Foggy day image salient target detection method

Abstract

The invention discloses a foggy day image salient target detection method, which comprises the following steps of: step 1, performing color space conversion on a foggy day image in a frequency domainto calculate the saliency of the foggy day image, and solving a frequency domain saliency map; step 2, performing super-pixel segmentation on the foggy day image in a spatial domain, calculating the significance of each super-pixel block, and solving a spatial domain saliency map; step 3, fusing the saliency map of the image in the frequency domain and the saliency map of the image in the space domain into a saliency map through discrete stationary wavelet transform; step 4, obtaining a contour map of the foggy day image through the target contour detection model; and step 5, adding the saliency map fused based on the frequency domain and the spatial domain to the contour map to obtain a final saliency map. According to the method, a traditional machine method and a deep learning method are combined, the robustness of traditional significant target detection is improved, and a significant target in a foggy day scene can be efficiently and accurately detected; meanwhile, for some imageswith complex backgrounds, a significance target can be well extracted.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a method for detecting a prominent target in a foggy image. Background technique [0002] Due to the dust suspended in the air, it has a great impact on the visibility of the target in the foggy environment. Therefore, the contrast of foggy images is generally low, the colors are indifferent, and the main objects are difficult to identify. Salient object detection is conducive to the completion of this task. It is a cognitive process that simulates the attention mechanism of the human visual system (HVS). for further processing. In recent years, the application of visually salient object detection in image processing has received increasing attention. Salient object detection in foggy images plays a key role in the field of pedestrian tracking, object recognition, object segmentation, remote sensing, intelligent vehicles, surveillance, etc. Various defogging techniqu...

AI Technical Summary

Problems solved by technology

However, the main disadvantages of these algorithms are: (1) high complexity and long execution time, it is difficult to guarantee the real-time performance of salient object detection; To a certain extent, it interferes with the recognition of prominent targets; (3) Image color distortion makes it impossible to accurately extract visual features such as edges and contours of targets

However, due to the characteristics of low resolution and low contrast of fog images, traditional saliency models based on spatial domain or frequency domain perform poorly in foggy environments.

Images