Proceedings, XXth congress: Proceedings, XXth congress

Altan, M. Orhan

Bibliographic data

Multivolume work

Persistent identifier:: 1663674213

Title:: Proceedings, XXth congress

Sub title:: Istanbul, 12 - 23 July 2004

Year of publication:: 2004

Place of publication:: Istanbul

Publisher of the original:: [Verlag nicht ermittelbar]

Identifier (digital):: 1663674213

Language:: English

Additional Notes:: Erscheinungsdatum des Originals ist aus dem Copyrightjahr ermittelt.; Auch bezeichnet als XXth International Congress for Photogrammetry and Remote Sensing

Editor:: Altan, M. Orhan

Corporations:: International Society for Photogrammetry and Remote Sensing, Congress, 20., 2004, Istanbul; International Society for Photogrammetry and Remote Sensing, Commission Primary Data Acquisition

Adapter:: International Society for Photogrammetry and Remote Sensing, Congress, 20., 2004, Istanbul; International Society for Photogrammetry and Remote Sensing, Commission Primary Data Acquisition

Founder of work:: International Society for Photogrammetry and Remote Sensing, Congress, 20., 2004, Istanbul; International Society for Photogrammetry and Remote Sensing, Commission Primary Data Acquisition

Other corporate:: International Society for Photogrammetry and Remote Sensing, Congress, 20., 2004, Istanbul; International Society for Photogrammetry and Remote Sensing, Commission Primary Data Acquisition

Document type:: Multivolume work

Volume

Persistent identifier:: 166368779X

Title:: Proceedings, XXth congress

Scope:: IV, 226 Seiten

Year of publication:: 2004

Place of publication:: Istanbul

Publisher of the original:: [Verlag nicht ermittelbar]

Identifier (digital):: 166368779X

Illustration:: Illustrationen, Diagramme

Signature of the source:: ZS 312(35,B8)

Language:: English

Additional Notes:: Erscheinungsdatum des Originals ist aus dem Copyrightjahr ermittelt.

Usage licence:: Attribution 4.0 International (CC BY 4.0)

Editor:: Altan, M. Orhan

Corporations:: International Society for Photogrammetry and Remote Sensing, Congress, 20., 2004, Istanbul; International Society for Photogrammetry and Remote Sensing

Adapter:: International Society for Photogrammetry and Remote Sensing, Congress, 20., 2004, Istanbul; International Society for Photogrammetry and Remote Sensing

Founder of work:: International Society for Photogrammetry and Remote Sensing, Congress, 20., 2004, Istanbul; International Society for Photogrammetry and Remote Sensing

Other corporate:: International Society for Photogrammetry and Remote Sensing, Congress, 20., 2004, Istanbul; International Society for Photogrammetry and Remote Sensing

Publisher of the digital copy:: Technische Informationsbibliothek Hannover

Place of publication of the digital copy:: Hannover

Year of publication of the original:: 2019

Document type:: Volume

Collection:: Earth sciences

Chapter

Title:: COMPARISON OF OBJECT ORIENTED IMAGE ANALYSIS AND MANUAL DIGITIZING FOR FEATURE EXTRACTION H. Sahin, H. Topan, S. Karakis, A. M. Marangoz

Document type:: Multivolume work

Structure type:: Chapter

es 1f d. In in a have | this 'ared ison. oses. s for s the mple nt in VR- es in ation s of 2S 10 g of 1000 1etric , For using j are | line from dable F the 1 this and International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol XXXV, Part B-YF. Istanbul 2004 2.1 Manual On-Screen Digitizing Evolving computer technology enabled digitizing interactively which was made in the former times on digitizing tables. The details on graphical map are traced on the screen via proper software. The end product is a compound of many user defined layers. The topology is created and edited by the user himself. 2.2 Object Oriented Image Analysis In object oriented image analysis the basic processing units are not only individual pixels but also image objects or segments. The classifiers in object oriented image analysis are soft classifiers that are based on fuzzy logic. Soft classifiers use membership to express an object’s assignment to a defined class. The membership value lies between 0.0 and 1.0, where 0.0 expresses absolute improbability and 1.0 expresses a complete assignment to a class. The degree of membership depends on the degree to which the objects fulfill the class- describing conditions. One advantage of these soft classifiers lies in their possibility to express uncertainties about the classes’ descriptions. The basic processing units in object oriented image analysis are objects or pixel clusters, with object oriented approach to analyze images, the first step is always to form the processing units by image segmentation (Yan, 2003). After all processes mentioned above the objects on the image can be recognized by software using pre-defined parameters. Thus, what at manual digitizing the user carries out is handed over to computer software. Operator intervenes in case of making essential alterations to the parameters. 3. STUDY AREA AND UTILIZED DATA The study area, which is shown in Figure 1, is a part of Zonguldak city, located in Western Black Sea region of Turkey. It is famous with being one of the main hard coal mining field in the world. Although losing economical interest, there are several coal mines still active in Zonguldak. Area has a rolling topography, in some parts, with steep and rugged terrain. While partly built city area is located alongside the sea coast, there are some agricultural lands and forest inner regions. In the study area the elevation ranges roughly up to 400 m. Figure 1. Study area 115 In this test, image part from full panoramic KVR-1000 frame with frame number of 2252 and the viewing date of October 17”, 2000 was implemented. The first phase in the production of KVR-1000 orthoimages in Sovinformsputnik (SIS) is the scanning of hardcopy KVR-1000 photographs. This task was realized by the Zeiss SCAI scanner using 7 um pixel size. For rectification of KVR-1000 images, the PC-based digital photogrammetric system called Ortho/Z-Space developed by the cooperation of SIS and Russian Institute GosNIAS was used. In this process, generally DEM from stereo TK-350 images or by the available mapping materials can be used. In the given case, for orthoimage generation, DEM digitized from the topographic maps of 1:100000 scale (with the height accuracy of 20 m) was used (information from the SIS). The used KVR-1000 orthoimage’s pixel size is 1.56 m, ellipsoid is WGS-84, projection is UTM. It is in 8-bit grayscale. For the purposes, large scale maps (1:1000) which photogrammetrically produced are used. These maps date back to 1997. 4. MANUAL AND AUTOMATIC DIGITIZING Two methods have been used in this study. The first one is on- screen digitizing which requires user intervention at the whole digitizing process. The second method requires some settings prior to processing. Here operator plays also a crucial role but the intervention is slightly reduced compared to manual methods. The method used in this study is object oriented image analysis approach as described in the second section briefly. The study area consists of 2 km x 1.8 km sub-image of a KVR- 1000 orthoimage covering nearly 14 km x 14 km on the ground. Computer Aided Design (CAD) software has been used for on- screen digitizing. While KVR-1000 image is in WGS-84 coordinate system, the 1:1000 maps are in national coordinate system. Thus, a transformation between both systems is necessary. The transformation has been made by polynomial methods and yielded an accuracy of 4.5 m. Corresponding transformation points in both systems are chosen visually. Buildings = Figure 2. Digitized structures and study area On-screen digitizing result is given in Figure 2 in green color overlapped on orthoimage. Centre lines of roads can be shown as red color in the same figure. The digitized vector results represent the area as seen from this overview image. For the

Access restriction

Copyright

fullscreen: Proceedings, XXth congress (Part 8)

Multivolume work

Volume

Chapter

Table of contents

Cite and reuse

Volume

Chapter

Image

Image fragment

Citation links

Citation recommendation