An Effective Data-Driven Method for 3-D Building Roof Reconstruction and Robust Change Detection
Abstract
:1. Introduction
2. Related Works
2.1. 3-D Building Roof Modelling
2.2. 3-D Building Change Detection
3. Challenges and Contributions
- Insertion of missing planes: A missing plane can be a small plane from where the number of reflected laser points is limited, possibly due to a low point density. It can also be due to a height jump between planes. A slanted plane is grown if there is an existence of unsegmented LiDAR points between any two planes. Otherwise, a vertical plane is inserted between the planes.
- Reconstruction of complete building models: When there are missing planes, the topological relationship among the roof planes is incorrect. Thus, an adjacency matrix that defines the topological relationships among the input roof planes of a building is first constructed. Then, the matrix is updated (i.e., the topological relationship is corrected) based on the inserted missing planes. Finally, the building model is generated using the correct topological relationship and the revised intersection lines among the inserted missing planes and the input roof planes.
4. Proposed 3-D Building Modelling Technique
4.1. Adjacency of Roof Planes and Their Intersection Lines
4.2. Detection and Insertion of Missing Roof Planes
4.3. Insertion of Vertical Roof Planes
4.4. Rooftop Topology and Modelling
4.5. Complete 3-D Building Models
5. Proposed 3-D Building Change Detection Method
5.1. Test Model Generation
5.2. 3-D Model Representation
5.3. Automatic Building Change Detection
5.3.1. Height Test
5.3.2. Plane Test
6. Performance Study
6.1. Datasets
6.2. Evaluation System
6.3. Parameter Setting
6.4. 3-D Building Modelling Results
6.4.1. Quantitative Results for 3-D Reconstruction
6.4.2. Comparative Results
6.4.3. Qualitative Analysis for 3-D Models
6.5. 3-D Building Change Detection Results
6.5.1. Quantitative Results
6.5.2. Qualitative Analysis
7. Conclusions
Author Contributions
Funding
Acknowledgments
Conflicts of Interest
References
- Awrangjeb, M. Effective generation and update of a building map database through automatic building change detection from LiDAR point cloud data. Remote Sens. 2015, 7, 14119–14150. [Google Scholar] [CrossRef]
- Zolanvari, S.M.I.; Laefer, D.F.; Natanzi, A.S. Three-dimensional building façade segmentation and opening area detection from point clouds. ISPRS J. Photogramm. Remote Sens. 2018, in press. [Google Scholar] [CrossRef]
- Aljumaily, H.; Laefer, D.F.; Cuadra, D. Big-Data Approach for Three-Dimensional Building Extraction from Aerial Laser Scanning. J. Comput. Civil Eng. 2016, 30, 04015049. [Google Scholar] [CrossRef]
