• 방송공학회논문지
• /
• 제23권5호
• /
• pp.614-621
• /
• 2018

본 논문에서는 generative adversarial network (GAN)을 이용한 비감독 학습을 통해 깊이 카메라로 깊이 영상을 취득할 때 발생한 손실된 부분을 복원하는 기법을 제안한다. 제안하는 기법은 3D morphable model convolutional neural network (3DMM CNN)와 large-scale CelebFaces Attribute (CelebA) 데이터 셋 그리고 FaceWarehouse 데이터 셋을 이용하여 학습용 얼굴 깊이 영상을 생성하고 deep convolutional GAN (DCGAN)의 생성자(generator)와 Wasserstein distance를 손실함수로 적용한 구별자(discriminator)를 미니맥스 게임기법을 통해 학습시킨다. 이후 학습된 생성자와 손실 부분을 복원해주기 위한 새로운 손실함수를 이용하여 또 다른 학습을 통해 최종적으로 깊이 카메라로 취득된 얼굴 깊이 영상의 손실 부분을 복원한다.

• Physical Therapy Rehabilitation Science
• /
• 제11권1호
• /
• pp.49-57
• /
• 2022

Objective: This study aims to conduct a comprehensive review of monitoring systems to monitor and manage physical function of community-dwelling elderly living alone and suggest future directions of unobtrusive monitoring. Design: Literature review Methods: The importance of health-related monitoring has been emphasized due to the aging population and novel corona virus (COVID-19) outbreak.As the population gets old and because of changes in culture, the number of single-person households among the elderly is expected to continue to increase. Elders are staying home longer and their physical function may decline rapidly,which can be a disturbing factorto successful aging.Therefore, systematic elderly management must be considered. Results: Frequently used technologies to monitor elders at home included red, green, blue (RGB) camera, accelerometer, passive infrared (PIR) sensor, wearable devices, and depth camera. Of them all, considering privacy concerns and easy-to-use features for elders, depth camera possibly can be a technology to be adapted at homes to unobtrusively monitor physical function of elderly living alone.The depth camera has been used to evaluate physical functions during rehabilitation and proven its efficiency. Conclusions: Therefore, physical monitoring system that is unobtrusive should be studied and developed in the future to monitor physical function of community-dwelling elderly living alone for the aging population.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2015년도 학술발표회
• /
• pp.557-557
• /
• 2015

To overcome main drawbacks of parametric models, k-nearest neighbor resampling (KNNR) is suggested for water quality analysis involving geographic information. However, with KNNR nonparametric model, Geographic information is not properly handled. In the current study, to manipulate geographic information properly, we introduce a depth function which is a novel statistical concept in the classical KNNR model for stormwater quality simulation. An application is presented for a case study of the total suspended solids throughout the entire United States. Total suspended solids concentration data of stormwater demonstrated that the proposed model significantly improves the simulation performance rather than the existing KNNR model.

• 한국생활과학회지
• /
• 제12권5호
• /
• pp.767-776
• /
• 2003

The purpose of this study was to classify side somatotypes of the trunk by analysing photographic data. Then their distribution according to the age groups was studied. The subjects were 315 females of 18 to 49 year-old. Thirty one photographic measurements were taken to each subject. The factors affecting the side somatotype of the trunk were obtained by principal component analysis, vertical size, posterior/anterior depth and neck posture. The side somatotypes of the trunk were classified into 4 types and their differences were shown by analysing photographic data. The side silhouettes of 4 types were compared with balanced type. By suggesting the canonical discriminant function with the unstandardized canonical coefficient, individual somatotype of the trunk could be discriminated from the photographic data of anterior neck height, anterior waist height, posterior waist depth, buttock height, and anterior depth at the level of back protrusion. The frequency distribution of the side somatotypes of the trunk according to the age groups could be applied for clothing construction and the rate of clothing production.

• 반도체디스플레이기술학회지
• /
• 제11권3호
• /
• pp.19-25
• /
• 2012

The accuracy of Shape From Focus (SFF) technique depends on the quality of the focus measurements which are computed through a focus measure operator. In this paper, we introduce a new approach to estimate 3D shape of an object based on Gaussian process regression. First, initial depth is estimated by applying a conventional focus measure on image sequence and maximizing it in the optical direction. In second step, input feature vectors consisting of eginvalues are computed from 3D neighborhood around the initial depth. Finally, by utilizing these features, a latent function is developed through Gaussian process regression to estimate accurate depth. The proposed approach takes advantages of the multivariate statistical features and covariance function. The proposed method is tested by using image sequences of various objects. Experimental results demonstrate the efficacy of the proposed scheme.

• 한국지능시스템학회논문지
• /
• 제25권4호
• /
• pp.412-417
• /
• 2015

Kinect sensor has two output data which are produced from red green blue (RGB) sensor and depth sensor, it is called color image and depth map, respectively. Although this device's prices are cheapest than the other devices for three-dimensional (3D) reconstruction, we need extra work for reconstruct a smooth 3D data and also have semantic meaning. It happened because the depth map, which has been produced from depth sensor usually have a coarse and empty value. Consequently, it can be make artifact and holes on the surface, when we reconstruct it to 3D directly. In this paper, we present a method for solving this problem by using implicit surface representation. The key idea for represent implicit surface is by using radial basis function (RBF) and to avoid the trivial solution that the implicit function is zero everywhere, we need to defined on-surface point and off-surface point. Based on our simulation results using captured face as an input, we can produce smooth 3D face and fill the holes on the 3D face surface, since RBF is good for interpolation and holes filling. Modified anisotropic diffusion is used to produced smoothed surface.

