• Journal of the Korean Society of Marine Environment & Safety
• /
• v.27 no.2
• /
• pp.238-246
• /
• 2021

Collision of small vessels such as fishing boats cause great personal injury. Prior to this study, the collision prevention algorithm was developed to assess the collision risk and make the collision alarm. However, a service provided for safety, such as a collision warning, not only prevents risks, but also requires a certain degree of user satisfaction to function effectively. In this study, the collision prevention algorithm for small vessels was improved to be more practical, and the effects of the improvement were confirmed by applying the algorithm. A survey conducted on the users of the collision warning service confirmed the user requirements for improving the accuracy of the collision warning system and reducing the volume and number of alarms. Accordingly, the algorithm was improved for user satisfaction, and the actual vessel experiment was performed applying the improved algorithm in an actual maritime environment. As a result, the frequency of alarm occurrence decreased compared to former algorithm, but the alarm was relatively steadily generated in dangerous situations. It was analyzed that the accuracy and practicality of the collision alarm were improved. If the practicality and reliability of the improved algorithm are verified in the further study, it will be able to effectively contribute to the prevention of collisions of small vessels.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2018.05a
• /
• pp.311-313
• /
• 2018

해양안전심판원의 해양사고 통계자료에 따르면 기관손상 등을 제외한 해양사고 중 충돌사고의 비중은 가장 높고, 대부분의 충돌사고는 경계소흘 등 운항과실이 약 90%를 차지한다. 본 연구에서는 운항자의 항행 안전을 지원하고자 육상 무선 통신기술을 이용하여 중소형 선박의 충돌예방 시스템을 최종적으로 개발하기 위해 먼저 소형어선(30톤미만) 운항자의 요구분석을 수행하였다. 분석을 통해 충돌회피거리, 당직자 배치, 긴급피항시 필요시간, 충돌 및 경보시스템 개발에 필요한 사항 등을 도출하였다. 향후 이를 바탕으로 해상에서의 선박충돌 예방을 위한 신뢰성 높은 충돌경보 알고리즘을 개발 적용하는 등 사용자 편의적인 충돌경보 시스템을 개발하고자 한다.

• Journal of Digital Convergence
• /
• v.10 no.10
• /
• pp.295-300
• /
• 2012

Various forward collision warning algorithms have studied in order to protect a car accident. For this, in general, algorithms using an external device such as a camera and sensor generate a forward collision warning. However, if using the external device, it can occur errors due to device characteristics when there is rain or fog. Also, the prevention of a chain-reaction collision is insufficient because the system generates a warning in case of only vehicle having a forward collision danger. If it combines the vehicle safety communications, the method becomes a solution to protect a chain-reaction collision. So, In this paper, we proposes a improved forward collision warning algorithm using the wireless communication technique, driver's information, breaking distance, and velocity. And we compare and analyze our algorithm and previous algorithms.

• Journal of Internet Computing and Services
• /
• v.13 no.4
• /
• pp.95-102
• /
• 2012

The development of applications for vehicular ad hoc networks (VANETs) has very specific and clear goals such as providing intellectual safe transport systems. An emergency warning technic for public safety is one of the applications which requires an intelligent broadcast mechanism to transmit warning messages quickly and efficiently against the time restriction. The broadcast storm problem causing several packet collisions and extra delay has to be considered to design a broadcast protocol for VANETs, when multiple nodes attempt transmission simultaneously at the access control layer. In this paper, we propose an early intelligent alert broadcasting (EI-CAST) algorithm to resolve effectively the broadcast storm problem and meet time-critical requirement. The proposed algorithm uses not only the early alert technic on the basis of time to collision (TTC) but also the intelligent broadcasting technic on the basis of fuzzy logic, and the performance of the proposed algorithm was compared and evaluated through simulation with the existing broadcasting algorithms. It was demonstrated that the proposed algorithm shows a vehicle can receive the alert message before a collision and have no packet collision when the distance of alert region is less than 4 km.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.6 no.3
• /
• pp.157-167
• /
• 2011

Although vehicles become more intelligent for convenience and safety of drivers, traffic accidents are increased more and more. Especially, car-to-car single rear impacts in the urban area are increased rapidly because of driver inattention. To prevent rear impacts in the urban area, commercial automobile vendor applies the low-speed short-distance collision warning system. This paper presents low-speed short-distance collision warning algorithm for the city driving by using sensor fusion of laser sensor and ultrasonic sensor. An experiment using embedded microprocessor in the driving track was used to demonstrate the feasibility of the collision warning algorithm.

