• 한국통신학회논문지
• /
• 제23권4호
• /
• pp.787-795
• /
• 1998

본 논문에서는 이동물체의 움직임 추정을 위한 옵티컬 플로우(Optical Flow: OF)의 계산에 필요한 그레디언트(Gradient)의 연산 속도를 개선하고. OF와 에지의 논리연산에 의하여 이동물체의 움직임 정계를 추정할 수 있으며 잡음이 있는 영상에서도 이동물체를 추정할 수 있는 방법을 제안한다. 이것은 저레벨에서 OF와 에지를 논리 연산하므로써 불확실한 배경에서 이동물체를 식별하고 물체를 추적하는 방법으로 기존의 이동물체 추정 알고리즘을 간소화시킨 것이다. 또한, 그레디언트 연산속도를 개선한 본 논문의 방법 I과 방법 II를 이용하여 그레이레 벨값의 변화가 있는 영상에 대하여 시뮬레이션을 행하였다. 그레디언트 연산에 걸리는 전체적인 시간을 평균한 결과 방법 I 은 기존의 방법보다 12% 연산속도가 개선되었고, 방법 II는 37% 연산속도가 개선되었다.

• 한국정보통신학회논문지
• /
• 제5권2호
• /
• pp.343-348
• /
• 2001

본 논문에서는 국부적인 미디안(median)규칙에 파라 움직이는 셀룰러 오토마타를 이용해 영상에 대한 사전 지식이 필요 없는 영상의 잡음제거 알고리즘을 제안한다. 각 규칙은 원영상이 가지는 특징의 손실없이 국부적으로 자기값(gray level)을 증감시킨다. 이러한 셀룰러 오토마타는 순차적이고 병렬적인 움직임을 가지며, 이 움직임은 Lyapunov functional을 만족하는 함수로 표현된다. 따라서 본 셀룰러 오토마타를 이용한 영상의 잡음제거 알고리즘은 매우 빠른 속도로 수렴하고, 안정적인 결과를 나타낸다. 실험을 통해 본 방법의 유효성을 확인한다.

• 한국통신학회논문지
• /
• 제21권7호
• /
• pp.1696-1705
• /
• 1996

중앙값여파기의 일반화된 형태인 스택여파기의 이론을 써서 잡음으로 왜곡된 영상에서의 윤곽선 검출기를 연구하였다. 이 논문에서 제안된 추정값 차이기법(difference of estimates:DoE)은 충격성 잡음의 환경에서 매우 효율적인 기법으로 기존의 형태학적 접근 방법을 개선하였다고 할 수 있다. 이 기법에서는 잡음이 있는 영상에 스택필터를 사용하여 잡음이 없는 원영상의 불림 영상(diated version)과 녹임 영상(eroded version)을 최적으로 추정한다. 그 결과로 얻어진 추정 영상의 차이에 적절한 문턱값 연산을 적용하여 윤곽선을 얻을 수 있다. 이 기법을 써서 얻은 결과는 가산상 정규 잡음의 경우에는 Canny의 기법을 이용하여 얻은 결과와 상응하는 성능을 갖고, 충격성 잡음의 경우에는 훨씬 좋은 성능을 보여준다.

• Nuclear Engineering and Technology
• /
• 제53권7호
• /
• pp.2371-2376
• /
• 2021

As the γ-ray energy increases, a reconstructed image becomes noisy and blurred due to the penetration of the γ-ray through the coded mask. Therefore, the thickness of the coded mask was increased for high energy regions, resulting in severely decreased the performance of the detection efficiency due to self-collimation by the mask. In order to overcome the limitation, a modified uniformly redundant array γ-ray imaging system using dual anti-mask method was developed, and its performance was compared and evaluated in high-energy radiation region. In the dual anti-mask method, the two shadow images, including the subtraction of background events, can simultaneously contribute to the reconstructed image. Moreover, the reconstructed images using each shadow image were integrated using a hybrid update maximum likelihood expectation maximization (h-MLEM). Using the quantitative evaluation method, the performance of the dual anti-mask method was compared with the previously developed collimation methods. As the shadow image which was subtracted the background events leads to a higher-quality reconstructed image, the reconstructed image of the dual anti-mask method showed high performance among the three collimation methods. Finally, the quantitative evaluation method proves that the performance of the dual anti-mask method was better than that of the previously reconstruction methods.

