Evaluating pixel-based vs. object-based image analysis approaches for lithological discrimination using VNIR data of WorldView-3

doi:10.1007/s11707-020-0848-7

Front. Earth Sci.

2021, Vol. 15

Issue (1) : 38-53 https://doi.org/10.1007/s11707-020-0848-7

RESEARCH ARTICLE

Evaluating pixel-based vs. object-based image analysis approaches for lithological discrimination using VNIR data of WorldView-3

Samira SHAYEGANPOUR¹, Majid H. TANGESTANI¹(

), Saeid HOMAYOUNI², Robert K. VINCENT³

¹. Department of Earth Sciences, Faculty of Sciences, Shiraz University, Shiraz 7196484334, Iran
². Centre Eau Terre Environnement, Insitut National de la Recherche Scientifique, Québec QCJ3X1S2, Canada
³. Department of Geography, Bowling Green State University, Ohio 43403-0001, USA

Download: PDF(9905 KB) HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks

Abstract

The object-based against pixel-based image analysis approaches were assessed for lithological mapping in a geologically complex terrain using Visible Near Infrared (VNIR) bands of WorldView-3 (WV-3) satellite imagery. The study area is Hormuz Island, southern Iran, a salt dome composed of dominant sedimentary and igneous rocks. When performing the object-based image analysis (OBIA) approach, the textural and spectral characteristics of lithological features were analyzed by the use of support vector machine (SVM) algorithm. However, in the pixel-based image analysis (PBIA), the spectra of lithological end-members, extracted from imagery, were used through the spectral angle mapper (SAM) method. Several test samples were used in a confusion matrix to assess the accuracy of classification methods quantitatively. Results showed that OBIA was capable of lithological mapping with an overall accuracy of 86.54% which was 19.33% greater than the accuracy of PBIA. OBIA also reduced the salt-and-pepper artifact pixels and produced a more realistic map with sharper lithological borders. This research showed limitations of pixel-based method due to relying merely on the spectral characteristics of rock types when applied to high-spatial-resolution VNIR bands of WorldView-3 imagery. It is concluded that the application of an object-based image analysis approach obtains a more accurate lithological classification when compared to a pixel-based image analysis algorithm.

Keywords object-based image analysis pixel-based image analysis lithological mapping Worldview-3 Hormuz Island spectral angle mapper support vector machine

Corresponding Author(s): Majid H. TANGESTANI

Online First Date: 17 March 2021 Issue Date: 19 April 2021

Cite this article:

Samira SHAYEGANPOUR,Majid H. TANGESTANI,Saeid HOMAYOUNI, et al. Evaluating pixel-based vs. object-based image analysis approaches for lithological discrimination using VNIR data of WorldView-3[J]. Front. Earth Sci., 2021, 15(1): 38-53.

URL:

https://academic.hep.com.cn/fesci/EN/10.1007/s11707-020-0848-7
https://academic.hep.com.cn/fesci/EN/Y2021/V15/I1/38

Fig.1 The study area in 1:250,000 geological map (Fakhari, 1994).

Fig.2 Hand samples of; (a) salt rock, (b) iron oxide, (c) rhyolite, (d) diabase, (e) green tuff, (f) basalt, (g) marl, (h) iron soil, and (i) volcanic tuff.

Fig.3 (a) High-resolution spectra of rock samples, (b) spectra of rocks resampled to the VNIR bands of WV-3.

Fig.4 Flowchart of the PBIA approach (PBIA= pixel-based image analysis; WV-3= worldview-3; SAM= spectral angle mapper; SID= spectral information divergence; MF= matched filtering; MTMF= mixture tuned matched filtering, ML= maximum likelihood, SFF= spectral feature fitting, LSU= linear spectral un-mixing)

Fig.5 (a) Spectral curves of lithological groups, extracted from VNIR bands of WV-3, and (b) locations and the names of collected end-members in a gray image.

Fig.6 Field photos of (a) red soil and marl, (b) anhydrite and marl, (c) tuff, (d) anhydrite and rhyolite, (e) red soil, gypsum and anhydrite, (f) diabase, (g) gypsum, (h) marl.

Fig.7 Flowchart of the OBIA approach.

Fig.8 The optimum hyperplane, margin, and support vectors in the SVM algorithm (^{Kavzoglu and Colkesen, 2009}).

