• 한국수자원학회논문집
• /
• 제54권11호
• /
• pp.933-942
• /
• 2021

홍수시 하천의 유속을 효율적이고 안전하게 측정할 수 있는 방법의 하나로 제시된 것이 표면 영상유속측정법이다. 표면영상유속측정법에는 영상분석 기법에 따라 다양한 종류가 있으나, 이 중에서도 최근 일정시간 동안의 유속의 시간평균을 한 번에 산정할 수 있는 시공간영상 유속계측법이 하천의 표면유속 측정에 대한 연구가 활발히 진행되고 있다. 시공간영상 유속계측법은 일정 시간 동안의 시공간 영상을 한 번에 분석하기 때문에, 유속산정 시간을 획기적으로 줄일 수 있는 장점이 있다. 그러나 시공간영상 유속계측법은 주흐름방향을 정확히 알지 못하면 오차를 유발할 수 있다. 본 연구는 표면영상을 시간적으로 누적한 시공간체적을 구성하고, 이 시공간체적에서 시간축 방향으로 최대값 영상을 만든 뒤 이를 고속푸리에변환하여 주흐름방향을 탐색하는 새로운 기법을 제안하였다. 이 방법은 공간영상에서 주흐름방향을 찾는 첫단계와 주흐름방향의 시공간영상에서 유속의 크기를 산정하는 두번째 단계로 구성되어 있다. 첫번째 단계에서 찾아낸 주흐름방향으로 시공간영상을 작성하고, 이 시공간영상의 고속푸리에변환을 이용하여 유속을 산정하였다. 제안된 방법은 주흐름방향을 정확하게 추정하여 시공간영상을 생성하고 분석하므로, 기존 방법들이 취약했던 이차원 흐름에 대해서도 신속하고 정확한 유속분석이 가능하다. 개발된 방법을 공동흐름에 대한 인공영상에 적용한 결과 비교적 정확하게 2차원 유속분포 측정이 가능한 것으로 나타났다.

• 방송공학회논문지
• /
• 제20권3호
• /
• pp.414-420
• /
• 2015

3차원 영상 시스템에서 깊이 영상은 3차원 콘텐츠를 표현하는데 있어 매우 중요한 역할을 수행한다. 그러나 깊이 카메라로부터 얻은 원본 깊이 영상은 해상도가 색상 영상에 비해 매우 작고 시간적 흐름의 측면에서 관찰하였을 때 깊이 값이 불안정하게 진동하는 깜빡임 문제가 발생한다. 이 문제는 시청자들이 3차원 콘텐츠를 감상할 때 불편한 느낌을 초래한다. 이 논문에서는 원본 깊이 영상의 저해상도 문제를 해결하기 위해 3차원 워핑과 깊이 가중치가 추가된 결합형 양방향 업샘플링 방법을 사용한다. 다음으로 깊이 영상의 배경 영역에서 발생하는 깜빡임 문제를 해결하기 위해 전경과 배경을 분리한 뒤, 전경 영역에는 업샘플링된 깊이 영상을 사용하고 배경 영역에는 시간적 평균값 필터 영상을 이용했다. 실험결과는 제안하는 방법이 시간적 일관성이 향상된 고해상도의 깊이 영상을 생성함을 보였다.

• Korean Journal of Radiology
• /
• 제25권4호
• /
• pp.374-383
• /
• 2024

Objective: To evaluate the diagnostic performance and image quality of 1.5-mm slice thickness MRI with deep learningbased image reconstruction (1.5-mm MRI + DLR) compared to routine 3-mm slice thickness MRI (routine MRI) and 1.5-mm slice thickness MRI without DLR (1.5-mm MRI without DLR) for evaluating temporal lobe epilepsy (TLE). Materials and Methods: This retrospective study included 117 MR image sets comprising 1.5-mm MRI + DLR, 1.5-mm MRI without DLR, and routine MRI from 117 consecutive patients (mean age, 41 years; 61 female; 34 patients with TLE and 83 without TLE). Two neuroradiologists evaluated the presence of hippocampal or temporal lobe lesions, volume loss, signal abnormalities, loss of internal structure of the hippocampus, and lesion conspicuity in the temporal lobe. Reference standards for TLE were independently constructed by neurologists using clinical and radiological findings. Subjective image quality, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR) were analyzed. Performance in diagnosing TLE, lesion findings, and image quality were compared among the three protocols. Results: The pooled sensitivity of 1.5-mm MRI + DLR (91.2%) for diagnosing TLE was higher than that of routine MRI (72.1%, P < 0.001). In the subgroup analysis, 1.5-mm MRI + DLR showed higher sensitivity for hippocampal lesions than routine MRI (92.7% vs. 75.0%, P = 0.001), with improved depiction of hippocampal T2 high signal intensity change (P = 0.016) and loss of internal structure (P < 0.001). However, the pooled specificity of 1.5-mm MRI + DLR (76.5%) was lower than that of routine MRI (89.2%, P = 0.004). Compared with 1.5-mm MRI without DLR, 1.5-mm MRI + DLR resulted in significantly improved pooled accuracy (91.2% vs. 73.1%, P = 0.010), image quality, SNR, and CNR (all, P < 0.001). Conclusion: The use of 1.5-mm MRI + DLR enhanced the performance of MRI in diagnosing TLE, particularly in hippocampal evaluation, because of improved depiction of hippocampal abnormalities and enhanced image quality.

