• Journal of the Korea Society of Computer and Information
• /
• v.26 no.1
• /
• pp.155-161
• /
• 2021

Recently, researches for military purposes such as precision tracking and mission completion using UAVs have been actively conducted. In particular, if the posture information of the leading UAV is estimated and the mission UAV uses this information to follow in stealth and complete its mission, the speed of the posture information estimation of the guide UAV must be processed in real time. Until recently, research has been conducted to accurately estimate the posture information of the leading UAV using image processing and Kalman filters, but there has been a problem in processing speed due to the sequential processing of the processing process. Therefore, in this study we propose a way to improve processing speed by applying methods that the image processing area is limited to the ROI area including the object, not the entire area, and the continuous processing is distributed to OpenMP-based multi-threads and processed in parallel with thread synchronization to estimate attitude information. Based on the experimental results, it was confirmed that real-time processing is possible by improving the processing speed by more than 45% compared to the basic processing, and thus the possibility of completing the mission can be increased by improving the tracking and estimating speed of the mission UAV.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.12
• /
• pp.49-57
• /
• 2011

Extraction of regions of interest (ROIs) is the first and important step for the applications in computer vision and affects the rest of the application process. However, ROI extraction can be easily affected by the environment such as illumination, camera, etc. Many applications adopt problem-specific knowledge and/or post-processing to correct the error occurred in ROI extraction. In this paper, proposed is a robust framework that could overcome the environmental change and is independent from the rest of the process. The proposed framework uses a differential image and a color distribution to extract ROIs. The color distribution can be learned on-line, which make the framework to be robust to environmental change. Even more, the components of the framework are independent each other, which makes the framework flexible and extensible. The usefulness of the proposed framework is demonstrated with the application of hand region extraction in an image sequence.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.11
• /
• pp.1437-1444
• /
• 2020

With the development of computer vision systems, many advances have been made in the fields of surveillance, biometrics, medical imaging, and autonomous driving. In the field of autonomous driving, in particular, the object detection technique using deep learning are widely used, and the paved road detection is a particularly crucial problem. Unlike the ROI detection algorithm used in general object detection, the structure of paved road in the image is heterogeneous, so the ROI-based object recognition architecture is not available. In this paper, we propose a deep neural network architecture for atypical paved road detection using Semantic segmentation network. In addition, we introduce the multi-scale semantic segmentation network, which is a network architecture specialized to the paved road detection. We demonstrate that the performance is significantly improved by the proposed method.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.54 no.8
• /
• pp.99-106
• /
• 2017

Electrical impedance tomography is a nondestructive imaging modality in which the internal resistivity distribution is reconstructed based on the injected currents and measured voltages inside a domain of interest. In this paper, an adaptive threshold value based region of interest (ROI) method is proposed to improve the spatial resolution of reconstructed images as well as to reduce the computational time of the inverse problem. Adaptive threshold value is calculated by INTERMODES method and ROI is determined from the domain based on this value. Moreover, the computational domain of image reconstruction is restricted within a ROI and iterative Gauss-Newton method is employed to estimate the resistivity distribution. To evaluate the performance of the proposed method, numerical experiments have been performed and the results are analyzed.

• Journal of radiological science and technology
• /
• v.32 no.3
• /
• pp.271-276
• /
• 2009

The aim of this study was to evaluate the effect of Bone Mineral Density(BMD) at mandible. So, we studied how to measure the BMD at mandible using DEXA(Dual energy X-ray absorptiometry, DEXA) by Horner er al (1996) and knew reproducibility of the measurements. Thirty-five patients (13 men, 22 women, mean age : 25.4 years) were examined using the GE Lunar Prodigy Advance(LUNAR Corporation, madison, USA). They were examined in Semiprone position of their body and true lateral position of their mandible selected the Lumbar lateral mode. We used the custom mode in analysis when ROI (area $30{\times}2.5\;mm^2$). Three ROIs ($30{\times}2.5\;mm^2$, $50{\times}2.5\;mm^2$, $20{\times}2.5\;mm^2$) were located each at the two different sites of the mandible (angle of mandible and mental symphysis) and BMD was measured. Differences in BMD measurement was statistically compared according to the size and location of ROI. BMD was $1.320{\pm}0.358g/cm^3$ in men and was $1.152{\pm}0.340g/cm^3$ in women. BMD at the angle of mandible was $1.201{\pm}0.361g/cm^3$ in men and was $1.025{\pm}0.377g/cm^3$ in women. BMD of men at the mental symphysis was $1.434{\pm}0.341g/cm^3$ and that of women was $1.19{\pm}0.358g/cm^3$. With the ROI of $20{\times}2.5\;mm^2$, BMD was $1.262{\pm}0.384g/cm^3$ in men and was $1.113{\pm}0.357g/cm^3$ in women. With the ROI of $50{\times}2.5\;mm^2$, BMD of men was $1.320{\pm}0.358g/cm^3$ and that of women was $1.129{\pm}0.340g/cm^3$. There was a statistically significant difference of BMD according to the size and location of ROI. When measuring mandible BMD, there are good for increasing ROI and locate between ramus and mental symphysis. Especially following exam, refer to same size and location with fore exam. According to study which measure mandible BMD, It's correct to measure better a portion of mandible then whole of BMD. Using DEXA protocol is studied good for the additional study to compare the BMD at mandible. Later date, It will be good for measurement value in implant and bone graft quantitatively. Using DEXA method gain BMD threshold value in korean.

