Devising an image processing method for transport infrastructure monitoring systems

Identifying and categorizing contours in images is important many areas of computer vision. Examples include such operational tasks solved by using unmanned aerial vehicles as dynamic monitoring the condition transport infrastructure, particular road markings. This study has established that current methods image contour analysis do not produce clear reliable results when solving task state Therefore, it a relevant scientific applied to improve models filtration, processing binary images, qualitative meaningful separation boundaries objects interest. To solve highlighting marking on acquired from an vehicle, method been devised includes tool for preprocessing – combined filter. The several advantages eliminates limitations known determining location object interest, cluster points histograms. procedures reported here make possible successfully problems are largely similar those expert person can face intelligent filtering information. proposed was verified at enterprise producing Ukrainian vehicle "Spectator" during tests information technology infrastructure. could be implemented promising control systems field modeling human conscious behavior sorting data required perception environmental features