Road networks are very important features in geospatial databases. Even though high-resolution optical satellite images have already been acquired for more than a decade, tools for automated extraction of road networks from these images are still rare. One consequence of this is the need for manual interaction which, in turn, is time and cost intensive. In this paper, a multi-stage approach is proposed which integrates structural, spectral, textural, as well as contextual information of objects to extract road networks from very high resolution satellite images. Highlights of the approach are a novel linearity index employed for the discrimination of elongated road segments from other objects and customized tensor voting which is utilized to fill missing parts of the network. Experiments are carried out with different datasets. Comparison of the achieved results with the results of seven state-of-the-art methods demonstrated the efficiency of the proposed approach.
17 May 2010 in International Journal of Remote Sensing
Flooding is a natural hazard that takes millions of lives each year. Remote sensing and geographic information systems (GIS), two fields of surveying engineering, can play an important role in flood management by generating floodplain maps. This paper proposes a model to generate a floodplain map for a flood event. A digital elevation model (DEM) is used to compute a flood-depth map for a given flood event. The flood-depth map is overlaid over the classified high-resolution image (IKONOS) to determine the inundated classes after flooding. This model is applied on a part of the river that is located in the northwest of Iran in Khoram-Abad city. Applying this model on this study area shows that the accuracy classification is improved by about 15% using a multi-layer perceptron neural network. This improvement could play an important role in flood risk assessment. A nonlinear regression model is also used for modelling the flood-water line.
10 July 2015 in Journal of the Indian Society of Remote Sensing
With the advent of the new generation of microwave and optical sensors with unique characteristics, the multi-sensor fusion for the soil moisture retrieval has given rise to a considerable research interest. The Sentinel satellites enable operational soil moisture mapping with moderate accuracy while providing regular temporal coverage and high spatial resolution at no cost to the users. In the meantime, working at the object level enables us to take advantage of some of the unique capabilities of this approach. This letter outlines an object-based approach for the multi-scale soil moisture retrieval by coupling the single polarization C-band synthetic aperture radar (SAR) and optical data. To fulfil this goal, a broad range of optical and texture features was extracted from the optical and single polarization mode SAR data. Subsequently, the relevant features were properly selected using the Random Forest-Recursive Feature Elimination (RF-RFE) algorithm. Then, the selected features were imported to the segmentation process to create the image objects. Afterwards, the support vector regression (SVR) technique was used to estimate the soil moisture value of the image objects and to conduct the multi-scale soil moisture retrieval with a small training database. It is observed that the proposed approach can provide multi-scale soil moisture maps with a reasonable accuracy in different applications requiring different scale requirements.
SAR (Synthetic Aperture Radar) raw data simulation has a significant role in the evaluation of newly-proposed methods for the estimation of moving target parameters. The evaluation of methods in different cases emphasizes the importance of the need to have fast simulators. Using reverse SAR imaging methods for the raw data simulations has achieved good results in the simulation of the static targets, but for the simulation of moving targets these methods have a few shortcomings. In this paper, we propose a method to simulate a speckled scene with moving targets in the hybrid domain. First, the scene is simulated, including speckle, which is statistically in accordance with real SAR image behavior. Then, a reverse imaging algorithm (inverse chirp scaling) was applied on the scene to generate the SAR raw data. The moving target simulation was also done in the time-domain as the next step. Finally, the results from two prior steps were superposed to generate the SAR raw data with moving targets. All steps of the proposed method were evaluated separately. The speckle procedure was evaluated by comparing the speckled SAR image before the simulation and the image of the SAR simulated raw data. The results show similar variations in real and imaginary parts of these data. The correlation between the reflectivity map and the SAR images after the simulation was calculated and the obtained correlation coefficient was about 0.95 for different images. The final data were further analyzed for the displacement of moving targets’ positions. The results show similar displacement between moving target SAR raw data with a background and without a background.