Wavelet domain fractal infrared volume cloud detection method fusing edge information

Abstract

The invention discloses a wavelet domain fractal infrared volume cloud detection method fusing edge information, belongs to the field of remote sensing image processing, and solves the problem that the false alarm rate is too high when a target is detected in the prior art. The method comprises the following steps: inputting and preprocessing a to-be-processed cirrus cloud image to obtain a preprocessed image; extracting a SUSAN edge feature map from the preprocessed image by using a minimum kernel value similarity region method; performing wavelet transformation on the preprocessed image to obtain a low-frequency coefficient approximation graph; obtaining a fractal dimension feature map and a multi-scale fractal area feature map of the low-frequency coefficient approximation map by usinga step-by-step triangular prism method and a carpet covering method; and calculating the consistency measure of each pixel point in the SUSAN edge feature map, the fractal dimension feature map and the multi-scale fractal area feature map as a fusion weight, carrying out pixel-level fusion on the three feature maps based on the fusion weight, obtaining a feature fusion map, and then processing thefeature fusion map to obtain a final detection result. The method is used for infrared cirrus cloud detection.

Description

technical field [0001] The invention discloses a wavelet domain fractal infrared cirrus detection method with edge information fusion, which is used for infrared cirrus detection and belongs to the field of remote sensing image processing. Background technique [0002] Space infrared satellite is an important part of the earth observation and remote sensing system, and plays an important role in military aspects such as infrared early warning and missile interception. Due to infrared imaging conditions, noise or interference will inevitably appear in infrared images. Among them, the false alarm source is similar to the target in the satellite infrared image, and both have high gray levels, so it may cause false alarms in the remote sensing early warning system. [0003] A large number of studies have shown that most of the false alarm sources come from natural scenery, such as high-altitude cirrus clouds, curved rivers, and frozen lakes. Natural scenes usually have complex...

AI Technical Summary

Problems solved by technology

[0005]Aiming at the problems of the above-mentioned research, the purpose of the present invention is to provide a wavelet domain fractal infrared cirrus detection method of fusing edge information, which solves the problem of target detection in the prior art. During detection, the false alarm rate is too high

Images