OPTICAL-ELECTRONIC DEVICE OF CALCULATION OF PARAMETERS OF VOLUME OBJECTS OF WORKING SCENE AT MULTIPLE SOURCES OF VIDEO DATA

The paper considers approaches to the construction of a geographically distributed optical-electronic device, providing an analysis of significant and long working scenes in the interests of automating the processes of control and management of robotic tools in industrial assembly shops and warehouses. The principal difference of the proposed solution is the possibility of obtaining images of the analyzed objects using optical-electronic sensors located in different parts of the workspace to realize the function of binocular vision on a much larger area of the working scene compared to analogues. A distinctive novelty of the developed theoretical approach is the approach to binocular technical vision, which consists in iteratively performing calibration procedures for selected pairs of opticalelectronic sensors and the subsequent calculation of the spatial coordinates of the objects being analyzed using calibrated pairs of optical-electronic sensors. The results of image analysis from each of the optoelectronic sensors are used to accompany moving objects and analyze their motion paths in the working scene space. To implement the developed theoretical approaches, a modular optoelectronic device has been developed, consisting of two types of modules. The first type of module is a standalone opto-electronic module, which includes an opto-electronic sensor and means for processing and extracting primary features immediately upon receiving images for their subsequent analysis. The second type is a computational module that provides processing of primary data from a set of modules of the first type. Data transfer between device modules is provided via radio over a WiFi network. A distinctive feature of the developed device is the primary processing of images immediately upon their receipt and transmission over the radio channel of a small amount of data about the selected objects to the computing module, which performs the final stages of data processing and generates a set of parameters describing the characteristics and spatial coordinates of the objects found on the working scene for their further of use. Experimental studies were conducted on the developed simulation model, which confirmed the correctness of the developed theoretical approach and the possibility of its application in practice.

1. Ellis R.E. Locating and acquiring on object in a robot workspace using multiple stereo images. SPIE Intelligent robots and computer vision, 1985, vol. 579, pp. 464 – 473.

2. Titov V.S., Panishhev V.S., Korostelev S.I., Denisjuk V.A. Metod raspoznavanija izobrazhenij ob#ektov s ispol'zovaniem trehmernyh vektornyh jetalonov i programma dlja ego realizacii. Telekommunikacii, 2007, no. 9, pp. 10-14.

3. Korostelev S.I., Titov V.S., Panishhev V.S., zaregistr Patent na izobretenie RUS 2361273 Sposob i ustrojstvo dlja raspoznavanija izobrazhenij ob#ektov. 12.03.2007.

4. Yeon C., Aggarwal J. Positioning three dimensional objects using stereo images. IEEE J. robotics and automation, 1987, vol. RA-3, no. 6, pp. 361-373.

5. Wang Y.F., Aggarwal J.K. Integration of active and passive sensing techniques for representing three-dimensional objects. IEEE transactions on robotics and automation, 1984, vol. 5, no. 4, pp. 460 – 470.

6. Mindru F., Tuytelaars T., Van Gool L., Moons T. Moment invariants for recognition under changing viewpoint and illumination. CVIU, 2004, pp. 3–27.

7. Gilboa G., Osher S. Nonlocal linear image regularization and supervised segmentation. SIAM Multiscale Model. Simul, 2007, vol.6. no. 2, pp. 595–630.

8. Prohorov I.V., Mysev A.Je Issledovanie algoritmov rekomendatel'nyh sistem, osnovannyh na verojatnostnyh modeljah. Izvestija Jugo-Zapadnogo gosudarstvennogo universiteta. Serija: Upravlenie. Vychislitel'naja tehnika, informatika. Medicinskoe priborostroenie, 2015, no.2 (15), pp. 16-21

9. Perona P., Malik J. Scale-space and edge detection using anisotropic diffusion. PAMI, 1990, no. 12, pp. 629–639.

10. Liao P., Chen T., Chung P. A Fast Algorithm for Multilevel Thresholding. J. Inf. Sci. Eng. 2001, no.17, pp. 713-727.

11. Titov V.S., Truphanov M.I. The method of automatic determination monochromatic aberration of vision’s optical subsystem. Information and Telecommunication Technologies in Intelligent Systems. Second international conference. Proceedings. Spain. Barcelona, 2004, pp. 40 – 43.