论文部分内容阅读
针对彩色遥感图像中薄云带来的降质问题,提出了一种基于低秩矩阵分解的去云方法。将彩色遥感图像分成三个单通道图像,对每一个通道进行低秩矩阵分解,得到单通道薄云信息;根据薄云在三个通道中均匀分布的特点,选取合适的阈值对薄云信息进行自动判定,提取代表三个通道的薄云图像;用三个通道的图像分别减去对应通道的薄云图像,并融合三个通道的结果得到去云后的彩色遥感图像。实验结果表明,该方法不仅能够保留无云区域信息的完整性,而且对有云区域的处理在主观视觉效果和客观评价指标上都具有较好的效果。
Aiming at the problem of quality degradation caused by the thin cloud in color remote sensing images, a cloud removing method based on low-rank matrix decomposition is proposed. The color remote sensing image is divided into three single-channel images, and the low-rank matrix is decomposed for each channel to obtain single-channel thin cloud information. According to the characteristics that the thin cloud is uniformly distributed in the three channels, the appropriate threshold is selected for the thin cloud information Automatically decides and extracts the thin cloud images representing the three channels; subtracts the thin cloud images corresponding to the channels respectively from the images in the three channels and combines the results of the three channels to obtain the color remote sensing images after going to the cloud. The experimental results show that this method can not only preserve the integrity of cloudless information, but also have good effect on the subjective visual effect and objective evaluation index.