An Object-Based Classification of Mangroves Using a Hybrid Decision Tree—Support Vector Machine Approach
"> Figure 1
<p>A stylized example of a cluster-type <b>(left)</b> and support vector machine likelihood classification <b>(right)</b> between two hypothetical classes shown in blue and red.</p> "> Figure 2
<p>Quickbird false color composites for the Puerto Villamil and Cartago study areas on Isabela Island in the Galapagos Islands.</p> "> Figure 3
<p>Examples of vegetation near Puerto Villamil (from upper left, clockwise): <b>(A)</b> tall black mangroves near a fresh water spring, <b>(B)</b> red mangroves growing on lava shoreline, <b>(C)</b> mixed arid vegetation and mangroves along a hyper-saline pond, <b>(D)</b> tall red mangroves mixed with white and black mangroves on a saline pond.</p> "> Figure 4
<p>Object-based image analysis (OBIA) Decision Tree (rectangle = image; diamond = rule; oval = class).</p> "> Figure 5
<p>Land cover classification for Puerto Villamil <b>(top)</b> and Cartago <b>(bottom)</b>.</p> "> Figure 6
<p>Boxplot of true mangrove (TM) fuzzy membership for validation field points.</p> ">
Abstract
:1. Introduction
1.1. Context
1.2. Study Objective
1.3. Background—Object Based Image Analysis
1.4. Background—Support Vector Machine
2. Methodology
2.1. Study Area
2.2. Field Data
Species | Plots* | Points | Total | Percent | |
---|---|---|---|---|---|
MA (Mangrove Associates) | AC (Acacia) | 8 | 27 | 35 | 3.472 |
MZ (Manzanillo) | 43 | 7 | 50 | 4.960 | |
OV (Other Vegetation) | 16 | 17 | 33 | 3.274 | |
BW (Buttonwood) | 56 | 55 | 111 | 11.012 | |
TM (True Mangroves) | RM (Red Mangrove) | 120 | 174 | 294 | 29.167 |
WM (White Mangrove) | 146 | 243 | 389 | 38.591 | |
BM (Black Mangrove) | 66 | 30 | 96 | 9.524 | |
Total | 455 | 553 | 1,008 |
2.3. Remote Sensing Data
Sensor | Quickbird | Worldview-2 |
---|---|---|
Acquisition Date | 27 August 2008 | 01 October 2010 |
Spatial Resolution (m) | ||
Pan | 0.6 | 0.5 |
MSS | 2.4 | 2.0 |
Spectral Channels (nm) | ||
Coastal Blue | N/A | 400–450 |
Blue | 450–520 | 450–510 |
Green | 520–600 | 510–580 |
Yellow | N/A | 585–625 |
Red | 630–690 | 630–690 |
Red Edge | N/A | 705–745 |
NIR-1 | 760–900 | 770–895 |
NIR-2 | N/A | 860–1,040 |
2.4. Spectral Separability
2.5. Object-Based Image Analysis
2.5.1. Decision-Tree Classification
2.5.2. Support Vector Machine Classification
True Mangroves | Mangrove Associates | Total | |
---|---|---|---|
Calibration | 143 | 54 | 197 |
Validation | 73 | 24 | 101 |
Total | 216 | 78 | 298 |
2.6. Accuracy Assessment
3. Results and Discussion
3.1. Spectral Separability Analysis
AC | MZ | OV | BW | RM | WM | BM | |
AC | 1.892 | 1.342 | 1.455 | 1.837 | 1.703 | 1.543 | |
MZ | 1.892 | 1.734 | 1.690 | 1.593 | 1.814 | 1.355 | |
OV | 1.342 | 1.734 | 0.994 | 1.725 | 1.673 | 1.233 | |
BW | 1.455 | 1.690 | 0.994 | 1.256 | 1.185 | 0.702 | |
RM | 1.837 | 1.593 | 1.725 | 1.256 | 0.508 | 1.129 | |
WM | 1.703 | 1.814 | 1.673 | 1.185 | 0.508 | 1.258 | |
BM | 1.543 | 1.355 | 1.233 | 0.702 | 1.129 | 1.258 | |
(B) Worldview-2 | |||||||
