中文摘要：

针对受环境影响造成红外图像热成像对比度不足的问题,应用多尺度Retinex增强算法,对低能见度的红外图像进行图像增强,并在此基础上提出了一种改进的基于S曲线多尺度Retinex红外图像增强算法,该S曲线函数具有定义域与值域区间一致、拐点非对称的特点。实验结果表明：利用改进后的算法,对红外图像进行图像增强,在目标图像增强的同时也抑制了背景噪声,提高了原图像的对比度与质量,获得了目标区域的最佳视觉效果。

英文摘要：

Due to the environmental impact caused the problem of infrared image which has low contrast,using multi-scale Retinex algorithm to enhance the low visibility of infrared image,and the paper proposes an improved image enhancement algorithm based on S curve Multi-Scale Retinex,the S curve function has the same domain and range,and the characteristics of asymmetric inflection point.The target is enhanced while the noise is suppressed by improved algorithm to enhance infrared image,meanwhile the original image contrast and quality are improved,and the best visual effect of target area is also achieved.The experiment results show that it can reach the goal of enhancing infrared image and getting better effect after using an improved infrared image enhancement algorithm based on S curves Multi-Scale Retinex.