Infrared weak and small target detection method based on fractional entropy
A technology of weak and small targets and detection methods, which is applied in the directions of instruments, calculations, character and pattern recognition, etc., can solve the problems of low detection accuracy, achieve accurate detection results, be easy to implement, and avoid the loss of target and label details.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0105] A 6x6 sliding window is established on the original infrared image where the pixel to be detected is 320x240, and a 315x235 standby entropy image is obtained according to the 6x6 sliding window, the sliding step of the given sliding window is 1x1 and the original infrared image, wherein, Raw infrared images such as figure 2 As shown, the edges are blurred;
[0106] Based on the sliding step of the sliding window, slide the window on the original infrared image from left to right and from top to bottom, and get a ROI area each time, calculate the fractional entropy of the ROI area and assign it to the backup entropy value Pixels corresponding to the image to obtain the fractional entropy image;
[0107] The sliding window slides the original infrared image, and maps the pixel values in the fractional entropy image to the space [0, 255] to obtain the mapped entropy image, such as image 3 shown;
[0108] Perform morphological filtering on the entropy image, first co...
Embodiment 2
[0112]A 6x6 sliding window is established on the acquired original infrared image with pixels to be detected as 256×172, and a backup entropy value of 251×167 is obtained according to the 6x6 sliding window, the sliding step of the given sliding window is 1x1 and the original infrared image image, among them, the original infrared image such as Figure 6 As shown, the background noise is very large;
[0113] Based on the sliding step of the sliding window, slide the window on the original infrared image from left to right and from top to bottom, and get a ROI area each time, calculate the fractional entropy of the ROI area and assign it to the backup entropy value Pixels corresponding to the image to obtain the fractional entropy image;
[0114] The sliding window slides the original infrared image, and maps the pixel values in the fractional entropy image to the space [0, 255] to obtain the mapped entropy image, such as Figure 7 shown;
[0115] Perform morphological fil...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


