Traffic monitoring video real-time defogging method based on moving targets

Abstract

The invention relates to a traffic monitoring video real-time defogging method based on moving targets. According to the characteristics of traffic monitoring videos, the contents of video frames are divided into foreground moving targets and background parts, and different methods are respectively adopted for carrying out defogging processing on the foreground and the background, wherein the foreground moving targets are mainly processed. Meanwhile, the relevance between the adjacent frames of the videos is utilized for adopting non-estimation or less-estimation methods on the background, and the processing speed is greatly accelerated. For 720*576 standard-definition videos, the processing speed being 25 frames / second can be reached, the real-time processing requirements can be met, and the problem that the defogging method in the prior art cannot meet the traffic monitoring video real-time processing requirement due to high processing complexity is solved. The defogging processing method provided by the invention has the advantages that higher pertinence is realized, the real color of the foreground moving targets can be more effectively remained, the color distortion can be reduced, and good foundation is laid for the further intelligent processing of traffic videos.

Description

technical field [0001] The invention belongs to the field of image / video signal processing, and relates to a real-time defogging method for traffic monitoring video based on moving objects. Background technique [0002] Severe fog and haze will have a serious impact on the quality of traffic surveillance video, and defogging processing is of great significance to the follow-up intelligent analysis of traffic surveillance video. The key to defogging is to estimate the transmittance and atmospheric light intensity. As long as the sum and y are estimated, the haze-removed image can be obtained by observing the image. At present, the dehazing method based on dark channel prior knowledge is the mainstream method. [0003] The prior law of dark channels points out that in a local area of ​​most natural images, some pixels have at least one color channel with a very low value. According to the prior law of the dark channel color, the atmospheric light intensity and transmittance...

AI Technical Summary

Problems solved by technology

This method can process small-sized video in real time, but it can only basically meet the real-time processing requirements for 720×576 standard-definition video

[0008] In addition, the above two methods do not distinguish the content of the image when processing

This equivalent approach does not work well for traffic surveillance video

This is because in order to ensure the overall defogging effect of the image, it will often cause color distortion of moving targets in the monitoring scene, which will have a certain impact on the subsequent intelligent analysis

Images