• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2007.04a
• /
• pp.383-387
• /
• 2007

The improved accuracy of the Land Cover/Land Use Map constructed using Hyperspectal Satellite Image and the possibility of real time classification of Land Use using optimal Band Selective Factor enable the change detection from automatic classification using the existed Land Cover/Land Use Map and the newly acquired Hyperspectral Satellite Image. In this study, the effective analysis techniques for automatic generation of training regions, automatic classification and automatic change detection are proposed to minimize the expert's interpretation for automatic update of the Land Cover/Land Use Map. The proposed algorithms performed successfully the automatic Land Cover/Land Use Map construction, automatic change detection and automatic update on the image which contained the changed region. It would increase applicability in actual services. Also, it would be expected to present the effective methods of constructing national land monitoring system.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2002.10a
• /
• pp.287-291
• /
• 2002

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2003.04a
• /
• pp.501-504
• /
• 2003

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2002.10a
• /
• pp.157-163
• /
• 2002

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2003.04a
• /
• pp.479-484
• /
• 2003

The renewal of digital map takes much time and the manual process. LiDAR data allows reduction of time, automatic manner, and acquisition of the precise position. So it is used to renew the digital map of 1:5,000 scale. From the accuracy test results using aerial imagery and digitizing, renewal of digital map are feasible in automatic manner to some extent.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2010.04a
• /
• pp.235-238
• /
• 2010

Since the mid 1990s airborne LiDAR data have been widely used, automation of building modeling is getting a central issue. LiDAR data processing for building modeling is involved with extracting surface patch elements by segmentation and surface fitting with optimal mathematical functions. In this study, simulation LiDAR data were generated with complex polyhedral roofs of buildings and an automatic modeling approach was proposed.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.11 no.2
• /
• pp.89-100
• /
• 1993

This paper is a study on the earth volume calculation using CAD and LISP(LIST Processing) in the route alignment. The utility enlargement in the industry field and the considerable progress of computer make the automatic design and manufacture for the development of CAD/CAM/CAE technique possible, and the automatic design of civil engineering works is continuously progressive. In this study we are intend to improve an effect of civil engineering work by the automatic earth volume calculation in route alignment. This paper aims to construct the automatic design system of civil engineering work and the procedures; (1) The programming of the self-scanning program of the land information introducing Digital Terrain Model concept in the map (2) Systematic algorithm construction using LISP and grafting CAD system (3) Automatic design and calculation of the mass curve and earth volume.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.22 no.4
• /
• pp.375-381
• /
• 2004

This study is to improve an automatic rate of mapping system through analysis of topographic map specification. The digital map ver 2.0(1/5,000) has used for this studv and the mapping information is to obtain digital and topographic map. This topographic map specification is compared with information that represented of today. The regulation of a map specification for automatic mapping system planed out $\circled1$ similar specification of topographic map $\circled2$ simplified specification $\circled3$ clearness specification. After this study, the automatic rate of a mapping is up to 7% and the map specification has been easily generated.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2010.04a
• /
• pp.277-280
• /
• 2010

There is a need to convert the old low- or medium-resolution satellite image-based thematic mapping to the high-resolution satellite image-based mapping of GSD 1m grade or lower. There is also a need to generate middle- or large-scale thematic maps of 1:5,000 or lower. In this study, the DEM and orthoimage is generated with the KOMPSAT-2 stereo image of Yuseong-gu, Daejeon Metropolitan City. By utilizing the orthoimage, automatic extraction experiments of land cover information are generated for buildings, roads and urban areas, raw land(agricultural land), mountains and forests, hydrosphere, grassland, and shadow. The experiment results show that it is possible to classify, in detail, for natural features such as the hydrosphere, mountains and forests, grassland, shadow, and raw land. While artificial features such as roads, buildings, and urban areas can be easily classified with automatic extraction, there are difficulties on detailed classifications along the boundaries. Further research should be performed on the automation methods using the conventional thematic maps and all sorts of geo-spatial information and mapping techniques in order to classify thematic information in detail.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.38 no.5
• /
• pp.407-414
• /
• 2020

SVM (Support vector machine) analysis was performed after applying a deep learning technique based on an Inception-based model (GoogLeNet). The accuracy of automatic image classification was analyzed using an SVM with multiple virtual grid sizes. Six classes were selected from a standard land cover map. Cars were added as a separate item to increase the classification accuracy of roads. The virtual grid size was 2-5 m for natural areas, 5-10 m for traffic areas, and 10-15 m for building areas, based on the size of items and the resolution of input images. The results demonstrate that automatic classification accuracy can be increased by adopting an integrated approach that utilizes weighted virtual grid sizes for different classes.