云检测是一种提供必要的信息，如云层覆盖在许多应用中非常重要。的经典方法云检测是基于图像像素的红色和蓝色的比率的阈值。然而，很难选择合适的阈值对所有云的条件。另外，对于不同的全天空照相机所需的阈值是不同的。准确的云检测是一项具有挑战性的任务，因为云的颜色有时很容易地与天空或太阳的区域相混淆。 在这篇论文中，我们提出利用监督学习技术来进行云检测。云模型是通过培训过程中的经验教训。有许多分类器可以被用于此目的。我们认为，流行的分类，包括随机森林，分类回归树，和支持向量机。我们使用本地图像补丁，而不是只使用一个像素值的颜色信息。在一个本地图像补丁的像素的颜色值被设置为一个特征向量。该结果表明，该云检测使用本地图像补丁的颜色信息获得比使用一个像素值更好的精度。该结果还表明，支持向量机（SVM）具有最高的检测精度。采取由多个分类器提供的线索的优势，我们提出以投票方式相结合的多分类，以进一步提高检测精度。在实验中，我们已经表明，该方法能更准确区分云和非云像素。 ;Cloud detection is important for providing necessary information such as cloud cover in many applications. The classic method for cloud detection is based on thresholding of the red and blue ratio of an image pixel. However, it is difficult to select a suitable threshold for all cloud conditions. Also, the desired thresholds for different all-sky cameras are different. Accurate cloud detection is a challenging task since the colors of cloud sometimes easily be confused with sky or sun regions. In this thesis, we propose to perform cloud detection using supervised learning techniques. The cloud models are learned through the training process. There are many classifiers that can be used for this purpose. We consider popular classifiers including random forest, classification and regression tree, and support vector machine. We use the color information of a local image patch instead of using only one pixel value. The color values of the pixels in a local image patch are arranged as a feature vector. The results show that the cloud detection using the color information of a local image patch get better accuracy than using one pixel value. The results also show that the support vector machine (SVM) has the highest detection accuracy. To take advantage of the clues provided by multiple classifiers, we propose a voting process to combine multiple classifiers to further increase the detection accuracy. In the experiments, we have shown that the proposed method can distinguish cloud and non-cloud pixels more accurately.