Fig.9 Classification map of lithological units in Hormuz Island using the spectral angle mapper algorithm.

Fig.10 Classification map of lithological units in Hormuz Island as produced by the SVM algorithm.

Tab.1 Confusion matrices for SAM (a) and SVM (b) classification methods.

Tab.2

Fig.11 Comparison of results achieved by object-based and pixel-based approaches: a) improvement in lithological mapping outcrops, b) omission of ambiguous mixture, and c) filtering salt and-pepper pixel in a mixture of red soil, gypsum, and anhydrite.

1	S A Aqanabati (2006). Geology and mineral potential of Hormozgan Province. Journal of Development of Geology Training, 12: 4–11
2	I Ayoobi, M H Tangestani (2018). Evaluation of subpixel unmixing algorithms in mapping the porphyry copper alterations using EO-1 Hyperion data, a case study from SE Iran. Remote Sensing Applications: Society and Environment, 10: 120–127 https://doi.org/10.1016/j.rsase.2018.03.009
3	M Aufaristama, D Hölbling, A Höskuldsson, I Jónsdóttir (2017). Comparison of SAM and OBIA as tools for lava morphology classification—a case study in Krafla, NE Iceland. In: EGU General Assembly, 19
4	T Blaschke (2010). Object based image analysis for remote sensing. ISPRS J Photogramm Remote Sens, 65(1): 2–16 https://doi.org/10.1016/j.isprsjprs.2009.06.004
5	T Blaschke , J Strobl (2001). What’s wrong with pixels? Some recent developments interfacing remote sensing and GIS. GIS – Zeitschrift für Geoinformations systeme 14(6), 12–17
6	T Blaschke, C Burnett, A Pekkarinen (2004). New contextual approaches using image segmentation for object-based classification. In: De Meer F, de Jong S, eds. Remote Sensing Image Analysis: Including the spatial domain. Dordrecht: Kluver Academic Publishers, 211–236
7	B Bedini (2019). Application of WorldView-3 imagery and ASTER TIR data to map alteration minerals associated with the Rodalquilar gold deposits, southeast Spain. Adv Space Res, 63(10): 3346–3357 https://doi.org/10.1016/j.asr.2019.01.047
8	J W Boardman, F A Kruse (1994). Automated spectral analysis: a geologic example using AVIRIS data, north Grapevine Mountains, Nevada. In: Tenth Thematic Conference on Geologic Remote Sensing, Environmental Research Institute of Michigan, Ann Arbor, MI
9	B Bahrambeygi, H Moeinzadeh (2017). Comparison of support vector machine and neutral network classification method in hyperspectral mapping of ophiolite mélanges–a case study of east of Iran. Egypt J Remote Sens Space Sci, 20(1): 1–10 https://doi.org/10.1016/j.ejrs.2017.01.007
10	C J C Burges, (1998). A tutorial on support vector machines for pattern recognition. Data Mining and Knowledge Discovery 2: 121–167 https://doi.org/10.1023/A: 1009715923555.
11	S M Bolouki, H R Ramazi, A Maghsoudi, A Beiranvand Pour, G Sohrabi (2019). A remote sensing-based application of bayesian networks for epithermal gold potential mapping in Ahar-Arasbaran Area, NW Iran. Remote Sens, 12(1): 105 https://doi.org/10.3390/rs12010105
12	U C Benz, P Hofmann, G Willhauck, I Lingenfelder, M Heynen (2004). Multiresolution, object-oriented fuzzy analysis of remote sensing data for GIS-ready information. ISPRS J Photogramm Remote Sens, 58(3–4): 239–258 https://doi.org/10.1016/j.isprsjprs.2003.10.002
13	R G Congalton, K Green (2009). Assessing the Accuracy of Remotely Sensed Data: Principles and Practices. Boca Raton: CRC Press
14	I L Castillejo-González, F López-Granados, A García-Ferrer, J M Peña-Barragán, M Jurado-Expósito, M S de la Orden, M González-Audicana (2009). Object- and pixel-based analysis for mapping crops and their agro-environmental associated measures using QuickBird imagery. Comput Electron Agric, 68(2): 207–215 https://doi.org/10.1016/j.compag.2009.06.004
