| Course Unit Code | 548-0024/06 |
|---|
| Number of ECTS Credits Allocated | 5 ECTS credits |
|---|
| Type of Course Unit * | Compulsory |
|---|
| Level of Course Unit * | Second Cycle |
|---|
| Year of Study * | First Year |
|---|
| Semester when the Course Unit is delivered | Winter Semester |
|---|
| Mode of Delivery | Face-to-face |
|---|
| Language of Instruction | English |
|---|
| Prerequisites and Co-Requisites | There are no prerequisites or co-requisites for this course unit |
|---|
| Name of Lecturer(s) | Personal ID | Name |
|---|
| HOR10 | prof. Ing. Jiří Horák, Dr. |
| Summary |
|---|
| The subject introduces the methods for digital processing of remotely sensed imagery. The subject has a practical orientation, combining conceptual foundations with a view towards applications. Students are offered a selection of advanced processing techniques for remotely sensed imagery. The course participant manages to choose the appropriate processing method, comprehends how to use the method practically and is able to assess the processing outcomes critically. |
| Learning Outcomes of the Course Unit |
|---|
| The main aim of this subject is to introduce students into the digital processing of remotely sensed data. This know-how can be used as a tool within some subjects studies. The course participant understands how to practically use these digital image processing methods. He achieves critically assess this processing outcome. |
| Course Contents |
|---|
1. Remote sensing image, properties, structure. Types of numerical data and their conversion. Raster data formats, import and export raster data, conversion of data formats.
2. Remote sensing image pre-processing. Atmospheric correction, terrain relief, and cirrus. The optical thickness of the atmosphere, relative and absolute atmospheric correction of image data. A complete model of electromagnetic radiation transmitted through the atmosphere. Modeling of terrain relief and cirrus influence on electromagnetic radiation in the atmosphere. Tools for atmospheric influence modeling (ATREM, ATMOSC, ATCOR2,3, Sen2cor,…).
3. Spectral indices from multispectral data. Ratio-based indices, orthogonal indices, distance-based indices. Application of spectral indices for vegetation studies, in geology, for identification and evaluation of fire, other spectral indices. Index database.
4. Supervised classification, classification scheme. Training stage, in-situ data collection and data acquisition from alternative sources. Training stage evaluation, correction of training areas. Parametric and non-parametric classifiers. Ground truthing Importance of reference data in the evaluation of classification success. Post-classification processing.
5. Comparing visual interpretation with computer-based image classification. Unsupervised classification. Clustering algorithms RGB clustering, K-means, ISODATA, ISOCLUSTER, Narendra-Goldberg, EM clustering. Transformation of spectral classes into information classes. Classification result adjustment based on the classification tree. The use of clusters for the hybrid classification technique. Evaluation of computer-based classification results.
6. Object-based analysis (OBIA). Methods of segmentation, methods of delimitation of image objects (watershed delineation approach, Baatz-Shäpe algorithm).
7. Identification of changes in the landscape, pairwise comparisons (simple differences, image regression, image rationing) and multiple comparisons - time-series analyses. Change mapping based on SAR data.
8. Complementary methods of classification. Bayes' theorem and maximum likelihood classification. Classification based on temporal changes in a landscape. Soft classification methods based on Bayes' theorem and maximum likelihood classification, Dempster-Shafer theory, Mahalanobis distance, fuzzy sets. Utilization of uncertainty theory in classification. Use of context and texture in classification.
9. Image spectrometry data processing.
10. Utilization of artificial intelligence, machine learning, a neural network for remote sensing image processing. Deep learning technique for image data processing.
11. Methods of thermal image processing from remote sensing. Images from thermoelectric, bolometric and quantum sensors. Thermal image visualization, thermogram. High-resolution thermal image interpretation and identification of thermal anomalies in a thermal image. Thermometry.
12. Processing of image data from radar systems. Co-registration of a pair of SAR products, interferogram creating and estimation of coherence, removal of demarcation from interferogram, image filtering. DInSAR method. Radar polarimetry. Mapping of land cover based on SAR image classification.
13. Methods of remote sensing for measuring the height and mapping of water objects. Radar Altimetry. Utilization of sonar.
14. Integration of remote sensing data into GIS. |
| Recommended or Required Reading |
|---|
| Required Reading: |
|---|
Avery, T.E.; Berlin, G.L.: Fundamentals of Remote Sensing and Airphoto Interpretation. Pearson Prentice Hall, 1992.
Eastman, J. R.: IDRISI Selva Tutorial (Part 4 a Part 5), Manual Version 17.01, Clark University, 2012.
Jensen, J.R.: Introductory Digital Image Processing: A Remote Sensing Perspective. Pearson Prentice Hall, 2005, ISBN-13: 978-0131453616
Lillesand, T.; Kiefer, R.: Remote sensing and image interpretation. John Wiley & Sons, 1994.
Smith, R. B.: Analyzing hyperspectral data. Microimages, Inc., 2013, on-line https://www.microimages.com/documentation/Tutorials/hypanly.pdf
Warner, T.A.; Campagna, D.J.: Remote Sensing with IDRISI. A Beginner's Guide. Geocarto International Centre, 2013. |
Dobrovolný P.: Dálkový průzkum Země. Digitální zpracování obrazu, Masarykova univerzita, 1998.
Halounová, L.; Pavelka, K.: Dálkový průzkum Země. Vydavatelství ČVUT. Praha, 2005. |
| Recommended Reading: |
|---|
Landgrebe, D.: On Information Extraction Principles for Hyperspectral Data: A White Paper. School of Electrical & Computer Engineering, Purdue University, West Lafayette, IN 47907-1285. On-line https://engineering.purdue.edu/~landgreb/whitepaper.pdf
Schott, J.R.: Remote Sensing. The Image Chain Approach. Oxford University, 1997. |
| Šmidrkal, J.; Černohorský, A.; Fujan, B.; Charvát, K.; Poláček J.: Zpracování informací dálkového průzkumu Země. ČVUT Praha, 1989. |
| Planned learning activities and teaching methods |
|---|
| Lectures, Tutorials, Project work |
| Assesment methods and criteria |
|---|
| Task Title | Task Type | Maximum Number of Points
(Act. for Subtasks) | Minimum Number of Points for Task Passing |
|---|
| Credit and Examination | Credit and Examination | 100 (100) | 51 |
| Credit | Credit | 33 (33) | 17 |
| Sample tutorials | Laboratory work | 6 | 0 |
| Individual projects | Project | 20 | 12 |
| Attendance at tutorials | Other task type | 7 | 5 |
| Examination | Examination | 67 (67) | 25 |
| Written test | Written examination | 40 | 18 |
| Oral exam | Oral examination | 27 | 0 |