- Mongus, D.; Lukač, N.; Žalik, B. Ground and building extraction from LiDAR data based on differential morphological profiles and locally fitted surfaces. ISPRS J. Photogramm. Remote Sens. 2014, 93, 145–156. [Google Scholar] [CrossRef]
- Bizjak, M. The segmentation of a point cloud using locally fitted surfaces. In Proceedings of the 18th Mediterranean Electrotechnical Conference (MELECON), Lemesos, Cyprus, 18–20 April 2016; pp. 1–6. [Google Scholar]
- Tran, T.H.G.; Ressl, C.; Pfeifer, N. Integrated Change Detection and Classification in Urban Areas Based on Airborne Laser Scanning Point Clouds. Sensors 2018, 18, 448. [Google Scholar] [CrossRef] [PubMed]
- Leichtle, T.; GeiB, C.; Wurm, M.; Lakes, T.; Taubenböck, H. Unsupervised change detection in VHR remote sensing imagery—An object-based clustering approach in a dynamic urban environment. Int. J. Appl. Earth Obs. Geoinf. 2017, 54, 15–27. [Google Scholar] [CrossRef]
- Gu, W.; Lv, Z.; Hao, M. Change detection method for remote sensing images based on an improved Markov random field. Multimedia Tools Appl. 2017, 76, 17719–17734. [Google Scholar] [CrossRef]
- Awrangjeb, M.; Fraser, C.S. Automatic Segmentation of Raw LiDAR Data for Extraction of Building Roofs. Remote Sens. 2014, 6, 3716–3751. [Google Scholar] [CrossRef]
- Kim, K.; Shan, J. Building roof modeling from airborne laser scanning data based on level set approach. ISPRS J. Photogramm. Remote Sens. 2011, 66, 484–497. [Google Scholar] [CrossRef]
- Truong-Hong, L.; Laefer, D.F. Quantitative evaluation strategies for urban 3D model generation from remote sensing data. Comput. Graph. 2015, 49, 82–91. [Google Scholar] [CrossRef] [Green Version]
- Awrangjeb, M.; Fraser, C.S. An automatic and threshold-free performance evaluation system for building extraction techniques from airborne LIDAR data. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2014, 7, 4184–4198. [Google Scholar] [CrossRef]
- Vo, A.V.; Truong-Hong, L.; Laefer, D.F.; Tiede, D.; d’Oleire Oltmanns, S.; Baraldi, A.; Shimoni, M.; Moser, G.; Tuia, D. Processing of Extremely High Resolution LiDAR and RGB Data: Outcome of the 2015 IEEE GRSS Data Fusion Contest—Part B: 3-D Contest. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2016, 9, 5560–5575. [Google Scholar] [CrossRef]
- Rottensteiner, F.; Sohn, G.; Gerke, M.; Wegner, J.D.; Breitkopf, U.; Jung, J. Results of the ISPRS benchmark on urban object detection and 3D building reconstruction. ISPRS J. Photogramm. Remote Sens. 2014, 93, 256–271. [Google Scholar] [CrossRef]
- Li, Y.; Wu, H. An improved building boundary extraction algorithm based on fusion of optical imagery and LiDAR Data. Int. J. Light Electron Opt. 2013, 124, 5357–5362. [Google Scholar] [CrossRef]
