The Method for Determining Informative Zones on Images from On-Board Surveillance Systems

Abstract

The article focuses on the stage of determining information zones on images from on-board surveillance systems in order to provide information for their classification, necessary for further semantic segmentation and recognition. Information zones in the study are understood as zones where objects of interest are most likely to be found. Objects of interest can be elements of urban infrastructure (roads, streets, buildings, etc.), railway stations and tracks, dividing lines between different texture objects, objects (cars, equipment, military facilities, etc.). The main motivation for the study is the allocation of such information zones in order to reduce the time for image processing (improving the efficiency of image processing). The method for determining information zones on images of on-board surveillance systems has been improved. It consists of the following steps: processing the original image with Canny edge detector and using the Hough transform on the segmented image. The results of the work of this method are presented on the color image of the space-based surveillance systems and on the color image from an unmanned aerial vehicle. Visual assessment of the quality of the proposed method is satisfactory. A quantitative indicator of the quality of the method for determining information zones on images of on-board surveillance systems was calculated. Analysis of the quantitative indicator showed that this method for determining information zones on images of on-board surveillance systems makes it possible to increase the efficiency of further image processing by the operator interpreter for further semantic segmentation and recognition images.