Object detection is important in unmanned aerial vehicle (UAV) reconnaissance missions. However, since a UAV flies at a high altitude to gain a large reconnaissance view, the captured objects often have small pixel sizes and their categories have high uncertainty. Given the limited computing capability on UAVs, large detectors based on convolutional neural networks (CNNs) have difficulty obtaining real-time detection performance. To address these problems, we designed a small-object detector for UAV-based images in this paper. We modified the backbone of YOLOv4 according to the characteristics of small-object detection. We improved the performance of small-object positioning by modifying the positioning loss function. Using the distance metric method, the proposed detector can classify trained and untrained objects through object features. Furthermore, we designed two data augmentation strategies to enhance the diversity of the training set. We evaluated our method on a collected small-object dataset; the proposed method obtained 61.00% m A P 50 on trained objects and 41.00% m A P 50 on untrained objects with 77 frames per second (FPS). Flight experiments confirmed the utility of our approach on small UAVs, with satisfying detection performance and real-time inference speed.


    Access

    Download


    Export, share and cite



    Title :

    Small-Object Detection for UAV-Based Images Using a Distance Metric Method


    Contributors:
    Helu Zhou (author) / Aitong Ma (author) / Yifeng Niu (author) / Zhaowei Ma (author)


    Publication date :

    2022




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    Unknown





    Perceptual color difference metric for complex images based on Mahalanobis distance

    Imai, F. H. / Tsumura, N. / Miyake, Y. | British Library Online Contents | 2001


    Learning a Distance Metric from Relative Comparisons between Quadruplets of Images

    Law, M. T. / Thome, N. / Cord, M. | British Library Online Contents | 2017


    Object distance detection device

    SASAMOTO MANABU / NONAKA SHINICHI | European Patent Office | 2021

    Free access

    OBJECT DISTANCE DETECTION DEVICE

    SASAMOTO MANABU / NONAKA SHINICHI | European Patent Office | 2017

    Free access