• Smart Structures and Systems
• /
• 제17권6호
• /
• pp.935-956
• /
• 2016

With the help of advanced image acquisition and processing technology, the vision-based measurement methods have been broadly applied to implement the structural monitoring and condition identification of civil engineering structures. Many noncontact approaches enabled by different digital image processing algorithms are developed to overcome the problems in conventional structural dynamic displacement measurement. This paper presents three kinds of image processing algorithms for structural dynamic displacement measurement, i.e., the grayscale pattern matching (GPM) algorithm, the color pattern matching (CPM) algorithm, and the mean shift tracking (MST) algorithm. A vision-based system programmed with the three image processing algorithms is developed for multi-point structural dynamic displacement measurement. The dynamic displacement time histories of multiple vision points are simultaneously measured by the vision-based system and the magnetostrictive displacement sensor (MDS) during the laboratory shaking table tests of a three-story steel frame model. The comparative analysis results indicate that the developed vision-based system exhibits excellent performance in structural dynamic displacement measurement by use of the three different image processing algorithms. The field application experiments are also carried out on an arch bridge for the measurement of displacement influence lines during the loading tests to validate the effectiveness of the vision-based system.

• 전자공학회논문지 IE
• /
• 제47권2호
• /
• pp.38-46
• /
• 2010

본 논문에서는 스테레오 비젼 기법에 기반한 작업자 모니터링을 위한 자동 감시추적 시스템을 제안하였다. 즉, 인간 시각 시스템을 모방한 교차식 스테레오 카메라 시스템의 특성을 이용하여 작업자의 인식은 물론 추적, 감시가 가능한 새로운 형태의 지능형 감시추적 시스템을 설계 제안하였다. 즉, 작업자 표적의 다양한 변화에 관계없이 배경과 분리된 표적인식은 물론 움직이는 표적의 3차원적 위치 정보를 검출함으로써 실시간적 물체인식 및 추적이 가능한 새로운 형태의 지능형 스테레오 감시 추적 시스템을 제시하였다. 실험결과, 교차식 스테레오 카메라 기반의 이동물체 감시추적 시스템의 실험결과 팬과 틸트를 통한 물체추적 후 표적 중심좌표의 수평, 수직 평균오차는 1.82%, 1.11%의 매우 낮은 에러 값을 각각 유지하였으며, 추정된 물체의 3차원 위치좌표의 경우도 실제 물체 위치값과 비교하여 평균 2.5% 이하의 낮은 오차가 나타남이 분석되었다. 따라서, 본 논문에서 제안한 팬과 틸트가 탑제된 스테레오 카메라 기반의 감시추적 시스템은 복잡한 배경 및 주위환경 변화에도 이동 물체를 효과적으로 추출하여 적응적으로 감시 및 추적이 가능한 산업용 무인 감시추적 시스템의 구현 가능성을 제시하였다.

• International Journal of Control, Automation, and Systems
• /
• 제5권1호
• /
• pp.51-60
• /
• 2007

This paper describes a visual tracking control law of an Unmanned Aerial Vehicle(UAV) for monitoring of structures and maintenance of bridges. It presents a control law based on computer vision for quasi-stationary flights above a planar target. The first part of the UAV's mission is the navigation from an initial position to a final position to define a desired trajectory in an unknown 3D environment. The proposed method uses the homography matrix computed from the visual information and derives, using backstepping techniques, an adaptive nonlinear tracking control law allowing the effective tracking and depth estimation. The depth represents the desired distance separating the camera from the target.

• 국제학술발표논문집
• /
• The 1th International Conference on Construction Engineering and Project Management
• /
• pp.1017-1021
• /
• 2005

There is a need for effective tracking and control of material loading and delivery time especially during the finishing-work phases to eliminate the need for lay-down space on the site. Hence, it is essential to monitor the relevant information regarding material procurement in construction sites, and it is also the key factor for successful site control and the adoption of the Just-in-Time concept for high-rise building construction. The purpose of this study is to test RFID's readability in order to develop a finishing material monitoring system through the application of RFID technology.

• 한국정보통신학회논문지
• /
• 제24권1호
• /
• pp.22-27
• /
• 2020

최근 1인 가구의 증가로 반려동물을 키우는 가구가 많아짐에 따라, 주인의 부재 시에도 반려동물의 상태나 행동을 모니터링하는 시스템에 대한 필요성이 요구되고 있다. 가정용 CCTV를 이용한 반려동물의 모니터링에는 지역적 한계가 있어, 다수의 CCTV를 필요로 하거나 반려동물의 행동반경을 제한하는 방법을 사용하게 된다. 본 논문에서는 반려동물 모니터링의 지역적 한계를 해결하고자 딥러닝을 이용하여 고양이를 검출하고 추적하는 이동식 시스템을 제안한다. 객체 검출 신경망 모델의 하나인 YOLO(You Look Only Once)를 이용하여 데이터셋을 학습하고, 이를 기반으로 라즈베리파이에 적용하여 영상에서 검출된 객체를 추적한다. 라즈베리파이와 노트북을 무선 랜으로 연결하고 고양이의 움직임과 상태를 실시간으로 확인이 가능한 이동식 모니터링 시스템을 설계하였다.