• 한국측량학회지
• /
• 제37권5호
• /
• pp.323-330
• /
• 2019

Radiometric normalization with multi-temporal satellite images is essential for time series analysis and change detection. Generally, relative radiometric normalization, which is an image-based method, is performed, and histogram matching is a representative method for normalizing the non-linear properties. However, since it utilizes global statistical information only, local information is not considered at all. Thus, this paper proposes a histogram matching method considering local information. The proposed method divides histograms based on density, mean, and standard deviation of image intensities, and performs histogram matching locally on the sub-histogram. The matched histogram is then further partitioned and this process is performed again, iteratively, controlled with the wasserstein distance. Finally, the proposed method is compared to global histogram matching. The experimental results show that the proposed method is visually and quantitatively superior to the conventional method, which indicates the applicability of the proposed method to the radiometric normalization of multi-temporal images with non-linear properties.

• 전기전자학회논문지
• /
• 제24권4호
• /
• pp.1148-1155
• /
• 2020

Fire must be extinguished as quickly as possible because they cause a lot of economic loss and take away precious human lives. Especially, the detection of smoke, which tends to be found first in fire, is of great importance. Smoke detection based on image has many difficulties in algorithm research due to the irregular shape of smoke. In this study, we introduce a new real-time smoke detection algorithm that reduces the detection of false positives generated by irregular smoke shape based on faster r-cnn of factory-installed surveillance cameras. First, we compute the global frame similarity and mean squared error (MSE) to detect the movement of smoke from the input surveillance camera. Second, we use deep learning algorithm (Faster r-cnn) to extract deferred candidate regions. Third, the extracted candidate areas for acting are finally determined using space and temporal features as smoke area. In this study, we proposed a new algorithm using the space and temporal features of global and local frames, which are well-proposed object information, to reduce false positives based on deep learning techniques. The experimental results confirmed that the proposed algorithm has excellent performance by reducing false positives of about 99.0% while maintaining smoke detection performance.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권7호
• /
• pp.2345-2358
• /
• 2022

This paper presents a method to generate stained-glass animation from video inputs. The method initially segments an input video volume into several regions considered as fragments of glass by mean-shift segmentation. However, the segmentation predominantly results in over-segmentation, causing several tiny segments in a highly textured area. In practice, assembling significantly tiny or large glass fragments is avoided to ensure architectural stability in stained glass manufacturing. Therefore, we use low-frequency components in the segmentation to prevent over-segmentation and subdivide segmented regions that are oversized. The subdividing must be coherent between adjacent frames to prevent temporal artefacts, such as flickering and the shower door effect. To temporally subdivide regions coherently, we obtain a panoramic image from the segmented regions in input frames, subdivide it using a weighted Voronoi diagram, and thereafter project the subdivided regions onto the input frames. To render stained glass fragment for each coherent region, we determine the optimal match glass fragment for the region from a dataset consisting of real stained-glass fragment images and transfer its color and texture to the region. Finally, applying lead came at the boundary of the regions in each frame yields temporally coherent stained-glass animation.

