• 한국측량학회지
• /
• 제35권2호
• /
• pp.75-80
• /
• 2017

Recently, there has been growing interest in spatial data that combines information and communication technology with smart cities. The high-precision LiDAR (Light Dectection and Ranging) equipment is mainly used to collect three-dimensional spatial data, and the acquired data is also used to model geographic features and to manage plant construction and cultural heritages which require precision. The LiDAR equipment can collect precise data, but also has limitations because they are expensive and take long time to collect data. On the other hand, in the field of computer vision, research is being conducted on the methods of acquiring image data and performing 3D reconstruction based on image data without expensive equipment. Thus, precise 3D spatial data can be constructed efficiently by collecting and processing image data using CCTVs which are installed as infrastructure facilities in smart cities. However, this method can have an accuracy problem compared to the existing equipment. In this study, experiments were conducted and the results were analyzed to increase the number of extracted matching points by applying the feature-based method and the area-based method in order to improve the precision of 3D spatial data built with image data acquired from stereo CCTVs. For techniques to extract matching points, SIFT algorithm and PATCH algorithm were used. If precise 3D reconstruction is possible using the image data from stereo CCTVs, it will be possible to collect 3D spatial data with low-cost equipment and to collect and build data in real time because image data can be easily acquired through the Web from smart-phones and drones.

• 정보보호학회논문지
• /
• 제31권5호
• /
• pp.987-999
• /
• 2021

최근 데이터로 인한 개인정보 침해로 인해 연합학습이 이슈화되고 있다. 연합학습은 학습데이터를 요구하지 않기 때문에 프라이버시 침해로부터 안전하다. 이로 인해 분산된 디바이스, 데이터를 활용하여 효율을 내기 위한 응용 방법에 대한 연구들이 진행되고 있다. 그러나 연합학습과정에서 전송되는 그래디언트로부터 학습데이터를 복원하는 재복원공격에 대한 연구가 진행됨에 따라 더는 연합학습도 안전하다고 볼 수 없다. 본 논문은 다양한 데이터 상황에서 데이터 복원 공격이 얼마나 잘되는지 수치적, 시각적으로 확인하는 것이다. 데이터가 1개만 존재할 때부터 크게는 클래스 안에 데이터가 여러 개 분포해 있을 때로 나누어 재복원공격이 얼마나 되는지 확인을 위해 MSE, LOSS, PSNR, SSIM인 평가지표로 MNIST 데이터를 활용해 수치로 확인한다. 알게 된 사실로 클래스와 데이터가 많아질수록 MSE, LOSS,이 높아지고 PSNR, SSIM이 낮아져 복원성능이 떨어지지만 몇 개의 복원된 이미지로 충분히 프라이버시 침해가 가능하다는 것을 확인할 수 있다.

• 대한기관식도과학회지
• /
• 제16권2호
• /
• pp.131-137
• /
• 2010

Background: Montgomery T-tube is widely used to maintain airway in many cases. Market-available tubes are not always fit to the trachea of each patient and need some modification such as trimming. Complications do happen in prolonged use like tracheostomy tubes. To overcome above limitations, we designed custom-made T-tube using CT data with the aid of 3D reconstruction software. Material and Method: Boundaries were extracted from neck CT data of normal person and processed by surface rendering methods. Real laryngotracheal model and tracheal inner surface-mimicking tube model were made with plaster and rubber. The main tube was designed by accumulation of circles or simple closed curves made from boundaries. Stomal tube was made by accumulation of squares due to limitation of software. Measurement data of tracheal lumen were used to custom-made T-tubes. Tracheal lumen residing portion (vertical limb) was made like circular cylinder or simple closed curved cylinder. Stomal portion (horizontal limb) was designed like square cylinder. Results: Custom made T-tube with cylindric vertical limb and horizontal limb of square cylinder was designed. Conclusion: CT data was helpful in making custom made T-tube with 3D reconstruction technique. If suitable materials are available, commercial T-tube can be printed out from 3D printers.

• 한국음향학회지
• /
• 제20권6호
• /
• pp.9-16
• /
• 2001

본 논문에서는 음파를 이용하여 덕트 내 길이 방향으로의 불균일 단면적을 역문제적으로 측정하는 방법에 대해서 연구하였다. 음파를 사사용하여 덕트 단면적을 구하는 이론 및 실험방법 등에 대해서 많은 연구가 되어왔으나, 본 연구에서는 덕트 내 충격응답을 구하고 이를 재구성 알고리즘에 대입하여 덕트 내 단면적을 구하는 방법을 채택하였다. 충격 가진을 통하여 덕트 내 충격응답을 구하는 기존 방법의 문제점을 살펴보았고, 광대역 가진 방법을 새로 제안하였다. 실험 및 이론적 고찰을 통하여 새로운 방법이 기존의 방법보다 면적 재구성 오차가 적음을 보였다. 덕트 단면적을 재구성 할 때의 오차 원인과 불규칙 잡음에 의한 오차범위를 파악하기 위하여 오차해석을 수행하여 음파를 이용한 면적 재구성 방법의 적용범위 및 대상을 명확히 하였다.

