A target saliency detection method for rainy day images

Abstract

The invention provides a target saliency detection method for rainy day images. The method comprises the following steps: S1, extracting visual saliency based on luminance and color features, calculating luminance saliency map Slc; S2, extracting visual saliency based on color difference features, and calculating color difference saliency map Scv; S3, extracting the visual saliency based on the dark channel, and calculating the saliency map Sd of the dark channel; S4, mixing the brightness saliency map Slc, the color difference saliency map Scv and the dark channel saliency map Sd to obtain the final saliency map Sfinal, Sfinal=Slc. * Scv-Sd. In the invention, the brightness and color characteristics, the color difference characteristics and the dark channel characteristics of the target in the rainy day image are utilized to extract the saliency characteristics of the target in the rainy day image and construct a target saliency detection model, thereby providing an effective preprocessing method for the image sharpening and the detection of the target in the rainy day.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a target saliency detection method for images in rainy days. Background technique [0002] The visual saliency model has a wide range of applications, and the more mature ones include target detection and segmentation, video analysis, etc. The quality of the saliency detection results plays a crucial role in these applications. Specifically, it can be generally divided into three types: (1) methods based on biological research (2) methods calculated through pure mathematical modeling (3) methods that combine the first two methods. And these methods are bottom-up research. Most of the method research still focuses on the detection and segmentation of salient objects, and is still based on the classic model framework, but the innovation of these methods is based on the improvement of modeling or the difference in feature selection. The existing models mainly have the fol...

AI Technical Summary

Problems solved by technology

The existing models mainly have the following deficiencies: (1) cannot deeply analyze and study the characteristics of salient objects (2) cannot deeply understand the mechanism of biological visual cognition (3) many models cannot be directly applied or applied with Conditional limitations

At present, many mature and practical methods have been proposed for the saliency detection of targets, and the visual attention model has also been studied in depth. Research needs to go further

In addition, there is no quantitative and effective standard for the classification of rain at present. How to form an image database containing different levels of rain for saliency detection is a difficult problem

Images