• Journal of the Korean Association of Geographic Information Studies
• /
• v.8 no.1
• /
• pp.88-95
• /
• 2005

Direct Georeferencing by combined multi-sensor based on the direct measurement of the projection centers and rotation angle of sensor through loading the GPS and INS in aircraft. The method of combined multi-sensor can offer us to acquire the exterior orientation parameters with only minimum GCPs, even the ground control process could be completely skipped. Consequently, It is possible extreme to reduce the time and expense for the mapping process. In this study, a CCD camera is simultaneously used in combined multi-sensor surveying, and acquired CCD image through Direct Georeferencing produce digital orthoimage. In this process, methods of combining sensor and digital orthoimage are examined and estimated. For the comparison of the positioning accuracy digital orthoimage through Direct Georeferencing, GCPs determined by GPS surveying are used. Two digital orthoimage are produced; one with a few GCP and the other without them. The accuracy of orthoimages produced through combined multi-sensor with GCPs meets that of 1:1,000 maps. Without GCPs, it meets that of 1:5,000 maps.

• Journal of IKEEE
• /
• v.26 no.3
• /
• pp.430-436
• /
• 2022

In this paper, we propose an intelligent camera for multiple body temperature detection. The proposed camera is composed of optical(4056*3040) and thermal(640*480), which detects abnormal symptoms by analyzing a person's facial expression and body temperature from the acquired image. The optical and thermal imaging cameras are operated simultaneously and detect an object in the optical image, in which the facial region and expression analysis are calculated from the object. Additionally, the calculated coordinate values from the optical image facial region are applied to the thermal image, also the maximum temperature is measured from the region and displayed on the screen. Abnormal symptom detection is determined by using the analyzed three facial expressions(neutral, happy, sadness) and body temperature values. In order to evaluate the performance of the proposed camera, the optical image processing part is tested on Caltech, WIDER FACE, and CK+ datasets for three algorithms(object detection, facial region detection, and expression analysis). Experimental results have shown 91%, 91%, and 84% accuracy scores each.

• Korean Journal of Remote Sensing
• /
• v.32 no.6
• /
• pp.647-656
• /
• 2016

Growth of UAV technology leads to expansion of UAV image applications. Many UAV image-based applications use a method called incremental bundle adjustment. However, incremental bundle adjustment produces large computation overhead because it attempts feature matching from all image pairs. For efficient feature matching process we have to confine matching only for overlapping pairs using exterior orientation parameters. When exterior orientation parameters are not available, we cannot determine overlapping pairs. We need another methods for feature matching candidate constitution. In this paper we compare matching candidate constitution methods without exterior orientation parameters, including partial feature matching, Bag-of-keypoints, image intensity method. We use the overlapping pair determination method based on exterior orientation parameter as reference. Experiment results showed the partial feature matching method in the one with best efficiency.

• Journal of Korean Society for Geospatial Information Science
• /
• v.12 no.3 s.30
• /
• pp.51-59
• /
• 2004

In the study, there has been a sharp upward trend in road maintenance cost as the expansion of road networks increases. Running a pavement management system(PMS) is indispensable for efficient and scientific maintenance of the whole road networks with limited maintenance budgets. With a PMS, a maintenance plan should be drawn up after surface conditions are precisely examined and analyzed. The majority of the present PMSs are run by the fact that experts first examine surface conditions on sites, and then enter results into systems. However, considering the actual circumstances of the present time and the increase in paved road hereafter, it is inefficient that experts examine the whole paved roads in person and long-lasting PMSs can not be kept up. As a result, after analyzing the accuracy of 3-D coordinates representing road surfaces that was decided using multi orientation and digital photogrammetry, the average of standard errors turned out to be 0.0427m on the X-axis, 0.0527m on the Y-axis and 0.1539m on the Z-axis. It was found to be good enough to be put to practical use for maps drawn on scales below 1 :1000, which are being currently made and used within the country, and GIS data.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.27 no.5
• /
• pp.585-597
• /
• 2009

This research aims to develop a registration method to remove the geometric inconsistency between aerial images and LIDAR data acquired from an airborne multi-sensor system. The proposed method mainly includes registration primitives extraction, correspondence establishment, and EOP(Exterior Orientation Parameters) adjustment. As the registration primitives, we extracts planar patches and intersection edges from the LIDAR data and object points and linking edges from the aerial images. The extracted primitives are then categorized into horizontal and vertical ones; and their correspondences are established. These correspondent pairs are incorporated as stochastic constraints into the bundle block adjustment, which finally precisely adjusts the exterior orientation parameters of the images. According to the experimental results from the application of the proposed method to real data, we found that the attitude parameters of EOPs were meaningfully adjusted and the geometric inconsistency of the primitives used for the adjustment is reduced from 2 m to 2 cm before and after the registration. Hence, the results of this research can contribute to data fusion for the high quality 3D spatial information.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2006.11a
• /
• pp.131-134
• /
• 2006

