The use of vehicle in-cabin monitoring has been increasing to fulfil the specifications of European safety regulations. These regulations present several requirements for detecting driver distraction, and more complex requirements are soon to be expected in higher automation levels. Today's restraint systems provide optimal protection in standard frontal seat positions and deviations to this might cause severe airbag-induced injuries. This makes in-cabin monitoring critical to improve safety and mitigate dangerous situations in case of a crash, and especially in high levels of autonomous driving. Defining the best sensor positioning inside the vehicle's cabin is a challenge due to its constraints and limitations. The main aim of this work was to verify if simulated 3D human models integrated into a 3D modelled vehicle interior environment can be used to run Deep Learning based human pose estimation models. To perform such task, we utilized the software MakeHuman combined with Blender, to build the virtual environment and create photorealistic scenes containing selected front occupants' postures use cases and then feed into Openpose and Mask R-CNN models. The results showed that using a 2D HPE (Human Pose Estimation) network pre-trained on real data, can detect successfully photorealistic synthetic data of humans under complex scenarios. It is also shown that complex and rare postures can cause failure on 2D HPE detections, as shown in the literature review. This work helps to define the most suitable camera positions which, in combination with specific camera lenses, can deliver quality images for a robust pose detection.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    In-Cabin vehicle synthetic data to test Deep Learning based human pose estimation models




    Publication date :

    2021-07-11


    Size :

    1650669 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    IN-CABIN VEHICLE SYNTHETIC DATA TO TEST DEEP LEARNING BASED HUMAN POSE ESTIMATION MODELS

    Ribas, Luis Gustavo Tomal / Cocron, Marta Pereira / Da Silva, Joed Lopes et al. | British Library Conference Proceedings | 2021


    Transfer Learning for Driver Pose Estimation from Synthetic Data

    Sagmeister, Daniel / Schorkhuber, Dominik / Nezveda, Matej et al. | IEEE | 2023


    Deep Learning-Based Covariance Estimation for Relative Pose Measurements

    Ahrabian, Alireza / Nguyen, Quan / Toulios, Nikos et al. | IEEE | 2024


    6DoF Pose Estimation for Industrial Manipulation Based on Synthetic Data

    Brucker, Manuel / Durner, Maximilian / Márton, Zoltán-Csaba et al. | Springer Verlag | 2020


    Large cabin decomposition pose measurement method and decomposition cabin carrying method

    LI RUIFENG / GUO JING / YANG NA et al. | European Patent Office | 2024

    Free access