• 한국측량학회지
• /
• 제26권4호
• /
• pp.367-378
• /
• 2008

국토를 효율적으로 이용하고 관리하기 위해서는 국토변화에 대한 지속적인 모니터링이 필요하며, 모니터링의 가장 효과적인 방법 중에 하나가 인공위성과 항공기 등을 이용하는 공중모니터링이다. 이에 본 연구에서는 공중모니터링체계 구축방안을 제시하였으며, 이를 위하여 국내외 선행연구 및 사례검토, 관련기술동향 파악, 국토분야별 관계기관에 대한 요구사항 조사를 수행하였다. 국토관리를 위한 공중모니터링체계 구축방안으로 첫째, 국토모니터링체계와 중장기계획을 수립 둘째, 공중모니터링 전담기관을 지정 셋째, 공중모니터링분야의 전문인력을 양성 넷째, 자료공유 및 유통체계를 마련 다섯째, 실시간 공중모니터링체계를 구축 여섯째, 관련 법제도를 개선 일곱째, 지속적인 관련기술의 연구개발 등에 대한 지원 등을 제시하였다.

• 한국대기환경학회지
• /
• 제23권1호
• /
• pp.1-13
• /
• 2007

This study was carried out to evaluate the applicability of the odor source tracking using wind field and fingerprint as a solution tool. First of all, CALMET and HYSPLIT modeling system, and database of odor discharge companies were utilized to track odor from industrial complexes. Secondly, industrial odor fingerprint was made by listing on the 19 domestic industries, and compared with foreign data to assess the representative, and thus the similarity was 86.7%. On the modeling experiment, Sihwa industrial complex did not show any difference because the matching rates of day and night were 49.5% and 50.0%, respectively. However, the Banwol and Sihwa industrial complexes did show some differences due to odor facility density. Separately, in this study, odor samples were obtained from 10 odor discharging companies, located in the Sihwa and Banwol industrial complexes, They were compared with the results of odor tracking modeling. The matched companies were 4 of 10 by three cases of tracking, while the fingerprint and industry of odor monitoring networks and companies matched each other. Therefore, this study confirmed the approach applicability of source tracking system using the fingerprint.

• 한국산업융합학회 논문집
• /
• 제27권2_2호
• /
• pp.319-324
• /
• 2024

In this paper, the Artificial Intelligence Space(AI-Space) for human-robot interface is presented, which can enable human-computer interfacing, networked camera conferencing, industrial monitoring, service and training applications. We present a method for representing, tracking, and objects(human, robot, chair) following by fusing distributed multiple vision systems in AI-Space. The article presents the integration of color distributions into particle filtering. Particle filters provide a robust tracking framework under ambiguous conditions. We propose to track the moving objects(human, robot, chair) by generating hypotheses not in the image plane but on the top-view reconstruction of the scene.

• 스마트미디어저널
• /
• 제11권8호
• /
• pp.84-92
• /
• 2022

Precision livestock monitoring promises greater management efficiency for farmers and higher welfare standards for animals. Recent studies on video-based animal activity recognition and tracking have shown promising solutions for understanding animal behavior. To achieve that, surveillance cameras are installed diagonally above the barn in a typical cattle farm setup to monitor animals constantly. Under these circumstances, tracking individuals requires addressing challenges such as occlusion and visual appearance, which are the main reasons for track breakage and increased misidentification of animals. This paper presents a framework for multi-cattle tracking in closed barns with appearance and motion models. To overcome the above challenges, we modify the DeepSORT algorithm to achieve higher tracking accuracy by three contributions. First, we reduce the weight of appearance information. Second, we use an Ensemble Kalman Filter to predict the random motion information of cattle. Third, we propose a supplementary matching algorithm that compares the absolute cattle position in the barn to reassign lost tracks. The main idea of the matching algorithm assumes that the number of cattle is fixed in the barn, so the edge of the barn is where new trajectories are most likely to emerge. Experimental results are performed on our dataset collected on two cattle farms. Our algorithm achieves 70.37%, 77.39%, and 81.74% performance on HOTA, AssA, and IDF1, representing an improvement of 1.53%, 4.17%, and 0.96%, respectively, compared to the original method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권9호
• /
• pp.2642-2664
• /
• 2024

In the process of modern traffic management, information technology has become an important part of intelligent traffic governance. Real-time monitoring can accurately and effectively track and record vehicles, which is of great significance to modern urban traffic management. Existing tracking algorithms are affected by the environment, viewpoint, etc., and often have problems such as false detection, imprecise anchor boxes, and ID switch. Based on the YOLOv5 algorithm, we improve the loss function, propose a new feature extraction module to obtain the receptive field at different scales, and do adaptive fusion with the SGE attention mechanism, so that it can effectively suppress the noise information during feature extraction. The trained model improves the mAP value by 5.7% on the public dataset UA-DETRAC without increasing the amount of calculations. Meanwhile, for vehicle feature recognition, we adaptively adjust the network structure of the DeepSort tracking algorithm. Finally, we tested the tracking algorithm on the public dataset and in a realistic scenario. The results show that the improved algorithm has an increase in the values of MOTA and MT etc., which generally improves the reliability of vehicle tracking.