• Journal of The Korean Society of Agricultural Engineers
• /
• v.65 no.6
• /
• pp.15-22
• /
• 2023

In this study, We conduct a comparative study of deep learning-based classification of agricultural field attributes using Tagged Image File (TIF) and Enhanced Compression Wavelet (ECW) images. The goal is to interpret and classify the attributes of agricultural fields by analyzing the differences between these two image formats. "FarmMap," initiated by the Ministry of Agriculture, Food and Rural Affairs in 2014, serves as the first digital map of agricultural land in South Korea. It comprises attributes such as paddy, field, orchard, agricultural facility and ginseng cultivation areas. For the purpose of comparing deep learning-based agricultural attribute classification, we consider the location and class information of objects, as well as the attribute information of FarmMap. We utilize the ResNet-50 instance segmentation model, which is suitable for this task, to conduct simulated experiments. The comparison of agricultural attribute classification between the two images is measured in terms of accuracy. The experimental results indicate that the accuracy of TIF images is 90.44%, while that of ECW images is 91.72%. The ECW image model demonstrates approximately 1.28% higher accuracy. However, statistical validation, specifically Wilcoxon rank-sum tests, did not reveal a significant difference in accuracy between the two images.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2010.04a
• /
• pp.311-313
• /
• 2010

This study is on the adapting vehicle-based mobile mapping system to the frequent unscheduled revision of 1:5000 scale national base map. We analyzed map layers which could be built by vehicle-based mobile mapping systems and studied surveying methods for each layers. Also, the methods of maintain surveying accuracy to satisfy accuracy standards of national base map were suggested. The maps of Yeouido, Hyangnam, and Suwon area were revised by vehicle-based mobile mapping system on a trial bases and possibility of utilizing vehicle-based mobile mapping system for map revision was analyzed. As a results it was revealed that vehicle-based mobile mapping systems were adequate for a irregular revision of national base map.

• Journal of Korean Society for Geospatial Information Science
• /
• v.5 no.2 s.10
• /
• pp.65-75
• /
• 1997

Nowadays, digital map plays a role as a container of spatial database.'there have been many researches concerning the improvements of the digital map accuracy. From the user's viewpoint, however, the quality level of digital nap is as important as its accuracy, because fitness-for-use is considered the most important factor to the users. This study aims to find the methodology for determining the grade nか digital map. To accomplish this, we propose two major stages. First, weight factors of the layers are given according to the importance of the functions which must be considered in digital map generation. Scond, weight factors of the components to evaluate the accuracy of the digital map are presented By scoring the components and by summing the scores, the method for determining fitness-for-use is developed.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2007.04a
• /
• pp.363-366
• /
• 2007

Road Design is being reached to the working design to produce drawings, calculate construction quantity and cost, through the basic design that contained feasibility study and all impact assessment. In general, to plan the route we use topographic map. The vertical positional accuracy is 30cm and horizontal positional accuracy is 35cm in 1:1,000 scale topographic map. In LiDAR, vertical positional accuracy is 15cm and horizontal positional accuracy is 30cm. So if we use LiDAR on road design, more accurate earth-volumn will be calculated when we plan the route. In this paper we try to find the method to use the LiDAR data on road design by drawing the profile and cross sectional view and comparing the earth-volumn to the road that working design is in process adopting the topographic map and LiDAR data.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.32 no.6
• /
• pp.581-590
• /
• 2014

With rapid land development, land category should be updated on a regular basis. However, manual field surveys have certain limitations. In this study, attempts were made to extract a feature vector considering spectral signature by parcel, PIMP (Percent Imperviousness), texture, and VIs (Vegetation Indices) based on RapidEye satellite image and cadastral map. A total of nine land categories in which feature vectors were significantly extracted from the images were selected and classified using SVM (Support Vector Machine). According to accuracy assessment, by comparing the cadastral map and classification result, the overall accuracy was 0.74. In the paddy-field category, in particular, PO acc. (producer's accuracy) and US acc. (user's accuracy) were highest at 0.85 and 0.86, respectively.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2002.05a
• /
• pp.86-89
• /
• 2002