AC | MZ | OV | BW | RM | WM | BM | |
AC | 1.963 | 1.647 | 1.698 | 1.820 | 1.498 | 1.785 | |
MZ | 1.963 | 1.861 | 1.925 | 1.900 | 1.943 | 1.647 | |
OV | 1.647 | 1.861 | 1.532 | 1.622 | 1.584 | 1.381 | |
BW | 1.698 | 1.925 | 1.532 | 1.617 | 1.336 | 1.634 | |
RM | 1.820 | 1.900 | 1.622 | 1.617 | 0.866 | 1.226 | |
WM | 1.498 | 1.943 | 1.584 | 1.336 | 0.866 | 1.540 | |
BM | 1.785 | 1.647 | 1.381 | 1.634 | 1.226 | 1.540 | |
(C) Difference | |||||||
AC | MZ | OV | BW | RM | WM | BM | |
AC | 0.071 | 0.304 | 0.243 | −0.017 | −0.205 | 0.242 | |
MZ | 0.071 | 0.127 | 0.235 | 0.307 | 0.129 | 0.292 | |
OV | 0.304 | 0.127 | 0.537 | −0.103 | −0.089 | 0.148 | |
BW | 0.243 | 0.235 | 0.537 | 0.361 | 0.151 | 0.932 | |
RM | −0.017 | 0.307 | −0.103 | 0.361 | 0.358 | 0.097 | |
WM | −0.205 | 0.129 | −0.089 | 0.151 | 0.358 | 0.282 | |
BM | 0.242 | 0.292 | 0.148 | 0.932 | 0.097 | 0.282 |
QB | QB w/BR | WV | WV w/ BR | QB = Quickbird | |
All Veg Points | 0.664 | 1.141 | 0.734 | 1.084 | WV = Worldview-2 |
Dense Veg Objects | 0.839 | 1.118 | 1.321 | 1.665 | BR = Band Ratios |
3.2. Classification
Puerto Villamil | Cartago | |||
Cover | Area | Percent | Area | Percent |
OC | 17.9304 | 38.1463 | 29.2249 | 43.4184 |
PD | 1.5400 | 3.2763 | * | |
LV | 14.1150 | 30.0291 | 32.4511 | 48.2114 |
SD | 0.8032 | 1.7087 | 0.0397 | 0.0589 |
UV | 6.8491 | 14.5712 | 0.2722 | 0.4043 |
QBC | 0.0985 | 0.2096 | 0.0000 | 0.0000 |
SCV | 2.8796 | 6.1262 | 1.2552 | 1.8648 |
DCVC | 0.1785 | 0.3798 | 1.0119 | 1.5033 |
MA | 1.5091 | 3.2106 | 0.0006 | 0.0009 |
TM | 1.1010 | 2.3423 | 3.0544 | 4.5379 |
Total | 47.004 | 12.0588 | 67.310 | 7.9069 |
Puerto Villamil | Cartago | |||
Cover | Area | Pct CV | Area | Pct CV |
SCV | 2.8796 | 0.5080 | 1.2552 | 0.2358 |
DCVC | 0.1785 | 0.0315 | 1.0119 | 0.1901 |
MA | 1.5091 | 0.2662 | 0.0006 | 0.0001 |
TM | 1.1010 | 0.1942 | 3.0544 | 0.5739 |
Total | 5.668 | 5.322 |
3.3. Accuracy Assessment
3.3.1. SVM
3.3.2. Total Classification vs. Field Points
(A) | TM | MA | QBC | SCV | DCVC | LV | OC | PD | SD | UV | Total |
AC | 2 | 0 | 0 | 18 | 0 | 11 | 0 | 0 | 0 | 0 | 31 |
MZ | 5 | 27 | 0 | 2 | 0 | 0 | 0 | 0 | 0 | 0 | 34 |
OV | 4 | 9 | 0 | 14 | 0 | 10 | 0 | 0 | 0 | 0 | 37 |
BW | 18 | 6 | 0 | 52 | 0 | 12 | 0 | 4 | 0 | 0 | 92 |
RM | 84 | 8 | 0 | 71 | 0 | 23 | 1 | 18 | 0 | 0 | 205 |
WM | 43 | 1 | 0 | 159 | 0 | 120 | 7 | 7 | 0 | 0 | 337 |
BM | 9 | 22 | 0 | 16 | 0 | 6 | 0 | 0 | 0 | 0 | 53 |
Total | 165 | 73 | 0 | 332 | 0 | 182 | 8 | 29 | 0 | 0 | 789 |
(B) | TM | MA | QBC | SCV | DCVC | LV | OC | PD | SD | UV | Total |
AC | 6.45 | 0.00 | 0.00 | 58.06 | 0.00 | 35.48 | 0.00 | 0.00 | 0.00 | 0.00 | 100 |
MZ | 14.71 | 79.41 | 0.00 | 5.88 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 100 |
OV | 10.81 | 24.32 | 0.00 | 37.84 | 0.00 | 27.03 | 0.00 | 0.00 | 0.00 | 0.00 | 100 |
BW | 19.57 | 6.52 | 0.00 | 56.52 | 0.00 | 13.04 | 0.00 | 4.35 | 0.00 | 0.00 | 100 |
RM | 40.98 | 3.90 | 0.00 | 34.63 | 0.00 | 11.22 | 0.49 | 8.78 | 0.00 | 0.00 | 100 |
WM | 12.76 | 0.30 | 0.00 | 47.18 | 0.00 | 35.61 | 2.08 | 2.08 | 0.00 | 0.00 | 100 |