- Awrangjeb, M.; Zhang, C.; Fraser, C.S. Automatic extraction of building roofs using LiDAR data and multispectral imagery. ISPRS J. Photogramm. Remote Sens. 2013, 83, 1–18. [Google Scholar] [CrossRef]
- Habib, A.; Kwak, E.; Al-Durgham, M. Model-based automatic 3D building model generation by integrating lidar and aerial images. Arch. Photogramm. Cartogr. Remote Sens. 2011, 22, 187–200. [Google Scholar]
- Cao, R.; Zhang, Y.; Liu, X.; Zhao, Z. 3D building roof reconstruction from airborne LiDAR point clouds: A framework based on a spatial database. Int. J. Geograph. Inf. Sci. 2017, 31, 1359–1380. [Google Scholar] [CrossRef]
- Oude Elberink, S.; Vosselman, G. Building Reconstruction by Target Based Graph Matching on Incomplete Laser Data: Analysis and Limitations. Remote Sens. 2009, 9, 6101–6118. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Xiong, B.; Oude Elberink, S.; Vosselman, G. A graph edit dictionary for correcting errors in roof topology graphs reconstructed from point clouds. ISPRS J. Photogramm. Remote Sens. 2014, 93, 227–242. [Google Scholar] [CrossRef]
- Jung, J.; Jwa, Y.; Sohn, G. Implicit Regularization for Reconstructing 3D Building Rooftop Models Using Airborne LiDAR Data. Sensors 2017, 17, 621. [Google Scholar] [CrossRef] [PubMed]
- Wu, B.; Yu, B.; Wu, Q.; Yao, S.; Zhao, F.; Mao, W.; Wu, J. A graph-based approach for 3D building model reconstruction from airborne LiDAR point clouds. Remote Sens. 2017, 9, 92. [Google Scholar] [CrossRef]
- Teo, T.A.; Shih, T.Y. Lidar-based change detection and change-type determination in urban areas. Int. J. Remote Sens. 2013, 34, 968–981. [Google Scholar] [CrossRef]
- Tian, J.; Cui, S.; Reinartz, P. Building Change Detection Based on Satellite Stereo Imagery and Digital Surface Models. IEEE Trans. Geosci. Remote Sens. 2014, 52, 406–417. [Google Scholar] [CrossRef] [Green Version]
- Chen, L.C.; Huang, C.Y.; Teo, T.A. Multi-type change detection of building models by integrating spatial and spectral information. Int. J. Remote Sens. 2012, 33, 1655–1681. [Google Scholar] [CrossRef]
- Stal, C.; Tack, F.; De Maeyer, P.; De Wulf, A.; Goossens, R. Airborne photogrammetry and lidar for DSM extraction and 3D change detection over an urban area—A comparative study. Int. J. Remote Sens. 2013, 34, 1087–1110. [Google Scholar] [CrossRef] [Green Version]
- Qin, R. Change detection on LOD 2 building models with very high resolution spaceborne stereo imagery. ISPRS J. Photogramm. Remote Sens. 2014, 96, 179–192. [Google Scholar] [CrossRef]
