In recent years, remote sensing imaging technology has developed rapidly. A growing number of high resolution remote sensing images become available, which largely facilitates the research and applications of remote sensing images. Landcover classification is one of the most important tasks of remote sensing image applications <sup></sup>. However, traditional classification methods rely on manual feature design, which is time-consuming and requires expertise. It is difficult to apply to massive data. Compared with the traditional classification methods, deep learning <sup></sup> can automatically acquire the most intrinsic and discriminative features of the image. Based on the deep learning image classification, this paper designs a high-level semantic information extraction system with high efficiency and robustness. A deep fully convolutional networks (FCN) is designed to extract the features from remote sensing images and to predict the landcover classes of each image, which include building, tree, road, and grass. On the basis of the classification results, we use binarization to highlight the building objects. Then the noise of the binarized image is removed by Gaussian filtering and morphological image processing. After that we set a threshold to delete small misdiagnosis areas. At last the connected domain algorithm is applied to detect the buildings and calculate the building number in each image. The forest coverage is then obtained by computing the proportion of the pixels with ‘tree’ class label to the total number of the pixels in each image. Different from the traditional image interpretation method, this systematic high-level semantic information extraction framework not only detects the number of buildings in the scene but also extracts forest coverage. Moreover, more high-level information extraction can be easily supplemented to this framework, such as road localization or interested object detection.
The position and attitude measurement of space object is a key problem in the field of real-time navigation, modern control and motion tracking. As a non-contact position and attitude estimation method, machine vision position and attitude estimation has the advantages of simple structure and convenient measurement. This paper presents a vision positioning system and method based on multiple reference markers. The camera moving along the object continuously collects images containing reference markers from the camera's field of view．The spatial position information of reference mark is determined in advance, and the position and direction of moving target are calculated according to location and attitude algorithm. The main contribution of this paper: first, a plurality of reference markers is arranged in the range of moving objects so as to enlarge the range of visual positioning; second, when more than one reference marker appears in the field of view, it is possible to improve the positioning accuracy by selecting the marker of the larger contour area or the marker of the distance closer to the imaging plane principal point; third, we use the decoder to transform the reference marker into digital number. This method can improve the robustness of the system.