• 대한산업공학회지
• /
• 제38권4호
• /
• pp.276-284
• /
• 2012

Classification algorithms generally assume that the data is complete. However, missing values are common in real data sets due to various reasons. In this paper, we propose to use locally linear reconstruction (LLR) for missing value imputation to improve the classification performance when missing values exist. We first investigate how much missing values degenerate the classification performance with regard to various missing ratios. Then, we compare the proposed missing value imputation (LLR) with three well-known single imputation methods over three different classifiers using eight data sets. The experimental results showed that (1) any imputation methods, although some of them are very simple, helped to improve the classification accuracy; (2) among the imputation methods, the proposed LLR imputation was the most effective over all missing ratios, and (3) when the missing ratio is relatively high, LLR was outstanding and its classification accuracy was as high as the classification accuracy derived from the compete data set.

• 한국의학물리학회:학술대회논문집
• /
• 한국의학물리학회 2002년도 Proceedings
• /
• pp.382-384
• /
• 2002

Filtered-Back-Projection technique is used in X-ray CT image reconstruction. This requires X-ray transmission data from all directions. As the transverse cross-section of the body is approximately 50 cm, transmitted X-rays in this direction are strongly attenuated. If X-ray transmission data in this direction is avoided, exposure to the patients seems to be reduced one 20th of usual value. Some alternative method has to be found for clinically sufficient image quality. New methods are under development and tentative results are reported that utilizes the principle of superposition.

• International Journal of Control, Automation, and Systems
• /
• 제3권2호
• /
• pp.211-216
• /
• 2005

In electrical impedance tomography (EIT), various image reconstruction algorithms have been used in order to compute the internal resistivity distribution of the unknown object with its electric potential data at the boundary. Mathematically, the EIT image reconstruction algorithm is a nonlinear ill-posed inverse problem. This paper presents a simulated annealing technique as a statistical reconstruction algorithm for the solution of the static EIT inverse problem. Computer simulations with 32 channels synthetic data show that the spatial resolution of reconstructed images by the proposed scheme is improved as compared to that of the mNR algorithm at the expense of increased computational burden.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.159-164
• /
• 2004

In electrical impedance tomography (EIT), various image reconstruction algorithms have been used in order to compute the internal resistivity distribution of the unknown object with its electric potential data at the boundary. Mathematically the EIT image reconstruction algorithm is a nonlinear ill-posed inverse problem. This paper presents a simultaneous perturbation method as an image reconstruction algorithm for the solution of the static EIT inverse problem. Computer simulations with the 32 channels synthetic data show that the spatial resolution of reconstructed images by the proposed scheme is improved as compared to that of the mNR algorithm at the expense of increased computational burden.

• 한국원자력학회:학술대회논문집
• /
• 한국원자력학회 1998년도 춘계학술발표회논문집(2)
• /
• pp.705-710
• /
• 1998

We describe a multigrid wavelet-based natural pixel (WNP) method for image reconstruction in emission computed tomography (ECT). The ECT is used to identify the tagged radioactive material's position in the body for detection of abnormal tissue such as tumor or cancer, as in SPECT and PET. With ECT methodology in parallel beam mode, we formulate a matrix-based reconstruction method for radionuclide sources in the human body. The resulting matrix for a practical problem is very large and nearly singular. To overcome this ill-conditioning, wavelet transform is considered in this study. Wavelets have inherent de-noising and multiscale resolution properties. Therefore, the multigrid wavelet-based natural pixel (WNP) method is very efficient to reconstruct image from projection data that is noisy and incomplete. We test this multigrid wavelet natural pixel (WNP) reconstruction method with the MCNP generated projection data for diagnosis of the simulated cancerous tumor.

• 한국분무공학회지
• /
• 제7권4호
• /
• pp.9-15
• /
• 2002

Convolution Fourier transformation tomographically reconstructs the spatially resolved spray injection rate from direct measuring cells. Asymmetric sprays generated from a twin-hole air shroud injector are tested with 12 equiangular projections of measurements. For each projection angle, line of sight integrated injection rate was measured at 35 positions with equal spacing measuring cells of 3 mm in width, 100 mm in length, 55 mm in depth and 0.5 mm thickness of separating wall. Interpolated data between the projection angles effectively increase the number of projections, which significantly enhances the signal-to-noise level in the reconstructed data. This modified convolution Fourier transformation scheme predicts well the structure of asymmetric sprays. Comparative study has been made between sprays with and without air shrouding. Tomograhpic reconstruction of injection rate from direct measuring cells obtained can be used to estimate the accuracy of volume fraction of spray from the LDPA tomographic reconstruction.