In NC machining, the ability to automatically generate an optimal process plan is an essential step toward achieving automation, higher productivity, and better accuracy. For this ability, a system that is capable of simulating the actual machining process has to be designed. In this paper, a milling process simulation system for the general NC machining was presented. The system needs first to accurately compute the cutting configuration. ME Z-map(Moving Edge node Z-map) was developed to reduce the entry/exit angle calculation error in cutting force prediction. It was shorn to drastically improve the conventional Z-map model. Experimental results applied to the pocket machining show the accuracy of the milling process simulation system.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.16 no.2
• /
• pp.327-335
• /
• 1998

Many kinds of map projection have been used, since this cannot be done without a distortion and seemless representation of the globe. To overcome the continues representation of large digital terrain information by the global coordinate system , to find out the sources of projection error and optimizing method, and to increase the map accuracy, specific map projection researches are needed. In this study, improvements of map projections are suggested for small scale mapping which covering entire Korean peninsula based on theoretical evaluation and limits of current map projection. Furthermore, distortion factors, positional errors, and accuracy increasing method are evaluated.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2009.04a
• /
• pp.75-78
• /
• 2009

As a digital map is tile based of 2D, it is difficult to be satisfied with accuracy and up-to-date. In this study, we analyzed requirements of an object-oriented continuous digital map and designed the system. The digital map is 3D continuous object and has the accuracy and up-to-date, and designs with management system, transfer system, change information management system, frequent updating system and, same time updating system.

• Journal of Korean Society for Geospatial Information Science
• /
• v.16 no.3
• /
• pp.79-85
• /
• 2008

This study aims to derive a practical coordinate transformation method for the existing geographic information database. After analyzing the status and problems of existing 1/1,000 digital base map and GIS application database, the transformation parameters are estimated and the accuracy of the transformation is determined based on the transformed coordinates. We analyzed the accuracy of a transformation using the published national transformation coefficients as well as the estimated local transformation coefficients using national and urban control points in a study area. In addition, the 1/1,000 digital base map from aerial triangulation is compared with respect to the coordinates of urban control points. Based on the comparison, the biases on the national control points which were used at the time of digital map generation was analyzed. Then, the accuracy of transformed coordinates based on the world geodetic system using local transformation coefficients estimated from urban control points are determined. We also analyzed the transformation accuracy of underground infrastructure database using the same transformation method as the case of 1/1,000 digital base map. Through this study, it was found that the estimation of transformation coefficients by Molodensky-Badekas using urban control points was suitable for a local government. Furthermore, it was obvious that the accuracy of a 2-dimensional affine transformation was comparable to that of 7 parameter transformation for a local area. Applying the coordinate transformation and bias correction, we could transform GIS application database which was built by an offset surveying based on digital base map within the transformation accuracy of 10 cm. Therefore, it was judged that there will not be a big problem on the transformation of the GIS DB to the world geodetic system.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.19 no.2
• /
• pp.173-181
• /
• 2001

It is very important to assess spatial data quality of a digital map produced through digital map generalization. In this study, as a aspect of spatial data quality maintenance, we examined the tolerate range of theoretical expectation accuracy and established the quality assessment standard in spatial data for the transformed digital map data do not act contrary to the digital map specifications and the digital map accuracy of the relational scale. And, transforming large scale digital map to small scale, if we reduce complexity through processes as simplification, smoothing, refinement and so on., the spatial position change may be always happened. thus, because it is very difficult to analyse the spatial accuracy of the transformed position, we used the buffering as assessment method of spatial accuracy in digital map generalization procedure. Although the tolerated range of generic positioning error for l/l, 000 and l/5, 000 scale is determined based on related law, because the algorithms adapted to each processing elements have different property each other, if we don't determine the suitable parameter and tolerance, we will not satisfy the result after generalization procedure with tolerated range of positioning error. The results of this study test which is about the parameters of each algorithm based on tolerated range showed that the parameter of the simplification algorithm and the positional accuracy are 0.2617 m, 0.4617 m respectively.