• Proceedings of the KSRS Conference
• /
• v.1
• /
• pp.260-262
• /
• 2006

One of future remote sensing techniques for transportation application is vehicle detection from the space, which could be the basis of measuring traffic volume and recognizing traffic condition in the future. This paper introduces an approach to vehicle detection using image object segmentation approach. The object-oriented image processing is particularly beneficial to high-resolution image classification of urban area, which suffers from noisy components in general. The project site was Dae-Jeon metropolitan area and a set of true color aerial images at 10cm resolution was used for the test. Authors investigated a variety of parameters such as scale, color, and shape and produced a customized solution for vehicle detection, which is based on a knowledge-based hierarchical model in the environment of eCognition. The highest tumbling block of the vehicle detection in the given data sets was to discriminate vehicles in dark color from new black asphalt pavement. Except for the cases, the overall accuracy was over 90%.

• Nuclear Engineering and Technology
• /
• v.53 no.7
• /
• 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.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.11a
• /
• pp.119-121
• /
• 2019

부가적 백색 잡음 모델(additive white Gaussian noise, AWGN에서 학습된 깊은 신경만 (deep neural networks)을 이용한 잡음 제거기는 제거하려는 잡음이 AWGN인 경우에는 뛰어난 성능을 보이지만 실제 카메라 잡음에 대해서 잡음 제거를 시도하였을 때는 성능이 크게 저하된다. 본 논문은 U-Net 구조의 깊은 인공신경망 모델에 residual block을 결합함으로서 실제 카메라 영상에서 기존 알고리즘보다 뛰어난 성능을 지니는 신경망을 제안하다. 제안한 방법을 통해 Darmstadt Noise Dataset에서 PSNR과 SSIM 모두 CBDNet 대비 향상됨을 확인하였다.

• Proceedings of the IEEK Conference
• /
• 2001.09a
• /
• pp.81-84
• /
• 2001

We propose a novel noise littering method based on adaptive windowing. To restore a noisy signal adaptive filtering methods have been widely researched and used. However, conventional adaptive filtering methods have a trade-off between noise suppression and edge preservation since they adopt fixed size filters. In this paper applying the adaptive windowing concept to adaptive filtering, we overcome the trade-off, The filter size is adaptively selected depending on signal statistics. The visual results of the signal and image restorations convincingly show the superior preservation of edge and detail and suppression of noise for the proposed adaptive windowed adaptive filter compared with conventional methods.

• Phonetics and Speech Sciences
• /
• v.3 no.2
• /
• pp.65-70
• /
• 2011

Recently, audio-visual speech recognition (AVSR) has been studied to cope with noise problems in speech recognition. In this paper we propose a novel method of deciding weighting factors for audio-visual information fusion. We adopt the particle swarm optimization (PSO) to weighting factor determination. The AVSR experiments show that PSO-based normalized confidence measures (NCM) improve the rejection performance of mis-recognized words by 33%.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.1456-1459
• /
• 2005

To compensate the drawbacks, a new localization method that estimates the global position of the mobile robot by using a camera set on ceiling in the corridor is proposed. This scheme is not a relative localization, which decreases the position error through algorithms with noisy sensor data. The effectiveness of the proposed localization scheme is demonstrated by the experiments.

• Proceedings of the IEEK Conference
• /
• 2008.06a
• /
• pp.1153-1154
• /
• 2008

본 논문에서는 ELA(Edge Line based Average) 알고리즘이 잡음 영상에서 IPC할 때 생기는 문제점을 개선하는 알고리즘을 제안한다. 먼저 잡음을 제거하는 필터링과 동시에 잡음이 없는 원화소의 크기와 잡음의 크기를 추정한다. 이에 따라 잡음의 크기를 고려하여 ELA 방법과 수직보간 방법에 가중치를 주어 보간값을 구한다. 이 후 잡음이 존재할 경우 포스트 필터링(Post Filtering)을 거쳐 잔재해 있는 잡음을 제거해준다. 실험결과 제안하는 알고리즘이 기존 ELA 알고리즘들 보다도 향상된 결과를 보인다.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1996.11a
• /
• pp.485-489
• /
• 1996

In this paper, an automatic gear inspection system has been developed using the computer aided vision system. Image processing and data analysis algorithms for gear inspection have been investigated and were shown to perform quickly with high accuracy. As a result, dimensions of a gear can be measured upto few micrometer size in real time. In addition, the system can be applied to a practical manufacturing process even under noisy conditions.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2012.11a
• /
• pp.105-107
• /
• 2012

본 논문에서는 영상의 잡음제거에 주로 적용되어 왔던 양방향 필터(bilateral filter) 기법을 개량하여 에지 정보를 더 잘 살리게 하는 방법을 제안한다. 우선, 잡음 영상에서 에지의 위치를 파악하기 위한 방법으로, 이웃픽셀값들의 분산을 이용하는 방법을 제안한다. 또한 에지와의 거리를 기반으로 필터의 계수를 조정하는 방법을 제시한다. 따라서 제안하는 알고리즘을 적용하여 잡음 제거를 수행하면 기존의 잡음 제거율을 유지하면서도 에지정보를 보존한 결과를 얻을 수 있다.

• ETRI Journal
• /
• v.11 no.1
• /
• pp.41-58
• /
• 1989

Neural network연구는 뇌로부터 얻은 아이디어를 공학적으로 응용하려는 생각을 바탕으로 뇌의 구조와 유사한 mechanism에 의한 정보처리장치의 기초가 되는 정보처리의 양식 확립과 함께 그 정보처리 양식을 구체적으로 각각의 정보처리 문제에 응용하기 위한 응용기술을 연구하는 것이다. Neural network의 계산 기능적 특성은 병렬처리, 학습 및 noisy한 정보의 효율적처리 등으로써 특히 pattern인식 문제에 효율적으로 응용될 수 있다. 본 논문에서는 neural network의 역사적 고찰과 기존의 model들을 살펴보고 새로운 계산 구조와 계산 방식을 가진 neural network의 응용분야를 살펴 봄으로써 기존의 AI 기법으로 해결하기 어려운 pattern recognition(image,문자,speech등), robot vision 및 control 등 여러가지 문제에 효율적으로 적용가능함과 neural network의 앞으로의 전망에 대하여 기술한다.