Identifying interactions of vehicles on the road is important for accident analysis and driving behavior assessment. Our interactions include those with passing/passed, cut-in, crossing, frontal, on-coming, parallel driving vehicles, and ego-vehicle actions to change lane, stop, turn, and speeding. We use visual motion recorded in driving video taken by a dashboard camera to identify such interaction. Motion profiles from videos are filtered at critical positions, which reduces the complexity from object detection, depth sensing, target tracking, and motion estimation. The results are obtained efficiently, and the accuracy is also acceptable. The results can be used in driving video mining, traffic analysis, driver behavior understanding, etc.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Detecting Vehicle Interactions in Driving Videos via Motion Profiles


    Contributors:
    Wang, Zheyuan (author) / Zheng, Jiang Yu (author) / Gao, Zhen (author)


    Publication date :

    2020-09-20


    Size :

    1721330 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English





    Vehicle–Bicyclist Dynamic Position Extracted From Naturalistic Driving Videos

    Liu, Chao / Fujishiro, Ryo / Christopher, Lauren et al. | IEEE | 2017


    Method for detecting vehicle speed based on road monitoring videos

    MIAO ZHENJIANG / HU BIYING / ZHANG QIANG et al. | European Patent Office | 2015

    Free access

    Driving Behavior Aware Caption Generation for Egocentric Driving Videos Using In-Vehicle Sensors*

    Zhang, Hongkuan / Takeda, Koichi / Sasano, Ryohei et al. | IEEE | 2021