• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.4
• /
• pp.451-455
• /
• 2008

In this paper we embody a system that recognizes the printed alphabet of two font types (Batang, Dodum) inputted by a black-and-white CCD camera and converts it into an editable text form. The image of the inputted printed sentences is binarized, then the rows of each sentence are separated through the vertical projection using the Histogram method, and the height of the characters are normalized to 48 pixels. With the reverse application of the basic principle of the Nonogram puzzle to the individual normalized character, the character is covered with the pixel-based squares, representing the characteristics of the character as the numerical information of the Nonogram puzzle in order to recognize the character through the comparison with the standard pattern information. The test of 2609 characters of font type Batang and 1475 characters of font type Dodum yielded a 100% recognition rate.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.3
• /
• pp.1-10
• /
• 2010

In this paper, we propose a novel way of combining color demosaicing and the auto white balance (AWB) method, which are important parts of image processing. Performance of the AWB is generally affected by demosaicing results because most AWB algorithms are performed posterior to color demosaicing. In order to increase the performance and efficiency of the AWB algorithm, the color constancy problem is considered during the color demosaicing step. Initial estimates of the directional luminance and chrominance values are defined for estimating edge direction and calculating the AWB gain. We propose a modified edge-based AWB method that used a pre-defined achromatic region. The estimation of edge direction is performed region adaptively by using the local statistics of the initial estimates of the luminance and chrominance information. The proposed method shows significant improvements in terms of visual and numerical criteria when compared to conventional methods.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.48 no.6
• /
• pp.91-98
• /
• 2011

This paper proposes an efficient and accurate vision based recognition and tracking framework for texture free objects. We approached this problem with a two phased algorithm: detection phase and tracking phase. In the detection phase, the algorithm extracts shape context descriptors that used for classifying objects into predetermined interesting targets. Later on, the matching result is further refined by a minimization technique. In the tracking phase, we resorted to meanshift tracking algorithm based on Bhattacharyya coefficient measurement. In summary, the contributions of our methods for the underwater robot vision are four folds: 1) Our method can deal with camera motion and scale changes of objects in underwater environment; 2) It is inexpensive vision based recognition algorithm; 3) The advantage of shape based method compared to a distinct feature point based method (SIFT) in the underwater environment with possible turbidity variation; 4) We made a quantitative comparison of our method with a few other well-known methods. The result is quite promising for the map based underwater SLAM task which is the goal of our research.

• Korean Journal of Remote Sensing
• /
• v.32 no.6
• /
• pp.657-672
• /
• 2016

Coastal erosion happens frequently in many different types. To control coastal erosion zone effectively and establish response plans, we need to accumulate data indicating topography changes through monitoring the erosion situation continuously. UAV photogrammetric systems, which can fly autonomously at a low altitude, are recommended as an economical and precision means to monitor the coastal zones. In this study, we aim to verify the accuracy of the generated orthoimages and DEM as a result of processing the UAV data of a coastal zone by comparing them with various reference data. We established a verification routine and examined the possibilities of applying the UAV photogrammetric systems to monitoring coastal erosion by checking the analyzed accuracy by the routine. As a result of verifying the generated the geospatial information from acquired data under various configurations, the horizontal and vertical accuracy (RMSE) were about 2.7 cm and 4.8 cm respectively, which satisfied 5 cm, the accuracy required for coastal erosion monitoring.

• The Journal of Engineering Geology
• /
• v.9 no.2
• /
• pp.161-176
• /
• 1999

The objectives of this study are to analyze the changes of geo-surface topography in the Siwha embankment and the Ahsan city area by the image processing of Landsat Thematic Mapper data, and to estimate the reclaimed amount of the exposed tidal flat in the Siwha area using the GIS. False color composite, Tasseled cap, NVDI(normalized difference vegetation index), and supervised classification techniques were used to analyze the distribution of sediments and the aspect of topographical variations caused by artificial human actions. The total amount of the exposed tidal flat was estimated on the basis of the database snch as aerial photography, hydrographic chart, geological map, and scheme drawing in the Siwha area. The possible excavation regions for a seawall were predicted analyzing the supervised classification image of Landsat TM data. Tasseled cap images were used to observe the distribution of sediments. The difference of the NDVI images between spring and summer seasons indicates that deciduous and coniferous forests were distributed over the whole areas. The total fill-volume of the exposed Siwha tidal flat and the fill-volume of the construction planning seawall were calculated as $581,485,354\textrm{m}^3{\;}and{\;}3,387,360\textrm{m}^3$, respectively, from the digital terrain analysis. Daebu Island, Sunkam Island, and the part of Songsan-myeon were chosen as the cut area to make the seawall, and their cut-volumes were estimated as $5,229,576\textrm{m}^3,{\;}79,227,072\textrm{m}^3,{\;}and{\;}47,026,008\textrm{m}^3$, respectively. Therefore, the cut-volume of Daebu Island alone among three areas was sufficient to make the seawall.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.42 no.12
• /
• pp.1013-1019
• /
• 2014

Solid-liquid Phase Change Material(PCM) as a thermal control hardware for the electro-optical payload of low earth orbit satellite is numerically studied which can be substituted with Thermal Buffer Mass(TBM). The electro-optical module in LEO satellite is periodically work and high heat is dissipated during the imaging period, however, the design temperature range is very tight and sensitive. In order to handle this problem TBM is added and as a result the time constant of the module temperature increases. TBM is made of Al6010 and its mass directly affects the system design. To save the mass PCM is suggested in this study. The latent heat of melting or solidification is very high and small amount of PCM can play a role instead of TBM. The result shows that only 12% of TBM mass is enough to control the module temperature using PCM.

