This paper proposes an improved Retinex theory based on a weighted guided filter method to enhance images in low-light conditions. The captured images under low illumination can cause dimness, distortion or details loss. We use the weighted guided filter method to perform illumination estimation and the original image is regarded as the guidance image, which can avoid color distortion and over-enhancement. It can adjust the regularization parameter adaptively based on the image content. Perceptual contrast is improved by using an illumination enhancement method with dynamic adjustment. To test the validness of our algorithm, the weighted guided filter method proposed in this paper is compared with bilateral filter and the guided filter method. Finally, experiment under low illumination is implemented on a NAO robot by using the proposed weighted guided filter method based on EKF-SLAM. The experiment result demonstrates that the proposed weighted guided filter method is feasible and effective in low-light environment.

中文翻译：

---

使用Retinex算法的自主机器人导航在弱光环境下的多尺度图像适应性

本文提出了一种基于加权导引滤波方法的改进的Retinex理论，以增强弱光条件下的图像。在低照度下拍摄的图像可能会导致暗淡，失真或细节丢失。我们使用加权导引滤波法进行照度估计，将原始图像视为指导图像，可以避免色彩失真和过度增强。它可以根据图像内容自适应地调整正则化参数。通过使用动态调整的照明增强方法，可以改善感知对比度。为了验证算法的有效性，将本文提出的加权导引滤波方法与双边滤波和导引滤波方法进行了比较。最后，利用提出的基于EKF-SLAM的加权导引滤波方法，在NAO机器人上进行了低照度的实验。实验结果表明，该方法在弱光环境下是可行和有效的。