Aircraft detection is a difficult task in the field of high remote sensing image application. In this paper we present an automatic system for aircraft detection based on locating the candidates of aircrafts and Support Vector Machine (SVM) to detect aircraft from high resolution remote sensing images. The system contains two main modules: in module one, we use segmentation based on statistical region merging and line segment to quickly locate the candidates of aircrafts; in module two, the precise detection process is accomplished by training the SVM classifier with combining the features of segmentation and line segment. Experimental results indicate that the system is effective in handling the remote sensing images. Therefore, it is a good choice for aircraft detection in high remote sensing images.

This paper proposes to employ graph Laplacian penalization in multi-image super-resolution reconstruction. Most state-of-the-art methods use an optimization model with two items: the data fidelity item and the penalization item. However, these methods often ignore the impact of the penalization item and utilize simple formulations such as high-pass filters to fulfill the super-resolution task. As a result, they can not restore much local structural information of the high resolution image. By using graph Laplacian, the proposed method in this paper can retain more local manifold structures in the high resolution images. Based on this idea, the optimization model is constructed and the solution is presented. Comparative experiments have validated our method. The experiments have also tested our method has much faster convergence speed.

Road information can be used for several applications, such as essential modes of transportation and updating geographic information systems (GIS) from VHR remote sensing images. In recent years, with the development of multi-sensor and multi-resolution remote sensing techniques, we have acquired a large quantity of high-resolution satellite images. Accurate road extraction from VHR sensing image has drawn considerable attention and a great deal of effort has been devoted to this topic.

Cloud detection, recognition has been received increasing attention during last decades in remote sensing application field. We propose a novel cloud detection algorithm based on statistical region merging segmentation with statistical and geometry features. To distinguish clouds objects from a background, the statistical region merging segmentation algorithm is firstly adopted to obtain semantic segmentation regions. Based on information of segmented patches, statistical features, including spectrum and geometry features are extracted to represent otherness between clouds and underlying surface. Such features are finally implied to math the feature temple by the nearest neighbor algorithm. We show in this paper the addressed method make a effective cloud detection without any prior constraints and auxiliary data. Experiments have been carried out on aerial optical images to validate our proposed method.