• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.8 no.3
• /
• pp.163-169
• /
• 2008

In this paper, we propose a real-time people tracking system with multiple CCD cameras for security inside the building. The camera is mounted from the ceiling of the laboratory so that the image data of the passing people are fully overlapped. The implemented system recognizes people movement along various directions. To track people even when their images are partially overlapped, the proposed system estimates and tracks a bounding box enclosing each person in the tracking region. The approximated convex hull of each individual in the tracking area is obtained to provide more accurate tracking information. To achieve this goal, we propose a method for 3D walking human tracking based on the IMPRESARIO framework incorporating cascaded classifiers into hypothesis evaluation. The efficiency of adaptive selection of cascaded classifiers have been also presented. We have shown the improvement of reliability for likelihood calculation by using cascaded classifiers. Experimental results show that the proposed method can smoothly and effectively detect and track walking humans through environments such as dense forests.

• Proceedings of the SAREK Conference
• /
• 2006.06a
• /
• pp.405-410
• /
• 2006

This paper presents a control algorithm of supply and exhaust diffusers by recognizing a contaminant source location. CFD analysis has been conducted to calculate steady state airflow and concentration distributions in a model room, which has two supply and two exhaust openings on the ceiling. Calculations have been performed for five cases out of nine different ventilation modes by combining on/off control of the supply and exhaust openings. Local mean residual life times are obtained and compared at 9 internal points for each ventilation case. Depending on the contaminant source location, the ventilation system is operated at an optimum ventilation mode, which can results in maximum exhaust performance.

• The Magazine of the Society of Air-Conditioning and Refrigerating Engineers of Korea
• /
• v.10 no.3
• /
• pp.185-219
• /
• 1981

To analyze two dimensional incompressible laminar natural convection in a rectangular enclosure heated from below and cooled by a horizontal ceiling and two vertical walls, he primitive Navier-Stokes equations and the energy equation were solved numerically in time dependent form by a marker and cell method. A successive over-relaxation method for the elliptic portion of the problem and an explicit method for the parabolic portion were applied for the range of Grashoff number of $5{\times}10^3\;to\;5{\times}10^4$ to get the transient and steady state dimensionless temperature and velocity profiles. For the range of aspect ratio $L/H{\leqq}2.4$ in which only a pair of convection rolls exists mean Nusselt number calculated are as follows : $$N_{NU}0.89\;N_{Gr}^{0.2}(H/L)^{0.45}$$ By path lines drawn by marker particle trajectories roll number of cellular motion were observed for various aspect ratio of the enclosure.

• Journal of Korea Multimedia Society
• /
• v.22 no.2
• /
• pp.128-135
• /
• 2019

This paper presents a deep learning-based object detection method for recognizing vehicles in images acquired through cameras installed on ceiling of underground parking lot. First, we present an image enhancement method, which improves vehicle detection performance under dark lighting environment. Second, we present a new CNN-based multiscale classifiers for detecting vehicles in images acquired through cameras with fisheye lens. Experiments show that the presented vehicle detector has better performance than the conventional ones.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.3
• /
• pp.11-17
• /
• 2019

In this paper, we propose a method to recognize the moving direction in the indoor environment by using the sensing system equipped with passive infrared (PIR) sensors and a deep learning algorithm. A PIR sensor generates a signal that can be distinguished according to the direction of movement of the user. A sensing system with four PIR sensors deployed by $45^{\circ}$ increments is developed and installed in the ceiling of the room. The PIR sensor signals from 6 users with 10-time experiments for 8 directions were collected. We extracted the raw data sets and performed experiments varying the number of sensors fed into the deep learning algorithm. The proposed sensing system using deep learning algorithm can recognize the users' moving direction by 99.2 %. In addition, with only one PIR senor, the recognition accuracy reaches 98.4%.

