Iterative optimization distance categorization-based space weak and small target detection method

Abstract

The invention discloses an iterative optimization distance categorization-based space weak and small target detection method, which is used for solving the technical problem that the existing space weak motion target detection method is low in detection efficiency. The technical scheme of the method comprises the steps: extracting a plurality of candidate targets by a method based on the iterative optimization distance categorization; constructing an error square and a criterion function; categorizing all star points into fixed stars and non-fixed stars; iteratively computing a class mean andan error square function to obtain an optimization distance categorization threshold value; and filtering out the great mass of fixed star backgrounds and noise points, so that the complexity of the successor operation is reduced. A correlation method of a target track is used in the process of filtering the candidate targets, so that the computing complexity of the algorithm is reduced, and the detection efficiency of the space weak motion target is improved.

Description

technical field

[0001] The invention relates to a space target detection method, in particular to a space weak and small target detection method based on iterative optimization distance classification. Background technique

[0002] The document "Weak and small target detection based on multi-level classification and reverse spatio-temporal fusion, Systems Engineering and Electronic Technology, 2009, Vol31(8), p1864-1869" discloses a weak and small target detection method based on multi-level classification and reverse spatio-temporal fusion. On the basis of image background suppression, the method uses adaptive multi-level classification method to extract candidate targets, which strengthens the detection ability of various weak and small candidate targets. At the same time, a dynamic space-time pipeline is constructed according to the position change information of the target between adjacent frames. When the authenticity of the candidate target points in the current frame ...

Examples

Embodiment Construction

[0033] 1. Background suppression and segmentation.

[0034] Use the median filter to calculate the mean value of all pixels in the 3×3 neighborhood centered on the current pixel point (x, y), and use the mean value as the new pixel value of the current pixel to remove random noise. Count the gray mean μ and variance σ of the entire image 2 , using μ+λ·σ as the threshold for binary segmentation, the segmented point is the star point, where λ is the set segmentation coefficient, the value in the present invention is 1.604, the mean value μ and the variance σ 2 for:

[0035] μ = 1 m · n Σ x = 1 m Σ y = 1 n I ( x , y ) - - - ...

technical field

[0001] The invention relates to a space target detection method, in particular to a space weak and small target detection method based on iterative optimization distance classification. Background technique

[0002] The document "Weak and small target detection based on multi-level classification and reverse spatio-temporal fusion, Systems Engineering and Electronic Technology, 2009, Vol31(8), p1864-1869" discloses a weak and small target detection method based on multi-level classification and reverse spatio-temporal fusion. On the basis of image background suppression, the method uses adaptive multi-level classification method to extract candidate targets, which strengthens the detection ability of various weak and small candidate targets. At the same time, a dynamic space-time pipeline is constructed according to the position change information of the target between adjacent frames. When the authenticity of the candidate target points in the current frame ...

Examples

Embodiment Construction

[0033] 1. Background suppression and segmentation.

[0034] Use the median filter to calculate the mean value of all pixels in the 3×3 neighborhood centered on the current pixel point (x, y), and use the mean value as the new pixel value of the current pixel to remove random noise. Count the gray mean μ and variance σ of the entire image 2 , using μ+λ·σ as the threshold for binary segmentation, the segmented point is the star point, where λ is the set segmentation coefficient, the value in the present invention is 1.604, the mean value μ and the variance σ 2 for:

[0035] μ = 1 m · n Σ x = 1 m Σ y = 1 n I ( x , y ) - - - ...

Images