Home > Search Results: Kolankiewiczová, Soňa
Search:
Search Tips :: Advanced Search
Search collections:
Sort by: Display results: Output format:
National Repository of Grey Literature 3 records found  Search took 0.00 seconds. 
Classification of line features from remote sensing data
 Kolankiewiczová, Soňa ; Potůčková, Markéta (advisor) ; Kupková, Lucie (referee)
This work deals with object-based classification of high resolution data. The aim of the thesis (paper, work) is to develope an acceptable classification process of linear features (roads and railways) from high-resolution satellite images. The first part shows different approaches of the linear feature classification and compares theoretic differences between an object-oriented and a pixel-based classification. Linear feature classification was created in the second part. The high-resolution QuickBird satellite images showing Prague surroudings were used for this classification. Using Definiens Developer software and the paper of Nobrega et al. (2006) the segmentation and object-based classification was created on the selected area of the satellite image. Minimum distance method of a pixel-based classification of the same part of image was generated to compare these two methods of classifications. Another classification was created in an another satellite image to verify developed classification process. At the end a visual and statistical accuracy assessment was done to compare an object-oriented and a pixel-based classification . Powered by TCPDF (www.tcpdf.org)
Detailed record
POLISH AGRICULTURE AND ACCESSION TO EU
 Kolankiewiczová, Soňa ; Jančák, Vít (advisor) ; Stockmann, Jiří (referee)
Detailed record
Classification of line features from remote sensing data
 Kolankiewiczová, Soňa ; Kupková, Lucie (referee) ; Potůčková, Markéta (advisor)
This work deals with object-based classification of high resolution data. The aim of the thesis (paper, work) is to develope an acceptable classification process of linear features (roads and railways) from high-resolution satellite images. The first part shows different approaches of the linear feature classification and compares theoretic differences between an object-oriented and a pixel-based classification. Linear feature classification was created in the second part. The high-resolution QuickBird satellite images showing Prague surroudings were used for this classification. Using Definiens Developer software and the paper of Nobrega et al. (2006) the segmentation and object-based classification was created on the selected area of the satellite image. Minimum distance method of a pixel-based classification of the same part of image was generated to compare these two methods of classifications. Another classification was created in an another satellite image to verify developed classification process. At the end a visual and statistical accuracy assessment was done to compare an object-oriented and a pixel-based classification . Powered by TCPDF (www.tcpdf.org)
Detailed record

Interested in being notified about new results for this query?
Subscribe to the RSS feed.
Digital Repository :: Search :: Submit :: Personalize :: Help
Powered by Invenio v1.1.2
Maintained by admin.invenio@techlib.cz
This site is also available in the following languages:
Česky  English