阅读说明：本技术 一种Swin Unet低照度图像增强方法 (Swin Unet low-illumination image enhancement method ) 是由 孙帮勇 赵兴运 高晓梅 于 2021-08-27 设计创作，主要内容包括：本发明公开了一种SwinUnet低照度图像增强方法,步骤包括：1)构建预处理模块,该预处理模块的输入为原始低照度图像,输出是特征图I1；2)构建SwinUnet模块,该SwinUnet模块的输入数据是步骤1输出的特征图I1,输出是提取后的特征图I2；3)构建恢复模块,该恢复模块的输入数据是步骤2输出的特征图I2,输出是增强后高质量无噪声的输出图像。本发明的方法,能够有效的将低照度图像恢复到正常光照条件下获取的图像,并保持图像的纹理细节以及颜色信息等。(The invention discloses a SwinUnnet low-illumination image enhancement method, which comprises the following steps: 1) constructing a preprocessing module, wherein the input of the preprocessing module is an original low-illumination image, and the output of the preprocessing module is a feature map I1; 2) constructing a Swinunet module, wherein input data of the Swinunet module is the feature map I1 output in the step 1, and output is the extracted feature map I2; 3) and constructing a recovery module, wherein input data of the recovery module is the feature map I2 output in the step 2, and output is a high-quality noise-free output image after enhancement. The method can effectively restore the low-illumination image to the image acquired under the normal illumination condition, and maintain the texture details, the color information and the like of the image.)