Remote sensing optical image cloud detection is one of the most important problems in remote sensing data processing. Aiming at the information loss caused by cloud cover, a cloud detection method based on convolution neural network (CNN) is presented in this paper. Firstly, a deep CNN network is used to extract the multi-level feature generation model of cloud from the training samples. Secondly, the adaptive simple linear iterative clustering (ASLIC) method is used to divide the detected images into superpixels. Finally, the probability of each superpixel belonging to the cloud region is predicted by the trained network model, thereby generating a cloud probability map. The typical region of GF-1/2 and ZY-3 were selected to carry out the cloud detection test, and compared with the traditional SLIC method. The experiment results show that the average accuracy of cloud detection is increased by more than 5 %, and it can detected thin-thick cloud and the whole cloud boundary well on different imaging platforms.

In order to analyze the making arc characteristics of AgSnO₂ contact, experiments were carried out with a self-developed experimental equipment. It was found that contact resistance had no obvious change with the increase of the number of experiments.In the later stage of the experiment, the contact bounces occurred during the contact closing process, which not only prolonged the making arc duration, but also increased making arc energy. When the contact was eroded to a certain extent by arc, making welding occurs.