Building Extraction from Remote Sensing Imagery Based on Scale-Adaptive Fully Convolutional Network

Fig. 7. Segmentation results of WHU dataset by different models. (a) Image; (b) label; (c) U-Net; (d) MultiResUNet; (e) Res-UNet; (f) S-UNet; (g) USPP; (h) SA-Net

Download full size

Fig. 8. Segmentation results of the Massachusetts dataset by different models. (a) Image; (b) label; (c) U-Net; (d) MultiResUNet; (e) Res-UNet; (f) S-UNet; (g) USPP; (h) SA-Net

Download full size

Table 1. Number of parameters and the maximum number of batches of different models
View table
Table 1. Number of parameters and the maximum number of batches of different models
Model U-Net USPP S-UNet Res-UNet SA-Net MultiResUNet
Parameter number /10⁶ 7.76 4.82 7.97 4.73 7.13 7.26
Max batch size 37 22 23 19 25 6

Table 2. Random sampling training and regular training results of different models in the WHU dataset

View table

Table 2. Random sampling training and regular training results of different models in the WHU dataset

Model	Batch size	Image size(pixel×pixel)	Graphic card	Video memory /G	IOU /%
U-Net (random cropping training)	16	256×256	RTX 2070	8	88.58
U-Net (Ref. [15])	8	512×512	Nvidia P6000	24	84.08
U-Net (Ref. [4])	6	512×512	Nvidia Titan XP	12	86.80

Table 3. Experimental settings of WHU ariel dataset and Massachusetts dataset

View table

Table 3. Experimental settings of WHU ariel dataset and Massachusetts dataset

Parameter	WHU ariel dataset	Massachusetts dataset
Training image number (size)	4736 (512 pixel×512 pixel)	8631 (512 pixel×512 pixel)
Validation image number (size)	4144 (256 pixel×256 pixel)	144 (256 pixel×256 pixel)
Training epoch	300	200
Steps per epoch	296	540
Batch size	16(6 for MultiResUNet)	16(6 for MultiResUNet)
Iteration number	296×300	540×200
Padding size	0	64

Table 4. Quantitative evaluation results of different models on the WHU and Massachusetts datasets unit: %

View table

Table 4. Quantitative evaluation results of different models on the WHU and Massachusetts datasets unit: %

Dataset	Model	Precision	Recall	IOU	F1 score
WHU	U-Net	94.37	93.52	88.58	93.94
	USPP	94.50	94.35	89.44	94.42
	MultiResUNet	97.00	90.01	87.57	93.37
	S-UNet (Ref. [14])	95.20	93.00	88.80	94.09
	SR-FCN (Ref. [4])	94.40	93.90	88.90	94.15
	S-UNet	94.74	93.77	89.14	94.25
	DeepLab V3+ (Ref. [4])	91.60	94.60	87.10	93.08
	Res-UNet	92.71	93.90	87.44	93.30
	SA-Net	95.27	93.80	89.62	94.53
Massachusetts	U-Net	85.84	81.18	71.60	83.44
	MultiResUNet	93.22	66.84	63.74	77.86
	USPP	88.50	79.37	71.95	83.69
	S-UNet	86.05	81.50	71.99	83.71
	Res-UNet	87.08	77.66	69.64	82.10
	Res-UNet (Ref. [11])	86.21	80.26	71.14	83.13
	JointNet (Ref. [11])	86.21	81.29	71.99	83.68
	SA-Net	86.78	82.70	73.45	84.69

Table 5. Training time of different models on the WHU dataset unit: h
View table
Table 5. Training time of different models on the WHU dataset unit: h
Model U-Net USPP S-UNet Res-UNet SA-Net MultiResUNet
Training time 10.7 11.8 12.8 13.4 13.3 35.1

Table 6. Evaluation results of ablation experiments unit: %
View table
Table 6. Evaluation results of ablation experiments unit: %
Dataset Index U-Net (base-line) MIMO RSPP AFR IOU F1 score
WHU 1 Ö 88.58 93.94
2 Ö Ö 89.37 94.38
3 Ö Ö Ö 89.67 94.55
4 Ö Ö Ö Ö 89.62 94.53
Massachusetts 1 Ö 71.60 83.44
2 Ö Ö 73.02 84.41
3 Ö Ö Ö 73.06 84.44
4 Ö Ö Ö Ö 73.45 84.69

Table 7. Experimental results of small sample conditions unit: %

View table

Table 7. Experimental results of small sample conditions unit: %

Dataset	Model	Precision	Recall	IOU	F1 score
WHU	U-Net	83.03	85.87	73.05	84.43
	USPP	87.42	86.60	77.00	87.01
	S-UNet	87.11	86.64	76.80	86.87
	SA-Net	88.92	86.23	77.86	87.55
Massachusetts	U-Net	86.30	73.46	65.79	79.36
	USPP	86.64	75.79	67.86	80.85
	S-UNet	84.56	79.21	69.20	81.80
	SA-Net	87.49	79.28	71.21	83.18

Tools

Get Citation

Copy Citation Text

Fan Feng, Shuangting Wang, Jin Zhang, Chunyang Wang, Bing Liu. Building Extraction from Remote Sensing Imagery Based on Scale-Adaptive Fully Convolutional Network[J]. Laser & Optoelectronics Progress, 2021, 58(24): 2428006

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites

Paper Information

Category: Remote Sensing and Sensors

Received: Jan. 6, 2021

Accepted: Jan. 20, 2021

Published Online: Dec. 3, 2021

The Author Email: Chunyang Wang (wcy@hpu.edu.cn)

DOI:10.3788/LOP202158.2428006

Topics

laser devices and laser physics

Lasers and Laser Optics

Laser physics

laser manufacturing

Instrumentation, Measurement and Metrology

Table 1. Number of parameters and the maximum number of batches of different models

Table 1. Number of parameters and the maximum number of batches of different models

Table 2. Random sampling training and regular training results of different models in the WHU dataset

Table 2. Random sampling training and regular training results of different models in the WHU dataset

Table 3. Experimental settings of WHU ariel dataset and Massachusetts dataset

Table 3. Experimental settings of WHU ariel dataset and Massachusetts dataset

Table 4. Quantitative evaluation results of different models on the WHU and Massachusetts datasets unit: %

Table 4. Quantitative evaluation results of different models on the WHU and Massachusetts datasets unit: %

Table 5. Training time of different models on the WHU dataset unit: h

Table 5. Training time of different models on the WHU dataset unit: h

Table 6. Evaluation results of ablation experiments unit: %

Table 6. Evaluation results of ablation experiments unit: %

Table 7. Experimental results of small sample conditions unit: %

Table 7. Experimental results of small sample conditions unit: %