BM | 16.98 | 41.51 | 0.00 | 30.19 | 0.00 | 11.32 | 0.00 | 0.00 | 0.00 | 0.00 | 100 |
Total | 0.209 | 0.093 | 0 | 0.421 | 0 | 0.231 | 0.010 | 0.037 | 0 | 0 | 1 |
4. Conclusions
Acknowledgements
References
- Hogarth, P. The Biology of Mangroves and Seagrasses; Oxford University Press: Oxford, UK; New York, NY, USA, 2007. [Google Scholar]
- Alongi, D.M. Present state and future of the world’s mangrove forests. Environ. Conserv. 2002, 29, 331. [Google Scholar] [CrossRef]
- Giri, C.; Ochieng, E.; Tieszen, L.L.; Zhu, Z.; Singh, A.; Loveland, T.; Masek, J.; Duke, N. Status and distribution of mangrove forests of the world using earth observation satellite data. Global Ecol. Biogeogr. 2011, 20, 154–159. [Google Scholar] [CrossRef]
- Heumann, B. Satellite remote sensing of mangrove forests: Recent advances and future opportunities. Progr. Phys. Geogr. 2011, 35, 87–108. [Google Scholar] [CrossRef]
- Kuenzer, C.; Bluemel, A.; Gebhardt, S.; Quoc, T.V.; Dech, S. Remote sensing of mangrove ecosystems: A review. Remote Sens. 2011, 3, 878–928. [Google Scholar] [CrossRef]
- Al Habshi, A.; Youssef, T.; Aizpuru, M.; Blasco, F. New mangrove ecosystem data along the UAE coast using remote sensing. Aquat. Ecosyst. Health Manage. 2007, 10, 309–319. [Google Scholar] [CrossRef]
- Benfield, S.L.; Guzman, H.M.; Mair, J.M. Temporal mangrove dynamics in relation to coastal development in Pacific Panama. J. Environ. Manage. 2005, 76, 263. [Google Scholar] [CrossRef] [PubMed]
- Gao, J. A hybrid method toward accurate mapping of mangroves in a marginal habitat from SPOT multispectral data. Int. J. Remote Sens. 1998, 19, 1887–1899. [Google Scholar] [CrossRef]
- Simard, M.; De Grandi, G.; Saatchi, S.; Mayaux, P. Mapping tropical coastal vegetation using JERS-1 and ERS-1 radar data with a decision tree classifier. Int. J. Remote Sens. 2002, 23, 1461–1474. [Google Scholar] [CrossRef]
- Manson, F.J.; Loneragan, N.R.; McLeod, I.M.; Kenyon, R.A. Assessing techniques for estimating the extent of mangroves: Topographic maps, aerial photographs and Landsat TM images. Mar. Freshwater Res. 2001, 52, 787–792. [Google Scholar] [CrossRef]
- Ramsey, E.W.; Jensen, J.R. Remote sensing of mangrove wetlands: Relating canopy spectra to site-specific data. Photogramm. Eng. Remote Sensing 1996, 62, 939. [Google Scholar]
- Vaiphasa, C.; Ongsomwang, S.; Vaiphasa, T.; Skidmore, A.K. Tropical mangrove species discrimination using hyperspectral data: A laboratory study. Estuar. Coast. Shelf Sci. 2005, 65, 371–379. [Google Scholar] [CrossRef]
- Wang, L.; Sousa, W.P. Distinguishing mangrove species with laboratory measurements of hyperspectral leaf reflectance. Int. J. Remote Sens. 2009, 30, 1267–1281. [Google Scholar] [CrossRef]
- Neukermans, G.; Dahdouh-Guebas, F.; Kairo, J.G.; Koedam, N. Mangrove species and stand mapping in GAzi bay (Kenya) using Quickbird satellite imagery. J. Spat. Sci. 2008, 53, 75–86. [Google Scholar] [CrossRef]
- Wang, L.; Sousa, W.P.; Gong, P. Integration of object-based and pixel-based classification for mapping mangroves with IKONOS imagery. Int. J. Remote Sens. 2004, 25, 5655–5668. [Google Scholar] [CrossRef]