• Nuclear Engineering and Technology
• /
• 제51권3호
• /
• pp.719-722
• /
• 2019

Gamma-ray images generally suffer from a lot of noise because of low photon detection in the gamma camera system. The purpose of this study is to improve the image quality in gamma-ray images using a gamma camera system with a fast nonlocal means (FNLM) noise reduction algorithm with an acceleration function. The designed FNLM algorithm is based on local region considerations, including the Euclidean distance in the gamma-ray image and use of the encoded information. To evaluate the noise characteristics, the normalized noise power spectrum (NNPS), contrast-to-noise ratio (CNR), and coefficient of variation (COV) were used. According to the NNPS result, the lowest values can be obtained using the FNLM noise reduction algorithm. In addition, when the conventional methods and the FNLM noise reduction algorithm were compared, the average CNR and COV using the proposed algorithm were approximately 2.23 and 7.95 times better than those of the noisy image, respectively. In particular, the image-processing time of the FNLM noise reduction algorithm can achieve the fastest time compared with conventional noise reduction methods. The results of the image qualities related to noise characteristics demonstrated the superiority of the proposed FNLM noise reduction algorithm in a gamma camera system.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2022년도 춘계학술대회
• /
• pp.104-107
• /
• 2022

오토인코더 딥러닝 모델은 이상 데이터도 정상 데이터로 복원하는 능력이 우수하여 이상탐지에 적절하지 못한 경우가 발생한다. 그리고 데이터의 일부를 가린(마스킹) 후 가린 데이터를 복원하는 방식인 Inpainting 방식은 잡음이 많은 이미지에 대해서는 복원능력이 떨어지는 문제점을 가지고 있다. 본 논문에서는 MLP-Mixer 모델을 수정·개선하여 이미지를 일정 비율로 마스킹하고 마스킹된 이미지의 압축된 정보를 모델에 전달해 이미지를 재구성하는 방식을 사용하였다. MVTec AD 데이터 셋의 정상 데이터로 학습한 모델을 구축한 뒤, 정상과 이상 이미지를 각각 입력하여 재구성 오류를 구하고 이를 통해 이상탐지를 수행하였다. 성능 평가 결과 제안된 방식이 기존의 방식에 비해 이상탐지 성능이 우수한 것으로 나타났다.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2021년도 추계학술발표대회
• /
• pp.700-703
• /
• 2021

Infrared cameras are widely used in recent research for automatic monitoring the abnormal behaviors of the pig. However, when deployed in real pig farms, infrared cameras always get polluted due to the harsh environment of pig farms which negatively affects the performance of pig monitoring. In this paper, we propose a real-time noise-robust infrared camera-based pig automatic monitoring system to improve the robustness of pigs' automatic monitoring in real pig farms. The proposed system first uses a preprocessor with a U-Net architecture that was trained as a GAN generator to transform the noisy images into clean images, then uses a YOLOv5-based detector to detect pigs. The experimental results show that with adding the preprocessing step, the average pig detection precision improved greatly from 0.639 to 0.759.

• Journal of information and communication convergence engineering
• /
• 제21권4호
• /
• pp.322-328
• /
• 2023

The number of senior citizens with large bowel obstruction is steadily growing in Korea. Plain radiography was used to examine the severity and treatment of this phenomenon. To avoid examiner subjectivity in radiography readings, we propose an automatic segmentation method to identify fluid-filled areas indicative of large bowel obstruction. Our proposed method applies the Hough transform to locate suspicious areas successfully and applies the possibilistic fuzzy c-means unsupervised learning algorithm to form the target area in a noisy environment. In an experiment with 104 real-world large-bowel obstruction radiographs, the proposed method successfully identified all suspicious areas in 73 of 104 input images and partially identified the target area in another 21 images. Additionally, the proposed method shows a true-positive rate of over 91% and false-positive rate of less than 3% for pixel-level area formation. These performance evaluation statistics are significantly better than those of the possibilistic c-means and fuzzy c-means-based strategies; thus, this hybrid strategy of automatic segmentation of large bowel suspicious areas is successful and might be feasible for real-world use.

• Journal of Computing Science and Engineering
• /
• 제2권1호
• /
• pp.98-108
• /
• 2008

Terrain reconstruction from images is an ill-posed, yet commonly desired Structure from Motion task when compositing visual effects into live-action photography. These surfaces are required for choreography of a scene, casting physically accurate shadows of CG elements, and occlusions. We present a novel framework for generating the geometry of landscapes from extremely noisy point cloud datasets obtained via limited resolution techniques, particularly optical flow based vision algorithms applied to live-action video plates. Our contribution is a new statistical approach to remove erroneous tracks ('outliers') by employing a unique combination of well established techniques-including Gaussian Mixture Models (GMMs) for robust parameter estimation and Radial Basis Functions (REFs) for scattered data interpolation-to exploit the natural constraints of this problem. Our algorithm offsets the tremendously laborious task of modeling these landscapes by hand, automatically generating a visually consistent, camera position dependent, thin-shell surface mesh within seconds for a typical tracking shot.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2001년도 제14회 신호처리 합동 학술대회 논문집
• /
• pp.747-750
• /
• 2001

The paper presents an algorithm for estimating the variance of additive zero mean Gaussian noise in an image. The algorithm uses the wavelet transform which is a good tool for energy compaction. The algorithm consists of three steps. At first, high frequency components, wavelet coefficients in HH band, are generated from a noisy image by the wavelet transform. In a second step, high frequency components which are out of the noise range ate eliminated. Finally, if the image has many components eliminated in the previous step, then its noise estimated value is reduced. Experimental results show that the wavelet filter has better performance than the other high pass filters such as a Laplacian filter, residual from a median filter, residual from a mean filter, and a difference operator. In various images, the algorithm reduces 50% of estimated error on an average.