• Laser & Optoelectronics Progress
  • Vol. 61, Issue 9, 0901004 (2024)
Xinglei Zhao1,*, Gang Liang1, Jianhu Zhao2, and Fengnian Zhou3
Author Affiliations
  • 1College of Information Science and Engineering, Shandong Agricultural University, Tai'an 271018, Shandong, China
  • 2School of Geodesy and Geomatics, Wuhan University, Wuhan 430079, Hubei, China
  • 3The Survey Bureau of Hydrology and Water Resources of Yangtze Estuary, Shanghai 200136, China
  • show less
    DOI: 10.3788/LOP223239 Cite this Article Set citation alerts
    Xinglei Zhao, Gang Liang, Jianhu Zhao, Fengnian Zhou. Ocean-Land Waveform Classification Based on Multichannel Weighted Voting of Airborne Green Laser[J]. Laser & Optoelectronics Progress, 2024, 61(9): 0901004 Copy Citation Text show less
    Structure of proposed MWV-CNN
    Fig. 1. Structure of proposed MWV-CNN
    Distributions of multichannel field of views of Optech CZMIL system (non-scaled)
    Fig. 2. Distributions of multichannel field of views of Optech CZMIL system (non-scaled)
    Structure of 1D CNN module
    Fig. 3. Structure of 1D CNN module
    Typical laser waveforms of ocean. (a) IR laser channel; (b) green laser deep channel; (c)‒(i) green laser shallow 0‒6 channels
    Fig. 4. Typical laser waveforms of ocean. (a) IR laser channel; (b) green laser deep channel; (c)‒(i) green laser shallow 0‒6 channels
    Typical laser waveforms of land. (a) IR laser channel; (b) green laser deep channel; (c)‒(i) green laser shallow 0‒6 channels
    Fig. 5. Typical laser waveforms of land. (a) IR laser channel; (b) green laser deep channel; (c)‒(i) green laser shallow 0‒6 channels
    Training process of 1D CNN in MWV-CNN
    Fig. 6. Training process of 1D CNN in MWV-CNN
    Classification results of different ocean-land waveform classification methods
    Fig. 7. Classification results of different ocean-land waveform classification methods
    Relationship between classification accuracy and channel number of MWV-CNN and MV-CNN
    Fig. 8. Relationship between classification accuracy and channel number of MWV-CNN and MV-CNN
    MethodClassPredictionOA /%KappaSDOA /%
    OceanLand
    SVMOcean24046167298.520.949
    Land369949822
    1D CNNOcean237975315898.700.9570.48
    Land68452837
    MV-CNNOcean24030982499.420.9800.03
    Land89852623
    MWV-CNNOcean24036676799.450.9820.02
    Land84952672
    Table 1. Confusion matrices and performance metrics of different ocean-land waveform classification methods
    Xinglei Zhao, Gang Liang, Jianhu Zhao, Fengnian Zhou. Ocean-Land Waveform Classification Based on Multichannel Weighted Voting of Airborne Green Laser[J]. Laser & Optoelectronics Progress, 2024, 61(9): 0901004
    Download Citation