Fast and automatic detection of airports from remote sensing images is useful for many military and civilian applications. In this paper, a fast automatic detection method is proposed to detect airports from remote sensing images based on convolutional neural networks using the Faster R-CNN algorithm. This method first applies a convolutional neural network to generate candidate airport regions. Based on the features extracted from these proposals, it then uses another convolutional neural network to perform airport detection. By taking the typical elongated linear geometric shape of airports into consideration, some specific improvements to the method are proposed. These approaches successfully improve the quality of positive samples and achieve a better accuracy in the final detection results. Experimental results on an airport dataset, Landsat 8 images, and a Gaofen-1 satellite scene demonstrate the effectiveness and efficiency of the proposed method.

The amount and intensity of runoff on catchment scale are strongly determinedby the presence of impervious land-cover types, which are the predominant cover types inurbanized areas. This paper examines the impact of different methods for estimatingimpervious surface cover on the prediction of peak discharges, as determined by a fullydistributed rainfall-runoff model (WetSpa), for the upper part of the Woluwe Rivercatchment in the southeastern part of Brussels. The study shows that detailed informationon the spatial distribution of impervious surfaces, as obtained from remotely sensed data,produces substantially different estimates of peak discharges than traditional approachesbased on expert judgment of average imperviousness for different types of urban land use.The study also demonstrates that sub-pixel estimation of imperviousness may be a usefulalternative for more expensive high-resolution mapping for rainfall-runoff modelling atcatchment scale.