Computer vision technology is crucial for environmental perception in autonomous driving, but online computer vision tasks based on object detection often need to perform object detection task first and then downstream tasks, which consumes a lot of time. This paper proposes a dynamic multi-ROI parallel inference architecture for online video analysis, which uses the correlation between video frames to parallelize object detection and downstream tasks, which greatly improves the execution efficiency of the algorithm. Based on this architecture, a two-step object detection algorithm based on parallel inference architecture is further evolved through model sharing, which effectively improves the accuracy of small object detection in high-definition video. The method proposed in this paper is not only suitable for autonomous driving tasks, but can also be extended to more online video analysis scenarios. A large number of experimental data prove that the parallel inference architecture has a significant efficiency improvement effect for online video analysis based on object detection, and can effectively improve the accuracy of small object detection in specific scenes of high-definition video.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Dynamic Multi-ROI Parallel Inference Architecture for Online Video


    Additional title:

    Sae Technical Papers


    Contributors:
    Xue, Dan (author) / Zhou, Mingyu (author) / Feng, Rui (author) / Liu, Tianbi (author) / Lu, Xinfei (author)

    Conference:

    SAE 2022 Intelligent and Connected Vehicles Symposium ; 2022



    Publication date :

    2022-12-22




    Type of media :

    Conference paper


    Type of material :

    Print


    Language :

    English




    Dynamic Multi-ROI Parallel Inference Architecture for Online Video

    Liu, Tianbi / Lu, Xinfei / Xue, Dan et al. | British Library Conference Proceedings | 2022


    2-D parallel memory architecture for video processor

    Di, Z. / Gongxun, S. | British Library Online Contents | 2008



    Forward chaining parallel inference

    Labhart, J. / Rowe, M.C. / Matney, S. et al. | Tema Archive | 1990


    PIPER - A parallel inference engine for the Butterfly multi-computer

    LABHART, JAY / ROWE, MICHAEL / BECHTEL, ROBERT et al. | AIAA | 1989