• Proceedings of the Korean Society of Disaster Information Conference
• /
• 2023.11a
• /
• pp.278-281
• /
• 2023

연구목적: 본 연구는 요양병원 등 재난취약시설에 재난이 발생할 경우 잔류한 요구조자를 정확하게 파악하여 소방 등 대응기관에 제공하는 APC(Auto People Counting)의 인식률 개선에 목적이 있다. 현재 재난 발생 시 건물 내 요구조자의 현황 파악을 위해 대응기관이 재난 현장에 도착하여 건물관계자에게 직접 물어보고 있다. 이는 요구조자에 대한 부정확한 정보일 가능성이 있어 대응기관의 업무범위가 확대되고 이로인해 구조자의 안전에도 위험이 될 수 있다. APC는 건물내 출입하는 인원을 자동으로 집계하여 실시간 잔류인원 정보를 제공함으로써 재난 시 요구조자 현황을 정확히 파악할 수 있다. 본 연구에서는 APC가 보다 정확하게 출입 인원을 집계할 수 있도록 최적의 인공지능 알고리즘을 선정하는데 목적이 있다. 연구방법: 본 연구에서는 실제 재난취약시설에 설치되어 운영 중인 APC를 대상으로 카메라를 통해 출입 인원의 이미지를 인식하는 알고리즘을 개선하기 위해 CNN모델을 활용하여 베이스라인 모델링을 하였다. 다양한 알고리즘의 성능을 분석하여 상위 7개의 후보군을 선정하고 전이학습 모델을 활용하여 성능이 가장 우수한 최적의 알고리즘을 선정하는 방법으로 연구를 수행하였다. 연구결과: 실험결과 시간과 성능이 가장 좋은 Densenet201, Resnet152v2 모델의 정밀도와 재현율을 확인한 결과 모든 라벨에 대해서 정확도 100%를 나타내는 것을 확인할 수 있었다. 이 중 Densenet201 모델이 더 높은 성능을 보여주었다. 결론: 다양한 인공지능 알고리즘 중 APC에 적용할 수 있는 최적의 알고리즘을 선정하였고 이는 APC의 인식률을 개선하여 재난시 요구조자의 정보를 정확하게 파악하여 신속하고 안전한 구조작업이 가능할 것이다. 이는 요구조자의 안전한 구조뿐만 아니라 구조작업을 수행하는 구조자의 안전을 확보하는 데 기여할 것으로 기대된다. 향후 연무 등 다양한 재난상황에서 재난취약시설 내 출입인원을 정확하게 파악할 수 있도록 알고리즘 분석 및 학습에 대한 추가 연구가 요구된다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.01a
• /
• pp.269-270
• /
• 2023

재해, 재난 발생 시에 구조대가 건물 내부나 지하철 등, 특정 구역 내의 대피하지 못한 잔류인원을 제대로 파악하데 어려움을 겪는다. 이를 개선하고자 YOLO와 DeepSORT를 활용하여 통행자를 인식하여 특정 구역의 잔류인원을 파악하고 이를 서버를 통해 확인할 수 있는 시스템을 개발하였다. 실시간 객체인식 알고리즘인 YOLOv4-tiny와 실시간 객체추적기술인 DeepSORT 알고리즘을 이용하여 제안한 방법을 Ubuntu환경에서 구현하고, 실내 상황에 맞춰 통행자 동선을 고려해서 적용하였다. 개발한 시스템은 인식된 통행자 객체방향으로 출입을 구분하여 데이터를 서버에 저장한다. 이에 따라 재해 발생 시 구역의 잔류인원을 파악하여 빠르고 효율적으로 요구조자 위치와 인원을 예측할 수 있다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.7
• /
• pp.1441-1446
• /
• 2017

In recent, the studies on the systems have been progressing that count the number of people passing through passageway or count people who exist in specific space. The existing people counting systems count the number of people using ultrared sensors, ultrasonic sensors or camera sensors, which can be installed only on pillar or around wall. Though ultrared sensors and ultrasonic sensors is low cost, they are inadequate to detect incoming/outgoing when several pedestrians pass through passageway concurrently. In this paper, we designed a sensor mat using piezoelectric sensors to complement the above-mentioned disadvantage. Also, we implemented the system that detects direction of progress and counts the number of people. The sensor mat detects direction of progress using pressure given on sensors and timing information and counts the number of people when pedestrians pass through on a sensor mat.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.7
• /
• pp.3236-3244
• /
• 2011

Negligent accidents are often caused by risk factors of working environment at most construction sites and construction schedules are delayed as the workers' work location and construction progress are not figured out accurately, and this leads to a lot of loss. In this paper, with the object of solving the problems at construction sites, RFID portable device, active tag and wireless RFID reader to provide the status of workers which is based on location are designed in order to send information about the location of workers and work progress in real time to a personal RFID device. Also an application system to monitor workers' approaching to prevent accidents from vehicles and danger zones and to manage the real time location of workers is designed.