- Sohn, G.; Huang, X.; Tao, V. A data-driven method for modeling 3D building objects using a binary space partitioning tree. In Topographic Laser Ranging and Scanning: Principles and Processing; CRC Press: Boca Raton, FL, USA, 2009; pp. 479–509. [Google Scholar]
- Kolbe, T.H.; Gröger, G.; Plümer, L. CityGML—Interoperable access to 3D city models. In Geo-Information for Disaster Management; Springer: Berlin/Heidelberg, Germany, 2005; pp. 883–899. [Google Scholar]
- Butkiewicz, T.; Chang, R.; Wartell, Z.; Ribarsky, W. Visual analysis and semantic exploration of urban lidar change detection. Comput. Graph. Forum 2008, 27, 903–910. [Google Scholar] [CrossRef]
- Gilani, S.A.N.; Awrangjeb, M.; Lu, G. Segmentation of Airborne Point Cloud Data for Automatic Building Roof Extraction. GISci. Remote Sens. 2018, 55, 63–89. [Google Scholar] [CrossRef]
- Awrangjeb, M. Using point cloud data to identify, trace, and regularize the outlines of buildings. Int. J. Remote Sens. 2016, 37, 551–579. [Google Scholar] [CrossRef] [Green Version]
- Verma, V.; Kumar, R.; Hsu, S. 3D Building Detection and Modeling from Aerial LIDAR Data. In Proceedings of the Conference on Computer Vision and Pattern Recognition, New York, NY, USA, 17–22 June 2006; Volume 2, pp. 2213–2220. [Google Scholar]
- Perera, G.S.N.; Maas, H.G. Cycle graph analysis for 3D roof structure modelling: Concepts and performance. ISPRS J. Photogramm. Remote Sens. 2014, 93, 213–226. [Google Scholar] [CrossRef]
- Siddiqui, F.U.; Teng, S.W.; Awrangjeb, M.; Lu, G. A Robust Gradient Based Method for Building Extraction from LiDAR and Photogrammetric Imagery. Sensors 2016, 16, 1110. [Google Scholar] [CrossRef] [PubMed]
- Awrangjeb, M.; Lu, G.; Fraser, C.S. Performance comparisons of contour-based corner detectors. IEEE Trans. Image Process. 2012, 21, 4167–4179. [Google Scholar] [CrossRef] [PubMed]
- Olsen, B.P.; Knudsen, T. Automated change detection for validation and update of geodata. In Proceedings of the 6th Geomatic Week, Barcelona, Spain, 8–10 February 2005. [Google Scholar]
- Matikainen, L.; Hyyppä, J.; Ahokas, E.; Markelin, L.; Kaartinen, H. Automatic detection of buildings and changes in buildings for updating of maps. Remote Sens. 2010, 2, 1217–1248. [Google Scholar] [CrossRef]
Test | Interchange | ||||||||
---|---|---|---|---|---|---|---|---|---|
Sites | Ah | Ab | Av | Rv | 3 Bp | 5 Bp | Rob | Rp | |
AV(1) | HB(1) | 🗸 | |||||||
AV(2) | HB(2) | 🗸 | |||||||
AV(3) | HB(3) | 🗸 | |||||||
AV(4) | HB(4) | 🗸 | |||||||
AV(5) | HB(5) | 🗸 | 🗸 | ||||||
AV(6) | HB(6) | 🗸 | 🗸 | ||||||
AV(7) | HB(7) | 🗸 | 🗸 | ||||||
AV(8) | HB(8) | 🗸 | 🗸 | ||||||
AV(9) | HB(9) | 🗸 | 🗸 | 🗸 | |||||
AV(10) | HB(10) | 🗸 | 🗸 | 🗸 | |||||
AV(11) | HB(11) | 🗸 | |||||||