• 한국의학물리학회:학술대회논문집
• /
• 한국의학물리학회 2002년도 Proceedings
• /
• pp.335-337
• /
• 2002

The aim of this study was investigate the epileptogenic zone in temporal lobe epilepsy (TLE). We evaluated the subtraction image of interictal SPECT from ictal SPECT coregistered to 3-dimensional (3D) MRI, and compared with the normal healthy SPECT using a SPM99. Forty-nine patients with TLE (M:F=28:21, mean age: 33${\pm}$2.1 years) underwent a pairs of ictal and interictal SPECT. We performed subtraction interictal SPECT from ictal SPECT in TLE patients. In addition, using SPM methods and t-statistics, SPECT images of the TLE patients were compared with normal healthy SPECT on a voxel by voxel basis. The voxels with a p-value of less than 0.05, 0.005, 0.001 were considered to be significantly different. The subtraction results by ictal and interictal SPECT coincided with the significant rCBF changes when compare of the normal healthy SPECT using a SPM99. The results suggested that analysis of difference of the two methods using healthy normal SPECT with SPM99 is useful tool in evaluation of seizure focus in epilepsy.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
• /
• pp.37-37
• /
• 2003

Rice is one of the most important crop in the world and is a major export of Thailand. Optical sensors are not useful for rice monitoring, because most cultivated areas are often obscured by cloud during the growing period, especially in South East Asia. Spaceborne Synthetic Aperture Radar (SAR) such as RADARSAT, can see through regardless of weather condition which make it possible to monitor rice growth and to retrieve rice acreage, using the unique temporal signature of rice fields. This paper presents the result of a study of examining the backscatter behavior of rice using multi-temporal RADARSAT dataset. Ground measurements of paddy parameters and water and soil condition were collected. The ground truth information was also used to identify mature rice crops, orchard, road, residence, and aquaculture ponds. Land use class distributions from the RADARSAT image were analyzed. Comparison of the mean DB of each land use class indicated significant differences. Schematic representation of temporal backscatter of rice crop were plotted. Based on the study carried out in Pathum Thani Province test site, the results showed variation of sigma naught from first tillering vegatative phase until ripenning phase. It is suggested that at least, three radar data acquisitions taken at 3 stages of rice growth circle namely; those are at the beginning of rice growth when the field is still covered with water, in the ear differentiation period, and at the beginning of the harvest season, are required for rice monitoring. This pilot project was an experimental one aiming at future operational rice monitoring and potential yield predicttion.

• 대한원격탐사학회지
• /
• 제26권2호
• /
• pp.87-98
• /
• 2010

한반도 전역과 같은 상대적으로 넓은 지역의 정확한 분류를 위해서는 단일 영상 분류 후 영상정합 방식보다는 영상 정합 후 분류방법이 보다 정확하다. 또한 다중시기 정보는 분류에 매우 유용하게 사용될 수 있다. 본 연구에서는 한반도 전역을 대상으로 최적의 Landsat ETM+ 영상정합 방식을 제시하였다. 한반도 전역에 대해 2000년부터 2001년까지 획득된 총 65개의 Landsat ETM+영상을 이용하여 낙엽기, 이앙기, 개엽기 각각 정합 영상을 제작하였다. 이때 보다 정확한 영상정합을 위해 히스토그램 매칭, 중앙영상을 기준으로 한 1차 회귀식적용방법, Landsat 촬영 패스별로 적용한 1차 회귀식 적용방법, 총 세 가지 상대복사보정 방법을 적용하였다. 적용 결과, 패스별 상대복사보정한 결과가 그 보정 효과가 크면서, 높은 분류 정확도를 나타냈다. 또한 시기별 정합영상을 살펴보면, 개엽기의 정합영상이 타시기에 비해 상대적으로 인접한 영상 간 지표물의 변이가 다양하게 나타나는 것을 볼 수 있었다.

• 한국정보통신학회논문지
• /
• 제6권6호
• /
• pp.812-818
• /
• 2002

본 연구에서는 1993년 야간 가시밴드 위성원격탐사 DMSP/OLS 자료를 이용하여 동해 전해역 야간 어선의 시공간적 변화를 GIS(Geographic Information System)에 적용하여 살펴보았다. 야간 어선의 월별 및 계절분포를 조사하기 위해 연구 영역을 위도 30$^{\circ}$ $N-44^{\circ} N, 경도 124^{\circ} E-142^{\circ}$ E을 선택했다. 어선의 시공간적 분포 분석에 이용한 GIS 소프트웨어는 ArcView 3.2로서 그 확장기능 중에서 Image Analyst를 이용하였다. 야간 가시밴드 Operational Linescan System(OLS) 영상은 야간 어선의 시공간적 분포에 대한 유용한 정보를 제공한다. 분석된 결과를 보면, 야간 어선이 밀집된 해역은 대마도와 대한해협주변, 한국 동해안 연안지역, 일본 혼슈열도 연안지역, 대화퇴 주변해역이었다