The task of detecting overwater objects in poor visibility conditions

. The article is devoted to the problem of detection and recognition of overwater objects from video surveillance data in poor visibility conditions, such as rain, snow, fog, twilight. Along with the problem of visibility degradation there are other factors that complicate the solution of this problem: changes in the shape and size of the image when changing the distance to the object of observation and the angle of view of the video camera. One of the approaches to the problem of video surveillance data processing is discussed – it consists in the joint application of two technologies: YOLO deep learning model and discrete wavelet image transformation. Experimental results show that the proposed algorithm achieves high accuracy and efficiency, which makes it suitable for application in drone video monitoring systems.