• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.8
• /
• pp.3136-3150
• /
• 2015

A vision-based 3D tracking of articulated human hand is one of the major issues in the applications of human computer interactions and understanding the control of robot hand. This paper presents an improved approach for tracking and recovering the 3D position and orientation of a human hand using the Kinect sensor. The basic idea of the proposed method is to solve an optimization problem that minimizes the discrepancy in 3D shape between an actual hand observed by Kinect and a hypothesized 3D hand model. Since each of the 3D hand pose has 23 degrees of freedom, the hand articulation tracking needs computational excessive burden in minimizing the 3D shape discrepancy between an observed hand and a 3D hand model. For this, we first created a 3D hand model which represents the hand with 17 different parts. Secondly, Random Forest classifier was trained on the synthetic depth images generated by animating the developed 3D hand model, which was then used for Haar-like feature-based classification rather than performing per-pixel classification. Classification results were used for estimating the joint positions for the hand skeleton. Through the experiment, we were able to prove that the proposed method showed improvement rates in hand part recognition and a performance of 20-30 fps. The results confirmed its practical use in classifying hand area and successfully tracked and recovered the 3D hand pose in a real time fashion.

• Spatial Information Research
• /
• v.23 no.4
• /
• pp.47-56
• /
• 2015

Recently, there has been an increase in the number of people who use the smart-phone navigation for using various latest functions such as group driving and location sharing. But smart-phone has a limited storage space for one application, since a lot of applications with different purposes are installed in the smart-phone. For this reason, road network data with a large space of memory used for map matching in the device for navigation cannot be stored in the smart-phone for this reason map matching is impossible. Besides, smart-phone which doesn't use the external GPS device, provides inaccurate GPS information, compared to the device for navigation. This is why the smart-phone navigation is hard to provide accurate location determination. Therefore, this study aims to help map matching that is more accurate than the existing device for navigation, by reducing the capacity of road network data used in the device for navigation through format design of a new road network and conversion and using a database of driver's driving patterns. In conclusion, more accurate map matching was possible in the smart-phone by using a storage space more than 80% less than existing device at the intersection where many roads cross, the building forest that a lot of GPS errors occur, the narrow roads close to the highway. It is considered that more accurate location-based service would be available not only in the navigation but also in various applications using GPS information and map in the future Navigation.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.5 no.1
• /
• pp.58-68
• /
• 2002

Recently as recognition to prevent nature disasters is reaching the climax, the most important job of government official is to provide information related to the prevention of nature disasters through the Web and to bring notice to prevent disaster under people. Especially, if the case of daily forest fire hazard index is provided within visualization on Web, people may have more chances to understand about forest fire and less damages by large scale of forest fire. Forest fire hazard index presentation system developed in this paper presents daily forest fire hazard index on map visually also provides the information related to it in text format. In order to develop this system, CBDP(Component Based Development Process) is proposed in this paper. This development process tries to emphasize the view of reusability so that it has lifecycle which starts from requirement and domain analysis and finishes to component generation. Moreover, The concept of this development process tries to reflect component based method, which becomes hot issue in software field nowadays. In the future, the component developed in this paper may be possibly reused in other Web GIS application, which has similar function to it so that it may take less cost and time to develop other similar system.

• Journal of Forest and Environmental Science
• /
• v.30 no.1
• /
• pp.91-100
• /
• 2014

This research was conducted on the conservation area of Baekdudaegan, Kangwondo under the purpose of evaluating bio-diversity according to the changes of spatial scale, using GIS data and spatial filtering method. The diversity index was calculated based on the information of species of The $5^{th}$ forest type map using Shannon-weaver index (H'), evenness index ($E_i$) and richness index ($R_i$). The diversity index was analyzed and compared according to the changes of 12 spatial scales from Kernel size $3{\times}3$ to $73{\times}73$ and basin unit. As for H' and $R_i$, spatial scale increased as diversity index decreased, while $E_i$ decreases gradually. H' and $R_i$ was highest; each 1.1 and 0.6, when the Kernel size was $73{\times}73$, while $E_i$ was 0.2, the lowest. When you look at according to the basin unit, for large basin unit, 'YeongDong' region shows higher diversity index than 'YeongSeo' region. For middle basin unit, 'Gangneung Namdaecheon' region, and for small basin unit, 'Gangneung Namdaecheon' and 'Gangneung Ohbongdaem' region shows high diversity index. When you look at the relationship between diversity index and Geographic factors, H' shows positive relation to curvature and sunshine factor while shows negative to elevation, slope, hillshade, and wetness index. Also $E_i$ was similar to the relationship between H' and Geographic factor. Meanwhile, $R_i$ shows positive relationship to curvature and sunshine factor, while negative to elevation, slope, hillshade, and wetness index. macro unit diversity index evaluation was possible through the GIS data and spatial filtering, and it can be a good source for local biosphere conservation policy making.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.23 no.1
• /
• pp.41-50
• /
• 2020

