为解决浓雾天气条件下近岸海域监控系统获取的图像清晰度低的问题，提出一种基于改进亮通道及引导滤波的海域图像去雾算法。首先，将Lab颜色空间L通道作为引导图，通过对原图像进行快速引导滤波来估计大气光值；其次，基于大气光值并利用亮通道先验理论，获得亮通道透射率函数；最后，通过改进的加权引导滤波优化亮通道透射率函数，利用大气散射模型，实现模糊图像的去雾，并利用伽马校正增强去雾结果。实验结果表明，改进方法图像去雾结果视觉效果明显，可以有效减少细节信息损失，提高图像清晰度 。与经典算法最优结果对比，NIQE、对比度及信息熵分别提升为10.92%、4.12%和4.37%，对完善近岸海域监控系统具有一定的理论价值和现实意义。

Aiming at the problem of low clarity of images obtained by the coastal sea area monitoring system under dense fog conditions, a sea area image defogging algorithm based on improved bright channel and guided filtering is proposed. First, the L channel of the Lab color space is used as a guide map to estimate the atmospheric light value through fast guided filtering of the original image. Then, the bright channel transmittance function can be obtained by using the bright channel prior theory based on the atmospheric light. Finally, an improved weighted guided filter is introduced to optimize the transmittance function of the bright channel，thus obtaining the final transmittance function, which is brought into the atmospheric scattering model to achieve image defogging，and gamma correction was performed on the results of defogging. The experimental results show that the visual effect of image defogging results are obvious, which can effectively reduce the loss of detail information and improve the clarity of the image. Compared with the optimal results of the classical algorithm, NIQE, contrast and information entropy are increased to 10.92 %, 4.12 % and 4.37 %. It has certain theoretical value and practical significance for perfecting the coastal waters monitoring system.