This paper focuses on monocular-video-based stationary detection of the pedestrian's intention to enter the traffic lane. We propose a motion contour image based HOG-like descriptor, MCHOG, and a machine learning algorithm that reaches the decision at an accuracy of 99 % within the initial step at the curb of smart infrastructure. MCHOG implicitly comprises the body language of gait initiation, especially the body bending and the spread of legs. In a case study at laboratory conditions we present ROC performance data and an evaluation of the span of time necessary for recognition. While MCHOG in special cases indicates detection of the intention before the whole body moves, on average it allows for detection of the movement within 6 frames at a frame rate of 50 Hz and an accuracy of 80 %. Feasibility of the method in a real world intersection scenario is demonstrated.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Early detection of the Pedestrian's intention to cross the street


    Contributors:


    Publication date :

    2012-09-01


    Size :

    1818271 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Stereo-Vision-Based Pedestrian's Intention Detection in a Moving Vehicle

    Kohler, Sebastian / Goldhammer, Michael / Zindler, Klaus et al. | IEEE | 2015



    Pedestrian's Psychology on Gap Selecting when Crossing Street

    Liu, G. / Li, K. / China Communications and Transportation Association; Transportation & Development Institute (American Society of Civil Engineers) | British Library Conference Proceedings | 2009


    Trajectory tracking and prediction of pedestrian's crossing intention using roadside LiDAR

    Zhao, Junxuan / Xu, Hao / Wu, Jianqing et al. | Wiley | 2019

    Free access

    Trajectory tracking and prediction of pedestrian's crossing intention using roadside LiDAR

    Zhao, Junxuan / Xu, Hao / Wu, Jianqing et al. | IET | 2019

    Free access