Aerial monitoring is critical for safeguarding governmental facilities, restricted areas, and borders, with drones playing a pivotal role due to their precise object location capabilities. However, traditional computer vision methods often lack accuracy, leading to detection errors. The developed system introduces a novel approach that integrates YOLOv4, an advanced object detection algorithm, with DeepSORT for real-time tracking, specifically tailored for drone surveillance. Developed alongside drone technology, the system effectively identifies and locates vehicles and humans within restricted zones. Utilizing YOLOv4 and its Darknet 53 backbone, it ensures precise object detection in drone-captured videos. DeepSORT further enhances geotagging and continuous tracking of identified objects. The system receives live video feeds from drones, processes data at a ground station, and activates surveil-lance protocols based on detected objects. This integration enhances surveillance capabilities, facilitating efficient monitoring and security enforcement in sensitive areas through drone technology.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Advanced Aerial Monitoring and Tracking System: YOLOv4 and DeepSORT Integration for Drone-Based Surveillance


    Contributors:


    Publication date :

    2024-04-26


    Size :

    990371 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English




    Vehicle Surveillance Using U-NET Segmentation and DeepSORT Over Aerial Images

    Hanzla, Muhammad / Yusuf, Muhammad Ovais / Jalal, Ahmad | IEEE | 2024


    Automated Drone Detection Using YOLOv4

    Subroto Singha / Burchan Aydin | DOAJ | 2021

    Free access


    Enhancing Real-Time Human Tracking using YOLONAS-DeepSort Fusion Models

    Athilakshmi, R. / Chandan Sainagakrishna, Pulavarthi Sri / Chaitanya Chowdary Kota, S. Sri et al. | IEEE | 2023