The National Geographic Information Institute of Korea takes digital aerial photograph images every two years to make and modify/renew the digital map. The cameras for aerial photogrammetry to capture these digital aerial photographs are divided into frame types and line types. Computer vision analysis of aerial photograph images was only possible for frame type. Thus, in this study, Line type aerial photograph images was intended to generate geospatial information through computer vision analysis, and forest geospatial information was created as a method for the utilization of aerial picture images. As a result, geospatial information generated by computer vision analysis of line type aerial photograph images showed that RMSE of horizontal and vertical position errors was less than quadruple that of GSD. Forest geospatial information was generated using geospatial information generated by computer vision analysis. It was confirmed that extraction of the crown of tree and calculation of tree height are possible. Through this study, it is expected that utilization of aerial photograph images will be improved.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.11 no.2
• /
• pp.108-120
• /
• 2008

This paper discusses the prediction of deforestation areas using probability models from forest census database, Geographic information system (GIS) database and the land cover database. The land cover data was analyzed using remotely-sensed (RS) data of the Landsat TM data from 1989 to 2001. Over the analysis period of 12 years, the deforestation area was about 40ha. Most of the deforestation areas were attributable to road construction and residential development activities. About 80% of the deforestation areas for residential development were found within 100m of the road network. More than 20% of the deforestation areas for forest road construction were within 100m of the road network. Geographic factors and vegetation change detection (VCD) factors were used in probability models to construct deforestation occurrence map. We examined the size effect of area partition as training area and validation area for the probability models. The Bayes model provided a better deforestation prediction rate than that of the regression model.

• Journal of Korean Society for Geospatial Information Science
• /
• v.12 no.3 s.30
• /
• pp.13-21
• /
• 2004

Landuse information is used to plan land use, urban and environmental management as base data. And, demand for landuse information is rising due to ecological consideration. But existing method to extract landuse information from aerial photographs or field survey is consume a lot of time and cost. In urban area where the pattern of landuse is densely aggregated, a landuse information needs to be classified in detail for urban planning and management. Therefore this study aims to examine the method to extract landuse information in detail from 1:1,000 digital topographic data. For the purpose, the method was applied to a part of metropolitan Seoul. The results of study shows that extraction of landuse information except forest area is possible. Forest area is needed to describe smaller spatial unit. For the future, the method of describing forest area is improved it will be effectively applicable for the city maintenance.

• Journal of Korean Society for Geospatial Information Science
• /
• v.22 no.4
• /
• pp.99-106
• /
• 2014

After 1960 forest and ecosystem are rapidly destroyed by industrialization and urbanization. Accordingly, studies that produce vegetation map continue for forest and ecosystem management. Since 1986 national natural environment survey is being conducted in Korea. Also, vegetation information is managed properly through forest geospatial information service(FGIS) of the Department of Environment when NGIS project was promoted since 1995. But it provide dominant species information based on text. In particular, some vegetation information dose not provide to end-user. Therefore, we suggest construction method of vegetation information management system based on GIS to solve the problem. Also, we suggest connection method of related system for an accurate analysis, planning and decision-making support.

• Journal of Climate Change Research
• /
• v.7 no.2
• /
• pp.157-167
• /
• 2016

This study aims to evaluate the effect of shortened final cutting age by estimating future $CO_2$ absorption in each different scenarios based on each final cutting ages before and after shortening. We used $5^{th}$ Forest Type Map and Forest Yield Table to obtain information to estimate $CO_2$ absorption of forest. We also designed a simulated future scenarios from 2010 to 2100 which repeats cutting and reforestation according to respected each final cutting ages. As the result, number of cuttings and total amount of $CO_2$ absorption of forest were increased with shortened final ages. Total cutting times increased up to 2 in both minimum and maximum amount for Quescus spp. and Larix kaempferi. Maximum number of cutting of Pinus densiflora and minimum number of Pinus koraiensis increased by 1. Total $CO_2$ absorption increased 12％ for Quercus spp. which had the largest number of increase in cutting times, while total $CO_2$ absorption of Pinus koraiensis only increased by 1％. The result could be used to evaluate the changes in forest management plans and policies and then develop optimal final age for efficient sustainable forest management plans.

• Korean Journal of Remote Sensing
• /
• v.27 no.1
• /
• pp.17-24
• /
• 2011

Global warming and climatic changes due to human activities impact on marine and terrestrial ecosystems, which feedbacks to climate system. These negative feedbacks amplify or accelerate again global climate change. In particular, it is important to analyze vegetation change. This study attempts to analyze quantitatively vegetation change in Korea peninsula by using harmonic analysis. Harmonic-Analysis based on Fourier Transform is the method to effectively demonstrate for time series data. Especially, Harmonic-Analysis is very suitable method to analyze vegetation change because the vegetation repeats the cycle growth and extinction every year. The result of harmonic-analysis shows vegetation change as time passes. In this study, SPOTNEGETATION S10 MVC NDVI data was used during last 10 years (1999-2008) in Korea Peninsula. Also, land type classification used MODIS Land Cover Map data. The study estimated that phase values moved up approximately 0.5 day per year in cropland and 0.8 day per year in forest.