• 대한기계학회논문집A
• /
• 제24권4호
• /
• pp.991-1000
• /
• 2000

Previous area-based stereo matching algorithms find the disparity by first computing the sum of squared differences (SSD) between corresponding points using a rectangular window, and then searching the position of the minimum SSD within the disparity range. These algorithms generate relatively many matching errors around depth discontinuities, since the SSD function may fail to search for the minimum because of varying disparity profiles in such areas. In this paper, in order to improve the matching accuracy around the depth discontinuities, a new correlation function based on robust estimation technique is proposed for stereo matching. In addition, while previous stereo algorithms utilize a single rectangular window for computing the correlation function, the proposed matching algorithm utilizes 4-directional line masks additionally to reduce the matching errors further. It has been turned out that the proposed algorithm reduces matching errors around depth discontinuities significantly. Experimental results are presented in this paper, comparing the performance of the proposed technique with those of previous algorithms using both synthetic and real images.

• 한국화재소방학회논문지
• /
• 제30권2호
• /
• pp.62-67
• /
• 2016

본 연구에서는 워터 커튼용 노즐(Water curtian nozzle)의 액적 크기 분포(droplet size distribution)에 따라서 복사열을 감쇄하기 위한 광학 두께(optical depth)를 분석하였다. 액적 크기 분포를 측정하기 위해서 HELOS/VARIO 물 입자 측정 장치를 사용하였으며, Deirmenjian의 수정된 감마 분포 함수(modified gamma distribution function)를 적용하여 분사 특성을 정량화 하였다. 본 연구에서 사용한 워터 커튼용 노즐은 분포 상수(distribution constant) ${\alpha}=1$, ${\gamma}=5.2$의 값으로 나타났으며, 액적의 밀도 수(number density)를 고려한 분포 하중(droplet loading)과 액적 크기 분포 변화에 따라서 광학 두께에 관한 일반화된 관계식을 제시하였다. 본 연구 결과는 워터 커튼용 노즐의 설계 조건을 분석하기 위한 유용한 연구 자료가 될 것으로 사료된다.

• 대한임베디드공학회논문지
• /
• 제17권4호
• /
• pp.209-215
• /
• 2022

This paper proposes a novel approach for training an unsupervised depth estimation algorithm. The objective of unsupervised depth estimation is to estimate pixel-wise distances from camera without external supervision. While most previous works focus on model architectures, loss functions, and masking methods for considering dynamic objects, this paper focuses on the training framework to effectively use depth cue. The main loss function of unsupervised depth estimation algorithms is known as the photometric error. In this paper, we claim that direct depth cue is more effective than the photometric error. To obtain the direct depth cue, we adopt the technique of knowledge distillation which is a teacher-student learning framework. We train a teacher network based on a previous unsupervised method, and its depth predictions are utilized as pseudo labels. The pseudo labels are employed to train a student network. In experiments, our proposed algorithm shows a comparable performance with the state-of-the-art algorithm, and we demonstrate that our teacher-student framework is effective in the problem of unsupervised depth estimation.

• 한국해안해양공학회지
• /
• 제10권4호
• /
• pp.204-210
• /
• 1998

최대 엔트로피 방법을 이용하여 강한 비정규분포과정의 특성을 갖는 비선형 불규칙 파고의 확률밀도 함수를 유도하였다. 파랑의 파고가 쇄파고(또는 수심)에 의해 제한되고 파고의 1, 2차 모멘트만 주어졌을 경우, 유도된 확률밀도함수는 $H_{b}$ (쇄파고), $H_{m}$(평균파고), $H_{rms}$(파고의 제곱평균평방근)의 매개변수로 폐합형(closed form)으로 표시된다. 파고의 3차 이상의 모멘트가 주어진 경우에는 최대 엔트로피를 갖는 확률밀도함수의 매개변수를 구하기 위해서 비선형 적분 방정식 계를 Newton-Raphson 방법을 이용하여 수치적으로 구하였다. 최대 엔트로피 방법을 이용하여 유도된 파고의 확률밀도함수를 비정규분포의 특성이 강한 실측자료와 비교하였다. 실측자료는 폭풍시 중간수심과 천해에서 측정된 쇄파고에 가까운 자료로서 강한 비선형 불규칙 파랑의 특성을 지니며, 이 경우에도 유도된 확률밀도함수가 측정된 파고의 막대그래프와 잘 일치하였다. 강한 비선형 불규칙파의 특성을 갖는 파랑의 파고일 경우에도 파고의 1, 2차 모멘트만으로도 파고의 분포를 잘 나타낼 수 있었다. 최대 엔트로피 방법을 이용하여 구해진 파고의 확률분포함수는 해안구조물의 설계파를 결정하는 극치파고분포와 파고의 통계적인 특성을 추정하는데 매우 유용하게 이용될 수 있다.