• Journal of Information Processing Systems
• /
• v.18 no.3
• /
• pp.428-442
• /
• 2022

A reliable automatic passenger counting (APC) system is a key point in transportation related to the efficient scheduling and management of transport routes. In this study, we introduce a lightweight head detection network using deep learning applicable to an embedded system. Currently, object detection algorithms using deep learning have been found to be successful. However, these algorithms essentially need a graphics processing unit (GPU) to make them performable in real-time. So, we modify a Tiny-YOLOv3 network using certain techniques to speed up the proposed network and to make it more accurate in a non-GPU environment. Finally, we introduce an APC system, which is performable in real-time on embedded systems, using the proposed head detection algorithm. We implement and test the proposed APC system on a Samsung ARTIK 710 board. The experimental results on three public head datasets reflect the detection accuracy and efficiency of the proposed head detection network against Tiny-YOLOv3. Moreover, to test the proposed APC system, we measured the accuracy and recognition speed by repeating 50 instances of entering and 50 instances of exiting. These experimental results showed 99% accuracy and a 0.041-second recognition speed despite the fact that only the CPU was used.

• Proceedings of the KSR Conference
• /
• 2009.05a
• /
• pp.418-423
• /
• 2009

Unlike domestic railway transportation system in which majority of station are equipped with gate access controller and ticket office, it has been a very common practice in overseas railway transit or railway station that they use a pressure door mat, infrared-sensors or CCTV cameras so as to automatically determine the number of passenger onboard and alight and to reflect the information to their business (i.e., deployment of vehicles and human resources). The data collected by the automatic passenger counting (APC) system provides methods how to obtain the information about the number of passenger using the vehicles on the basis of date, time and stop(station) which enables large-scaled transit company to create profits through effective vehicle deployment and management of their employees. This paper addresses the basic features of the automatic passenger counting system using infrared sensor and describes those of the extended APC system in conjunction with wireless technologies such as GPS, WLAN or Cellular network.

• The Journal of the Korea Contents Association
• /
• v.9 no.12
• /
• pp.31-38
• /
• 2009

The objective of this paper is to propose the bus information system that provides bus passenger number. Recently, we use a bus conveniently through introduction of bus information system offering location-based information. However, we need additional information for decision making in order to use a bus comfortably. To do this, first, we analyzed the needs of providing passenger number; second, we adopted GPS and RFID type's transportation card to get location and passenger number. Finally, we implemented the system displaying that information by three types, and tested it. Our proposed system has advantages to use a bus comfortably and to manage a bus efficiently by providing bus passenger number which is the important element for decision making as well as location based information provided by existing bus information systems.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.9 no.3
• /
• pp.622-626
• /
• 2005

This paper presents an active vision system for ITS(intelligent transportation system : ITS). We have described a novel method to provide high quality imaging signals to a system that will perform passenger detection and counting in the roadway. The method calls for two co-registered near-infrared cameras with spectral sensitivity above (upper-band) and below (lower-band) the quality of the signal remains. We propose a novel system based on fusion of near-infrared imaging signals and we demonstrate its adequacy with theoretical and experimental arguments.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.10b
• /
• pp.475-477
• /
• 2001

본 논문에서는 버스에 설치되어 있는 비디오 카메라의 연속된 승차 영상과 추출해둔 배경 영상간의 영상차 분석을 통해 승객이 특정 구역을 통과하는 것을 감지하여 계수하는 방법을 연구하였다. 배경 영상은 운행 시와 같이 배경이 급변할 때는 연속된 두 프레임의 영상차를 이용하여 동적으로 배경 영상을 얻고 정차 시에는 배경 영상을 승차 영상과 비교하여 보정하여 주는 방법으로 최적화된 배경 영상을 얻어내었다. 본 시스템은 실제 상황에서 얻어진 비디오 영상에 적용하여 93.6%의 계수 성공률을 얻어내었다.

• Journal of Internet Computing and Services
• /
• v.21 no.2
• /
• pp.9-18
• /
• 2020

In the field of image processing, a method of detecting and counting passengers as moving objects when getting on and off the bus has been studied. Among these technologies, one of the artificial intelligence techniques, the deep learning technique is used. As another method, a method of detecting an object using a stereo vision camera is also used. However, these techniques require expensive hardware equipment because of the computational complexity of used to detect objects. However, most video equipments have a significant decrease in computational processing power, and thus, in order to detect passengers on the bus, there is a need for an image processing technology suitable for various equipment using a relatively low computational technique. Therefore, in this paper, we propose a technique that can efficiently obtain the number of passengers on the bus by detecting the contour of the object through the background subtraction suitable for low-cost equipment. Experiments have shown that passengers were counted with approximately 70% accuracy on lower-end machines than those equipped with stereo vision camera.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.5
• /
• pp.49-63
• /
• 2019

Crowdedness management at subway platforms is essential to improve services, including the prevention of train delays and ensuring passenger safety. Establishing effective crowdedness mitigation measures for platforms requires accurate estimation of the congestion level. There are temporal and spatial constraints since crowdedness on subway platforms is assessed at certain locations every 1-2 years by hand counting. However, smart cards generate real-time big data 24 hours a day and could be used in estimating congestion. This study proposes a model based on data from transit cards to estimate crowdedness dynamically. Crowdedness was defined as demand, which can be translated into passengers dynamically moving along a subway network. The trajectory of an individual passenger can be identified through this model. Passenger flow that concentrates or disperses at a platform is also calculated every minute. Lastly, the platform congestion level is estimated based on effective waiting areas for each platform structure.

• Journal of Korean Society of Forest Science
• /
• v.77 no.4
• /
• pp.401-413
• /
• 1988

To investigate the users' activity, impact and psychology in Naejang Temple district at Mt. Naejang National Park in Korea, users' density and questionnaire survey at three major picnic areas and passenger counting at major pass were executed and environmental impacton on the site was surveyed. The total number of visitors showed stability at the level of one million persons every year after 1984. Users' impact was much severe along the main trail, the upper cablecar station and the slope from the observatory to Keumsun Valley, The maximum momentary number of users was estimated as 53,000 persons in autumn. Approximately 20% of the total number of visitor used Keumsun Valley and Weonjeok Valley area and 80% of visitors left after using only grassland and cablecar. The visitors' characteristics was similiar to the type of long-distanced national park and the main visiting purpose was to see autumn leaves. The psychological satisfaction did not very significantly as to increasing user's speace. As a result of varimax rotated factor analysis, the 1st factor, most affecting users' psychological satisfaction, was related to landscape and consisted of nature disturbance, crowdedness, noisiness, cleanness, in order of importance. The 2nd factor was related to facilities and consisted of number of toilet, number of waste-baskets, amount of drinking water, safety, in order of importance.