• Journal of Navigation and Port Research
• /
• v.47 no.6
• /
• pp.358-366
• /
• 2023

This study aimed to provide a solution for improving ship collision alert of the 'accident vulnerable ship monitoring service' among the 'intelligent marine traffic information system' services of the Ministry of Oceans and Fisheries. The current ship collision alert uses a supervised learning (SL) model with survey labels based on large ship-oriented data and its operators. Consequently, the small ship data and the operator's opinion are not reflected in the current collision-supervised learning model, and the effect is insufficient because the alarm is provided from a longer distance than the small ship operator feels. In addition, the supervised learning (SL) method requires a large number of labeled data, and the labeling process requires a lot of resources and time. To overcome these limitations, in this paper, the classification model of collision alerts for small ships using unlabeled data with the semi-supervised learning (SSL) algorithms (Label Propagation and TabNet) was studied. Results of real-time experiments on small ship operators using the classification model of collision alerts showed that the satisfaction of operators increased.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2004.10a
• /
• pp.939-943
• /
• 2004

The side and rear-side collision warning system using fuzzy control algorithms is discussed in this paper. Common rearside warning system has many problems. For example if target vehicle comes into the warning area, it must unconditionally warn. Drivers could be interrupted by it. To solve the problem, I divided measuring area into two sections. One section is blind area of vehicle and the other rear-side area. For blind area, obtained data was filtered inefficient warning signal by using relative velocity method. For rear-side area, a fuzzy logic algorithm is used to recognition of obstacles. According to our experiment relative velocity method and fuzzy logic algorithms were very efficient.

• Journal of the Korean Society for Precision Engineering
• /
• v.24 no.2 s.191
• /
• pp.73-85
• /
• 2007

The rear lateral collision warning system using fuzzy control algorithms is discussed in this paper. Common rear lateral warning system has many problems. For example if target vehicle comes into the warning area, it must unconditionally warn. Drivers could be interrupted by it. To solve the problem, I divided measuring area into two sections. One section is blind area of vehicle and the other rear lateral area. For blind area, obtained data was filtered inefficient warning signal by using relative velocity method. For rear lateral area, a fuzzy logic algorithm is used to recognition of obstacles. According to our experiment relative velocity method and fuzzy logic algorithms were very efficient.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.10a
• /
• pp.890-893
• /
• 2014

In this paper, we present a signal processing algorithm for a marine radar system, in which the evaluation of probability of collision as well as target detection and tracking are performed. Moreover, the digital signal processor that implements the algorithm is proposed. As simulation environment, a mechanically scanning antenna utilizing FMCW signal is used, conducting the beamforming operation with 1 degrees intervals. Test board consists of DSP chips and FPGA, which enable the implemented system to operate in real-time.

• Proceedings of the KSME Conference
• /
• 2007.05a
• /
• pp.849-854
• /
• 2007

This paper describes design and tuning of a full-range Adaptive Cruise Control (ACC) with collision avoidance. The control scheme is designed to control the vehicle so that it would feel natural to the human driver and passengers during normal safe driving situations and to avoid rear-end collision in vehicle following situations. In this study, driving situations are determined using a non-dimensional warning index and time-to-collision (TTC). A confusion matrix method based on natural driving data sets was used to tune control parameters in the proposed ACC System. An ECU-Brake Hardware-in-the-loop Simulation (HiLS) was developed and used for an evaluation of ACC System. The ECU-Brake HiLS results for alternative driving situation are compared to manual driving data measured on actual traffic way. The ACC/CA control logic implemented in an ECU was tested using the ECU-Brake HiLS in a real vehicle environment.