• 한국항행학회논문지
• /
• 제27권6호
• /
• pp.770-775
• /
• 2023

최근 디지털 데이터 양의 기하급수적 증가는 데이터 처리 시스템의 중요성을 부각시켰다. 이 연구는 클라우드 컴퓨팅 (CC; cloud computing), 엣지 컴퓨팅 (EC; edge computing), 그리고 UAV (unmanned aerial vehicle) 기반 지능형 에지 컴퓨팅 (UEC; unmanned aerial vehicle-based intelligent edge computing) 간의 성능을 비교하였으며, 특히 회랑감시와 같은 실시간 대용량 데이터 처리 상황에 초점을 맞추었습니다. UAV 기반 지능형 에지 컴퓨팅은 이동성과 특수 환경에서의 대규모 데이터 처리 및 분석에 높은 효과성을 보인다. 이러한 연구 결과를 바탕으로 각 상황에 맞게 최적화된 시스템 선택 방법론을 제안한다.

• 센서학회지
• /
• 제24권1호
• /
• pp.54-61
• /
• 2015

In recent years, there has been increasing use of automatic surveillance and monitoring systems based on vision sensors. Humans are often the most important target in the systems, but processing human images is difficult due to the small sizes and flexible motions. Particularly, occlusion among pedestrians in camera images brings practical problems. In this paper, we propose a novel method to separate image regions of occluded pedestrians. A camera equipped with a wide angle lens is attached to the ceiling of a building corridor for sensing pedestrians with a wide field of view. The output images of the camera are processed for the human detection, tracking, identification, distortion correction, and occlusion handling. We resolve the occlusion problem adaptively depending on the angles and positions of their heads. Experimental results showed that the proposed method is more efficient and accurate compared with existing methods.

• 의료ㆍ복지 건축 : 한국의료복지건축학회 논문집
• /
• 제22권3호
• /
• pp.27-34
• /
• 2016

Purpose: The purpose of this paper is to develop a predictive model for patient visibility in Korean ICUs (corridor or continental type). Methods: The measures of static visibility were used to quantify the patient visibility (upper third part of the patient bed) from the nurse station. The measure of space programme and area distribution (patient zone percentage, staff zone percentage and departmental gross square meter per patient bed) were calculated by using AutoCAD and MS Excel programs. Regression analysis was conducted for visibility as dependant variable with independent variables of patient area percentage, staff area percentage as well as departmental gross square meter per bed by using IBM SPSS. Results: (1) Average patient visibility and percentage of patient area in ICU shows a strong negative correlation ($r^2$=0.66), p=0.01. (2) Patient visibility in Korean ICU (corridor or continental type) can be calculated as below with the given conditions: Y= $-1.449(X)+124.3{\pm}6$, Y is the total visibility of the ICU (corridor or continental type) and X is the percentage of patient area in the unit. Conditions:1. Given that the unit has a mixed programme of open bed and closed patient rooms and 2. The unit have a minimum of 20% patient rooms. Implications: This study may contribute to the visibility analysis of existing and future ICU design (corridor or continental type) in Korea to achieve maximum patient visibility and reduced patient mortality.

