• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.997-999
• /
• 2022

아기의 심장 박동 소리를 듣지 못하는 청각 장애 부모를 위한 태아 초음파 심장박동 촉각 변환 시스템을 개발하고자 하였다. 본 시스템은 아기의 심장박동 소리를 USB 마이크를 이용하여 소릿값을 입력받아 이에 대응하는 값을 진동 모터의 진동 출력 세기와 LED 밝기의 세기로 출력시키도록 하였다. 아기의 심장박동 느낌을 진동으로 표현해 내기 위해 진동의 샘플링 주기를 구체적인 수치로 조절하였고 산모에 따라 진동의 세기와 주변 잡음 제거를 할 수 있도록 조절하는 가변저항 2개를 연결하였다. 그 결과 태아 초음파 심장박동 촉각 변환 시스템을 성공적으로 개발하였으며 장치 체험자들로부터 총 평균 4.63점으로 높은 만족도를 얻었다. 개발 제품은 청각장애 산모들의 모성애를 충족시키고 아기의 심장박동을 느낌으로써 아기의 존재를 느낄 수 있을 것이며, 산부인과의 초음파 영상진단의 확장 신기술로 활용할 수 있을 것으로 기대된다.

• KIPS Transactions on Software and Data Engineering
• /
• v.4 no.4
• /
• pp.177-186
• /
• 2015

For data fusion of laser range finder (LRF) and vision camera, accurate calibration of external parameters which describe relative pose between two sensors is necessary. This paper proposes a new calibration method which can acquires more accurate external parameters between a LRF and a vision camera compared to other existing methods. The main motivation of the proposed method is that any corner data of a known 3D structure which is acquired by the LRF should be projected on a straight line in the camera image. To satisfy such constraint, we propose a 3D geometric model and a numerical solution to minimize the energy function of the model. In addition, we describe the implementation steps of the data acquisition of LRF and camera images which are necessary in accurate calibration results. In the experiment results, it is shown that the performance of the proposed method are better in terms of accuracy compared to other conventional methods.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.32 no.4_1
• /
• pp.319-326
• /
• 2014

The accurate geo-referencing processes that apply ground control points is prerequisite for effective end use of HRSI (High-resolution satellite imagery). Since the conventional control point acquisition by human operator takes long time, demands for the automated matching to existing reference data has been increasing its popularity. Among many options of reference data, the airborne LiDAR (Light Detection And Ranging) data shows high potential due to its high spatial resolution and vertical accuracy. Additionally, it is in the form of 3-dimensional point cloud free from the relief displacement. Recently, a new matching method between LiDAR data and HRSI was proposed that is based on the image projection of whole LiDAR data into HRSI domain, however, importing and processing the large amount of LiDAR data considered as time-consuming. Therefore, we wmotivated to ere propose a local LiDAR chip generation for the HRSI geo-referencing. In the procedure, a LiDAR point cloud was rasterized into an ortho image with the digital elevation model. After then, we selected local areas, which of containing meaningful amount of edge information to create LiDAR chips of small data size. We tested the LiDAR chips for fully-automated geo-referencing with Kompsat-2 and Kompsat-3 data. Finally, the experimental results showed one-pixel level of mean accuracy.

• Geophysics and Geophysical Exploration
• /
• v.12 no.1
• /
• pp.77-84
• /
• 2009

Ground penetrating radar (GPR) is an effective tool for detecting shallow subsurface targets. In many GPR applications, these targets are veiled by the strong waves reflected from the ground surface, so that we need to apply a signal processing technique to separate the target signal from such strong signals. A pulse-compression technique is used in this research to compress the signal width so that it can be separated out from the strong contaminated clutter signals. This work introduces a filter algorithm to carry out pulse compression for GPR data, using a Wiener filtering technique. The filter is applied to synthetic and field GPR data acquired over a buried pipe. The discrimination method uses both the reflected signal from the target and the strong ground surface reflection as a reference signal for pulse compression. For a pulse-compression filter, reference signal selection is an important issue, because as the signal width is compressed the noise level will blow up, especially if the signal-to-noise ratio of the reference signal is low. Analysis of the results obtained from simulated and field GPR data indicates a significant improvement in the GPR image, good discrimination between the target reflection and the ground surface reflection, and better performance with reliable separation between them. However, at the same time the noise level slightly increases in field data, due to the wide bandwidth of the reference signal, which includes the higher-frequency components of noise. Using the ground-surface reflection as a reference signal we found that the pulse width could be compressed and the subsurface target reflection could be enhanced.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.39 no.9
• /
• pp.848-857
• /
• 2011

Vision-based collision avoidance system for air traffic management requires a excellent multiple target detection algorithm under low signal-to-noise ratio (SNR) levels. The track-before-detect (TBD) approaches have significant applications such as detection of small and dim targets from an image sequence. In this paper, two detection algorithms with the TBD approaches are proposed to satisfy the multiple target detection requirements. The first algorithm, based on a dynamic programming approach, is designed to classify multiple targets by using a k-means clustering algorithm. In the second approach, a hidden Markov model (HMM) is slightly modified for detecting multiple targets sequentially. Both of the proposed approaches are used in numerical simulations with variations in target appearance properties to provide satisfactory performance as multiple target detection methods.