본 논문에서는 가정용 로봇 및 서비스 로봇과 같은 이동로봇에서 사용자의 감정을 인식하는 방법중 한가지인 얼굴영상을 이용한 감정인식 방법을 제안한다. 얼굴영상인식을 위하여 얼굴의 여러 가지 특징(눈썹, 눈, 코, 입)의 움직임 및 위치를 이용하며, 이동로봇에서 움직이는 사용자를 인식하기 위한 움직임 추적 알고리즘을 구현하고, 획득된 사용자의 영상에서 얼굴영역 검출 알고리즘을 사용하여 얼굴 영역을 제외한 손과 배경 영상의 피부색은 제거한다. 검출된 얼굴영역의 거리에 따른 영상 확대 및 축소, 얼굴 각도에 따른 영상 회전변환 등의 정규화 작업을 거친 후 이동 로봇에서는 항상 고정된 크기의 얼굴 영상을 획득 할 수 있도록 한다. 또한 기존의 특징점 추출이나 히스토그램을 이용한 감정인식 방법을 혼합하여 인간의 감성 인식 시스템을 모방한 로봇에서의 감정인식을 수행한다. 본 논문에서는 이러한 다중 특징점 추출 방식을 통하여 이동로봇에서의 얼굴 영상을 이용한 사용자의 감정인식 시스템을 제안한다.

• Korean Journal of Remote Sensing
• /
• v.20 no.2
• /
• pp.125-137
• /
• 2004

In case of using image sequence taken from a moving camera along a road in an urban area, general video mosaicing technique based on a single baseline cannot create 2-D image mosaics. To solve the drawback, this paper proposed a new image mosaicing technique through 3-D multi-baselines that can create image mosaics in 3-D space. The core of the proposed method is that each image frame has a dependent baseline, an equation of first order, calculated by using ground control point (GCP) of optical flows. The proposed algorithm consists of 4 steps: calculation of optical flows using hierarchical strategy, calculation of camera exterior orientation, determination of multi-baselines, and seamless image mosaics. This paper realized and showed the proposed algorithm that can create efficient image mosaics in 3-D space from real image sequence.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2001.06a
• /
• pp.553-557
• /
• 2001

얼굴 표정을 애니메이션하는 것은 얼굴 구조의 복잡성과 얼굴 표면의 섬세한 움직임으로 인해 컴퓨터 애니메이션 분야에서 가장 어려운 분야로 인식되고 있다. 최근 3D 애니메이션, 영화 특수효과 그리고 게임 제작시 모션 캡처 시스템(Motion Capture System)을 통하여 실제 인간의 동작 및 얼굴 표정을 수치적으로 측정해내어 이를 실제 애니메이션에 직접 사용함으로써 막대한 작업시간 및 인력 그리고 자본을 획기적으로 줄이고 있다. 그러나 기존의 모션 캡처 시스템은 고속 카메라를 이용함으로써 가격이 고가이고 움직임 추적에서도 여러 가지 문제점을 가지고 있다. 본 논문에서는 일반 저가의 카메라와 신경회로망 및 영상처리기법을 이용하여 얼굴 애니메이션용 모션 캡처 시스템에 적응할 수 있는 경제적이고 효율적인 얼굴 움직임 추적기법을 제안한다.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2000.04a
• /
• pp.474-477
• /
• 2000

최근 3D 애니메이션 , 영화 특수효과 그리고 게임제작시 모션 캡처 시스템(Motion Capture System)을 통하여 실제 인간의 동작 및 표정을 수치적으로 측정해내어 이를 실제 애니메이션에 직접 사용함으로써 막대한 작업시간 및 인력 드리고 자본을 획기적으로 줄이고 있다. 그러나 기존의 모션 캡처 시스템은 고속 카메라를 이용함으로써 가격이 고가이고 움직임 추적에서도 여러 가지 문제점을 가지고 있다. 본 논문에서는 일반 저가의 카메라와 신경회로망 및 영상처리를 이용하여 얼굴 애니메이션용 모션 캡처 시스템에 적용할 수 있는 경제적이고 효율적인 얼굴 움직임 추적 기법을 제안한다.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2009.10a
• /
• pp.398-398
• /
• 2009

본 논문에서는 카메라의 원근감을 이용하여 케이블의 모드형상을 추출하는 과정을 제안한다. 제안 기법을 검증하기 위해 디지털 카메라와 캠코더를 이용하여 서로 다른 위치에서 동일 화면을 동시에 촬영하고, 촬영된 영상을 사진 변환프로그램을 통해서 초당 30프레임으로 영상이미지를 추출해 낸다. 추출된 좌.우 영상이미지의 영상좌표를 이용하여 케이블에 부착된 표적의 3차원 위치를 결정한다. 이때 디지털 카메라와 캠코더간의 위치 및 자세는 제안된 종속적 상호표정 방법을 통하여 결정한다. 결정된 케이블의 시간이력으로부터 고유진동수과 감쇠비는 다중 템플릿 매칭 알고리즘(multi-template matching algorithm)기법으로 추출하고, 모드형상은 TDD(Time Domain Decomposition)기법을 통하여 추출한다.