• Laser & Optoelectronics Progress
  • Vol. 55, Issue 6, 061010 (2018)
Tingting Gu1、1; , Haitao Zhao1、1; , and Shaoyuan Sun2、2;
Author Affiliations
  • 1 School of Information Science and Engineering, East China University of Science and Technology, Shanghai 200237, China
  • 2 School of Information Science and Technology, Donghua University, Shanghai 201620, China
  • show less
    DOI: 10.3788/LOP55.061010 Cite this Article Set citation alerts
    Tingting Gu, Haitao Zhao, Shaoyuan Sun. Depth Estimation of Single Infrared Image Based on Interframe Information Extraction[J]. Laser & Optoelectronics Progress, 2018, 55(6): 061010 Copy Citation Text show less
    Radar scatter plot
    Fig. 1. Radar scatter plot
    Hierarchies of the ground truth. (a) 12 hierarchies; (b) 22 hierarchies; (c) 32 hierarchies; (d) original ground truth
    Fig. 2. Hierarchies of the ground truth. (a) 12 hierarchies; (b) 22 hierarchies; (c) 32 hierarchies; (d) original ground truth
    Architecture of proposed network
    Fig. 3. Architecture of proposed network
    Comparison of (a) 2D convolution and (b) 3D convolution
    Fig. 4. Comparison of (a) 2D convolution and (b) 3D convolution
    Data acquisition equipment
    Fig. 5. Data acquisition equipment
    Infrared imaging and radar scatter plot at corresponding time. (a) Infrared imaging; (b) radar scatter points
    Fig. 6. Infrared imaging and radar scatter plot at corresponding time. (a) Infrared imaging; (b) radar scatter points
    Comparison of traditional methods. (a) Scenario1; (b) scenario2; (c) scenario3; (d) scenario4
    Fig. 7. Comparison of traditional methods. (a) Scenario1; (b) scenario2; (c) scenario3; (d) scenario4
    Comparison of proposed method with traditional methods
    Fig. 8. Comparison of proposed method with traditional methods
    Data joint distribution. (a) Scenario1; (b) scenario2; (c) scenario3; (d) scenario4
    Fig. 9. Data joint distribution. (a) Scenario1; (b) scenario2; (c) scenario3; (d) scenario4
    Comparison of experimental results. (a) Scenario1; (b) scenario2; (c) scenario3; (d) scenario4
    Fig. 10. Comparison of experimental results. (a) Scenario1; (b) scenario2; (c) scenario3; (d) scenario4
    LayerConv1kernel strideConv2kernel stride
    Init1×11×1
    Residual block1 init1×11×1
    Residual block2 init2×21×1
    Residual block2 init2×21×1
    Table 1. Convolutional kernel stride of 2D network residual blocks
    LayerChannelKernelStrideLayerChannelKernelStride
    Conv1641×1×11×1×1Conv4a5121×1×11×1×1
    Pool1641×2×21×2×2Conv4b5121×1×11×1×1
    Conv21281×1×11×1×1Pool45122×2×22×2×2
    Pool21282×2×22×2×2Conv5a5121×1×11×1×1
    Conv3a2561×1×11×1×1Conv5b5121×1×11×1×1
    Conv3b2561×1×11×1×1Pool55122×2×22×2×2
    Pool32562×2×22×2×2Fc--
    Table 2. Architecture of 3D network
    Methodδ<1.25δ<1.252δ<1.253RELlog 10RMSE
    Proposed method0.7690.8990.9380.1960.0813.112
    method0.7520.8900.9250.2180.0873.201
    ResNet-320.7410.8750.9190.2410.0873.285
    FCN-Vgg0.7370.8790.9130.2510.0803.290
    method0.6250.8260.8920.2970.1154.098
    FCN-AlexNet0.5750.8060.8900.3200.1214.101
    MLP0.1750.3770.6016.6980.2949.883
    SVM0.1820.3790.6226.8080.2989.615
    KNN0.1820.6560.5055.4200.38510.250
    DT0.2570.5080.6986.2420.27610.323
    Table 3. Performance evaluation of comparative experiments
    Tingting Gu, Haitao Zhao, Shaoyuan Sun. Depth Estimation of Single Infrared Image Based on Interframe Information Extraction[J]. Laser & Optoelectronics Progress, 2018, 55(6): 061010
    Download Citation