LEADER IN THE FIELD OF SATELLITE MONITORING
RU EN

ScanEx Image Processor Software. In-Depth ERS Data Processing Technology. The Art of Thematic Interpretation

19 - 26 October 2022
60 000
for   8   days per person
Enroll in a course
Location
SCANEX Group
Information
Phone: +7 (495) 739-73-85 Email: course@scanex.ru
The course covers the main aspects of working with remote sensing materials - from data acquisition and their radiometric correction to photogrammetric processing and implementation of thematic classifications.
19 October 2022 — ScanEx Image Processor Software. In-Depth ERS Data Processing Technology. The Art of Thematic Interpretation
10:00 — 18:00
Day 1 Theoretical part
10:00 — 18:00
Day 1 Practical part
10:00 — 18:00
Day 2 Theoretical part
10:00 — 18:00
Day 2 Practical part
10:00 — 18:00
Day 3 Theoretical part
10:00 — 18:00
Day 3 Practical part
10:00 — 18:00
Day 4 Practical part
10:00 — 18:00
Day 5 Practical part
ScanEx Image Processor Software. In-Depth ERS Data Processing Technology. The Art of Thematic Interpretation
The course covers the issues of in-depth processing and advanced analysis of Earth remote sensing data.
During the training period, students will get acquainted with the basic principles of working with an image, gain skills in working with vector data, learn how to create image mosaics, work with digital elevation models (DTM) and much more. The course uses the ScanEx Image Processor software package.
10:00 — 18:00
Day 1 Theoretical part
  • Satellite imagery and its features, the current database of satellite images;
  • Parameters of imaging orbits;
  • Different classes and types of imaging equipment;
  • Basic principles of imagery generation by modern imaging systems
  • 10:00 — 18:00
    Day 1 Practical part
  • General description of ScanEx Image Processor software (purpose, specific features, main formats supported, software interface);
  • Getting started (downloading data in the software, changing projection and project file resolution, working windows and navigation tools, operations with imagery, operations with histograms, saving processing results in a file);
  • Operations with vector layers (downloading vector layers in the software, creating and editing vector objects, selecting a display option for object captions, creating a new vector layer, adding and viewing the attribute data of vector layers);
  • Creation of a raster data library and importing data therefrom.
  • 10:00 — 18:00
    Day 2 Theoretical part
  • Basic approaches to correcting the geometric distortions of different imagery types, with account of imaging equipment specifics and local relief;
  • Digital elevation models (DEMs);
  • Determination of reflectance and atmospheric correction methods offered by SIP;
  • Enhancements, spectral transformations;
  • Topographic correction;
  • Methods of creating digital elevation models (DEMs) and digital terrain models (DTMs);
  • Index-based imagery.
  • 10:00 — 18:00
    Day 2 Practical part
  • Geometrical correction: georeferencing based on a strict sensor model;
  • Batch download of publicly available digital elevation models DEMs (GTOPO-30, SRTM-30 etc.);
  • Orthotransformation;
  • RPC-based geometrical correction;
  • Automatic co-registration of imagery.
  • 10:00 — 18:00
    Day 3 Theoretical part
  • Application areas and possible use of satellite imagery;
  • Preliminary image analysis required for data decryption;
  • Key methods and approaches to satellite imagery decryption: visually interactive and automatic decryption;
  • Algorithms of automated satellite imagery classification: per-pixel and object-oriented classification;
  • Additional methods and tools of decryption;
  • General technology chain of satellite imagery thematic processing.
  • 10:00 — 18:00
    Day 3 Practical part
  • Satellite image classification by the method of spectral non-learning per-pixel classification;
  • Creation of learning classification standards;
  • Satellite image classification based on feedforward neural networks.
  • 10:00 — 18:00
    Day 4 Practical part
  • Satellite image classification by the method of pre-trained self-organizing neural networks;
  • Managing the display and representation of the neural network, preliminary assessment of a created neural network and classification quality;
  • Creating a thematic legend and the system of hierarchical classes;
  • Vectorization and rasterization of classification results, saving classification results;
  • Segmentation of a multi-channel satellite image;
  • Post-processing of satellite imagery classification results;
  • Binary classification;
  • Detection of variations in multi-temporal data (Channel Change).
  • 10:00 — 18:00
    Day 5 Practical part
  • Bundle adjustment;
  • Creation of mosaic coverage with automatic tonal balancing and automatic cutline generation
  • Improvement of spatial resolution (Image Fusion operation);
  • Synthesis of green and blue channels (for data without any blue elements);
  • Haze compensation in multispectral imagery;
  • Determination of reflectance and atmospheric correction;
  • Arithmetic operations with raster layers, creation of macros;
  • Operations with index-based imagery (creation, visualization).
  • Up