15	R N Clark, T L Roush (1984). Reflectance spectroscopy: quantitative analysis techniques for remote sensing applications. J Geophys Res Solid Earth, 89(B7): 6329–6340 https://doi.org/10.1029/JB089iB07p06329
16	J Cai, J Luo, S Wang, S Yang (2018). Feature selection in machine learning: a new perspective. Neurocomputing, 300: 70–79 https://doi.org/10.1016/j. neucom.2017.11.077.
17	L K Dorren, B Maier, A C Seijmonsbergen (2003). Improved Landsat-based forest mapping in steep mountainous terrain using object-based classification. Forest Ecology and Management, 183 (1–3): 31–46.
18	A Darwish, K Leukert, W Reinhardt (2003). Image segmentation for the purpose of object-based classification. In: Geoscience and Remote Sensing Symposium, IGARSS’03. 2003 IEEE International, (3): 2039–2041
19	D F Ducart, A M Silva, C L B Toledo, L M Assis (2016). Mapping iron oxides with Landsat-8/OLI and EO-1/ Hyperion imagery from the Serra Norte iron deposits in the Carajás Mineral Province, Brazil. Braz J Geol, 46(3): 331–349 https://doi.org/10.1590/2317-4889201620160023
20	A H Elnagheeb, D W Bromley (1994). Extensification of agriculture and deforestation: empirical evidence from Sudan. Agricultural Economics 10(2): 193–200
21	M Fakhari (1994). Geological Quadrangle Map of Bandar-Abbas, 1:250000. Sheet No. 1–13, National Iranian Oil Company
22	J Elyasi, E Aminsobhani, A Behzad, H Moeinvaziri, A Meysami (1975). Geology of Hormuz Island. Geological Survey of Iran Publication, Tehran, 1: 13
23	S Grebby, E Field, K Tansey (2016). Evaluating the Use of an Object-Based Approach to Lithological Mapping in Vegetated Terrain. Remote Sens, 8(10): 843 https://doi.org/10.3390/rs8100843
24	A Gasmi, C Gomez, H Zouari, A Masse, D Ducrot (2016). PCA and SVM as geo-computational methods for geological mapping in the southern of Tunisia, using ASTER remote sensing data set. Arab J Geosci, 9(20): 753 https://doi.org/10.1007/s12517-016-2791-1
25	C K Huang, P F Kerr (1960). Infrared study of the carbonate minerals, Am Mineral, 45: 311–324
26	G R Hunt (1980). Electromagnetic radiation: the communication link in remote sensing. In: Siega1 BS, Gillepie AR, eds, Remote Sensing in Geology, Wiley: New York, 5–45
27	R D Hewson, D Robson, A Carlton, P Gilmore (2017). Geological application of ASTER remote sensing within sparsely outcropping terrain, Central New South Wales, Australia. Cogent Geosci, 3(1): 1319259 https://doi.org/10.1080/23312041.2017.1319259
28	G J Hay, G Castilla (2008). Geographic object-based image analysis (GEOBIA): a new name for a new discipline. In: Blaschke T, Lang S, Hay G, eds, Object Based Image Analysis. Heidelberg: Springer, 93–112
29	G J Hay, K O Niemann (1994). Visualizing 3-D texture: a three dimensional structural approach to model forest texture. Can J Rem Sens, 20(2): 90–101
30	E Ibrahim, P Barnabé, E Ramanaidou, E Pirard (2018). Mapping mineral chemistry of a lateritic outcrop in New Caledonia through generalized regression using Sentinel-2 and field reflectance spectra. Int J Appl Earth Obs Geoinformation, 73: 653–665 https://doi.org/10.1016/j.jag.2018.08.004
31	J R Jensen (2005). Introductory Digital Image Processing. Upper Saddle River: Person Prentice Hall
32	A Karatzoglou, A Smola, K Hornik, A Zeileis (2004). kernlab – an S4 package for kernel methods in R. J Stat Softw, 11(9): 1–20 https://doi.org/10.18637/jss.v011.i09
33	M Kuester (2016). Radiometric use of WV-3 imagery. Technical Note. DigitalGlobe
34	T Kavzoglu, I Colkesen (2009). A kernel functions analysis for support vector machines for land cover classification. Int J Appl Earth Obs Geoinf, 11(5): 352–359 https://doi.org/10.1016/j.jag.2009.06.002