• Journal of Korea Society of Industrial Information Systems
• /
• v.25 no.6
• /
• pp.25-32
• /
• 2020

The seed, the most basic component, is an important factor in increasing production and efficiency in agriculture. Seeds with superior genes can be expected to improve agricultural productivity, crop survival, and reproduction. Currently, however, screening of superior seeds depends mostly on manual work, which requires a lot of time and manpower. In this paper, we propose a system that can extract the characteristics of seed phenotypes by using computer image processing technology, so that even a small number of people and a short period of time are needed to extract the characteristics of seeds. The proposed system detects individual seeds from images containing large quantities of seeds, and extracts and stores various characteristics such as representative colors, area, perimeter and roundness for each individual seed. Due to the regularity of input images, the accuracy of individual seed extraction in the proposed system is 99.12% for soybean seeds and 99.76% for rice seeds. The extracted data will be used as basic data for various data analyses that reflect the opinions of experts in the future, and will be used as basic data to determine the expressive nature of each seed.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.19 no.1
• /
• pp.80-93
• /
• 2016

Parcel boundary demarcation in agricultural area is commonly performed by terrestrial surveying methods, which have been pointed out as drawbacks to require consuming too much time and heavy expenditure. With the developments of high performance digital aerial cameras, however, studies on cadastral boundary demarcation with an aerial photogrammetric method attract a great attention in recent years. In this paper, an approach is presented to rapidly demarcate parcel boundaries coinciding with real ground ones in agricultural areas by extracting boundaries from the high resolution aerial orthoimages based on aerial targets. In order to investigate the feasibility of the proposed method, the accuracy of coordinates and area of parcel boundaries extracted from the aerial targets appeared in orthoimages compared with that of terrestrial boundary surveying results over the selected two test agricultural areas. Aerial image data were processed taken by a ADS80 digital camera with a GSD of 8cm in Changwon region, and by a DMCII camera with a GSD of 5cm in Suwon respectively. The result shows that the accuracy of parcel demarcation using aerial images is within the tolerance limits of coordinates and areas compared with that of terrestrial surveying. The proposed method using aerial target-based high resolution aerial images is therefore expected to be usefully applied in the agricultural parcel demarcation.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.20 no.2
• /
• pp.127-136
• /
• 2002

DEM(Digital Elevation Model) is used widely in image processing, water resources, construction, GIS, landscape architecture, telecommunication, military operations and other related areas. And it is used especially in producing ortho-photo based on specific DEM and developing 3D GIS database vividly. As LiDAR(Light and Detection And Ranging) system emerged recently, DEM could be developed in urban area more efficiently and more economically, compared to the conventional DEM Production. Traditional method using check points for elevation has tome limitations in structure's height accuracy by LiDAR, because it uses only terrain height. Accordingly after the downtown of Chungju city was selected as a test field in this paper and DEM and digital ortho images was produced by way of LiDar survey, the accuracy was evaluated through analytical plotting map. The result shows that in case of buildings in LiDAR DEM, the accuracy is 0.30 m in X, 0.62 m in Y and RMS is 1.17 m. The difference distribution between DEM and plotting map in range of $\pm$10 cm was 36.2% and $\pm$10 cm $\pm$20 cm was 43.53%. The accuracy of LiDAR in this study meets 1/5,000 which is the regulation for map of NGI(National Geography Institute) and LiDAR can be possibly used in many other applied area.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2007.06a
• /
• pp.227-230
• /
• 2007

If we use the microwave of SAR, we can observe on the ocean in spite of bad weather, day and night time. Sea surface images on the ocean of SAR have a lot of information on the atmospheric phenomena related to surface wind vector. Information of wind speed which is extracted from SAR images is used variously. Wind direction data and sigma nought value are put in the CMOD which can extract wind information in order to estimate sea surface wind from SAR images. Wind spectrum which is extracted from SAR always presents opposed two points of $180^{\circ}$ because of applying to 2D-FFT. These ambiguities should be decided by position of land, wind direction or numerical model. Previously, we converted into sigma nought after extracting Digital Number from RadarSat-1 SAR using ENVI4.0, thus, it took a long time because every process was manual. Therefore, we converted sigma nought by matlab code after making matlab code. After that, we are extracting wind direction from sigma nought. Now, to decide wind direction needs further study because wind direction has $180^{\circ}$ ambiguity.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.38 no.4
• /
• pp.363-373
• /
• 2020

During last decades numerous studies generating orthoimage have been carried out. Traditional methods require exterior orientation parameters of aerial images and precise 3D object modeling data and DTM (Digital Terrain Model) to detect and recover occlusion areas. Furthermore, it is challenging task to automate the complicated process. In this paper, we proposed a new concept of true orthoimage generation using DL (Deep Learning). DL is rapidly used in wide range of fields. In particular, GAN (Generative Adversarial Network) is one of the DL models for various tasks in imaging processing and computer vision. The generator tries to produce results similar to the real images, while discriminator judges fake and real images until the results are satisfied. Such mutually adversarial mechanism improves quality of the results. Experiments were performed using GAN-based Pix2Pix model by utilizing IR (Infrared) orthoimages, intensity from LiDAR data provided by the German Society for Photogrammetry, Remote Sensing and Geoinformation (DGPF) through the ISPRS (International Society for Photogrammetry and Remote Sensing). Two approaches were implemented: (1) One-step training with intensity data and high resolution orthoimages, (2) Recursive training with intensity data and color-coded low resolution intensity images for progressive enhancement of the results. Two methods provided similar quality based on FID (Fréchet Inception Distance) measures. However, if quality of the input data is close to the target image, better results could be obtained by increasing epoch. This paper is an early experimental study for feasibility of DL-based true orthoimage generation and further improvement would be necessary.