Traditional path loss methods typically employ statistical or empirical models, without fully considering the dynamic propagation environment. In this paper, we introduce a method called Visual Sensing-Based Path Loss Prediction (VSB-PLM), which predicts path loss using visual data obtained from multi-view sensing cameras. Specifically, we deploy multi-view cameras in real-world scenarios. Then, a Convolutional Neural Network (CNN) is designed to integrate environmental image features, the existence of the Line-Of-Sight (LOS) path, and the distance between the Transmitter (Tx) and Receiver (Rx) for path loss prediction. Finally, optimal path loss prediction results are obtained utilizing a multi-view selection algorithm. Simulation results demonstrate that the proposed algorithm has successfully improved path loss prediction accuracy by 9% compared to single-view sensing, achieving a Root Mean Squared Error (RMSE) of 3.66 dB.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Visual Sensing-Based Path Loss Prediction Method


    Contributors:
    Tian, Yixuan (author) / Sun, Yutong (author) / Yu, Li (author) / Zhang, Jianhua (author) / Zhang, Yuxiang (author) / Liu, Guangyi (author)


    Publication date :

    2024-06-24


    Size :

    1066933 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Path Loss Prediction in Smart Campus Environment: Machine Learning-based Approaches

    Singh, Harsh / Gupta, Shivam / Dhawan, Charchit et al. | IEEE | 2020


    Path prediction device and path prediction method

    YANAGIHARA TADASHI / HORIGUCHI KENJI / KURIHARA KEISUKE et al. | European Patent Office | 2019

    Free access

    PATH PREDICTION DEVICE AND PATH PREDICTION METHOD

    YANAGIHARA TADASHI / HORIGUCHI KENJI / KURIHARA KEISUKE et al. | European Patent Office | 2017

    Free access

    Comparing Path Loss Prediction Methods for Low Altitude UAS Flights

    Wieland, Frederick / Drescher, Zach / Houser, John | IEEE | 2021