For self driving cars one of the current key technologies are deep neural networks. Especially in camera based environment perception they are absolutely irreplaceable. The currently developed network models are usually executed on high end consumer or server GPUs. Also the verification of the real-time properties is mostly based on these GPUs. However, if these models are to be used in near-series applications, the question arises whether they can also be used on significantly reduced hardware. To address this question, we conduct a case study with a camera based traffic light detection system [1]. Promising optimization techniques are adapted and applied to the model to investigate potential performance gains achievable with these techniques in the context of self driving car environment perception. In particular, the trade-off between quality and speed is to be examined in detail.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Runtime Optimization of a CNN Model for Environment Perception


    Contributors:


    Publication date :

    2020-10-19


    Size :

    281506 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Sichere AUTOSAR Runtime Environment

    Weich,C. / TTTech,AT | Automotive engineering | 2013


    Runtime Verification

    Alwyn E Goodloe | NTRS


    Runtime FPGA Partial Reconfiguration

    McDonald, E. J. | IEEE | 2008



    Runtime FPGA Partial Reconfiguration

    McDonald, E.J. | Online Contents | 2008