• Title/Summary/Keyword: 편향주행

Search Result 5, Processing Time 0.017 seconds

A Study on Efficient Vehicle Classification based on 3-Piezo Sensor AVC SYSTEM (3-Piezo 센서 기반 교통량 조사시스템의 차종분류방식에 대한 연구)

  • Cho, Sung-Yun;Lee, Dong-Gyu;Ruy, Seung-Ki
    • The Journal of the Institute of Internet, Broadcasting and Communication
    • /
    • v.13 no.3
    • /
    • pp.25-31
    • /
    • 2013
  • The AVC System which has operated in Highways has two-piezo sensors. In this system the piezo sensors are installed on parally each other this configuration has a defect about diversion driving and sensor damage. In this reserch, 3-Sensor AVC algorithm has been proposed which is supported enhance accuracy of the vehicle classification rate compare with usual 2-Sensor systems. This algorithm is allowed to calculate wheel tread, wheel width. The third inclinded piezo sensor can detec twheel tread, wheel width using signal processing. 3-Sensor AVC has been installed in real highway and the outcome performance has been proof.

Object Detection Method Using Adversarial Learning on Domain Discriminator (도메인 판별기의 적대적 학습을 이용한 객체 검출 방법)

  • Hyeonseok Kim;Yeejin Lee
    • Proceedings of the Korean Society of Broadcast Engineers Conference
    • /
    • 2022.11a
    • /
    • pp.91-94
    • /
    • 2022
  • 자율주행 자동차 개발 연구가 활발히 진행됨에 따라 객체 검출기의 성능이 중요하게 되었다. 딥러닝 기술의 발전하면서 객체 검출기의 성능도 큰 발전을 이루었다. 그에 따라 도로 위 차량 검출기의 성능도 발전하고 있으나 평상시 낮 도로상황에서 잘 동작하던 모델은 안개가 끼거나 밤 상황이 되면 제대로 동작하지 못하는 문제를 가지고 있다. 이유는 딥러닝 모델이 학습할 때 사용한 데이터셋의 정보에 따라 특정 도메인에 편향된 특성을 학습하기 때문이다. 따라서, 본 논문에서는 객체 검출 신경망에 도메인 판별기를 적용하여 이와 같은 도메인 이동 문제를 극복하는 모델을 제안한다. 모델의 성능을 Cityscapes 데이터셋과 Foggy Cityscapes 데이터셋을 사용하여 평가한 결과, 기존의 특정 도메인에서 학습한 모델보다 제안하는 모델의 검출 성능이 개선된다는 것을 확인하였다.

  • PDF

A meta-study on the analysis of the limitations of modern artificial intelligence technology and humanities insight for the realization of a super-intelligent cooperative society of human and artificial intelligence (인간 및 인공지능의 초지능 협력사회 실현을 위한 현대 인공지능 기술의 한계점 분석과 인문사회학적 통찰력에 대한 메타 연구)

  • Hwang, Su-Rim;Oh, Hayoung
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.25 no.8
    • /
    • pp.1013-1018
    • /
    • 2021
  • Due to the recent accident caused by the automated vehicle, discussions on the ethical aspects of AI have been actively underway. This paper confirms that AI is inevitably connected to ethical components through the concepts and techniques related to robots-AI, and argues that ethical aspects are built-in, not post facto. Furthermore, this devises a solution to the trolley dilemma that can serve as a clue to ethical problems associated with automated vehicles. Preferentially, that process contains writing Bayesian networks. Next, only important and influential data are left after the pre-processing stage, and crowd-sourcing & extrapolation is used to calculate the exact figures of the networks. Through this process, this argues that humans' subjects are certainly included in implementing algorithms and models and discusses the necessity and direction of engineering liberal arts, especially education of ethics that distinguished from major education to prevent distortions and biases abouts AI systems.

A Study on Safety Improvement of Safety Devices at Entrance of Expressway Tunnels (터널 입구부 안전시설물 안전성 증대방안 연구)

  • Lee, Jeom-Ho;Kim, Jang-Wook;Kim, Deok-Soo;Lee, Soo-Beom
    • International Journal of Highway Engineering
    • /
    • v.10 no.4
    • /
    • pp.235-245
    • /
    • 2008
  • Since rapidly increase of tunnel with increasing of expressway, the study on safety improvement of safety device at entrance of expressway tunnels is necessary. The existence of tunnel occurs more speed reduction than an upward slope by itself, the collision accident of tunnel entrance causes heavier damage than that of general accident on the road. So, many kinds of safety devices such as poly-ethylene barrier, guard-rail are placed on the road side. But these devices affect the drivers as an obstacle. Although there are various safety devices that are placed at tunnel entrance, this study is related to following 2-cases. One is that the poly-ethylene barrier is placed and the other is that a safety devices is not placed. The reason that these two cases are selected, is that poly-ethylene barrier is usually placed at many tunnel entrances and safety devices can affect the drivers as an obstacle. This study is related to the difference of right-hand side clearance between inside tunnel and outside tunnel, too. The average difference observed car speed and VDS(vehicle detect system) speed nearby the tunnel is analysed. Through the statistical analysis of the average difference, this study suggests an alternatives on safety improvement of safety devices at entrance of expressway tunnels. It is concluded that the small difference of right-hand side clearance is desirable to drivers when a poly-ethylene barrier is placed. And when the difference of right-hand side clearance is large, no safety devices is desirable, and when the difference of right-hand side clearance is small, poly-ethylene barrier should be placed to improve safety.

  • PDF

A Study on the Estimation of the V2 X-Rate Ratio for the Collection of Highway Traffic Information (고속도로 교통정보 수집을 위한 V2X 차량비율 추정연구)

  • Na, Sungyong;Lee, Seungjae;Ahn, Sanghyun;Kim, Jooyoung
    • The Journal of The Korea Institute of Intelligent Transport Systems
    • /
    • v.17 no.1
    • /
    • pp.71-78
    • /
    • 2018
  • Transportation is gradually changing into the era of V2X and autonomous cars. Accurate judgement of traffic conditions is an important indicator of route choice or autonomous driving. There are many ways to use probes car such as taxis, as a way to identify accurate traffic conditions. These methods may vary depending on the characteristics of the probe vehicle, and there is a problem with the cost. The V2X vehicle can solve these problems and collect traffic information in real time. If all vehicles are of V2X vehicle, these issues are expected to be resolved briefly. However, if the communication information of a V2X vehicle is represented by a traffic representative in a traffic with only V2X, the traffic information of some V2X vehicles will be able to collect traffic information. To accomplish this, a virtual network and transport were created and various scenarios were performed through SUMO simulations. It has been analyzed that 3-5 % of V2 vehicles are capable of representative the road traffic characteristics. In the future, various follow-up studies are planned.