• The KIPS Transactions:PartB
• /
• v.19B no.2
• /
• pp.113-122
• /
• 2012

This paper presents a new stereo matching technique which is based on the matching of feature windows and feature links. The proposed method uses the FAST feature detector to find image features in stereo images and determines the correspondences of the detected features in the stereo images. We define a feature window which is an image region containing several image features. The proposed technique consists of two matching steps. First, a feature window is defined in a standard image and its correspondence is found in a reference image. Second, the corresponding features between the matched windows are determined by using the feature link technique. If there is no correspondence for an image feature in the standard image, it's disparity is interpolated by neighboring feature sets. We evaluate the accuracy of the proposed technique by comparing our results with the ground truth of in a stereo image database. We also compare the matching accuracy and computation time with two conventional feature-based stereo matching techniques.

• Journal of Korean Society for Geospatial Information Science
• /
• v.4 no.2 s.8
• /
• pp.35-45
• /
• 1996

The reflectance of chlorophyll was measured using UV-VIS spectrophotometer with the reflectance integrator in the laboratory in order to define its spectral characteristics. Sharp peaks appear at around 485nm and 655nm due to fluorescence and scattering, and the reflectance of chlorophyll increases at 580nm. With the increase in the chlorophyll concentration, the reflectance also increases. We have applied TM data to the reflectance spectrum of chlorophyll and have developed two formula with which one can estimate the chlorophyll concetration. Satellite re sensing, with its synoptic overage, is used to obtain the chlorophyll concentration in Daecheong reservoir. The approach involved acquisition of water quality samples front boat simultaneous with Landsat 5 satellite overpass. The remotely-sensed data and the ground truth data were obtained oil 20 June 1995 and on 18 March 1996. Regression models have been developed between the chlorophyll concentration and Landsat Thematic Mapper digital data. As the regression model was determined based on the correlation coefficient which was higher than 0.7 and the spectral characteristics of chlorophyll, and we have applied it to the entire study area to genelate a distribution map of trophic state. According to the trophic state map made based upon Aizaki's TSI and chlorophyll a concentration, the area where Okchun stream was flowing into was shown to be polluted the most all over the Daechung reservoir by showing an eutrophic state in June 1995 and a mesotrophic state in March 1996.

• Proceedings of the KSRS Conference
• /
• 2007.10a
• /
• pp.294-297
• /
• 2007

Steam and advection fogs are frequently observed in the Yellow Sea located between Korea and China during the periods of March-April and June-July respectively. This study uses the remote sensing (RS) data for monitoring sea fog. Meteorological data obtained from the Ieodo Ocean Research Station provided an informative synopsis for the occurrence of steam and advection fogs through a ground truth. The RS data used in this study was GOES-9, MTSAT-1R images and QuikSCAT wind data. A dual channel difference (DCD) approach using IR and near-IR channel of GOES-9 and MTSAT-1R satellites was applied to estimate the extension of the sea fog. For the days examined, it was found that not only the DCD but also the texture-related measurement and the weak wind condition are required to separate the sea fog from the low cloud. The QuikSCAT wind is used to provide a weak wind area less than threshold under stable condition of the surface wind around a fog event. The Laplacian computation for a measurement of the homogeneity was designed. A new combined method of DCD, QuikSCAT wind speed and Laplacian was applied in the twelve cases with GOES-9 and MTSAT-1R. The threshold values for DCD, QuikSCAT wind speed and Laplacian are -2.0 K, 8 m $s^{-1}$ and 0.1, respectively. The validation methods such as Heidke skill score, probability of detection, probability of false detection, true skill score and odds ratio show that the new combined method improves the detection of sea fog rather than DCD method.

