Method and system for removing raindrops in real image after raining

Abstract

The invention relates to a method and a system for removing raindrops in a real image after raining. The raindrop removing method comprises the following steps: acquiring a historical real image afterraining; constructing a recursive attention residual error network fusing a long-short-term memory model, a spatial attention mechanism and a residual error block according to the historical real images after raining; acquiring an after-rain real image to be subjected to rain removal, and processing the after-rain real image to be subjected to rain removal by utilizing the recursive attention residual network to generate an after-rain real image subjected to rain removal; based on an image enhancement theory, filtering residual raindrops in the after-rain real image after rain removal by utilizing a raindrop detection and filtering algorithm, and determining the after-rain real image after rain removal; based on a computer graphics theory, processing the filtered real image after rainingby using a pixel value conversion algorithm, and determining the real image after raining after pixel point enhancement. According to the invention, the quality difference of the rain-removed image and the processing effect of the synthesized image can be improved.

Description

technical field [0001] The invention relates to the field of computer vision, in particular to a method and system for removing raindrops in a real image after rain. Background technique [0002] Rain is liquid water that condenses from water vapor in the atmosphere and becomes heavier and falls by gravity. Raindrops will cause blurred images and lower contrast, and will affect the performance of visual tasks such as object detection, autonomous driving, and video tracking, and even cause visual tasks to fail. Removing rain from images or videos can improve the productivity of vision tasks and is more helpful for related vision tasks. Therefore, in recent years, the problem of deraining has been widely concerned by scholars. [0003] Restoring the degraded rainy image to a clear image without rain is called single image deraining. Existing deraining methods mainly include video-based deraining methods and single image-based deraining methods. The video-based deraining me...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a method and system for removing raindrops in real images after rain, to solve the problems of poor quality of images after rain removal and poor processing effect of synthetic images

Images