AV(12) | HB(12) | 🗸 | 🗸 | ||||||
AV(13) | HB(13) | 🗸 | 🗸 | ||||||
AV(14) | HB(14) | 🗸 | 🗸 | ||||||
AV(15) | HB(15) | 🗸 | 🗸 | ||||||
AV(16) | HB(16) | 🗸 | 🗸 | 🗸 | |||||
AV(17) | HB(17) | 🗸 | 🗸 | 🗸 | 🗸 | ||||
AV(18) | HB(18) | 🗸 | 🗸 | 🗸 | |||||
AV(19) | HB(19) | 🗸 | 🗸 | 🗸 | 🗸 | ||||
AV(20) | HB(20) | 🗸 | 🗸 | ||||||
AV(21) | HB(21) | 🗸 | 🗸 | 🗸 | |||||
AV(22) | HB(22) | 🗸 | 🗸 | 🗸 | |||||
AV(23) | HB(23) | 🗸 | 🗸 | ||||||
AV(24) | HB(24) | 🗸 | 🗸 | 🗸 | |||||
AV(25) | HB(25) | 🗸 | 🗸 | 🗸 | |||||
AV(26) | HB(26) | 🗸 | 🗸 | 🗸 | 🗸 | ||||
AV(27) | HB(27) | 🗸 | 🗸 | 🗸 | 🗸 | ||||
AV(28) | HB(28) | 🗸 | |||||||
AV(29) | HB(29) | 🗸 | |||||||
AV(30) | HB(30) | 🗸 | |||||||
AV(31) | HB(31) | 🗸 |
Test-Case | Total Planes | Inserted Planes | ||||||
---|---|---|---|---|---|---|---|---|
AV | 25 | 24 | 1 | 29 | 1 | 4 | 5 | 0 |
HB | 167 | 147 | 20 | 158 | 7 | 4 | 11 | 9 |
Test-Case | Per-Plane Object | Segmentation | Per-Plane Pixel | Error in Area | ||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|
Input roof planes [9] | ||||||||||||
AV | 95.65 | 100.0 | 95.65 | 4.5 | 0 | 88.96 | 93.63 | 83.89 | 11.0 | 5.9 | 0.02 | 0.03 |
HB | 85.62 | 95.33 | 82.18 | 8.7 | 0.5 | 73.44 | 82.13 | 63.32 | 26.55 | 17.86 | 0.39 | 0.03 |
Proposed 3-D reconstructed roof planes | ||||||||||||
AV | 100.0 | 100.0 | 100.0 | 0 | 0 | 90.95 | 94.02 | 85.14 | 9.0 | 5.1 | 0.02 | 0.03 |
HB | 88.02 | 98.0 | 86.47 | 7.9 | 0.8 | 76.38 | 85.43 | 72.42 | 23.61 | 14.86 | 0.34 | 0.02 |
Modified Sites | Object-Based | Pixel-Based | ||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|
AV(1) | 100 | 95.2 | 95.2 | 100 | 100 | 100 | 100 | 100 | 100 | 93.6 | 97.4 | 91.4 |
AV(2) | 100 | 95.8 | 95.8 | 100 | 100 | 100 | 100 | 100 | 100 | 95 | 97.4 | 92.6 |
AV(3) | 100 | 96.0 | 96.0 | 100 | 100 | 100 | 100 | 100 | 100 | 95.1 | 97.4 | 92.7 |
AV(4) | 100 | 96.1 | 96.1 | 100 | 100 | 100 | 100 | 100 | 100 | 94.0 | 86.8 | 82.2 |
AV(5) | 100 | 95.8 | 95.8 | 100 | 100 | 100 | 100 | 100 | 100 | 95 | 97.4 | 92.6 |
AV(6) | 100 | 95.8 | 95.8 | 100 | 100 | 100 | 100 | 100 | 100 | 94.9 | 97.4 | 92.6 |
AV(7) | 100 | 96.1 | 96.1 | 100 | 100 | 100 | 100 | 100 | 100 | 94.4 | 96.5 | 91.3 |
AV(8) | 100 | 96.1 | 96.1 | 100 | 100 | 100 | 100 | 100 | 100 | 94.3 | 96.5 | 91.3 |
AV(9) | 100 | 96.1 | 96.1 | 100 | 100 | 100 | 100 | 100 | 100 | 94.4 | 96.6 | 91.3 |
AV(10) | 100 | 96.1 | 96.1 | 100 | 100 | 100 | 100 | 100 | 100 | 94.4 | 96.6 | 91.3 |
AV(11) | 100 | 95.8 | 95.8 | 100 | 100 | 100 | 100 | 100 | 100 | 94.9 | 97.3 | 92.6 |
AV(12) | 100 | 96.0 | 96.0 | 100 | 100 | 100 | 100 | 100 | 100 | 95.1 | 97.4 | 92.7 |
AV(13) | 100 | 96.0 | 96.0 | 100 | 100 | 100 | 100 | 100 | 100 | 95.0 | 97.4 | 92.7 |