• Korean Journal of Remote Sensing
• /
• v.36 no.5_3
• /
• pp.1067-1076
• /
• 2020

In this paper, an unsupervised saliency guided change detection method using UAV and aerial imagery is proposed. Regions that are more different from other areas are salient, which make them more distinct. The existence of the substantial difference between two images makes saliency proper for guiding the change detection process. Change Vector Analysis (CVA), which has the capability of extracting of overall magnitude and direction of change from multi-spectral and temporal remote sensing data, is used for generating an initial difference image. Combined with an unsupervised CVA and the saliency, Principal Component Analysis(PCA), which is possible to implemented as the guide for change detection method, is proposed for UAV and aerial images. By implementing the saliency generation on the difference map extracted via the CVA, potentially changed areas obtained, and by thresholding the saliency map, most of the interest areas correctly extracted. Finally, the PCA method is implemented to extract features, and K-means clustering is applied to detect changed and unchanged map on the extracted areas. This proposed method is applied to the image sets over the flooded and typhoon-damaged area and is resulted in 95 percent better than the PCA approach compared with manually extracted ground truth for all the data sets. Finally, we compared our approach with the PCA K-means method to show the effectiveness of the method.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.19 no.4
• /
• pp.840-847
• /
• 2005

This study was written in order to help understanding of visible diagnosis of energy and color(기색). Visible diagnosis of energy and color is a very important factor of diagnosis and a necessary step of visible diagnosis. As human's body is under the control of spirit(신) and spirit(신) is stored by five viscera(오장), so spirit expresses the change of five viscera and is reflected by energy and color(기색). Strictly speaking, energy and color(기색) is not divided into each other. But, we can say that glittering glossy part belongs to energy(기) and blue, red, yellow, white and black part belongs to color(색). Various changes of energy and color(기색) observe the rules of yin-yang(음양). If we consider the interior and exterior(내외), top and bottom(상하), right and left(좌우), rise and fall(부침), clearness and muddiness(청탁), weak and severe(미심), spread and gather(산박), gloss and dness(택요) etc. we can decide the yin and yang(음양), inside and outside(표리), coldness and heatness(한열), truth and false(허보), life and death(생사) and prognosis. One man's own color is determined by the five human type(오형인), There are very various points of changing colors. As divided into principal groups, there are three main groups, that is, sky(천), earth(지) and man(인). A season(사시), day and night(주야) and cloud and clear(음청) belong to the factor of sky(천), a direction and configuration of the ground(지형) belong 治 the factor of earth(지), and motion and rest(동정), seven emotions(칠정), age and youth(노소), poor and rich(빈부) and high and low(귀천) belong to the factor of man(인).

• Journal of KIISE:Software and Applications
• /
• v.34 no.1
• /
• pp.52-58
• /
• 2007

In this paper we propose a new robust method to extract accurate human silhouettes indoors with active stereo camera. A prime application is for gesture recognition of mobile robots. The segmentation of distant moving objects includes many problems such as low resolution, shadows, poor stereo matching information and instabilities of the object and background color distributions. There are many object segmentation methods based on color or stereo information but they alone are prone to failure. Here efficient color, stereo and image segmentation methods are fused to infer object and background areas of high confidence. Then the inferred areas are incorporated in graph cut to make human silhouette extraction robust and accurate. Some experimental results are presented with image sequences taken using pan-tilt stereo camera. Our proposed algorithms are evaluated with respect to ground truth data and proved to outperform some methods based on either color/stereo or color/contrast alone.

• Smart Media Journal
• /
• v.9 no.2
• /
• pp.22-32
• /
• 2020

The hippocampal volume atrophy is known to be linked with neuro-degenerative disorders and it is also one of the most important early biomarkers for Alzheimer's disease detection. The measurements of hippocampal pure volumes from Magnetic Resonance Imaging (MRI) is a crucial task and state-of-the-art methods require a large amount of time. In addition, the structural brain development is investigated using MRI data, where brain morphometry (e.g. cortical thickness, volume, surface area etc.) study is one of the significant parts of the analysis. In this study, we have proposed a patch-based ensemble model of 3-D convolutional neural network (CNN) to measure the hippocampal pure volume from MRI data. The 3-D patches were extracted from the volumetric MRI scans to train the proposed 3-D CNN models. The trained models are used to construct the ensemble 3-D CNN model and the aggregated model predicts the pure volume in one-step in the test phase. Our approach takes only 5 seconds to estimate the volumes from an MRI scan. The average errors for the proposed ensemble 3-D CNN model are 11.7±8.8 (error%±STD) and 12.5±12.8 (error%±STD) for the left and right hippocampi of 65 test MRI scans, respectively. The quantitative study on the predicted volumes over the ground truth volumes shows that the proposed approach can be used as a proxy.

