Infrared weak small target detection method based on background suppression and multi-scale local entropy

Abstract

The invention provides an infrared weak small target detection method based on background suppression and multi-scale local entropy. Firstly, the infrared image is normalized. Secondly, the infrared image is filtered by steering filter, and the background suppressed image is obtained after the difference. Then, by calculating the multi-scale local entropy weight map, the maximum of the local entropy salience map of different scales is obtained for the same pixel position, and the final local entropy weight map is obtained. Then, the background suppressed image is multiplied with the local entropy saliency map to obtain the saliency map of the infrared small target. Finally, the salient image is filtered by Susan filter, and the isolated bright spots are removed. The non-zero region of theprocessed image is the small target region. The invention can be used for detecting weak and small targets in infrared images, and can effectively improve the detection accuracy of small targets in infrared images.

Description

technical field [0001] The invention belongs to the technical field of image processing, and further relates to an infrared weak and small target detection method based on background suppression and multi-scale local entropy in the field of infrared image processing under complex backgrounds. Background technique [0002] Infrared small target detection has been widely used in many fields, such as infrared target tracking, precision guidance and long-range early warning, etc. Due to the complexity of the imaging environment and the characteristics of infrared images, infrared small targets are generally small in size, weak in signal, and complex in background, making their detection and tracking very difficult. Therefore, the detection of small infrared targets has always been a hot and difficult point in the field of infrared image processing. [0003] In recent years, the research on the human visual attention mechanism has been widely used in the detection of small infra...

AI Technical Summary

Problems solved by technology

The algorithm compares the central area with the surrounding 8 neighborhoods to obtain a local comparison map, and then performs target detection, but it is easily affected by noise and has a high false alarm rate

On the basis of the LCM algorithm, Han et al. proposed an improved LCM (ILCM) algorithm. The algorithm first processes the image into sub-pixel blocks, and then replaces the maximum value in the LCM algorithm with the mean value, which reduces the false alarm rate, but still susceptible to noise

Images