Parham Pahlavani; Mahdi Hasanlou
Abstract
Abstract
Nowadays, the combination of data and images obtained from different remote sensing sources is considered as an optimal solution for extracting more information, since these data, with their own wide vision, digital format, their periodically preparation, and high temporal resolution provide ...
Read More
Abstract
Nowadays, the combination of data and images obtained from different remote sensing sources is considered as an optimal solution for extracting more information, since these data, with their own wide vision, digital format, their periodically preparation, and high temporal resolution provide researchers with a variety of information about the land surface. In this regard, the passive optical sensors are widely used in mapping horizontal structures. Given that, radar data can often be collected 24-hours a day and Independent of atmospheric conditions, and also some ground structures and artificial targets have a specific response in the radar frequency, they complete the capabilities of optical images. LiDAR airborne data can also provide sample measurements from vertical structures with very high accuracy. As a result, the simultaneous use of optical, radar and LiDAR data can provide more information in a variety of applications. In this research, by simultaneously applying these three categories of data, we tried to identify the urban specific features in an optimal way. In this regard, by utilizing and producing various descriptors (57 descriptors), and using the feature extraction methods (including PCA and ICA) and estimating the intrinsic dimensions of the data (including SML and NWHFC), an optimal space for the supervised classification was created. After classifying (K-NN method) using the obtained results, descriptors (information layers) produced to identify specific urban features including buildings, roads and vegetation were obtained and grouped according to the classification accuracy. The numerical results indicate the high efficiency of the proposed procedure as well as the applied methods of estimating intrinsic dimension and extracting the features.
Alirerza Sofianian; Samereh Falahatkar
Volume 17, Issue 68 , February 2008, , Pages 13-18
Abstract
Remote sensing and GIS are widely used in identifying and analyzing land use change. Satellite remote sensing provides multi-time and multi-spectral data that can be used to quantify the type and amount and position of land use change. Furthermore, the GIS also provides a flexible environment for displaying, ...
Read More
Remote sensing and GIS are widely used in identifying and analyzing land use change. Satellite remote sensing provides multi-time and multi-spectral data that can be used to quantify the type and amount and position of land use change. Furthermore, the GIS also provides a flexible environment for displaying, storing and analyzing the digital data needed to detect changes. Since environmental changes are important in order to give a general impression of the region's environment and build credible hypotheses based on sustainable development, detecting these changes is an important process in the monitoring and management of natural resources and urban development. Detection of changes is also considered as a part of modern science due to dependence on remote sensing sciences and GIS. With the rapid growth of cities in recent years, the recognition of their biophysical compounds and their dynamism is of particular importance and is considered as an important research topic. The operations that are carried out in the course of digital analysis and interpretation of satellite data and with the aim of identifying and distinguishing ground phenomena can be summarized in three stages of initial surveys and information preparation, classification of information and finalized reviews and processing. Geometric correction of images and their classification based on existing methods and algorithms, and the accuracy of production maps, and finally comparing the maps at different times are among the stages of detecting changes. In the present study, we try to describe the steps briefly.