Infrared image enhancement method and device, computer equipment and storage medium

Abstract

The invention relates to an infrared image enhancement method and device, computer equipment and a storage medium. The method comprises the steps of obtaining an original infrared image; Segmenting the original infrared image to obtain a basic layer image and a detail layer image; Respectively carrying out image enhancement on the basic layer image and the detail layer image; And fusing the enhanced base layer image and the detail layer image to obtain a detail enhanced image. According to the infrared image enhancement method, the details of the infrared image are obviously enhanced, the detail information of the infrared image is prevented from being lost, and the infrared image enhancement method can adapt to infrared images of most scenes.

Description

technical field [0001] The present application relates to the technical field of image processing, in particular to an infrared image enhancement method, device, computer equipment and storage medium. Background technique [0002] In nature, electromagnetic waves with a wavelength between 2.0-1000 μm are called thermal infrared rays (also called thermal radiation). As long as the temperature of an object is above thermodynamic zero (-273°C), it can emit infrared light. Since the human eye cannot recognize infrared light, a special device must be used to visualize the infrared signal, that is, an infrared imaging system. A typical infrared imaging system consists of an optical system, an infrared detector, and an electronic processing system. The main function of the optical system is to image the thermal radiation of the target object on the photosensitive surface of the infrared detector. The detector converts the infrared light signal into a digital signal, and finally co...

AI Technical Summary

Problems solved by technology

The histogram equalization method improves the contrast of the image by stretching the gray area of ​​the histogram, but the enhancement effect is not obvious for different images, and the difference is large; the gray scale transformation method grays out the pixels of the original image one by one according to the mapping function. Degree value transformation, but different mapping functions are required for different scenes; the filter removes image noise by filtering the original image, but if the filter template is not selected properly, a large amount of detailed information will be lost; the weighted histogram equalization method compresses the The pixels in the small and large areas distinguish most of the background information to improve image contrast, but the application scenarios are limited, and some details will be lost while distinguishing the background

Therefore, the enhancement effect of the traditional infrared image enhancement method is not obvious, and the detailed information of the infrared image will be lost.

Images