Infrared weak small target detection method based on spectral residual and fuzzy clustering

Abstract

The present invention discloses an infrared weak small target detection method based on spectral residual and fuzzy clustering. The method comprises: inputting an original infrared image and performing normalization of the infrared image; performing filtering of the infrared image after normalization; obtaining the significance graph of the infrared image through a spectral residual method; performing clustering segmentation of the infrared image through adoption of local intuitionist fuzzy c mean clustering; adding a significance image and the image after clustering, and obtaining an image after fitting; subtracting the original infrared image from the fitting image to obtain a target significance graph; and searching a point with the maximum gray value in the graph, wherein the point is the position where the infrared weak small target is located. The infrared weak small target detection method based on the spectral residual and fuzzy clustering can perform effective combination of time domain information and frequency domain information of the infrared image, avoid the setting of a threshold through image fitting and improve the precision of image detection.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a weak and small target detection method based on spectral residual and fuzzy clustering in the field of infrared image processing under complex backgrounds. The invention can be used to detect weak and small targets in infrared images, and can effectively improve the detection accuracy of small targets in infrared images. Background technique [0002] With the continuous enhancement of national defense scientific research strength, in the field of national defense such as infrared guidance, space machine early warning and target monitoring, the detection technology of weak and small targets in infrared images has always been a focus of attention and research by scholars at home and abroad. However, due to the long imaging distance of infrared images, the large background noise, the complex imaging environment, and the uncertain trajectory of the target, this...

AI Technical Summary

Problems solved by technology

Although this patented technology solves the technical problem of poor adaptability of the existing saliency model-based target segmentation method for visible light images, it has a better detection effect on weak and small targets in infrared images; The feature information of the image depends on the time domain. When the processed infrared image background is relatively complex, the extracted feature information is not sufficient, which will make the processing result poor.

Images