• Korean Journal of Construction Engineering and Management
• /
• v.4 no.2 s.14
• /
• pp.59-65
• /
• 2003

The purpose of this study is to suggest a improved tact planning and scheduling by reliable Toning of work area in high-rise building construction. To do this, the characteristics of main work including electric & mechanical work were considered through the interview with field work forces. The content of the study is focused mainly on reliable work flow and rhythmical repetition of uniform resource quantity to manage effective tact planning & scheduling. And also the study recommends more implement of tact planning and scheduling to manage human resources successfully in repetitive building construction.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2017.01a
• /
• pp.63-66
• /
• 2017

현대인의 실생활은 무수히 많은 사물간의 데이터를 주고받을 수 있는 연결고리로 이루어져 있다. 이러한 연결고리 속에서 우리는 IoT(Information of Things), 즉 사물인터넷을 쉽게 경험할 수 있다. 본 논문에서는 이러한 사물인터넷의 활용으로 인한 차량 내 각 시트에 무게를 측정할 수 있는 하드웨어 시스템 및 안전벨트 연결 확인 하드웨어 시스템을 부착하여, 차량 내 탑승인원을 파악하고 그에 대한 할인 시스템을 개발하여 차량감소 효과로 인한 주차공간 확보 및 대기오염으로부터 청정효과를 기대할 수 있는 시스템을 제안하고자 한다.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.30 no.6D
• /
• pp.569-575
• /
• 2010

The occupancy based O/D is essential for measuring efficiency of various transportation policies like HOV/HOT lane, ramp metering, and public parking station. There has been many studies on occupancy survey methodology and O/D estimation using TCS (Toll Collection System) data separately. The occupancy O/D estimation methodology using TCS data has not been attempted thus far. An overall process from data collection stage to the occupancy O/D estimation stage has been suggested. Field survey was performed at the northbound Seoul toll station of Gyeongbu Expressway by each 2 hours of AM peak, PM non-peak, PM peak, midnight periods on a day. The process of matching the TCS data and field survey data classified by tollbooth ID, car type/mode, and arrival time was also performed. One typical output of the results showed that the ratio of single occupancy vehicles bounding for Seoul during the AM peak amounted to 60%. With the key output of this study and the specific O/D estimation methodology suggested, the whole centroid-to-centroid occupancy O/D of the country could be available, and then various applications in which the occupancy information is required could be possible.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.13 no.5
• /
• pp.1029-1036
• /
• 2018

This paper is a study on the development of optimal control system for lighting and air conditioning equipment to save the energy in campus environment. In the case of controling system developed through this research, lighting and air conditioner are controlled by both information on the number of people entering and leaving the room through the motion sensor and image processing, and the information on temperature and humidity. In addition, energy saving is enabled by the results that are controlled through data integration monitoring and command execution functions according to the control signals.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.1
• /
• pp.146-151
• /
• 2021

Currently, the demand for vehicles from one family is increasing in many countries at home and abroad, reducing the number of people on the vehicle and increasing the number of vehicles on the road. The multi-passenger lane system, which is available to solve the problem of traffic congestion, is being implemented. The system allows police to monitor fast-moving vehicles with their own eyes to crack down on illegal vehicles, which is less accurate and accompanied by the risk of accidents. To address these problems, applying deep learning object recognition techniques using images from road sites will solve the aforementioned problems. Therefore, in this paper, we compare and analyze the performance of existing deep learning models, select a deep learning model that can identify real-time vehicle occupants through video, and propose a vehicle occupancy detection algorithm that complements the object-ident model's problems.

• Journal of Korean Society of Transportation
• /
• v.22 no.7 s.78
• /
• pp.41-48
• /
• 2004

We may consider the inducement of demand to public transportation as a solution to relieve traffic congestion and pollution. Subway has merits as moving on schedule, transporting more people than bus. But subway is required a vast investment in the early stage of construction has a huge debt. So it runs into red figures, and on this account, services of subway are falling more and more. Development of subway's operation cost function is useful to understand structure of subway's operation and catch the relations of operation cost and actual results. In addition, we can present the policy that is a helpful to the operation as development of operation cost function. But there are short of studies about operation cost deal with a subway comparison with local train. Because local train has many lines and data, on the other hand, subway has one to four lines and less data. Most of previous studies sought the operation cost function of Seoul. So this study aimed to develop and apply the operation cost function of Seoul, Incheon, Busan and Daegu area using full allocation method. In this study, we considered the number of passengers, track-km, train-km, revenue as actual results. By appling the operation cost function, we compared the average cost of each city and confirmed the existence of economies of scale about the number of passengers, train-km.