Unmanned Aerial Vehicles (UAVs) are able to provide instantaneous visual cues and a high-level data throughput that could be further leveraged to address complex tasks, such as semantically rich scene understanding. In this work, we built on the use of Large Language Models (LLMs) and Visual Language Models (VLMs), together with a state-of-the-art detection pipeline, to provide thorough zero-shot UAV scene literary text descriptions. The generated texts achieve a GUNNING Fog median grade level in the range of 7–12. Applications of this framework could be found in the filming industry and could enhance user experience in theme parks or in the advertisement sector. We demonstrate a low-cost highly efficient state-of-the-art practical implementation of microdrones in a well-controlled and challenging setting, in addition to proposing the use of standardized readability metrics to assess LLM-enhanced descriptions.


    Access

    Download


    Export, share and cite



    Title :

    Semantic Scene Understanding with Large Language Models on Unmanned Aerial Vehicles


    Contributors:


    Publication date :

    2023




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    Unknown





    Large unmanned aerial vehicle device internally provided with four small unmanned aerial vehicles

    PAN LINGFANG / WANG HUAN | European Patent Office | 2024

    Free access

    UNMANNED AERIAL VEHICLES

    NUÑEZ FERNANDEZ ALBERTO / HILARIO SERRANO EDUARDO / SERRANO MONTERO CESAR | European Patent Office | 2024

    Free access

    UNMANNED AERIAL VEHICLES

    NUÑEZ FERNANDEZ ALBERTO / HILARIO SERRANO EDUARDO / SERRANO MONTERO CESAR | European Patent Office | 2024

    Free access

    Unmanned Aerial Vehicles

    IAIN MATTHEW RUSSELL | European Patent Office | 2023

    Free access