DEVELOPMENT OF A VIDEO PROCESSING MODULE FOR THE TASK OF AIR OBJECT RECOGNITION BASED ON THEIR CONTOURS

The subject of research in the article is module automatic segmentation and subtraction background, which created, based on sequential application methods image preprocessing modified method interactive images implemented system optical monitoring air situation. aim work to develop an increase efficiency recognition object type a video visual environment by means qualitative segmentation. To solve this problem, algorithm mode selection image, allows more accurately, without participation operator, determine foreground pixels for further airborne object. following tasks are solved article: analysis existing binarization color semantic images, used systems; development pipeline environment. In work, used: digital processing, filtering graph analysis. results obtained: processing with proposed background confirm performance procedures. developed included demonstrates correct 93% test operator participation, us conclude about effectiveness module. Conclusions: implementation allowed problem aerial objects high degree reliability, thus increasing operational system.