• Journal of the Korean Society for Railway
• /
• v.18 no.3
• /
• pp.270-277
• /
• 2015

In some sections of the Seoul Metropolitan Subway, severe congestion can be observed during rush hours and on specific days. The subway operators have been conducting regular surveys to measure the level of congestion on trains: the results are then used to make plans for congestion reduction. However, the survey has so far focused just on train' congestion and has been unable to determine non-recurring congestion due to special events. This study develops an algorithm to estimate the platform congestion rate by time using individual public transportation card data. The algorithm is evaluated by comparison of the estimated congestion rate and the ground truth data that are actually observed at non-transfer subway stations on Seoul subway line 2. The error rates are within ${pm}2%$ and the performance of the algorithm is fairly good. However, varying walking times from gates to platforms, which are applied to both non-peak periods and peak time periods, are needed to improve the algorithm.

• Journal of International Society for Simulation Surgery
• /
• v.2 no.1
• /
• pp.13-16
• /
• 2015

Purpose We conducted a study on the reconstruction of the head's shape in 3D using the ToF depth sensor. A time-of-flight camera (ToF camera) is a range imaging camera system that resolves distance based on the known speed of light, measuring the time-of-flight of a light signal between the camera and the subject for each point of the image. The above method is the safest way of measuring the head shape of plagiocephaly patients in 3D. The texture, appearance and size of the head were reconstructed from the measured data and we used the SDF method for a precise reconstruction. Materials and Methods To generate a precise model, mesh was generated by using Marching cube and SDF. Results The ground truth was determined by measuring 10 people of experiment participants for 3 times repetitively and the created 3D model of the same part from this experiment was measured as well. Measurement of actual head circumference and the reconstructed model were made according to the layer 3 standard and measurement errors were also calculated. As a result, we were able to gain exact results with an average error of 0.9 cm, standard deviation of 0.9, min: 0.2 and max: 1.4. Conclusion The suggested method was able to complete the 3D model by minimizing errors. This model is very effective in terms of quantitative and objective evaluation. However, measurement range somewhat lacks 3D information for the manufacture of protective helmets, as measurements were made according to the layer 3 standard. As a result, measurement range will need to be widened to facilitate production of more precise and perfectively protective helmets by conducting scans on all head circumferences in the future.

• Imaging Science in Dentistry
• /
• v.46 no.2
• /
• pp.93-101
• /
• 2016

Purpose: The objective of this study was to investigate the effect of varying resolutions of cone-beam computed tomography images on the accuracy of linear measurements of edentulous areas in human cadaver heads. Intact cadaver heads were used to simulate a clinical situation. Materials and Methods: Fiduciary markers were placed in the edentulous areas of 4 intact embalmed cadaver heads. The heads were scanned with two different CBCT units using a large field of view ($13cm{\times}16cm$) and small field of view ($5cm{\times}8cm$) at varying voxel sizes (0.3 mm, 0.2 mm, and 0.16 mm). The ground truth was established with digital caliper measurements. The imaging measurements were then compared with caliper measurements to determine accuracy. Results: The Wilcoxon signed rank test revealed no statistically significant difference between the medians of the physical measurements obtained with calipers and the medians of the CBCT measurements. A comparison of accuracy among the different imaging protocols revealed no significant differences as determined by the Friedman test. The intraclass correlation coefficient was 0.961, indicating excellent reproducibility. Inter-observer variability was determined graphically with a Bland-Altman plot and by calculating the intraclass correlation coefficient. The Bland-Altman plot indicated very good reproducibility for smaller measurements but larger discrepancies with larger measurements. Conclusion: The CBCT-based linear measurements in the edentulous sites using different voxel sizes and FOVs are accurate compared with the direct caliper measurements of these sites. Higher resolution CBCT images with smaller voxel size did not result in greater accuracy of the linear measurements.