• Journal of Advanced Information Technology and Convergence
• /
• v.8 no.2
• /
• pp.13-25
• /
• 2018

The paper analyzes the sum spectral efficiency (SE) for a heterogeneous cellular network (HetNet) which has the backhaul, provided with wireless full-duplex massive multiple-input multiple-out (MIMO) with hardware distortions. We derive approximate expressions to obtain the uplink/downlink sum SE of the backhaul. The analytic results have been shown to be exact when compared to Monte Carlo simulations. From the analysis, it is shown that the desired signal and the hardware distortion noise have the same order. The sum SE generally improves when the number of receive antennas increases but degrades when the hardware quality reduces. A sum SE performance ceiling is introduced by the hardware quality level.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.10a
• /
• pp.857-860
• /
• 2014

This paper proposes a human movement detection system by a thermopile array sensor. In the system, the sensor is attached to the ceiling and it acquires spatial temperatures, which is called thermal distribution. The system obtains $4{\times}4$ pixels thermal distributions from the sensor. The distributions are analyzed to extract human movement. As the experimental result, the proposed system successfully detected human movements.

• The Journal of Korea Robotics Society
• /
• v.17 no.2
• /
• pp.216-220
• /
• 2022

This paper proposes an inspection robot that can operate on a single square rail. Various inspection robots have been developed to identify emergency situations in industrial environments, such as those involving fires or individuals with cardiac arrest. Because the robots must operate in wide areas and long tunnels, they are designed to move along a rail installed on the ceiling. Double rail track are typically used to ensure the stability of robot movement. However, the cost for installing a double rail track is nearly two times that for a single rail track. Moreover, it is challenging to install double rail tracks while ensuring the same curvature and interval between the two rails. Therefore, in this study, an inspection robot that operate on a single square rail track is developed. To ensure stable movement in the longitudinal and lateral directions, two passive guide parts are used, and the main active wheel is allowed to move on the upper side of the square rail. The prototype was manufactured, and experiments were performed for different robot velocities.

• The Magazine of the Society of Air-Conditioning and Refrigerating Engineers of Korea
• /
• v.18 no.2
• /
• pp.130-137
• /
• 1989

본 논문은 1. 초청정기술의 현황, 2. 초청정장치의 요소기술, 3. 초청정장치의 개요, 4. 국부청정실의 기본계획에 대해 기술하고 있다. 1. 초청정기술의 현황에서는, 본 연구수행의 방향설정을 위해 미국과 일본의 관련 학${\cdot}$협회의 동향 및 최근에 발표된 논문에 근거한 초청정기술의 연구경향과 과제 등을 파악 분석했다. 2. 초청정장치의 요소기술에서는, 초청정장치 개발에 필요한 미립자제거, 환경조건과 오염제어 기술을 확립하기 위해, Filter와 System Ceiling 방식, 온${\cdot}$습도, 진동, 정전기제어 기술에 관한 문제점과 대책에 대해 검토했다. 3. 초청정장치의 개요에서는, 초청정장치로써 대표적인 클린벤취의 관련규격, 설계요점 등을 검토하여 설계를 위한 기초자료로 삼았다. 4. 국부청정실의 기본계획에서는 상기의 요소기술과 기초자료에 근거하여 본 연구를 수행하기 위한 Line 형의 클린터널 유닛의 기본계획을 수립했다.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2022.04a
• /
• pp.235-236
• /
• 2022

In the present study, the effect of horizontal vent position on fire phenomena in the enclosure with vertical and horizontal vents was examined using numerical simulation. Case 1 indicates the condition that the horizontal vent is in the center of the ceiling. Case 3 indicates the condition that the horizontal vent is far away from the vertical vent. Case 2 indicates the condition that the horizontal vent is installed between Case 1 and Case 3. The temperature distribution, smoke layer temperature, velocity distribution, and mass flow rate of horizontal vent flow were analyzed. In Case 2, the temperatures were lowest and the mass flow rate through the horizontal vent was largest. This is because the flame is inclined by the inflow through the vertical vent. Hence, to determine the proper horizontal vent location for the high smoke ventilation performance, the inflow through the vertical vent and its effect on flame behavior should be considered.