Journals Articles Conferences News About CLP
Submit a paper Email Alert
Search
Search
Articles
Journals
News
Advanced Search
Top Searches
2D MaterialsTransformation opticsQuantum PhotonicsSmall lasersSemiconductor UV PhotonicsSupersymmetric microring laser arrays

Laser & Optoelectronics Progress, Volume. 58, Issue 16, 1615007(2021)

Lightweight Real-Time Target Detection Model for Remote Sensing Images

Yuhuan Li1、*, Jie Wang1, Li Lu1, and Ying Nie2
Author Affiliations
  • 1Air Defense and Missile Academy, Air Force Engineering University, Xi'an, Shaanxi 710051, China
  • 2Unit 93861 of Sanyuan, Shaanxi, Xianyang, Shaanxi 713800, China
    • show less
    AbstractGet PDF(in Chinese)
    Figures&Tables (13)
    Equations (0)
    References (22)
    Cited By (1)
    Tools
    Paper Information
    Topics
    Figures & Tables(13)
    Tiny YOLO-V3 network structure

    Fig. 1. Tiny YOLO-V3 network structure

    Download full size
    Improved backbone network structure

    Fig. 2. Improved backbone network structure

    Download full size
    Structure of detection head in Tiny YOLO-V3

    Fig. 3. Structure of detection head in Tiny YOLO-V3

    Download full size
    Improved detection head structure

    Fig. 4. Improved detection head structure

    Download full size
    Partial sample images in dataset. (a) Aircraft; (b) oiltank; (c) flyover; (d) playground

    Fig. 5. Partial sample images in dataset. (a) Aircraft; (b) oiltank; (c) flyover; (d) playground

    Download full size
    Experimental process

    Fig. 6. Experimental process

    Download full size
    Change curve of learning rate in training process

    Fig. 7. Change curve of learning rate in training process

    Download full size
    Change curve of loss value during training

    Fig. 8. Change curve of loss value during training

    Download full size
    Partial test results of different models. (a) Tiny YOLO - V3; (b) test results of improved model; (c) dataset labels

    Fig. 9. Partial test results of different models. (a) Tiny YOLO - V3; (b) test results of improved model; (c) dataset labels

    Download full size

    • Table 1. Number of partitions in dataset

      View table

      Table 1. Number of partitions in dataset

      DatasetAircraftOiltankFlyoverPlayground
      Training set390136141130
      Test set56293519

    • Table 2. Configuration of experimental environment

      View table

      Table 2. Configuration of experimental environment

      FacilitieVersion
      Operating system of trainingWindows10.0
      Processor of trainingIntel(R)Core(TM) i7-9700 CPU 3.00 GHz
      Operating system of testLinux raspberrypi 4.19.118-v7l+
      Processor of testCortex-A72(ARM v8)
      PyThon3.6.5
      TensorFlow1.14.0

    • Table 3. mAP values of Tiny YOLO-V3 and improved model

      View table

      Table 3. mAP values of Tiny YOLO-V3 and improved model

      ModelAPmAP
      AircraftOiltankFlyoverPlayground
      Tiny YOLO-V30.6080.3970.0070.0230.253
      Improved model0.6350.4310.0120.0220.275

    • Table 4. Complexity and frame rate of different models

      View table

      Table 4. Complexity and frame rate of different models

      ModelTime complexitySpace complexityFPS
      Tiny YOLO-V32767598080591762521.83
      Improved model423320000190237083.01
    Tools

    Get Citation

    Copy Citation Text

    Yuhuan Li, Jie Wang, Li Lu, Ying Nie. Lightweight Real-Time Target Detection Model for Remote Sensing Images[J]. Laser & Optoelectronics Progress, 2021, 58(16): 1615007

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Set citation alerts for article
    Save article for my favorites
    Paper Information

    Category: Machine Vision

    Received: Oct. 20, 2020

    Accepted: Dec. 22, 2020

    Published Online: Aug. 25, 2021

    The Author Email: Yuhuan Li (xiao_wandering@163.com)

    DOI:10.3788/LOP202158.1615007

    Topics

    laser devices and laser physics
    Lasers and Laser Optics
    Laser physics
    laser manufacturing
    Instrumentation, Measurement and Metrology