• Infrared and Laser Engineering
  • Vol. 53, Issue 2, 20230564 (2024)
Ruishu Xu1、2、3, Xiaonan Luo3, Yaoqiong Shen1、2, Chuangwei Guo1、2, Wentao Zhang3, Yuqing Guan1、2, Yunxia Fu1、2, and Lihua Lei1、2、*
Author Affiliations
  • 1Shanghai Institute of Measurement and Testing Technology, Shanghai 201203, China
  • 2Shanghai Key Laboratory of Online Testing and Control Technology, Shanghai 201203, China
  • 3School of Computer Science and Information Security, Guilin University of Electronic Technology, Guilin 541004, China
  • show less
    DOI: 10.3788/IRLA20230564 Cite this Article
    Ruishu Xu, Xiaonan Luo, Yaoqiong Shen, Chuangwei Guo, Wentao Zhang, Yuqing Guan, Yunxia Fu, Lihua Lei. Research on phase unwrapping technology based on improved U-Net network[J]. Infrared and Laser Engineering, 2024, 53(2): 20230564 Copy Citation Text show less
    (a) Absolute phase (real data set); (b) Wrapped phase (real data set); (c) Absolute phase (simulated data set 1, 2); (d) Wrapped phase (simulated data set 1); (e) Wrapped phase (simulated data set 2); (f) Wrapped phase (simulated data set 3)
    Fig. 1. (a) Absolute phase (real data set); (b) Wrapped phase (real data set); (c) Absolute phase (simulated data set 1, 2); (d) Wrapped phase (simulated data set 1); (e) Wrapped phase (simulated data set 2); (f) Wrapped phase (simulated data set 3)
    Comparison of Shannon entropy between real and simulated dataset
    Fig. 2. Comparison of Shannon entropy between real and simulated dataset
    Network model diagram
    Fig. 3. Network model diagram
    Schematic diagram of CBiLSTM module
    Fig. 4. Schematic diagram of CBiLSTM module
    Attention gate schematic
    Fig. 5. Attention gate schematic
    The performance of each network model under different noise conditions
    Fig. 6. The performance of each network model under different noise conditions
    The performance of each network model in the case of discontinuity
    Fig. 7. The performance of each network model in the case of discontinuity
    Performance of individual network models in case of aliasing
    Fig. 8. Performance of individual network models in case of aliasing
    The generalization ability of each network model in the real data set
    Fig. 9. The generalization ability of each network model in the real data set
    Different performance comparison of each network model
    Fig. 10. Different performance comparison of each network model
    Comparison between the predicted phase and the true absolute phase of the network model proposed in this article in the above three situations
    Fig. 11. Comparison between the predicted phase and the true absolute phase of the network model proposed in this article in the above three situations
    Experimental test system
    Fig. 12. Experimental test system
    Data acquisition diagram
    Fig. 13. Data acquisition diagram
    Horizontal and vertical phase unwrapping on real data sets
    Fig. 14. Horizontal and vertical phase unwrapping on real data sets
    Picture of the experimental situation with dust and scratches on the lens
    Fig. 15. Picture of the experimental situation with dust and scratches on the lens
    Phase unwrapping on complex real datasets
    Fig. 16. Phase unwrapping on complex real datasets
    Network modelNoise NRMSEDiscontinuous NRMSEAliased NRMSE
    Our Net(Loss=Lmeaw)2.05%2.93%2.64%
    Our Net(Loss=Lerror)1.49%2.99%2.35%
    U-Net[20]14.03%12.59%13.48%
    Wang et al[13]13.27%11.6%12.24%
    Res-UNet[21]13.26%14.69%12.98%
    Our Net1.12%1.81%1.68%
    Perera et al[19]1.46%2.09%1.87%
    Table 1. Performance comparison of various network models in terms of errors
    Network modelNoiseDiscontinuousAliased
    Time/sTotal time/sTime/sTotal time/sTime/sTotal time/s
    U-Net[20]726256240662124
    Wang et al[13]113256123996113080
    Res-UNet[21]166384216153176443
    Our Net151275182250132860
    Perera et al[19]181746182574174709
    Table 2. Performance comparison of various network models in terms of time consumption
    Serial number Based on improved U-NetModel CBiLSTMSoft attentionNRMSEPSNRSSIM
    110.06%13.80.46
    20.92%35.780.96
    31.16%34.260.94
    40.75%40.870.98
    Table 3. Quantitative comparison of ablation experiments on noisy datasets
    Ruishu Xu, Xiaonan Luo, Yaoqiong Shen, Chuangwei Guo, Wentao Zhang, Yuqing Guan, Yunxia Fu, Lihua Lei. Research on phase unwrapping technology based on improved U-Net network[J]. Infrared and Laser Engineering, 2024, 53(2): 20230564
    Download Citation