AV(14) | 100 | 96 | 96 | 100 | 100 | 100 | 100 | 100 | 100 | 95.1 | 97.4 | 92.7 |
AV(15) | 100 | 96.4 | 96.4 | 100 | 100 | 100 | 100 | 100 | 100 | 94.4 | 96.5 | 91.4 |
AV(16) | 100 | 96.4 | 96.4 | 100 | 100 | 100 | 100 | 100 | 100 | 94.4 | 96.5 | 91.4 |
AV(17) | 100 | 96.4 | 96.4 | 100 | 100 | 100 | 100 | 100 | 100 | 94.4 | 96.5 | 91.4 |
AV(18) | 100 | 96.4 | 96.4 | 100 | 100 | 100 | 100 | 100 | 100 | 94.4 | 96.5 | 91.3 |
AV(19) | 100 | 96.4 | 96.4 | 100 | 100 | 100 | 100 | 100 | 100 | 94.4 | 96.5 | 91.4 |
AV(20) | 100 | 95.2 | 95.2 | 100 | 100 | 100 | 100 | 100 | 100 | 93.6 | 97.4 | 91.4 |
AV(21) | 100 | 95.2 | 95.2 | 100 | 100 | 100 | 100 | 100 | 100 | 93.6 | 97.5 | 91.4 |
AV(22) | 100 | 95.2 | 95.2 | 100 | 100 | 100 | 100 | 100 | 100 | 93.6 | 97.5 | 91.4 |
AV(23) | 100 | 95.6 | 95.6 | 100 | 100 | 100 | 100 | 100 | 100 | 92.7 | 86.51 | 81.0 |
AV(24) | 100 | 95.6 | 95.6 | 100 | 100 | 100 | 100 | 100 | 100 | 93.2 | 96.6 | 90.2 |
AV(25) | 100 | 95.6 | 95.6 | 100 | 100 | 100 | 100 | 100 | 100 | 93.1 | 96.6 | 90.2 |
AV(26) | 100 | 95.6 | 95.6 | 100 | 100 | 100 | 100 | 100 | 100 | 93.2 | 96.6 | 90.3 |
AV(27) | 100 | 95.6 | 95.6 | 100 | 100 | 100 | 100 | 100 | 100 | 93.2 | 96.6 | 90.3 |
AV(28) | 100 | 95.8 | 95.8 | 100 | 100 | 100 | 100 | 100 | 100 | 95.0 | 97.4 | 92.6 |
AV(29) | 100 | 96.1 | 96.1 | 100 | 100 | 100 | 100 | 100 | 100 | 83.0 | 97.2 | 81.1 |
AV(30) | 100 | 95.8 | 95.8 | 100 | 100 | 100 | 100 | 100 | 100 | 95.1 | 97.3 | 92.7 |
AV(31) | 100 | 95.2 | 95.2 | 100 | 100 | 100 | 100 | 100 | 100 | 93.4 | 96.6 | 90.5 |
Average | 100 | 95.8 | 95.8 | 100 | 100 | 100 | 100 | 100 | 100 | 93.9 | 96.4 | 90.7 |
Modified Sites | Object-Based | Pixel-Based | ||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|
HB(1) | 90.9 | 99.2 | 88.5 | 98.0 | 100 | 96.5 | 100 | 100 | 100 | 84.4 | 96.9 | 82.2 |
HB(2) | 90.5 | 99.3 | 88.5 | 97.4 | 100 | 96.5 | 100 | 100 | 100 | 84.7 | 99.6 | 84.4 |
HB(3) | 90.5 | 99.3 | 88.6 | 97.4 | 100 | 96.5 | 100 | 100 | 100 | 85.0 | 99.6 | 84.8 |
HB(4) | 90.9 | 99.3 | 89.0 | 97.5 | 100 | 96.7 | 100 | 100 | 100 | 85.4 | 99.6 | 85.1 |
HB(5) | 90.5 | 99.3 | 88.5 | 97.4 | 100 | 96.5 | 100 | 100 | 100 | 84.7 | 99.6 | 84.4 |
HB(6) | 90.5 | 99.3 | 88.5 | 97.4 | 100 | 96.5 | 100 | 100 | 100 | 84.7 | 99.6 | 84.4 |
HB(7) | 90.9 | 99.3 | 89.0 | 97.5 | 100 | 96.7 | 100 | 100 | 100 | 85.4 | 99.6 | 85.1 |
HB(8) | 90.9 | 99.3 | 89.0 | 97.5 | 100 | 96.7 | 100 | 100 | 100 | 85.4 | 99.6 | 85.1 |
HB(9) | 90.9 | 99.3 | 89.0 | 97.6 | 100 | 96.7 | 100 | 100 | 100 | 85.4 | 99.6 | 85.1 |
HB(10) | 90.9 | 99.3 | 89.0 | 97.5 | 100 | 96.7 | 100 | 100 | 100 | 85.4 | 99.6 | 85.1 |
HB(11) | 90.4 | 99.3 | 88.5 | 97.4 | 100 | 96.5 | 100 | 100 | 100 | 84.7 | 99.6 | 84.4 |
