Volume 33 #1

Contents

1. Analysis of sexual partner preferences in Eurydema ornata and E. oleracea in free choice context
2. Optimal affine approximation of image projective transformation
3. Recognition of projectively transformed planar figures XII. On new methods for projectively-invariant description of ovals in composition with a linear element of a plane
4. Edge detection based mobile robot indoor localization
5. Robust criterion for vanishing point estimation of linear trajectories of detected vehicles in a video stream
6. Matching SAR and optical images by independed referencing to a vector map
7. Increase of computational efficiency of projective image transformation on SIMD-architectures
8. Comparison of the classifying and similarity metric-based neural networks through the recognition of the filed “gender” in Russian Federation passport
9. Heartbeat-evoked responses on EEG in slow wave sleep in cats
10. Polysomnographic study of central sleep apnea in cats

The paper proposes a method for computational efficiency increase of projective image transformation, which is achived by reducing the number of checks for the boundary options of the transformation. These checks occur because, as a result of the projective transformation, there may be points on the resulting image that correspond to points outside the original image. The proposed method makes it possible to effectively use SIMD-extensions of modern calculators, which allow to process several data elements at once. Experiments have shown that in this way, the algorithm can be accelerated from 1.35 to 2 times, depending on the number of points that fall outside the limits of the original image.

Key words: projective image transformation, computational efficiency, SIMD architecture, image processing

DOI: 10.1134/S023500921901013X

References:

• Cabral B., Cam N., Foran J. Accelerated volume rendering and tomographic reconstruction using texture mapping hardware. Proceedings of the symposium on Volume visualization. 1994. Р. 91–98.
• Fedorenko F., Usilin S. Real-time object-to-features vectorisation via Siamese neural networks. Proc. of Ninth International Conference on Machine Vision. 2017. V. 10341. P. 1–5.
• Hartshorne R. Foundations of projective geometry. 1967. 91 p.
• Kuznetsova E., Shvets E., Nikolaev D. Viola-Jones based hybrid framework for real-time object detection in multispectral images. ICMV. 2015. V. 9875. P. 1–6.
• McMillan L. An image-based approach to three-dimensional computer graphics. Ph.D. thesis, Citeseer. 1997.
• Musin O.R. Fast geometric transformations for image processing. International Journal of imaging Systems and technology. 1991. V. 3 (3). P. 257–261.
• Skoryukina N., Chernov T., Bulatov K., Nikolaev D.P., Arlazarov V. Snapscreen: Tv-stream frame search with projectively distorted and noisy query. Ninth International Conference on Machine Vision. 2017. V. 10341. P. 103410Y.
• Skoryukina N., Nikolaev D.P., Sheshkus A., Polevoy D. Real time rectangular document detection on mobile devices. Seventh International Conference on Machine Vision. 2015. V. 9445. P. 94452A.
• Tuceryan M., Genc,Y., Navab N. Single-point active alignment method (spaam) for optical see-through hmd calibration for augmented reality. Presence: Teleoperators & Virtual Environments. 2002. V. 11 (3). P. 259–276.
• Wolberg G. Digital Image Warping. IEEE Computer Society Press, Los Alamitos, CA, USA, 1st edn. 1994.
• Xu J., Chen G., Xie M. Vision-guided automatic parking for smart car. Proceedings of the IEEE Intelligent Vehicles Symposium. 2000. P. 725–730.