35	F A Kruse, A B Lefkoff, J B Boardman, K B Heidebrecht, A T Shapiro, P J Barloon, A F H Goetz (1993). The Spectral Image Processing System (SIPS)–interactive visualization and analysis of imaging spectrometer data. Remote Sens Environ, 44(2-3): 145–163 https://doi.org/10.1016/0034-4257(93)90013-N
36	S Lang, E Schöpfer, T Langanke (2008). Combined object-based classification and manual interpretation — synergies for a quantitative assessment of parcels and biotopes. Geocarto Int, 23(4): 1–16
37	L Liu, J Feng, B Rivard, X Xu, J Zhou, L Han, J Yang, G Ren (2018). Guangli Ren Mapping alteration using imagery from the Tiangong-1 hyperspectral spaceborne system: example for the Jintanzi gold province, China. Int J Appl Earth Obs Geoinf, 64: 275–286 https://doi.org/10.1016/j.jag.2017.03.013
38	D Marceau (1999). The scale issue in the social and natural sciences. Can J Rem Sens, 25(4): 347–356 https://doi.org/10.1080/07038992.1999.10874734
39	M G Mahyari (2016). Comparison of ASTER reflective and thermal infrared data for discriminating lithological units and identifying potash-bearing areas in Hormoz salt plug. Dissertation for Master’s Degree. Shiraz: Shiraz University
40	G S Matton, F Canto, S Waldner, D Valero, J Morin, M Inglada, S Arias, B Bontemps, P Koetz, P Defourny (2015). DefournyAn automated method for annual cropland mapping along the season for various globally-distributed agrosystems using high spatial and temporal resolution time series. Remote Sens, 7(10): 13208–13232 https://doi.org/10.3390/rs71013208
41	F Melgani, L Bruzzone (2004). Classification of hyperspectral remote sensing images with support vector machines. IEEE Trans Geosci Remote Sens, 42(8): 1778–1790 https://doi.org/10.1109/TGRS.2004.831865
42	D J Marceau, P J Howarth, J M M Dubois, D J Gratton (1990). Evaluation of the grey level co-occurrence matrix method for land-cover classification using SPOT imagery. IEEE Trans Geosci Remote Sens, 28(4): 513–519 https://doi.org/10.1109/TGRS.1990.572937
43	J C Mars (2018). Mineral and lithologic mapping capability of WorldView 3 data at Mountain Pass, California, using true- and false-color composite images, band ratios, and logical operator algorithms. Econ Geol, 113(7): 1587–1601 https://doi.org/10.5382/econgeo.2018.4604
44	D C Mason, D G Corr, A Cross, D C Hogg, D H Lawrence, M Petrou, A M Tailor (1988). The use of digital map data in the segmentation and classification of remotely-sensed images. Int J Remote Sens, 2: 195–215
45	P M Mather, B Tso, M Koch (1998). An evaluation of Landsat TM spectral data and SAR-derived textural information for lithological discrimination in the Red Sea Hills, Sudan. Int J Remote Sens, 19(4): 587–604 https://doi.org/10.1080/014311698215874
46	P R Markoski, S B A Rolim (2014). Evaluation of ASTER images for characterization and mapping of volcanic rocks (Basalts). International Journal of Advanced Remote Sensing and GIS, 3(1): 486–498
47	B S Mengisteab, L Blesius, L Hennessy (2014). Application of object based image analysis (OBIA) in detection and quantifying forest loss caused by artisanal gold mining activities in Upper Mazaruni River Basin, Guyana. In: AGU Fall Meeting, 2014
48	L Noori, B A Pour, G Askari, N Taghipour, B Pradhan, C W Lee, M Honarmand (2019). Comparison of different algorithms to map hydrothermal alteration zones using ASTER remote sensing data for polymetallic vein-type ore exploration: toroud–chahshirin magmatic belt (TCMB). North Iran. Remote Sensing, 11(5): 495 https://doi.org/10.3390/rs11050495
49	K M Naghadehi, A Hezarkhani, S Asadzadeh (2014). Mapping the alteration footprint and structural control of Taknar IOCG deposit in east of Iran, using ASTER satellite data. Int J Appl Earth Obs Geoinf, 33: 57–66 https://doi.org/10.1016/j.jag.2014.04.016