- Wang, L.; Silvan-Cardenas, J.L.; Sousa, W.P. Neural network classification of mangrove species from multi-seasonal ikonos imagery. Photogramm. Eng. Remote Sensing 2008, 74, 921–927. [Google Scholar] [CrossRef]
- Huang, X.; Zhang, L.P.; Wang, L. Evaluation of morphological texture features for mangrove forest mapping and species discrimination using multispectral IKONOS imagery. IEEE Geosci. Remote Sens. Lett. 2009, 6, 393–397. [Google Scholar] [CrossRef]
- Vaiphasa, C.; Skidmore, A.K.; de Boer, W.F. A post-classifier for mangrove mapping using ecological data. ISPRS J. Photogramm. 2006, 61, 1–10. [Google Scholar] [CrossRef]
- Wang, L.; Sousa, W.P.; Gong, P.; Biging, G.S. Comparison of IKONOS and QuickBird images for mapping mangrove species on the Caribbean coast of Panama. Remote Sens. Environ. 2004, 91, 432–440. [Google Scholar] [CrossRef]
- Myint, S.W.; Giri, C.P.; Le, W.; Zhu, Z.L.; Gillette, S.C. Identifying mangrove species and their surrounding land use and land cover classes using an object-oriented approach with a lacunarity spatial measure. GISci. Remote Sens. 2008, 45, 188–208. [Google Scholar] [CrossRef]
- Krause, G.; Bock, M.; Weiers, S.; Braun, G. Mapping land-cover and mangrove structures with remote sensing techniques: A contribution to a synoptic GIS in support of coastal management in North Brazil. Environ. Manage. 2004, 34, 429–440. [Google Scholar] [CrossRef] [PubMed]
- Tomlinson, P.B. The Botany of Mangroves; Cambridge University Press: Cambridge, UK; New York, NY, USA, 1986; p. 413. [Google Scholar]
- Woodcock, C.E.; Strahler, A.H. The factor of scale in remote sensing. Remote Sens. Environ. 1987, 21, 311–332. [Google Scholar] [CrossRef]
- Benz, U.C.; Hofmann, P.; Willhauck, G.; Lingenfelder, I.; Heynen, M. Multi-resolution, object-oriented fuzzy analysis of remote sensing data for GIS-ready information. ISPRS J. Photogramm. 2004, 58, 239–258. [Google Scholar] [CrossRef]
- Chubey, M.S.; Franklin, S.E.; Wulder, M.A. Object-based analysis of IKONOS-2 imagery for extraction of forest inventory parameters. Photogramm. Eng. Remote Sensing 2006, 72, 383–394. [Google Scholar] [CrossRef]
- Desclee, B.; Bogaert, P.; Defourny, P. Forest change detection by statistical object-based method. Remote Sens. Environ. 2006, 102, 1–11. [Google Scholar] [CrossRef]
- Hay, G.J.; Castilla, G.; Wulder, M.A.; Ruiz, J.R. An automated object-based approach for the multiscale image segmentation of forest scenes. Int. J. Appl. Earth Obs. Geoinf. 2005, 7, 339–359. [Google Scholar] [CrossRef]
- Wulder, M.A.; White, J.C.; Hay, G.J.; Castilla, G. Towards automated segmentation of forest inventory polygons on high spatial resolution satellite imagery. Forest. Chron. 2008, 84, 221–230. [Google Scholar] [CrossRef]
- Conchedda, G.; Durieux, L.; Mayaux, P. Object-Based Monitoring of Land Cover Changes in Mangrove Ecosystems of Senegal. In Proceedings of 4th International Workshop on the Analysis of Multi-Temporal Remote Sensing Images, Louvain, Belgium, 18–20 July 2007; pp. 44–49.
