• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2015.11a
• /
• pp.132-133
• /
• 2015

본 논문에서는 블랙박스 카메라에 적합한 기하왜곡 보정 기법을 제안한다. 제안하는 기법은 정교한 카메라 보정 기법 없이 카메라 중심점을 지나는 직선주행 평균 영상에 나타나는 소실점과 카메라 중심점의 기하학적 관계와 기하왜곡에 의해 왜곡된 소실선을 특징으로 한 향상된 Hough 기법을 이용하여 기하왜곡된 블랙박스 카메라 영상에 대한 단일 기하왜곡 매개변수 모델을 추정한다. 제안하는 기법은 각각의 기하왜곡 매개변수 후보들에 의해 보정된 영상의 소실선들에 대한 에지픽셀들의 향상된 Hough 기법의 투표과정을 통한 최적의 후보선출 과정, 선출된 기하왜곡 매개변수를 초기변수로 최다 투표된 소실선들에 대한 에너지함수 최적화 과정, 최적의 기하왜곡 매개변수를 추정하여 왜곡된 블랙박스 카메라 영상보정 과정으로 이뤄진다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2016.11a
• /
• pp.21-22
• /
• 2016

본 논문에서는 동영상에서 객체를 자동 검출하는 기법을 제안한다. 제안하는 기법은 정지 영상에서 객체를 검출하는 기법과 동영상에서 객체를 추적하는 기법을 동시에 수행하여 동영상에서 객체를 검출한다. 매 프레임 검출기는 학습된 종류의 객체들을 검출하고 추적기는 이전 프레임에서 검출되었던 객체를 추적한다. 검출기가 검출한 결과와 추적기가 추적한 결과를 매칭하고, 겹치는 결과와 그렇지 않은 결과에 대해 각각 다른 검사를 수행하여 신뢰도 있는 결과를 도출한다. 실험 결과를 통해 제안하는 기법이 기존 검출 기법에 비해 우수한 성능을 보임을 확인한다.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_4
• /
• pp.1945-1953
• /
• 2022

Korea Aerospace Research Institute produces mosaic images of the Korean Peninsula every year to promote the use of satellite images and provides them to users in the public sector. However, since the pan-sharpening and color balancing methodologies are applied during the mosaic image processing, the original spectral information is distorted. In addition, there is a limit to analyze using mosaic images as mosaic images provide only Red, Green and Blue bands excluding Near Infrared (NIR) band. Therefore, in order to compensate for these limitations, this study applied the Principal Component Analysis (PCA) technique and indices extracted from R, G, B bands together for image classification and compared the classification results. As a result of the analysis, the accuracy of the mosaic image classification result was about 67.51%, while the accuracy of the image classification result using both PCA and RGB indices was about 75.86%, confirming that the accuracy of the image classification result can be improved. As a result of comparing the PCA and the RGB indices, the accuracy of the image classification result was about 64.10% and 74.05% respectively. Through this, it was confirmed that the classification accuracy using the RGB indices was higher among the two techniques, and implications were derived that it was important to use high quality reference or supplementary data. In the future, additional indices and techniques are needed to improve the classification and analysis results of mosaic images, and related research is expected to increase the utilization of images that provide only R, G, B or limited spectral information.

• Spatial Information Research
• /
• v.13 no.4 s.35
• /
• pp.345-354
• /
• 2005

Super resolution image reconstruction method refers to image processing algorithms that produce a high resolution(HR) image from observed several low resolution(LR) images of the same scene. This method has proven to be useful in many practical cases where multiple frames of the same scene can be obtained, such as satellite imaging, video surveillance, video enhancement and restoration, digital mosaicking, and medical imaging. In this paper, we applied the super resolution reconstruction method in spatial domain to video sequences. Test images are adjacently sampled images from continuous video sequences and are overlapped at high rate. We constructed the observation model between the HR images and LR images applied with the Maximum A Posteriori(MAP) reconstruction method which is one of the major methods in the super resolution grid construction. Based on the MAP method, we reconstructed high resolution images from low resolution images and compared the results with those from other known interpolation methods.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.10 no.1
• /
• pp.95-101
• /
• 2017

In natural images, there is generally locality, and the values of adjacent pixels are similar. It is possible to estimate the curved surface characteristics of the original image using adjacent pixels having similar pixel values. In this paper, after precisely estimating the characteristics of the curved surface existing in the image, interpolation values are obtained so as to faithfully reflect the estimated characteristics of the curved surface, We propose an effective image enlarging method that generates an enlarged image using the obtained interpolation values. The image enlarged by the proposed method maintains the curved surface characteristics of the original image, and thus the image quality of the enlarged image is improved. Experimental results show that the image quality of the proposed method is superior to that of the conventional techniques.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.6
• /
• pp.1296-1300
• /
• 2015

Ganglion cysts are commonly observed cystic tumor in association with the joints and tendons of the appendicular skeleton. In this paper we propose a method to extract ganglion cysts from ultrasound images with intelligent image processing. The method consists of fuzzy stretching preprocessing to enhance the contrast between related organs and 8-directional contour tracking to model the boundaries of the cysts and labelling procedure to compute the size of cysts. In experiment, we verified that the proposed method extracts ganglion cysts accurately from ultrasound images.