• Tunnel and Underground Space
• /
• v.26 no.1
• /
• pp.24-31
• /
• 2016

Recently, many studies have been conducted to use fixed-wing and rotary-wing unmanned aerial vehicles (UAVs, Drones) for topographic surveying in open-pit mines. Because the fixed-wing and rotary-wing UAVs have different characteristics such as flight height, speed, time and performance of mounted cameras, their results of topographic surveying at a same site need to be compared. This study selected a construction site in Yangsan-si, Gyeongsangnam-do, Korea as a study area and compared the topographic surveying results from a fixed-wing UAV (SenseFly eBee) and a popular rotary-wing UAV (DJI Phantom2 Vision+). As results of data processing for aerial photos taken from eBee and Phantom2 Vision+, orthomosaic images and digital surface models with about 4 cm grid spacing could be generated. Comparisons of the X, Y, Z-coordinates of 7 ground control points measured by differential global positioning system and those determined by eBee and Phantom2 Vision+ revealed that the root mean squared errors of X, Y, Z-coordinates were around 10 cm, respectively.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.38 no.1
• /
• pp.43-48
• /
• 2020

Open pit mines for limestone mining require rapid development of technologies and efforts to prevent safety accidents due to rapid deterioration of the slope due to deforestation and rapid changes in the topography. Accurate three-dimensional spatial information on the terrain should be the basis for reducing environmental degradation and safe development of open pit mines. Therefore, this study constructed spatial information about open pit mine using UAV(Unmanned Aerial Vehicle) and analyzed its utility. images and 3D laser scan data were acquired using UAV, and digital surface model, digital elevation model and ortho image were generated through data processing. DSM(Digital Surface Model) and ortho image were constructed using image obtained from UAV. Trees were removed using 3D laser scan data and numerical elevation models were produced. As a result of the accuracy analysis compared with the check points, the accuracy of the digital surface model and the digital elevation model was about 11cm and 8cm, respectively. The use of three-dimensional geospatial information in the mineral resource development field will greatly contribute to effective mine management and prevention of safety accidents.

• Journal of Korean Society for Geospatial Information Science
• /
• v.24 no.3
• /
• pp.49-58
• /
• 2016

Applications of drone in various fields have been increasing in recent years. Drone has great potential for forest management. Therefore this paper is using drone for forest damage areas. Forest damage areas is divided into caused by anthropogenic and occurs naturally, the possibility of disasters, such as slope sliding, slope failures and landslides, sediment runoff exists. Therefore, this research was to utilize the drone photogrammetry to perform the damage analysis of forest damage areas. Geometrical treatment processing results in Drone Photogrammetry, the plane position error RMSE was ${\pm}0.034m$, the elevation error RMSE was ${\pm}0.017m$. The plane position error of orthophoto RMSE was ${\pm}0.083m$, the elevation error of digital elevation model RMSE was ${\pm}0.085m$. In addition, It was possible to current state analysis of damage in forest damage areas of airborne LiDAR data of before forest damage and drone photogrammetry data of after forest damage. and application of drone photogrammetry for production base data for restoration and design in forest damage areas.

• Proceedings of the Korean Information Science Society Conference
• /
• 2012.06a
• /
• pp.200-202
• /
• 2012

공정기술의 발달로 인해 GPU는 빠르게 발전하고 있다. GPU는 영상처리뿐만 아니라 한 번에 많은 양의 데이터를 처리하는 범용 작업에도 많이 쓰이고 있다. 한편, 최근에는 3차원으로 코어를 적층하는 3차원 CPU구조에 대해 많은 연구가 수행되고 있다. 3차원 구조는 코어를 수직으로 적층시켜 내부 연결망의 길이를 크게 줄여주어 성능을 크게 개선하는 장점을 가지고 있다. 이를 반영하여 GPU에도 3차원 구조를 적용하여 GPU의 성능을 향상시키려는 선행연구에 맞춰 본 논문에서는 3차원 구조 GPU의 성능 향상을 저해하는 요소들에 대해서 분석해 보고자한다. 본 논문에서는 선행연구에서 밝힌 메모리 인터페이스에서 발생하는 병목현상 이외에도 주 메모리 큐 용량과 네트워크 방식에 따른 3차원 GPU의 성능향상을 실험을 통하여 알아본다. 실험 결과 주 메모리 큐 용량에 따른 3차원 GPU의 IPC는 가장 큰 사이즈와 가장 작은 사이즈의 차이가 4 미만으로 주 메모리 큐 용량은 3차원 GPU의 성능에 큰 영향을 미치지 않는 것으로 분석된다. 주 메모리로의 읽기 또는 쓰기 요청들을 순서대로 저장하는 큐의 역할이 3차원 구조 GPU의 동작에는 큰 영향을 미치지 않기 때문으로 분석된다. 반면 네트워크 방식에 따른 실험에서는 fly 네트워크 방식에 비해서 crossbar 네트워크 방식이 더 빠른 데이터 통신을 가능하게 해주어 crossbar네트워크 방식에서 IPC수치가 약 14 증가함을 알 수 있다. 두 가지 실험을 통하여 3차원 GPU의 성능에 네트워크 방식 차이가 주 메모리 큐 용량 변화보다 더 큰 영향을 주는 것을 확인할 수 있다.