- Pal, M.; Mather, P.M. Support vector machines for classification in remote sensing. Int. J. Remote Sens. 2005, 26, 1007–1011. [Google Scholar] [CrossRef]
- Vapnik, V. The Nature of Statistical Learning Theory; Springer: New York, NY, USA, 1995. [Google Scholar]
- Huang, C.; Davis, L.S.; Townshend, J.R.G. An assessment of support vector machines for land cover classification. Int. J. Remote Sens. 2002, 23, 725–749. [Google Scholar] [CrossRef]
- Hsu, C.; Cahng, C.; Lin, C. A Practical Guide to Support Vector Classification; Department of Computer Science, National Taiwan University: Taipei, Taiwan, 2010. [Google Scholar]
- Yang, X. Parameterizing Support Vector Machines for Land Cover classification. Photogramm. Eng. Remote Sensing 2011, 77, 27–38. [Google Scholar] [CrossRef]
- Foody, G.M.; Mathur, A. The use of small training sets containing mixed pixels for accurate hard image classification: Training on mixed spectral responses for classification by a SVM. Remote Sens. Environ. 2006, 103, 179–189. [Google Scholar] [CrossRef]
- Li, H.T.; Gu, H.Y.; Han, Y.S.; Yang, J.H. Object-oriented classification of high-resolution remote sensing imagery based on an improved colour structure code and a support vector machine. Int. J. Remote Sens. 2010, 31, 1453–1470. [Google Scholar] [CrossRef]
- Van Der Werff, H.H.; Adsersen, H. Dry coastal ecosystems of the Galapagos Islands. In Dry Coastal Ecosystems: Africa, America, Asia and Oceania; van der Maarel, E., Ed.; Ecosystems of the World 2B; Elsevier Science Ltd.: Amsterdam, The Netherlands, 1993; pp. 459–475. [Google Scholar]
- Schmidt, K.S.; Skidmore, A.K. Spectral discrimination of vegetation types in a coastal wetland. Remote Sens. Environ. 2003, 85, 92–108. [Google Scholar] [CrossRef]
- Swain, P. Remote sensing. In The Handbook of Pattern Recognition and Processing; Young, T., Fu, K., Eds.; Academic Press: Orlando, FL, USA, 1986; pp. 613–627. [Google Scholar]
- Metz, C.E. Basic principles of ROC analysis. Semin. Nucl. Med. 1978, 8, 283–298. [Google Scholar] [CrossRef]
- Song, C.; White, B.; Heumann, B.W. Hyperspectral remote sensing of salinity stress on red (Rhizophora mangle) and white (Laguncularia racemosa) mangroves on Galapagos Islands. Unpublished data.
- Song, C.; White, B.; Heumann, B. Hyperspectral remote sensing of salinity stress on red (Rhizophora mangle) and white (Laguncularia racemosa) mangroves on Galapagos Islands. Remote Sens. Lett. 2011, 2, 221–230. [Google Scholar] [CrossRef]
- Ward, G.A.; Smith, T.J.; Whelan, K.R.T.; Doyle, T.W. Regional processes in mangrove ecosystems: Spatial scaling relationships, biomass, and turnover rates following catastrophic disturbance. Hydrobiologia 2006, 569, 517. [Google Scholar] [CrossRef]
- Blaschke, T.; Lang, S.; Hay, G. Object-Based Image Analysis: Spatial Concepts for Knowledge-Driven Remote Sensing Applications; Springer: Berlin/Heidelberg, Germany, 2008. [Google Scholar]
© 2011 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 license (http://creativecommons.org/licenses/by/3.0/).
Share and Cite
Heumann, B.W. An Object-Based Classification of Mangroves Using a Hybrid Decision Tree—Support Vector Machine Approach. Remote Sens. 2011, 3, 2440-2460. https://doi.org/10.3390/rs3112440
Heumann BW. An Object-Based Classification of Mangroves Using a Hybrid Decision Tree—Support Vector Machine Approach. Remote Sensing. 2011; 3(11):2440-2460. https://doi.org/10.3390/rs3112440
Chicago/Turabian StyleHeumann, Benjamin W. 2011. "An Object-Based Classification of Mangroves Using a Hybrid Decision Tree—Support Vector Machine Approach" Remote Sensing 3, no. 11: 2440-2460. https://doi.org/10.3390/rs3112440