Method for detecting infrared target by using local difference of structure similarity
A technology of structural similarity and local structure, applied in the field of infrared target detection, which can solve the problems of large random noise and non-uniform interference in infrared images.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0036] The effectiveness of this target detection algorithm is directly tested using several infrared target images.
[0037] Use the method of the present invention to process detection targets, such as figure 1 As shown, the input infrared image containing the target f , the final target detection result can be obtained. by Figure 4a (defined as target image f ) as an example:
[0038] (1) For the target image f Any pixel in f (i, j), calculate the difference value of the structural similarity between it and the surrounding area D (i, j), after calculating pixel by pixel, get the same as f Structural similarity difference map of the same size D .
[0039] (a) For the entire image f , in order to obtain the same f Figures of the same size (A, B) D , need to first f Periodic continuation is performed to meet the calculation requirements of boundary pixels.
[0040] Such as figure 2 As shown, the central image is subjected to cycle boundary method to obtain the...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 