Advanced driver assistance and automated driving systems rely on risk estimation modules to predict and avoid dangerous situations. Current methods use expensive sensor setups and complex processing pipelines, limiting their availability and robustness. To address these issues, we introduce a novel deep learning based driving risk assessment framework for classifying dangerous lane change behavior in short video clips captured by a monocular camera. First, semantic segmentation masks were generated from individual video frames with a pre-trained Mask R-CNN model. Then, frames overlayed with these masks were fed into a time distributed CNN-LSTM network with a final softmax classification layer. This network was trained on a semi-naturalistic lane change dataset with annotated risk labels. A comprehensive comparison of state-of-the-art pre-trained feature extractors was carried out to find the best network layout and training strategy. The best result, with a 0.937 AUC score, was obtained with the proposed framework. Our code and trained models are available open-source1.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Risky Action Recognition in Lane Change Video Clips using Deep Spatiotemporal Networks with Segmentation Mask Transfer


    Contributors:


    Publication date :

    2019-10-01


    Size :

    996116 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Lane Change Behavior on Freeways: An Online Survey Using Video Clips

    V. L. Knoop / M. Keyvan-Ekbatani / M. de Baat et al. | DOAJ | 2018

    Free access

    Video action recognition for lane-change classification and prediction of surrounding vehicles

    Biparva, Mahdi / Fernández-Llorca, David / Izquierdo-Gonzalo, Rubén et al. | ArXiv | 2021

    Free access

    Video Action Recognition for Lane-Change Classification and Prediction of Surrounding Vehicles

    Biparva, Mahdi / Fernandez-Llorca, David / Gonzalo, Ruben Izquierdo et al. | IEEE | 2022


    Emotion Recognition in Video Clips Using Simple and Extended Center Symmetric LBP

    Zahid, Zaki / Shaukat, Arslan / Khan, Rizwan Ahmed et al. | IEEE | 2019


    Drivers’ Emotions’ Recognition Using Facial Expression from Live Video Clips in Autonomous Vehicles

    Rameshtrh, Tumaati / Sanampudi, Anusha / Srijayanthis, S. et al. | Wiley | 2024