HB(12) | 90.5 | 99.3 | 88.6 | 97.4 | 100 | 96.5 | 100 | 100 | 100 | 85.0 | 99.6 | 84.8 |
HB(13) | 90.5 | 99.3 | 88.6 | 97.4 | 100 | 96.5 | 100 | 100 | 100 | 85.0 | 99.6 | 84.8 |
HB(14) | 90.5 | 99.3 | 88.6 | 97.4 | 100 | 96.5 | 100 | 100 | 100 | 85.0 | 99.6 | 84.8 |
HB(15) | 90.5 | 93.9 | 84.3 | 97.4 | 95.2 | 92.1 | 100 | 100 | 100 | 85.0 | 91.8 | 79.0 |
HB(16) | 90.9 | 99.3 | 89.1 | 97.5 | 100 | 96.7 | 100 | 100 | 100 | 85.7 | 99.6 | 85.5 |
HB(17) | 90.9 | 99.3 | 89.1 | 97.6 | 100 | 96.7 | 100 | 100 | 100 | 85.7 | 99.6 | 85.5 |
HB(18) | 90.9 | 99.3 | 89.1 | 97.5 | 100 | 96.7 | 100 | 100 | 100 | 85.7 | 99.6 | 85.5 |
HB(19) | 90.9 | 99.3 | 89.1 | 97.6 | 100 | 96.7 | 100 | 100 | 100 | 85.8 | 99.6 | 85.5 |
HB(20) | 90.9 | 99.3 | 88.5 | 98.0 | 100 | 96.5 | 100 | 100 | 100 | 84.5 | 96.9 | 82.3 |
HB(21) | 90.9 | 99.3 | 88.5 | 98.0 | 100 | 96.5 | 100 | 100 | 100 | 84.5 | 96.9 | 82.3 |
HB(22) | 90.9 | 99.3 | 88.5 | 98.0 | 100 | 96.5 | 100 | 100 | 100 | 84.5 | 96.9 | 82.3 |
HB(23) | 91.3 | 99.3 | 89.0 | 98.1 | 100 | 96.7 | 100 | 100 | 100 | 85.2 | 97.1 | 83.1 |
HB(24) | 91.3 | 99.3 | 89.0 | 98.1 | 100 | 96.7 | 100 | 100 | 100 | 85.2 | 97.1 | 83.1 |
HB(25) | 91.3 | 99.3 | 89.0 | 98.1 | 100 | 96.7 | 100 | 100 | 100 | 85.2 | 97.1 | 83.1 |
HB(26) | 91.3 | 99.3 | 89.0 | 98.1 | 100 | 96.7 | 100 | 100 | 100 | 85.3 | 97.1 | 83.1 |
HB(27) | 91.3 | 99.3 | 89.0 | 98.1 | 100 | 96.7 | 100 | 100 | 100 | 85.3 | 97.1 | 83.1 |
HB(28) | 90.4 | 99.2 | 88.5 | 97.4 | 100 | 96.5 | 100 | 100 | 100 | 84.7 | 99.6 | 84.4 |
HB(29) | 90.2 | 99.2 | 88.2 | 97.3 | 100 | 96.4 | 100 | 100 | 100 | 85.1 | 99.6 | 84.4 |
HB(30) | 90.4 | 99.2 | 88.5 | 97.4 | 100 | 96.5 | 100 | 100 | 100 | 84.7 | 99.6 | 84.4 |
HB(31) | 90.1 | 98.5 | 87.4 | 97.3 | 99.2 | 95.6 | 100 | 100 | 100 | 79.4 | 95.7 | 76.7 |
Average | 90.8 | 99.1 | 88.6 | 97.6 | 99.8 | 96.4 | 100 | 100 | 100 | 84.9 | 98.5 | 83.8 |
© 2018 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
Share and Cite
Awrangjeb, M.; Gilani, S.A.N.; Siddiqui, F.U. An Effective Data-Driven Method for 3-D Building Roof Reconstruction and Robust Change Detection. Remote Sens. 2018, 10, 1512. https://doi.org/10.3390/rs10101512
Awrangjeb M, Gilani SAN, Siddiqui FU. An Effective Data-Driven Method for 3-D Building Roof Reconstruction and Robust Change Detection. Remote Sensing. 2018; 10(10):1512. https://doi.org/10.3390/rs10101512
Chicago/Turabian StyleAwrangjeb, Mohammad, Syed Ali Naqi Gilani, and Fasahat Ullah Siddiqui. 2018. "An Effective Data-Driven Method for 3-D Building Roof Reconstruction and Robust Change Detection" Remote Sensing 10, no. 10: 1512. https://doi.org/10.3390/rs10101512