• The Journal of Korean Association of Computer Education
• /
• v.11 no.5
• /
• pp.57-66
• /
• 2008

An adaptive optimization of parametric cubic convolution for image interpolation is derived in this paper. The proposed technique is based on optimizing the standard cubic convolution interpolation formula at each interpolated pixel. Conventional parametric cubic convolution methods use a fixed parameter in an image, so properties of each pixel cannot be incorporated into the interpolation. The proposed method optimizes the interpolation kernel by obtaining parameters adaptively on each pixel. A new cost function is introduced to reflect frequency properties of the original data. The proposed technique produces noticeably sharper edges than traditional techniques and exhibits an average PSNR improvement of traditional techniques.

• Investigative Magnetic Resonance Imaging
• /
• v.13 no.1
• /
• pp.9-14
• /
• 2009

T1-, and T2-weighted imagings and FLAIR (fluid attenuated inversion recovery) imaging are fundamental imaging methods in the brain. T1-weighted imaging is a spin-echo sequence with short TR and short TE and produces the tissue contrast by different T1 relaxation times. In other words, short TR maximizes the difference of the longituidinal magnetization recovery between the tissues. T2-weighted imaging is a spin-echo sequence with long TR and long TE and produces the tissue contrast by different T2 relaxation times. Long TE maximizes the difference of the transverse magnetization decay between the tissues. FLAIR is an inversion recovery sequence using 180 degree inversion pulse. 2500 msec of inversion time is applied to suppress the CSF signal.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2015.05a
• /
• pp.79-79
• /
• 2015

현재 홍수 시 유량조사에 가장 많이 사용하고 있는 부자법은 측정 인력, 측정비용 및 위험성이 높다는 단점이 있다. 또한 교량에서 부자를 투하하고 측면에서 부자의 이동을 추적하기 때문에 평면상의 이동에 대한 정보를 얻기 어렵다는 한계가 있다. 이에 김서준 등(2014)은 PTV 기법을 이용한 부자 추적 알고리즘을 개발하였으나 부자가 회전하거나 물속에 잠기는 부분이 변화하여 수면 위로 확인되는 부자의 길이가 변할 경우 추적이 어렵다는 한계가 있었다. 이를 개선하고자 본 연구에서는 Template Match 알고리즘과 색상 기반 영상 처리 기법을 이용한 목표물 인식 방법인 Camshift 기법을 적용하여 부자를 추적할 수 있는 알고리즘을 개발하였다. Template Match 알고리즘의 경우는 입자가 많을수록 추적을 잘한다는 장점이 있지만 회전 및 변형에 취약하다는 단점이 있고, Camshift 영상 처리 기법의 경우 다수의 추적자가 존재할 경우 추적에 어려움이 있으나 추적자의 회전과 변형을 정확하게 추적할 수 있다는 장점이 있다. 따라서 Template Match 알고리즘을 이용하여 이동 예상영역을 결정하고 Camshift 영상 처리 기법으로 추적을 하게되면 두 방법의 장점을 모두 살릴 수 있다. Camshift 영상 처리 기법을 실제 부자 추적에 적용해 본 결과 부자의 회전 및 변형에도 정확하게 추적할 수 있는 것을 확인하였다. 향후 부자법을 이용한 유량 조사에 본 연구에서 개발한 알고리즘을 적용한다면 현장에서 동영상 촬영만 하면 되기 때문에 측정 인원을 최소화 할 수 있어 매우 경제적이고, 홍수 시 위험성도 감소할 것으로 기대된다.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.29 no.6
• /
• pp.577-582
• /
• 2011

In remote sensing, spatial/spectral distortions are recognized as two of the main problems in the pansharpening algorithm. Most pansharpening methodologies show a tendency to distort spatial information from objects such as buildings and vehicles because there are local spatial dissimilarities among multispectral bands in Worldview-2 satellite imagery. In this paper, we propose a new pansharpening algorithm in order to minimize the effects of the local displacement of spatial information in the pansharpening process. In experiments using Worldview-2 images, our method provided better spectral and spatial quality than pre-existing pansharpening methods.