• 한국ITS학회 논문지
• /
• 제22권2호
• /
• pp.133-146
• /
• 2023

도심지역의 교통 상태는 효과적인 교통 운영과 교통 제어를 수행하는 데 필수 요소이다. 하지만 교통 상태를 얻기 위해서 수많은 도로 구간에 교통 센서를 설치하는 것은 막대한 비용이 든다. 이를 해결하기 위해서 시장침투율이 높은 센서인 차량 블랙박스 카메라를 이용하여 교통 상태를 추정하는 것이 효과적이다. 하지만 기존의 방법론은 객체 추적 알고리즘이나 광학 흐름과 같이 계산 복잡도가 높고, 연속된 프레임이 있어야 연산을 수행할 수 있다는 단점이 존재한다. 이에 본 연구에서는 심층학습 모델로 차량과 차선을 탐지하고, 차선 사이의 공간을 관심 영역으로 설정하여 해당 영역의 교통밀도를 추정하는 방법을 제안하였다. 이 방법론은 객체 탐지 모델만을 이용해서 연산량이 적고, 연속된 프레임이 아닌 샘플링된 프레임에 대해 교통 상태를 추정할 수 있다는 장점이 있기에, 보유하고 있는 컴퓨팅 자원에 맞는 교통 상태 추정이 가능하다. 또, 도심지역에서 운행하는 서로 다른 특성의 2개의 버스 노선에서 수집한 블랙박스 영상을 검증한 결과, 교통밀도 추정 정확도가 90% 이상인 것을 확인하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권1호
• /
• pp.41-60
• /
• 2018

Recently, road traffic congestion is becoming a serious urban phenomenon, leading to massive adverse impacts on the ecology and economy. Therefore, solving this problem has drawn public attention throughout the world. One new promising solution is to take full advantage of vehicular ad hoc networks (VANETs). In this study, we propose a new traffic congestion detection and quantification method based on vehicle clustering and fuzzy assessment in VANET environment. To enhance real-time performance, this method collects traffic information by vehicle clustering. The average speed, road density, and average stop delay are selected as the characteristic parameters for traffic state identification. We use a comprehensive fuzzy assessment based on the three indicators to determine the road congestion condition. Simulation results show that the proposed method can precisely reflect the road condition and is more accurate and stable compared to existing algorithms.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권2호
• /
• pp.647-669
• /
• 2016

Multiple attribute for decision making including user preference will increase the complexity of route selection process. Various approaches have been proposed to solve the optimal route selection problem. In this paper, multi attribute decision making (MADM) algorithms such as Simple Additive Weighting (SAW), Weighted Product Method (WPM), Analytic Hierarchy Process (AHP) method and Total Order Preference by Similarity to the Ideal Solution (TOPSIS) methods have been proposed for acoustic signature based optimal route selection to facilitate user with better quality of service. The traffic density state conditions (very low, low, below medium, medium, above medium, high and very high) on the road segment is the occurrence and mixture weightings of traffic noise signals (Tyre, Engine, Air Turbulence, Exhaust, and Honks etc) is considered as one of the attribute in decision making process. The short-term spectral envelope features of the cumulative acoustic signals are extracted using Mel-Frequency Cepstral Coefficients (MFCC) and Adaptive Neuro-Fuzzy Classifier (ANFC) is used to model seven traffic density states. Simple point method and AHP has been used for calculation of weights of decision parameters. Numerical results show that WPM, AHP and TOPSIS provide similar performance.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권11호
• /
• pp.4268-4289
• /
• 2020

Advanced traffic signal timing method plays very important role in reducing road congestion and air pollution. Reinforcement learning is considered as superior approach to build traffic light timing scheme by many recent studies. It fulfills real adaptive control by the means of taking real-time traffic information as state, and adjusting traffic light scheme as action. However, existing works behave inefficient in complex intersections and they are lack of feasibility because most of them adopt traffic light scheme whose phase sequence is flexible. To address these issues, a novel adaptive traffic signal timing scheme is proposed. It's based on actor-critic reinforcement learning algorithm, and advanced techniques proximal policy optimization and generalized advantage estimation are integrated. In particular, a new kind of reward function and a simplified form of state representation are carefully defined, and they facilitate to improve the learning efficiency and reduce the computational complexity, respectively. Meanwhile, a fixed phase sequence signal scheme is derived, and constraint on the variations of successive phase durations is introduced, which enhances its feasibility and robustness in field applications. The proposed scheme is verified through field-data-based experiments in both medium and high traffic density scenarios. Simulation results exhibit remarkable improvement in traffic performance as well as the learning efficiency comparing with the existing reinforcement learning-based methods such as 3DQN and DDQN.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권3호
• /
• pp.1152-1167
• /
• 2018

In this paper, I propose an application layer cooperative congestion control scheme for safety message broadcast in vehicular networks, called CMS, that adaptively controls a vehicle's safety message rate and transmit timing based on the channel congestion state. Motivated by the fact that all vehicles should transmit and receive an application layer safety message in a periodic manner, I directly exploit the message itself as a means of estimating the channel congestion state. In particular, vehicles can determine wider network conditions by appending their local channel estimation result onto safety message transmissions and sharing them with each other. In result CMS realizes cooperative congestion control without any modification of the existing MAC protocol. I present extensive NS-3 simulation results which show that CMS outperforms conventional congestion control schemes in terms of the packet collision rate and throughput, especially in a high-density traffic environment.