SAR image man-made target detection method based on visual contrast and information entropy
A target detection and information entropy technology, applied in the field of remote sensing image processing, can solve the problems of unsatisfactory detection results, inconvenient engineering implementation, and low processing efficiency, and achieve good universality, easy engineering implementation, and high processing efficiency Effect
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Publication Date
- 2016-03-16
- Estimated Expiration
- Not applicable · inactive patent
Smart Images
Figure 1 Figure 2 Figure 3
Abstract
Description
technical field
[0001] The invention relates to a synthetic aperture radar (Synthetic Aperture Radar, SAR) image artificial target rapid detection method based on visual contrast and information entropy, which belongs to the technical field of remote sensing image processing. Background technique
[0002] Object detection is an important research topic in the field of SAR image interpretation. Since SAR technology has reached the practical level, the research on SAR image object detection has been widely concerned. Man-made targets such as buildings, bridges, vehicles, and ships are the key monitoring objects in SAR earth observation. The detection and identification of such targets are of great significance in both military and civilian use, and have been widely used in military reconnaissance and urban planning. , disaster monitoring, resource survey and other fields.
[0003] The existing SAR image target detection algorithms mainly include: target detection algorithms b...
Examples
Embodiment Construction
[0026] The present invention will be further described below in conjunction with the accompanying drawings. The following examples are only used to illustrate the technical solution of the present invention more clearly, but not to limit the protection scope of the present invention.
[0027] refer to figure 1 , the specific implementation steps of the present invention are as follows.
[0028] Step 1): Create a Gaussian pyramid image:
[0029]Pyramid is one of the multi-scale image representation methods. The bottom of it is the most original image with the highest resolution. Every time it moves up one layer, the scale of the image is reduced by half, and the resolution is also reduced. According to the image characteristics of different sampling layers of the Gaussian pyramid, and on the basis of multiple experiments, the present invention establishes a 4-layer image pyramid to perform down-sampling operations on the SAR image. Let δ be the number of layers of the pyram...