• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.7 no.4
• /
• pp.13-24
• /
• 2008

Real-time traffic data are readily obtainable by traffic surveillance systems of intelligent transportation systems (ITS). Such data greatly support further applications in the field of traffic operations, planning, and safety. However, traffic data should be appropriately processed to fully exploit the benefits of data collection capability. Rather than developing individual data processing techniques, which is major concern of existing studies, this study proposes a novel methodology for evaluating data processing techniques in an integrated manner. Also, a tool for implementing the proposed methodology is developed. Users can extract useful and more reliable traffic data based upon their ultimate purpose of data usage by the evaluation tool developed in this study. Actual freeway traffic data are, as an example, fed into the evaluation tool, and results are discussed.

• Journal of Advanced Navigation Technology
• /
• v.19 no.3
• /
• pp.182-191
• /
• 2015

The automatic dependent surveillance - broadcast (ADS-B) system which is a core system of aviation system block upgrade is designed and implemented. The ADS-B system consists of the 4 blocks and 10 units, and filtering algorithm is applied to the implemented ADS-B system. To evaluate a performance of the implemented ADS-B system, real aircraft position data is used and compared reliable radar data. The comparison results show that average position difference of 99.57 m. In addition, comparisons of aircraft position data between the implemented ADS-B system employing filtering algorithm and the conventional ADS-B system under various situations are carried out, such as aircraft turning, taking off, landing, and cruising. The comparison results show that average position difference of 8.02 m.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.45 no.9
• /
• pp.67-74
• /
• 2008

This paper proposes, designs and implements an architecture of a server involved with the network camera based video surveillance systems to solve common problems including lack of inter-network operability at the video information sharing, drawback of bandwidth and processing-overhead caused by increase of the number of users, and difficulty of continuous monitoring over changes of network configurations. The proposed saver was designed to manage and service numerous network cameras and users as well as solving the existing problems by providing video distribution facility. Through the empirical study after applying the implemented server to a real video surveillance system we proved that the server can provide reasonable service quality while it processes several hundreds of simultaneous user connections under persisting more than one hundred connections to network cameras. We expect the developed video distribution server to enhance service quality of the large scale video surveillance systems for citizen-wide services such as traffic reporting informatics or natural calamities supporting.

• Journal of Advanced Navigation Technology
• /
• v.19 no.2
• /
• pp.123-132
• /
• 2015

Among various fields of the CNS/ATM, the surveillance field which includes ADS-B system, MLAT system, and WAM system is implemented. These next generation systems provide superior performance in tracking aircrafts. However, They still have error. In this paper, filtering algorithm is proposed in order to enhance aircraft tracking performance of ADS-B, MLAT, and WAM systems. The proposed method is a Robust Interacting Multiple Model filter, called Robust IMM filter, that improves IMM filter. The Robust IMM filter can not only improves the aircraft tracking performance but also track aircraft continually using estimates calculated from the filter when data losses occur. The simulation results of the proposed aircraft tracking methods show that the filtering data provides a better performance up to an average of 19.21%.

• Proceedings of the Korea Association of Information Systems Conference
• /
• 2000.05a
• /
• pp.195-199
• /
• 2000

본 논문에서는 인터넷 상의 영상에 기반한 교통 감시 시스템을 구현한다. 영상 기반의 교통 감시 시스템은 루프 감지기 등의 센서를 이용한 방법에 비해 비용과 설치, 유지, 보수면에서의 장점으로 인하여 많이 연구되고 있다. 제안한 시스템은 인터넷상에서 FPA(Field Processing Agent)와 TSM(Traffic Surveillance Manager)으로 구성되며, FPA는 TSM에게 도로 영상과 차량의 속도, 도로 점유율과 같은 교통 정보를 제공한다. 차량의 평균 속도와 도로 점유율은, 도로색 영상과 연속된 입력 영상간의 샘플링 지점의 색상 차이변화를 이용하여 추출한다. 제안한 방법은 근사적인 교통정보를 추출해 주며, 입력 영상 전체에 대한 처리 과정 없이 제한된 영역만을 처리하기 때문에, 실시간 감시 시스템을 구축하는데 용이하다.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2000.06a
• /
• pp.57-81
• /
• 2000

Universal AIS technology is effective and could enhance navigational safety -The AIS provides and improved method of vessel traffic surveillance -Complement to radar in collision avoidance -Invaluable in Search And Rescue operations -Reduce voice communications -Effective Fleet management

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2015.11a
• /
• pp.139-140
• /
• 2015

본 논문에서는 교통 감시 시스템에서 차량추적방법을 제안한다. 교통 감시 카메라를 이용한 차량추적시스템은 차량 감시, 사고감지 및 교통정보를 확인할 수 있게 하는 시스템이다. 차량추적을 위하여 먼저 가우스 혼합 모델(Gaussian Mixture Model)을 이용하여 배경과 전경을 분리하고 형태학적 필터링을 이용하여 차량을 검출한다. 검출된 차량으로부터 SURF(Speed Up Robust Features) 매칭을 통하여 차량추적방법을 제안한다.

• Journal of Korean Society of Transportation
• /
• v.14 no.3
• /
• pp.7-26
• /
• 1996

The estimation of real-time Origin-Destination(O-D) parameters, which gives travel demand between combinations of origin and destination points on a urban freeway network, from on-line surveillance traffic data is essential in developing an efficient ATMS strategy. On this need a real-time O-D parameter estimation model is formulated as a parameter adaptive filtering model based on the extended Kalman Filter. A Monte Carlo test have shown that the estimation of time-varying O-D parameter is possible using only traffic counts. Tests with field data produced the interesting finding that off-ramp volume predictions generated using a constant freeway O-D matrix was replaced by real-time estimates generated using the parameter adaptive filter.

• Journal of information and communication convergence engineering
• /
• v.13 no.3
• /
• pp.197-204
• /
• 2015

In this paper, we present an algorithm for the detection of illegally parked vehicles based on a combination of some image processing algorithms. A digital camera is fixed in the illegal parking region to capture the video frames. An adaptive Gaussian mixture model (GMM) is used for background subtraction in a complex environment to identify the regions of moving objects in our test video. Stationary objects are detected by using the pixel-level features in time sequences. A stationary vehicle is detected by using the local features of the object, and thus, information about illegally parked vehicles is successfully obtained. An automatic alarm system can be utilized according to the different regulations of different illegal parking regions. The results of this study obtained using a test video sequence of a real-time traffic scene show that the proposed method is effective.

• Journal of Information Processing Systems
• /
• v.12 no.4
• /
• pp.661-680
• /
• 2016

The vehicle license plate recognition (VLPR) system analyzes and monitors the speed of vehicles, theft of vehicles, the violation of traffic rules, illegal parking, etc., on the motorway. The VLPR consists of three major parts: license plate detection (LPD), license plate character segmentation (LPCS), and license plate character recognition (LPCR). This paper presents an efficient method for the LPCS and LPCR of Korean vehicle license plates (LPs). LP tilt adjustment is a very important process in LPCS. Radon transformation is used to correct the tilt adjustment of LP. The global threshold segmentation method is used for segmented LP characters from two different types of Korean LPs, which are a single row LP (SRLP) and double row LP (DRLP). The cross-correlation matching method is used for LPCR. Our experimental results show that the proposed methods for LPCS and LPCR can be easily implemented, and they achieved 99.35% and 99.85% segmentation and recognition accuracy rates, respectively for Korean LPs.