基于图像融合的低光照水下图像增强

Low Illumination Underwater Image Enhancement Based on Image Fusion

水下机器人可用于水产养殖动态监测和水下拍摄,然而摄像机在水下抓拍的海洋图像呈现蓝绿色调、对比度低、细节模糊、亮度暗等问题,严重影响水下目标识别与检测的准确率。为此,本文提出了一种基于图像融合的低照度水下图像增强方法。首先,利用灰度世界算法对图像颜色进行校正,有效去除水下图像的蓝(绿)色基调;然后,对颜色校正后的图像分别进行锐化处理和HSV颜色空间下的亮度增强,分别得到细节增强图像和亮度增强图像;最后,将细节增强图像和亮度增强图像进行多尺度融合,得到最后的增强图像。实验结果表明,该算法不仅有效地解决了水下图像呈现蓝绿色的问题,而且增强了图像的整体亮度,使得细节更加清晰,提高了水下机器人的视觉感知能力。

Underwater robots can be used for dynamic monitoring of aquaculture and underwater photographing.However,the marine images captured by the camera underwater show blue-green tones,low contrast,fuzzy details,dark brightness and other problems,which seriously affect the accuracy of underwater target recognition and detection.In view of the above problems,this paper proposes a low illumination underwater image enhancement method based on image fusion.First,the gray world algorithm is used to correct the color of the image and effectively remove the blue(green)tone of the underwater image;Then,the image after color correction is sharpened and the brightness in HSV color space is enhanced respectively to obtain a detail enhanced image and a brightness enhanced image;Finally,the detail enhanced image and the brightness enhanced image are fused to obtain the final enhanced image.The experimental results show that the algorithm not only effectively solves the problem that the underwater image appears blue-green,but also enhances the overall brightness of the image,makes the details clearer,and improves the visual perception ability of the underwater robot.