• Laser & Optoelectronics Progress
  • Vol. 59, Issue 12, 1228006 (2022)
Zhenliang Chang1、*, Xiaogang Yang1, Ruitao Lu1, and Hao Zhuang2
Author Affiliations
  • 1College of Missile Engineering, Rocket Force Engineering University, Xi’an 710025, Shaanxi , China
  • 2The 32023 Unit of the People’s Liberation Army, Dalian 116085, Liaoning , China
  • show less
    DOI: 10.3788/LOP202259.1228006 Cite this Article Set citation alerts
    Zhenliang Chang, Xiaogang Yang, Ruitao Lu, Hao Zhuang. High-Resolution Remote Sensing Image Change Detection Based on Improved DeepLabv3+[J]. Laser & Optoelectronics Progress, 2022, 59(12): 1228006 Copy Citation Text show less
    Network structure of DeepLabv3+ basic model
    Fig. 1. Network structure of DeepLabv3+ basic model
    Model structure of improved DeepLabv3+
    Fig. 2. Model structure of improved DeepLabv3+
    Hollow convolution of fusion of different receptive fields. (a) Channel stitching; (b) sampling point distribution of r=12 convolutional layer in original feature map; (c) sampling point distribution of r=12 convolutional layer in r=6 feature map
    Fig. 3. Hollow convolution of fusion of different receptive fields. (a) Channel stitching; (b) sampling point distribution of r=12 convolutional layer in original feature map; (c) sampling point distribution of r=12 convolutional layer in r=6 feature map
    Optimization of intermediate flow structure of backbone network
    Fig. 4. Optimization of intermediate flow structure of backbone network
    Structure of channel attention module
    Fig. 5. Structure of channel attention module
    Part of training samples
    Fig. 6. Part of training samples
    Basic structure of deep convolutional generative confrontation network
    Fig. 7. Basic structure of deep convolutional generative confrontation network
    Changes in different scenarios and time periods. (a) Scene 1; (b) scene 2
    Fig. 8. Changes in different scenarios and time periods. (a) Scene 1; (b) scene 2
    Accuracy curve and loss curve of DeepLabv3+ network. (a) Accuracy curve; (b) loss curve
    Fig. 9. Accuracy curve and loss curve of DeepLabv3+ network. (a) Accuracy curve; (b) loss curve
    Accuracy curve and loss curve of improved DeepLabv3+ network. (a) Accuracy curve; (b) loss curve
    Fig. 10. Accuracy curve and loss curve of improved DeepLabv3+ network. (a) Accuracy curve; (b) loss curve
    Change detection results of DeepLabv3+ (left) and improved DeepLabv3+ (right). (a) Scene 1; (b) scene 2
    Fig. 11. Change detection results of DeepLabv3+ (left) and improved DeepLabv3+ (right). (a) Scene 1; (b) scene 2
    Landsat 8 test images. (a) Scene 3; (b) scene 4
    Fig. 12. Landsat 8 test images. (a) Scene 3; (b) scene 4
    DeepLabv3+ (left) and improved DeepLabv3+ (right) detection results. (a) Scene 3; (b) scene 4
    Fig. 13. DeepLabv3+ (left) and improved DeepLabv3+ (right) detection results. (a) Scene 3; (b) scene 4
    Part of images of OSCD dataset. (a) Scene 5; (b) scene 6
    Fig. 14. Part of images of OSCD dataset. (a) Scene 5; (b) scene 6
    DeepLabv3+ (left) and improved DeepLabv3+ (right) change detection results. (a) Scene 5; (b) scene 6
    Fig. 15. DeepLabv3+ (left) and improved DeepLabv3+ (right) change detection results. (a) Scene 5; (b) scene 6
    Expansion rate rEffective operation elementReceptive fieldInformation utilization
    69135.33
    129251.44
    189370.66
    12+649373.58
    18+1281612.18
    Table 1. Effect of fusion of different receptive fields on convolution of holes
    Evaluation index(EI)Improved DeepLabv3+DeepLabv3+Literature[11Literature[12Literature[13
    Kappa coefficient(Kappa)0.750.640.580.190.35
    Overall accuracy(OA)95.1%93.6%92.8%95.1%87.7
    Omission rate(OR)4.6%5.2%3.4%78.1%5.0%
    Error rate(ER)5.6%18.0%21.2%2.5%37.2%
    Sensitivity(SS)94.4%81.2%68.6%21.8%65.9%
    Specificity(SP)95.2%94.9%94.0%97.4%94.2%
    Balance accuracy(BA)94.8%88.1%81.3%59.6%80.1%
    F1-score(F1)77.8%69.7%70.1%21.5%64.3%
    Time required /s12.7112.6516.061.100.26
    Table 2. Comparison of change detection results of different methods
    Evaluation index(EI)KappaOA%OR%ER%SP%BA%FI%
    DeepLabv3+0.4195.748.63.196.974.143.1
    Improved DeepLabv3+0.5696.420.03.196.888.457.7
    Table 3. Change detection results of deep convolution method based on Landsat 8 data
    Evaluation index(EI)KappaOA%OR%ER%SP%BA%FI%
    DeepLabv3+0.3975.28.735.583.776.839.0
    Improved DeepLabv3+0.4483.65.327.289.180.344.8
    Table 4. Comparison of depth change detection results based on OSCD data
    Zhenliang Chang, Xiaogang Yang, Ruitao Lu, Hao Zhuang. High-Resolution Remote Sensing Image Change Detection Based on Improved DeepLabv3+[J]. Laser & Optoelectronics Progress, 2022, 59(12): 1228006
    Download Citation