We developed an end-to-end pipeline for brake light transition detection based on cognitive theories of anomaly-detection and model based systems engineering principles. Inspired by cognitive theory, we decompose the visual input stream into the submodalities color, shape, intensity and motion which is closely coupled with a graphical model. A memory module that contains priors is populated by exploitation of knowledge from specifications and simulation. High-fidelity 3D-Simulations have been created to populate motion memory, whereas low-fidelity 3D-projections have been used to create geometric priors. We captured real world sequences containing RGB images, GPS- and inertial measurement-data and annotated them with boundingboxes for cars and their tail and brakelight states, which are used to evaluate the proposed pipeline.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Anomaly detection for automotive visual signal transition estimation


    Contributors:


    Publication date :

    2017-10-01


    Size :

    487774 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Automotive network switch with anomaly detection

    RUAN XIAOFAN / YEO YEE-SENG | European Patent Office | 2020

    Free access

    Automotive network switch with anomaly detection

    RUAN XIAOFAN / YEO YEE-SENG | European Patent Office | 2022

    Free access

    Deep AI for Anomaly Detection in Automotive Cyber-Physical Systems

    Thiruloga, Sooryaa Vignesh / Kukkala, Vipin Kumar / Pasricha, Sudeep | Springer Verlag | 2023


    Stacked LSTM Based Anomaly Detection in Time-Critical Automotive Networks

    Kukkala, Vipin Kumar / Thiruloga, Sooryaa Vignesh / Pasricha, Sudeep | Springer Verlag | 2023