• The KIPS Transactions:PartB
• /
• v.14B no.2
• /
• pp.99-106
• /
• 2007

In this paper, we present an AAW(Adaptive Attention Window) based cell image segmentation method. For semantic AAW detection we create an initial Attention Window by using a luminance map. Then the initial AW is reduced to the optimal size of the real ROI(Region of Interest) by using a quad tree segmentation. The purpose of AAW is to remove the background and to reduce the amount of processing time for segmenting ROIs. Experimental results show that the proposed method segments one or more ROIs efficiently and gives the similar segmentation result as compared with the human perception.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2014.07a
• /
• pp.419-422
• /
• 2014

본 논문에서는 환자와 검사자에게 초음파 영상의 객관화된 정보를 정확하게 제공하기 위해 간과 신장의 초음파 영상에 SOM 기법을 적용하여 지방간 농도 수치를 분류하는 방법을 제시한다. 제안된 방법은 간, 신장 영역을 촬영한 초음파 영상에서 촬영정보나 눈금자 등과 같이 필요 없는 부분을 잡음으로 간주하여 제거한 Region Of Interest(ROI) 영상을 추출하고, 추출된 ROI 영상에서 명암대비를 강조하기 위해 Fuzzy Stretching 기법을 적용한다. Stretching된 영상에 Enhanced Average Binary와 Labeling 기법으로 적용하여 얻은 Contour 정보를 분석하여 잡음을 제거한 후, 지방간의 측정 영역을 추출한다. 추출된 간과 신장의 측정 영역에 SOM 기법을 적용하여 명암도 값을 분류한 후, 간과 신장의 실질 영역의 대표 명암도를 각각 추출하여 비교 분석한다. 제안된 방법을 초음파 영상에 적용한 결과, 효율적이고 객관적으로 간의 지방도를 분류할 수 있는 가능성을 확인하였다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2018.06a
• /
• pp.207-208
• /
• 2018

기술의 발달로 인해 휴대폰카메라와 간단한 광학 장치를 통해 나노 단위의 유해물질 영상을 획득할 수 있게 되었지만, 휴대폰카메라의 한계로 영상 전역에 원치 않는 잡음이 발생하여 유해물질 농도 검출의 정확도는 좋지 않다. 또한 기존의 관심영역 검출 알고리즘은 검출하고자 하는 대상의 형태학적 특성을 이용한 상관성 비교를 사용하는데, 처리 시간이 길어 휴대폰 어플리케이션에 적합하지 않다. 이에 착안하여, 본 논문에서는 실용화를 목적으로 영상처리를 기반으로 한 유해물질 영역 검출의 고속화 알고리즘을 제안한다. 영상보간 및 잡음제거의 전처리를 진행한 영상에 휴리스틱 관심 대상 검출 알고리즘을 적용한 결과, 기존의 관심영역 검출 알고리즘과 대비 검출 시간은 약 70% 감소하였으며 검출 정확도는 증가하였다.

• Journal of KIISE:Computer Systems and Theory
• /
• v.37 no.5
• /
• pp.314-318
• /
• 2010

This paper proposes an image retrieval method based on the Multiple Region-of-Interest. In the proposed method, the image is segmented into blocks, among which the blocks overlapped with multiple ROIs are selected. The similarity of images is measured using the MPEG-7 dominant color descriptor(DCD) and considering the relative location of the overlapped blocks. The experimental results showed that the proposed method improves the retrieval performance than the previous methods using the global DCD or comparing the blocks at the same position. In addition, the method that considers the relative position of blocks overlapped with the multiple ROIs also showed a better performance than the existing methods.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.186-188
• /
• 2021

본 논문에서는 초음파 영상에서 DBSCAN(Density-based spatial clustering of applications with noise)과 FCM 클러스터링 기반 양자화 기법을 적용하여 결절종을 추출하는 방법을 제안한다. 본 논문에서는 초음파 영상 촬영 시 좌우 상단의 지방층 영역과 하단 영역의 명암도가 어두운 영역을 잡음 영역으로 설정한다. 그리고 초음파 영상에 퍼지스트레칭 기법을 적용하여 잡음 영역을 최대한 제거 한 후에 ROI 영역을 추출한다. 추출된 ROI 영역에서 밀도 분포를 분석하기 위하여 히스토그램을 분석한 후에 DBSCAN을 적용하여 초음파 영상에서 결절종 후보에 해당되는 명암도를 추출한다. 추출한 후보 명암도를 대상으로 FCM 클러스터링 기법을 적용한다. FCM을 적용하는 단계에서 결절종의 저에코 혹은 무에코의 특징을 이용하여 클러스터 중심 값이 가장 낮은 클러스터를 양자화 한 후에 라벨링 기법을 적용시켜 결절종의 후보 객체를 추출한다. 제안된 결절종 추출 방법의 성능을 분석하기 위해 전문의가 결절종 영역을 표기한 초음파 영상과 표기되지 않은 초음파 영상 120쌍을 대상으로 DBSCAN, FCM, 그리고 제안된 방법 간의 성능을 비교 분석하였다. 제안된 방법에서는 120개의 초음파 영상에서 106개 결절종 영역이 추출되었고 FCM 기법에서는 80개가 추출되었고 DBSCAN에서는 36개가 추출되었다. 따라서 제안된 방법이 결절종 추출에 효율적인 것을 확인하였다.