance to the viewing plane. (In Russian).
Key words and phrases:
3D object model, range image, projection, comparison, orientation control, invariant moments.
Received: 01.12.2017 Accepted: 28.12.2017
Citation:
D. T. Nguyen, M. V. Khacumov, “The method of comparing a 3D object model with a 2D image based on invariant moments”, Program Systems: Theory and Applications, 8:4 (2017), 209–220
Linking options:
https://www.mathnet.ru/eng/ps277 https://www.mathnet.ru/eng/ps/v8/i4/p209
|
Statistics & downloads: |
Abstract page: | 162 | Full-text PDF : | 60 | References: | 29 |
|