• 의료ㆍ복지 건축 : 한국의료복지건축학회 논문집
• /
• 제22권4호
• /
• pp.37-45
• /
• 2016

Purpose: The purpose of this paper is to analyze a sample of single corridor, pod type and composite type of ICUs in terms of patient visibility, spatial configurations and nurse walking distance focused on Korean cases. Methods: The measures of static visibility were used to quantify the patient visibility (upper third part of the patient bed) from the nurse station. The measure of space programme and area distribution (patient zone percentage, staff zone percentage, circulation zone percentage, corridor length per bed, distance from nurse station (NS) to patient bed and departmental gross square meter (DGSM) per patient bed) were calculated by using AutoCAD and MS Excel programs. In the second step of analysis the values of space distribution were compared among the three type of ICUs as well as the nurse walking distance, DGSM per bed and gross factor. in the third step of analysis regression analysis was conducted for the possible correlation between visibility and space programme and area distribution factors as well as nurse walking distance factors. Results: (1) It was found that on average composite type unit offer highest value of patient visibility followed by pod type, while single corridor type unit offers the minimum value of patient visibility among the three plan typologies. (2) Average patient visibility and DGSM per bed shows a strong positive correlation ($r^2=0.75$) and p=0.026. (3) Average patient visibility and average distance from NS has a strong negative correlation ($r^2=0.78$), and P=0.02. (4) On average composite type unit offer the minimum walking distance from NS (7.22 meter) followed by pod type unit (8.35 meter) and single corridor (9.76 meter). (5) Maximum distance from NS was noted in single corridor (18.19 meter) followed by pod type unit (15.14 meter) and Composite type unit (11.1 meter). Implications: This study may contribute to the visibility analysis of existing and future ICU design in Korea to achieve maximum patient visibility and reduced nurse walking distance.

• 한국멀티미디어학회논문지
• /
• 제11권11호
• /
• pp.1491-1500
• /
• 2008

본 논문은 은닉 마르코프 모델을 사용하여 사람의 특정한 행동을 인식하여 사용자에게 알려주는 지능형 영상 감시 시스템을 제안한다. 본 방법에는 카메라를 통해 입력된 영상에서 사람 영역을 찾은 후 발 영역만을 추출하여 특징이 되는 관측열을 생성한다 특징 영역은 입력 영상의 각 프레임을 16개의 영역으로 나누어 발바닥이 위치한 곳의 코드를 읽어 사용하고, 인식하고자 하는 패턴 행동들에 대해서는 각각의 관측열을 구하고 HMM의 Baum-Welch 알고리즘을 사용하여 학습한다. 인식에는 전향 알고리즘을 사용하여 입력된 행동과 학습된 행동을 확률적으로 비교하여 영상 내의 행동이 어떤 패턴 행동인지를 결정하여 출력한다. 제시된 방법은 복도에서 사람의 특정 행동을 인식하는데 성공적으로 적용될 수 있음을 실험을 통해 확인했다.

• 한국HCI학회:학술대회논문집
• /
• 한국HCI학회 2006년도 학술대회 1부
• /
• pp.355-361
• /
• 2006

In large scale environments like airport, museum, large warehouse and department store, autonomous mobile robots will play an important role in security and surveillance tasks. Robotic security guards will give the surveyed information of large scale environments and communicate with human operator with that kind of data such as if there is an object or not and a window is open. Both for visualization of information and as human machine interface for remote control, a 3D model can give much more useful information than the typical 2D maps used in many robotic applications today. It is easier to understandable and makes user feel like being in a location of robot so that user could interact with robot more naturally in a remote circumstance and see structures such as windows and doors that cannot be seen in a 2D model. In this paper we present our simple and easy to use method to obtain a 3D textured model. For expression of reality, we need to integrate the 3D models and real scenes. Most of other cases of 3D modeling method consist of two data acquisition devices. One for getting a 3D model and another for obtaining realistic textures. In this case, the former device would be 2D laser range-finder and the latter device would be common camera. Our algorithm consists of building a measurement-based 2D metric map which is acquired by laser range-finder, texture acquisition/stitching and texture-mapping to corresponding 3D model. The algorithm is implemented with laser sensor for obtaining 2D/3D metric map and two cameras for gathering texture. Our geometric 3D model consists of planes that model the floor and walls. The geometry of the planes is extracted from the 2D metric map data. Textures for the floor and walls are generated from the images captured by two 1394 cameras which have wide Field of View angle. Image stitching and image cutting process is used to generate textured images for corresponding with a 3D model. The algorithm is applied to 2 cases which are corridor and space that has the four wall like room of building. The generated 3D map model of indoor environment is shown with VRML format and can be viewed in a web browser with a VRML plug-in. The proposed algorithm can be applied to 3D model-based remote surveillance system through WWW.