Environment perception for automated vehicles is achieved by fusing the outputs of different sensors such as cameras, LIDARs and RADARs. Images provide a semantic understanding of the environment at object level using instance segmentation, but also at background level using semantic segmentation. We propose a fully convolutional residual network based on Mask R-CNN to achieve both semantic and instance level recognition. We aim at developing an efficient network that could run in real-time for automated driving applications without compromising accuracy. Moreover, we compare and experiment with two different backbone architectures, a classification type of network and a faster segmentation type of network based on dilated convolutions. Experiments demonstrate top results on the publicly available Cityscapes dataset.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Efficient Instance and Semantic Segmentation for Automated Driving


    Contributors:


    Publication date :

    2019-06-01


    Size :

    1942784 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    EFFICIENT INSTANCE AND SEMANTIC SEGMENTATION FOR AUTOMATED DRIVING

    Petrovai, Andra / Nedevschi, Sergiu | British Library Conference Proceedings | 2019


    Exploiting the Joint Potential of Instance Segmentation and Semantic Segmentation in Autonomous Driving

    Usman, Mohammed / K, Thirumala Akash / Ahmed, Mohammed Riyaz et al. | IEEE | 2023



    Fusion Scheme for Semantic and Instance-level Segmentation

    Costea, Arthur Daniel / Petrovai, Andra / Nedevschi, Sergiu | IEEE | 2018


    Automated Evaluation of Semantic Segmentation Robustness for Autonomous Driving

    Zhou, Wei / Berrio, Julie Stephany / Worrall, Stewart et al. | IEEE | 2020