SELECTION OF RECOGNITION OBJECTS’ OUTER CONTOURS ON MULTICHANNEL IMAGES

Ирина Карловна Васильева, Анатолий Владиславович Попов

Abstract


Methods for detecting contour points of objects on segmented images formed by the method of statistical recognition of multichannel data are proposed. Algorithms for linking of adjacent isolated points of the contour of the selected area using distance criteria have been developed. The obtained arrays of points belonging to the outer contour allow us to represent the boundary in the form of scans along the axes in the inertial coordinate system placed at the center of gravity of the object’s image. The algorithms approbation results confirming their effectiveness in problems of constructing brightness-geometric models of recognition objects are presented.

Keywords


probability filter; statistical segmentation of an image; color model; contour selection; linking of contour points; distance criterion

References


Popov, A. V., Vasil'eva, I. K., Ugarova, A. S. Al-goritm soprovozhdeniya ob"ektov v videopotoke, registriruemom s bespilotnogo letatel'nogo appa-rata [Algorithm for tracking objects on a video flow recorded from an unmanned aerial vehicle]. Avіatsіino-kosmіchna tekhnіka і tekhnologіya – Aerospace engineering and technology, 2015, no. 6 (123), pp. 77 – 84.

Liu, Chun., Xiao, Yingying., Yang, Jian. A Coast-line Detection Method in Polarimetric SAR Images Mixing the Region-Based and Edge-Based Active Contour Models. IEEE Transactions on Geo-science and Remote Sensing, 2017, vol. PP, iss. 99, pp. 1 – 13. doi: 10.1109/TGRS.2017.2679112.

Iglesias, Andres., Galvez, Akemi., Avila, Andreina. Immunological Approach for Full NURBS Reconstruction of Outline Curves from Noisy Data Points in Medical Imaging. IEEE/ACM Transactions on Computational Biology and Bio-informatics, 2017, vol. PP, iss. 99, p. 1. doi: 10.1109/TCBB.2017.2688444.

Vizil'ter, Yu. V., Zheltov, S. Yu. Problemy tekhnicheskogo zreniya v sovremennykh aviatsionnykh sistemakh [Problems of technical vi-sion in modern aviation systems]. Trudy nauchno-tekhnicheskoi konferentsii-seminara “Tekhnicheskoe zrenie v sistemakh upravleniya mobil'nymi ob"ektami” [Proc. Scientific and Technical Conference-seminar “Technical vision in mobile ob-ject control systems”]. Moscow, 2011, vol. 4, pp. 11 – 44. (In Russian).

Furman, Ya. A., Krevetskii, A. V., Leukhin, A. N., Peredreev, A. K. Vvedenie v konturnyi analiz i ego prilozheniya k obrabotke izobrazhenii i signalov [Introduction to contour analysis and its applications to image and signal processing]. Moscow, Fizmatlit Publ., 2003. 592 p.

Dudinova, O. B. Metod kategoriinoi klassifikatsii ob"ektov pri komp'yuternom analize aerosnimkov [The method of categorical classification of objects in computer analysis of aerial photographs]. Sistemi obrobki іnformatsії – Information processing systems, 2016, vol. 7 (144), pp. 36 – 44.

Gao, Guowei., Wen, Chenglin., Wang, Huibin., Xu, Lizhong. Fast Multiregion Image Segmentation Using Statistical Active Contours. IEEE Signal Processing Letters, 2017, vol. 24, iss. 4, pp. 417 – 421. doi: 10.1109/LSP.2017.2664659.

Song, Jianfeng., Wang, Panfeng., Miao, Qiguang., Liu, Ruyi., Huang, Bormin. The Reconnection of Contour Lines from Scanned Color Images of Topographical Maps Based on GPU Implementation. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2017, vol. 10, iss. 2, pp. 400 – 408. doi: 10.1109/JSTARS.2016.2580903.

Zheng, Amin., Cheung, Gene., Florencio, Dinei. Context Tree-Based Image Contour Coding Using a Geometric Prior. IEEE Transactions on Image Processing, 2017, vol. 26, iss. 2, pp. 574 – 589. doi: 10.1109/tip.2016.2627813.


Refbacks

  • There are currently no refbacks.