UDC 621.396
CLASSIFICATION OF RADIO THERMAL OBJECTS IMAGES IN SYSTEM OF SEVERAL RADIOMETERS
V. K. Klochko, full professor, RSREU, the department of automation and information technologies in control, PhD (technical sciences); This email address is being protected from spambots. You need JavaScript enabled to view it.
S. M. Gudkov, graduate student, RSREU, the department of radioengineering systems; This email address is being protected from spambots. You need JavaScript enabled to view it.
In the distributed systems of passive radiovision intended for automatic detection and recognition of observation objects according to several radiometers there is a need for the classification of the images received by radiometers by their compliance to these or those objects. The aim of the paper is to offer the optimum approach to solve the task of images classification responding to criterion of maximum likelihood and allowing to increase definition of images and also to concretize this approach for the offered indices of images closeness which do not require the recovery of images. In operation the algorithm of quasioptimum classification allowing to break a computing barrier in case of search of options is reasonable. The rules of computation of images closeness indices allowing to solve the problem of classification without operations of images recovery and by that to increase high-speed performance of classification algorithm are offered. The possibility of classification on the example of two real radio thermal images is shown
Key words: passive radiovision, radiometer, millimetric range, classification of images, indices of closeness of images