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. 57, Issue 2, 21508(2020)

Recognition Method for Weeds in Rapeseed Field Based on Faster R-CNN Deep Network

Zhang Le, Jin Xiu, Fu Leiyang, and Li Shaowen*
Author Affiliations
  • Anhui Provincial Key Laboratory of Smart Agricultural Technology and Equipment, School of Information & Computer, Anhui Agricultural University, Hefei, Anhui 230036, China
    • show less
    AbstractGet PDF(in Chinese)
    Figures&Tables (10)
    Equations (0)
    References (25)
    Cited By (4)
    Tools
    Paper Information
    Topics
    Figures & Tables(10)
    Results of image data enhancement. (a) Mixed image of rapeseed and weeds; (b) horizontally flipped image; (c) vertically flipped image; (d) horizontally and vertically flipped image; (e) brightness-enhanced image; (f) brightness-reduced image; (g) saturation-enhanced image; (h) saturation reduced image

    Fig. 1. Results of image data enhancement. (a) Mixed image of rapeseed and weeds; (b) horizontally flipped image; (c) vertically flipped image; (d) horizontally and vertically flipped image; (e) brightness-enhanced image; (f) brightness-reduced image; (g) saturation-enhanced image; (h) saturation reduced image

    Download full size
    Framework of Faster R-CNN deep network

    Fig. 2. Framework of Faster R-CNN deep network

    Download full size
    Framework of RPN

    Fig. 3. Framework of RPN

    Download full size
    Comparison of total losses on SSD

    Fig. 4. Comparison of total losses on SSD

    Download full size
    Comparison of total losses on faster R-CNN model

    Fig. 5. Comparison of total losses on faster R-CNN model

    Download full size
    Comparison of total losses for SSD andFaster R-CNN models

    Fig. 6. Comparison of total losses for SSD andFaster R-CNN models

    Download full size
    Comparison of accuracy for two models

    Fig. 7. Comparison of accuracy for two models

    Download full size
    Comparison of recall rates for two models

    Fig. 8. Comparison of recall rates for two models

    Download full size
    Results of target recognition for rapeseed and weeds. (a) Results of recognition with occlusion; (b) results of recognition without occlusion; (c) results of recognition with complex background; (d) results of recognition with simple background

    Fig. 9. Results of target recognition for rapeseed and weeds. (a) Results of recognition with occlusion; (b) results of recognition without occlusion; (c) results of recognition with complex background; (d) results of recognition with simple background

    Download full size

    • Table 1. Comparison of deep network models

      View table

      Table 1. Comparison of deep network models

      ModelExtraction networkAccuracy /%Recall /%F1 value /%Detection time /ms
      SSDVGG-1678.4772.6475.44178
      SSDResNet-5062.7658.2460.42189
      SSDResNet-10151.6846.1248.74196
      Faster R-CNNVGG-1683.9078.8681.30295
      Faster R-CNNResNet-5060.9654.5057.55308
      Faster R-CNNResNet-10155.3749.3352.18310
    Tools

    Get Citation

    Copy Citation Text

    Zhang Le, Jin Xiu, Fu Leiyang, Li Shaowen. Recognition Method for Weeds in Rapeseed Field Based on Faster R-CNN Deep Network[J]. Laser & Optoelectronics Progress, 2020, 57(2): 21508

    Download Citation

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

    Category: Machine Vision

    Received: Jun. 12, 2019

    Accepted: --

    Published Online: Jan. 3, 2020

    The Author Email: Li Shaowen (shwli@ahau.edu.cn)

    DOI:10.3788/LOP57.021508

    Topics

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