• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.118-121
• /
• 2003

In the conventional boundary estimation in EIT (Electrical Impedance Tomography), the interface between anomalies and background is expressed in usual as Fourier series and the boundary is reconstructed by obtaining the Fourier coefficients. This paper proposes a method for the boundary estimation, where the boundary of anomaly is approximated as the interpolation of front points located discretely along the boundary and is imaged by tracking the points in the region of interest. In the solution to the inverse problem to estimate the front points, the multi-layer neural network is introduced. For the verification of the proposed method, numerical experiments are conducted and the results indicate a good performance.

• Annual Conference of KIPS
• /
• 2006.05a
• /
• pp.693-696
• /
• 2006

One of the most significant characteristics of JPEG 2000, the emerging still image standards, is the Region of Interest(ROI) coding. Until now, there have been many proposed ROI methods. However, all of these methods can not be applied completely in applications. In this paper, the ROI coding mechanisms in JPEG2000 is first outlined and the diversity of ROI coding methods is discussed in detail. Then a comparative selection about using a proper ROI method according to ROI applications' requirements is proposed. Finally the experimental results show that there are also several parameters that control the effectiveness of ROI coding, such as the codeblock size, ROI size, wavelet filter type, the number of wavelet decomposition levels, and ROI importance score.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.9 no.2
• /
• pp.99-106
• /
• 2001

NHTSA has been conducting biomechanical studies to reduce inujuries sustained sustained during automotive collision. Furthermore, NHTSA added the regulation to the FMVSS 201, limiting the equivalent HIC(Head Injury Criterion) value under 1000. In the presont work, a methodology was developed for the optimum design of the A-pillar trim with rib-structures. The design variables for the rib-strucrures were the transverse spacing, the longitudinal spacing, and the thickness. The required sets of the design varibles were decided based on the design of experiments. The head impact simulations were carried out using the LS-DYNA3D, and the HIC(d) values were computed using the resulrs of the head impact simulation. The objective function was constructed using the response surface methed (RSM). When the obtained optimum values were not inside the region of interest, the design proceduers were repeated by changing the region of interest. Finally, an A-pillar trim with rib-structures, which resulred in HIC(d) value under 850 for 15 mph head-trim impact, was developed.

• Journal of Magnetics
• /
• v.22 no.2
• /
• pp.234-237
• /
• 2017

This study is aimed to optimize a location of region of interest (ROI) in test bolus carotid contrast enhanced magnetic resonance angiography (CE-MRA) at 3.0T. A total of consecutive 270 patients with no cardiovascular and vessel diseases were selected. Patients underwent elliptical centric 3D CE-MRA with the test bolus technique to identify the individual arterial arrival time. Quantitative measurements were performed by drawing ROIs of $25mm^2$ and signal intensities (SI) were measured in the center of common carotid artery (CCA), internal carotid artery (ICA) and aortic arch (AA). As a result, ROIs located within AA showed a significantly clarified arterial peak and over three times increased SI, while no significant arterial peak time differences were observed compared to ROIs located within CCA. In conclusion, it was demonstrated that the aortic arch is the optimal position to locate ROI in test bolus images of the carotid CE-MRA.

• Journal of Astronomy and Space Sciences
• /
• v.28 no.4
• /
• pp.285-290
• /
• 2011

This paper presents an algorithm that can provide initial conditions for formation flying at the beginning of a region of interest to maximize scientific mission goals in the case of a tetrahedral satellite formation. The performance measure is to maximize the quality factor that affects scientific measurement performance. Several path constraints and periodicity conditions at the beginning of the region of interest are identified. The optimization problem is solved numerically using a direct transcription method. Our numerical results indicate that there exist an optimal configuration and states of a tetrahedral satellite formation. Furthermore, the initial states and algorithm presented here may be used for reconfiguration maneuvers and fuel balancing problems.

• Journal of the Korean Society for Precision Engineering
• /
• v.25 no.2
• /
• pp.131-139
• /
• 2008

This paper presents a new saliency map which is constructed by providing dynamic weights on individual features in an input image to search ROI(Region Of Interest) or FOA(Focus Of Attention). To construct a saliency map on there is no a priori information, three feature-maps are constructed first which emphasize orientation, color, and intensity of individual pixels, respectively. From feature-maps, conspicuity maps are generated by using the It's algorithm and their information quantities are measured in terms of entropy. Final saliency map is constructed by summing the conspicuity maps weighted with their individual entropies. The prominency of the proposed algorithm has been proved by showing that the ROIs detected by the proposed algorithm in ten different images are similar with those selected by one-hundred person's naked eyes.

• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06c
• /
• pp.365-368
• /
• 2011

흉부 CT 영상은 각종 흉부 질환의 진단에 널리 사용되고 있으며, 영상 분석 기술을 이용하여 암이나 다양한 형태의 종양 등의 관심 영역(region-of-interest)을 자동으로 탐지하는 기법들이 최근 많이 연구되고 있다. 본 논문에서는 흉부 CT 영상에서 연속된 여러 장의 2D 영상의 변화를 분석하여 중요 관심 영역인 노듈(nodule)을 찾는 방법을 제안한다. 인접 영상에서의 노듈의 연속성과 크기의 변화, 모양, 밝기의 특징을 분석하여 노듈을 검출하였고, 실험 결과, 상당한 정도의 정확도를 보였다. 향후 추가적인 연구를 통하여 실제 환경에서도 활용 가능할 것으로 기대된다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2011.06a
• /
• pp.355-358
• /
• 2011

본 논문에서는 이미지에서 사용자가 관심을 갖는 영역(ROI)의 내용을 나타내는 특성값과 영역의 위치를 함께 고려하여 이미지를 검색하는 방법을 제안한다. 제안한 방법은 검색 대상 이미지를 일정 크기의 블록으로 구분한 후 사용자가 선택한 다중 ROI와 가장 근접하는 특성을 가진 블록을 선택한다. 블록의 특성값은 MPEG-7의 도미넌트 컬러 기술자를 사용한다. 사용자가 선택한 블록의 특성값과 함께 블록의 위치를 측정한 후, 검색 대상 이미지의 블록들의 특성값 및 위치와 비교하여 유사도를 측정한다. 본 논문에서는 실험결과 제안한 방법이 전역 이미지 검색이나 동일한 위치의 블록만 비교하는 경우보다 다중 ROI의 내용과 위치를 함께 고려하는 방법이 다른 방법에 비해 우수한 성능을 나타냈다.

• Journal of Electrical Engineering and information Science
• /
• v.3 no.2
• /
• pp.222-229
• /
• 1998

In the circumstances we want to deal with, a transmission channel is limited and a global motion can happen by camera movement, and also there exists a region-of-interest(ROI) which is more important than background. So very low bit rate coding algorithm is required and processing of global motion must be considered. Also ROI must be reconstructed with required quality after decoding because of its importance. But the existing methods such as H.261, H.263 can not reconstruct ROIs with high quality because they do not consider the fact that ROIs are more important than background. So a new coding scheme is proposed that describes a method for encoding image sequences distinguishing bits between ROI and background. Experimental results show that the suggested algorithm performs well especially in the circumstances where background changes and the area of ROI is small enough compared with that of background.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.06a
• /
• pp.146-149
• /
• 2022

기존 RDO(Rate Distortion Optimization) 기반 압축 방식은 압축 성능에 초점을 두기 때문에 영상 내 인지 특성이 무시될 수 있다. 따라서 RoI(Region of Interest)을 기반으로 압축률을 조절하는 연구가 고안[1, 2, 3, 4] 되었으며, HVS(Human Visual System) 관점에서 영상 내 중요한 부분에 대해 더 높은 품질로 영상을 압축하는 연구가 대부분이다. 최근 인공지능 기술이 발전함에 따라 지능형 영상 분석에 대한 수요가 증가하고 있으며, 이에 따라 머신 비전을 위한 영상 부호화 및 효율적인 전송에 대한 필요성이 대두되고 있다. 본 논문에서는 VVC(Versatile Video Coding)의 dQP(delta Quantization Parameter)를 활용하여 RoI(Region of Interest) 기반압축 방법을 제안하고, 두가지의 RoI 추출 방식을 소개한다. Detectron2 Faster R-CNN X101-FPN [5]의 첫번째 탐지기를 통해 후보 영역 기반 RoI 을 추출하고, 두번째 탐지기를 통해 객체 기반 RoI 을 추출하여, 영상 내 객체 부분과 비객체 부분으로 나누어 서로 다른 압축률로 압축을 수행하였으며, 이에 따른 성능을 비교하고자 한다.