Remote Sensing Image Segmentation Model Based on Attention Mechanism

Fig. 6. Remote sensing images and road labels in Massachusetts Roads dataset. (a) Part of the remote sensing images in the training set; (b) road labels corresponding to images in the training set; (c) some remote sensing images in the test set; (d) road labels corresponding to images in the test set

Download full size

Fig. 7. Remote sensing images and road labels in DeepGlobe dataset. (a) Part of the remote sensing images in the training set; (b) road labels corresponding to images in the training set; (c) some remote sensing images in the test set; (d) road labels corresponding to images in the test set

Download full size

Fig. 8. Segmentation results of different depth models in the Massachusetts Roads test set. (a) Original images; (b) labels; (c) segmentation results of LinkNet; (d) segmentation results of RSANet

Download full size

Fig. 9. Segmentation results of different depth models on the DeepGlobe Road Extraction test set. (a) Original images; (b) labels; (c) segmentation results of LinkNet; (d) segmentation results of RSANet

Download full size

Table 1. Segmentation results of depth models on each test image in Fig. 8

View table

Table 1. Segmentation results of depth models on each test image in Fig. 8

Model	Image 1		Image 2		Image 3
Model	P_r	F_1-score	P_r	F_1-score				P_r	F_1-score	P_r	F_1-score	P_r	F_1-score
LinkNet^[3]	0.839				0.859	0.913	0.881	0.821	0.832	0.800	0.817	0.747	0.779
RSANet	0.979				0.976	0.923	0.892	0.829	0.835	0.822	0.889	0.818	0.827

Table 2. Segmentation results of different depth models on the Massachusetts Roads test set
View table
Table 2. Segmentation results of different depth models on the Massachusetts Roads test set
Model P_r F_1-score Training time /h Inference time per picture /s
LinkNet^[3](baseline) 0.802 0.815 31 0.31
LinkNet-PAM 0.812 0.823 32 0.32
LinkNet-CAM 0.818 0.828 40 0.40
RSANet 0.827 0.843 41 0.41

Table 3. Segmentation results of different depth models on each test image in Fig. 9
View table
Table 3. Segmentation results of different depth models on each test image in Fig. 9
Model Image 6 Image 7 Image 8 Image 9 Image 10
P_r P_IOU P_r P_IOU P_r P_IOU P_r P_IOU P_r P_IOU
LinkNet^[3] 0.770 0.712 0.597 0.515 0.733 0.631 0.886 0.722 0.729 0.704
RSANet 0.792 0.735 0.824 0.696 0.835 0.694 0.907 0.790 0.773 0.723

Table 4. Segmentation results of different depth models on the DeepGlobe Road Extraction test set
View table
Table 4. Segmentation results of different depth models on the DeepGlobe Road Extraction test set
Model P_P P_IOU Training time /h Inference time per picture /s
LinkNet^[3](baseline) 0.785 0.598 31 0.31
LinkNet-PAM 0.791 0.610 32 0.32
LinkNet-CAM 0.796 0.616 40 0.40
RSANet 0.811 0.624 41 0.41

Table 5. Segmentation results of different depth models on the Massachusetts Roads test set
View table
Table 5. Segmentation results of different depth models on the Massachusetts Roads test set
Model P_r P_P F_1-score
FCN-4s^[2] 0.660 0.710 0.684
SegNet^[18] 0.765 0.773 0.768
ELU-SegNet^[18] 0.773 0.852 0.788
ELU-SegNet-R^[18] 0.780 0.847 0.812
DCED^[19] 0.839 0.825 0.829
RSANet 0.827 0.859 0.843

Table 6. Segmentation results of different depth models on the DeepGlobe Road Extraction test set
View table
Table 6. Segmentation results of different depth models on the DeepGlobe Road Extraction test set
Model P_P F_1-score Training time /h Inference time per picture /s
U-Net^[1] 0.764 0.597 70 0.94
SegNet^[20] 0.774 0.602 98 1.8
LinkNet^[3](baseline) 0.785 0.598 31 0.31
RSANet 0.811 0.624 41 0.41

Tools

Get Citation

Copy Citation Text

Hang Liu, Xili Wang. Remote Sensing Image Segmentation Model Based on Attention Mechanism[J]. Laser & Optoelectronics Progress, 2020, 57(4): 041015

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites

Paper Information

Category: Image Processing

Received: Jun. 22, 2019

Accepted: Aug. 14, 2019

Published Online: Feb. 20, 2020

The Author Email: Wang Xili (wangxili@snnu.edu.cn)

DOI:10.3788/LOP57.041015

Topics

laser devices and laser physics

Lasers and Laser Optics

Laser physics

laser manufacturing

Instrumentation, Measurement and Metrology

Table 1. Segmentation results of depth models on each test image in Fig. 8

Table 1. Segmentation results of depth models on each test image in Fig. 8

Table 2. Segmentation results of different depth models on the Massachusetts Roads test set

Table 2. Segmentation results of different depth models on the Massachusetts Roads test set

Table 3. Segmentation results of different depth models on each test image in Fig. 9

Table 3. Segmentation results of different depth models on each test image in Fig. 9

Table 4. Segmentation results of different depth models on the DeepGlobe Road Extraction test set

Table 4. Segmentation results of different depth models on the DeepGlobe Road Extraction test set

Table 5. Segmentation results of different depth models on the Massachusetts Roads test set

Table 5. Segmentation results of different depth models on the Massachusetts Roads test set

Table 6. Segmentation results of different depth models on the DeepGlobe Road Extraction test set

Table 6. Segmentation results of different depth models on the DeepGlobe Road Extraction test set