Optimization of Building Contours by Classifying High-Resolution Images

Wang Shuangxi; Yang Yuanwei; Chang Jingxin; Gao Xianjun

doi:10.3788/LOP57.022801

Journals >Laser & Optoelectronics Progress >Volume 57 >Issue 2 >Page 22801 > Article

Laser & Optoelectronics Progress
Vol. 57, Issue 2, 22801 (2020)

Optimization of Building Contours by Classifying High-Resolution Images

Wang Shuangxi¹, Yang Yuanwei^1、2、*, Chang Jingxin¹, and Gao Xianjun^1、2

Author Affiliations

¹School of Geoscience, Yangtze University, Wuhan, Hubei 430100, China

²State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, Hubei 430079, China

show less

DOI: 10.3788/LOP57.022801 Cite this Article Set citation alerts

Wang Shuangxi, Yang Yuanwei, Chang Jingxin, Gao Xianjun. Optimization of Building Contours by Classifying High-Resolution Images[J]. Laser & Optoelectronics Progress, 2020, 57(2): 22801 Copy Citation Text

show less

Initial results of buildings extracted by shifted shadow analysis. (a) Original remote sensing image A; (b) initial result of building A; (c) original remote sensing image B; (d) initial result of building B

Fig. 1. Initial results of buildings extracted by shifted shadow analysis. (a) Original remote sensing image A; (b) initial result of building A; (c) original remote sensing image B; (d) initial result of building B

Download full size

Fig. 2. Flow chart of building contour optimization

Download full size

Fig. 3. Principle of preliminary fitting

Download full size

Fig. 4. Preliminary fitting effect of building edge contour. (a) Original remote sensing image; (b) initial results of building extraction; (c) building contour after preliminary fitting

Download full size

Fig. 5. Inclination of building contour and its circumscribed rectangle with minimum area. (a) Consistent; (b) inconsistent

Download full size

Fig. 6. Schematics for judging inclination of polygon. (a) Overall positive inclination; (b) overall negative inclination

Download full size

Fig. 7. Principles of regularization of building contour. (a) Schematic for dividing contour into equal segments; (b) schematic of Hausdorff distance calculation

Download full size

Fig. 8. Principle and effect of regularization of building contour

Download full size

Fig. 9. Comparison of extraction results of building contour in image 1#. (a) Original remote sensing image; (b) extraction result by object-oriented segmentation and classification method; (c) extraction result by shifted shadow analysis method; (d) extraction result by proposed method

Download full size

Fig. 10. Comparison of extraction results of building contour in image 2#. (a) Original remote sensing image; (b) extraction result by object-oriented segmentation and classification method; (c) extraction result by shifted shadow analysis method; (d) extraction result by proposed method

Download full size

Fig. 11. Comparison of extraction results of building contour in image 3#. (a) Original remote sensing image; (b) extraction result by object-oriented segmentation and classification method; (c) extraction result by shifted shadow analysis method; (d) extraction result by proposed method

Download full size

Fig. 12. Comparison of extraction results of building contour in image 4#. (a) Original remote sensing image; (b) extraction result by object-oriented segmentation and classification method; (c) extraction result by shifted shadow analysis method; (d) extraction result by proposed method

Download full size

Fig. 13. Comparison of extraction results of building contour in image 5#. (a) Original remote sensing image; (b) extraction result by object-oriented segmentation and classification method; (c) extraction result by shifted shadow analysis method; (d) extraction result by proposed method

Download full size

Imagenumber	Extraction method	Pixel-based performance parameter				Object-based performance parameter
Imagenumber	Extraction method	V_CM	V_CR	F₁	V_OA	V_CM	V_CR	F₁	V_OA
	Proposed method	95.69	94.46	95.07	90.61	100.00	100.00	100.00	100.00
1#	Object-oriented method	92.75	73.18	81.81	69.22	100.00	43.33	60.46	43.33
	Shifted shadow analysis method	89.98	95.62	92.72	86.42	100.00	100.00	100.00	100.00
	Proposed method	88.12	97.13	92.41	85.89	100.00	100.00	100.00	100.00
2#	Object-oriented method	89.76	81.37	85.36	74.46	100.00	78.57	88.00	78.57
	Shifted shadow analysis method	85.92	98.13	91.62	84.54	100.00	100.00	100.00	100.00
	Proposed method	94.11	99.81	96.88	93.95	100.00	100.00	100.00	100.00
3#	Object-oriented method	91.86	84.62	88.09	78.72	100.00	74.07	85.10	74.07
	Shifted shadow analysis method	87.30	98.49	92.55	86.14	100.00	00.00	100.00	100.00
	Proposed method	88.39	97.53	92.73	86.46	98.59	100.00	99.29	98.59
4#	Object-oriented method	80.11	72.07	75.88	61.13	100.00	80.68	89.30	80.68
	Shifted shadow analysis method	73.77	98.40	84.33	72.90	95.77	100.00	97.84	95.77
	Proposed method	91.26	99.05	95.00	90.48	100.00	100.0	100.00	100.00
5#	Object-oriented method	75.52	89.51	81.92	69.38	97.85	95.80	96.81	93.83
	Shifted shadow analysis method	75.49	99.11	85.70	74.98	99.28	97.88	98.58	97.20

Table 1. Comparison of precision of building extraction results shown in Figs. 9--13%

Wang Shuangxi, Yang Yuanwei, Chang Jingxin, Gao Xianjun. Optimization of Building Contours by Classifying High-Resolution Images[J]. Laser & Optoelectronics Progress, 2020, 57(2): 22801

Download Citation

Set citation alerts for the article

Tools

Set citation alerts for the article

Save the article for my favorites

Paper Information