Infopaket

Automatic interpretation of remote sensimg data

ОК. 05

Обов’язкова дисципліна для ОП

Second

2023/2024

1 Semester

5

-Physical bases of DZ, principles of processing and interpretation -Methods of pre-processing of data DZ -Fundamentals of visual and automated decryption and classification of decryption features -Methods of mathematical processing and interpretation of multichannel data -Fundamentals of spectral analysis of remote sensing data -Approaches to the creation of parametric and non-parametric reference training samples for automated classification -Fundamentals of morphostructural analysis of remote sensing data -Perform visual decoding of space imagery, based on the spectral and spatial informativeness of the image -Perform mathematical data processing and statistical analysis -Decipher linear structures, and processing results and interpretation -Determine the thermophysical parameters of the earth's surface -Be able to organize expert analysis of data, make collective decisions -Understanding of personal responsibility for solving part of a common problem

Full-time form

Basic skills of mastering software environments for creating GIS projects.

It is based on landscape, spectral, statistical analysis of remote sensing data and automated methods of their processing and interpretation. Students will get acquainted with the basics of remote processing of remote sensing data in order to prepare them for high-level processing, gain knowledge and skills to perform accurate visual decryption of data and automated processing in professional software environments. Different approaches to the automated classification of the earth's surface will be considered: using the decision tree, parametric and spectral standards, threshold binarization, etc. Methods and features of remote sensing data processing of different origin are highlighted: short - wave multispectral data, thermal imaging data, active radar imaging.

1. Robert A. Schowengerdt. Remote Sensing: Models and Methods for Image Processing. Third Edition. Elsevier, 2007. 2. Jon Atli Benediktsson, Pedram Ghamisi. Spectral-Spatial Classification of Hyperspectral Remote Sensing Images. Artech House, 2015 3. Jerome O Connell, Ute Bradter, Tim G. Benton. Using high resolution CIR imagery in the classification of non-cropped areas in agricultural landscapes in the UK. Remote Sensing for Agriculture, Ecosystems, and Hydrology XV, edited by Christopher M. U. Neale, Antonino Maltese. Proc. of SPIE Vol. 8887, 888708 · © 2013 SPIE. doi: 10.1117/12.2028356 4. Jaromir Borzuchowski and Karsten Schulz. Retrieval of Leaf Area Index (LAI) and Soil Water Content (WC) Using Hyperspectral Remote Sensing under Controlled Glass House Conditions for Spring Barley and Sugar Beet. Remote Sensing 2010, 2, 1702-1721; doi:10.3390/rs2071702

Lectures, practical classes and student's independent work

The control is carried out according to the module-rating system and provides: performance of 7 practical works (where students have to demonstrate the quality of the acquired knowledge and solve the tasks using the methods and tools outlined by the teacher) and conducting 2 modular tests. The final grade is conducted in the form of a written and oral exam. Content modules form scores, which are set based on the results of the student's work throughout the semester, as the sum (simple or weighted) of points for systematic work during the semester. The final grade consists of the sum of points for content modules and points for the exam

English