50	T Oommen, D Misra, N K C Twarakavi, A Prakash, B Sahoo, S Bandopadhyay (2008). An objective analysis of support vector machine based classification for remote sensing. Math Geosci, 40(4): 409–424 https://doi.org/10.1007/s11004-008-9156-6
51	F Petitjean, C Kurtz, N Passat, P Gançarski (2012). Spatio-temporal reasoning for the classification of satellite image time series. Pattern Recognit Lett, 33(13): 1805–1815 https://doi.org/10.1016/j.patrec.2012.06.009
52	P Petropoulos G, K Vadrevu, Ch Kalaitzidis (2012). Spectral Angle Mapper and Object-based classification combined with hyperspectral remote sensing imagery for obtaining land use/cover mapping in a Mediterranean region. Geocarto Int, 28(2)
53	F Qiu, M Abdelsalam, P Thakkar (2006). Spectral analysis of ASTER data covering part of the Neoproterozoic Allaqi-Heiani suture, Southern Egypt. J Afr Earth Sci, 44(2): 169–180 https://doi.org/10.1016/j.jafrearsci.2005.10.009
54	J A Richards (1993). Remote Sensing Digital Image Analysis: An Introduction. 2nd ed. Berlin Heidelberg: Springer-Verlag https://doi.org/10.1007/978-3-642-30062-2.
55	S Rajendran, S Nasir (2019). ASTER capability in mapping of mineral resources of arid region: a review on mapping of mineral resources of the Sultanate of Oman. Ore Geol Rev, 108: 33–53 https://doi.org/10.1016/j.oregeorev.2018.04.014
56	Research Systems, Inc. (2002). ENVI Tutorials. Boulder: Research Systems, Inc
57	S Rajendran, S Nasir, T M Kusky, A Ghulam, S Gabr, M El Ghali (2013). Detection of hydrothermal mineralized zones associated with listwaenites in Central Oman using ASTER data. Ore Geol Rev, 53: 470–488 https://doi.org/10.1016/j.oregeorev.2013.02.008
58	J Stocklin (1972). Lexique Stratigraphique International. Geological Survey of Iran Publication, Tehran, 36: 15
59	N S Faramarzi, S Amini, A K Schmitt, J Hassanzadeh, G Borg, K McKeegan, S M H Razavi, S M Mortazavi (2015). Geochronology and geochemistry of rhyolites from Hormuz Island, southern Iran: a new record of Cadomian arc magmatism in the Hormuz Formation. Lithos, 236–237: 203–211 https://doi.org/10.1016/j.lithos.2015.08.017
60	J Stocklin (1974). Possible ancient continental margins in Iran. In: The Geology of Continental Margins. Berlin: Springer, 873–887
61	J W Salisbury, G R Hunt (1974). Remote sensing of rock type in the visible and near infrared. In: Proceedings of 9th International Symposium on Remote Sensing Environment, Ann Arbor, vol III, 1953–1958
62	Y Sun, S Tian, B Di (2017). Extracting mineral alteration information using Worldview-3 data. Geoscience Frontiers, 8(5): 1051–1062 https://doi.org/10.1016/j.gsf.2016.10.008
63	D B Segal (1983). Use of Landsat multispectral scanner data for the definition of limonitic exposures in heavily vegetated areas. Econ Geol, 78(4): 711–722 https://doi.org/10.2113/gsecongeo.78.4.711
64	R B Thapa, Y Murayama (2009). Urban mapping, accuracy, and image classification: a comparison of multiple approaches in Tsukuba City, Japan. Applied Geography 29:135–144
65	F J Testa, C Villanueva, D Cooke, L Zhang (2018). Lithological and Hydrothermal Alteration Mapping of Epithermal, Porphyry and Tourmaline Breccia Districts in the Argentine Andes Using ASTER Imagery. Remote Sens, 10(2): 203 https://doi.org/10.3390/rs10020203
66	T Tormos, P Kosuth, S Durrieu, S Dupuy, B Villeneuve, J Wasson (2012). Object-based image analysis for operational fine-scale regional mapping of land cover within river corridors from multispectral imagery and thematic data. Int J Remote Sens, 33(14): 4603–4633 https://doi.org/10.1080/01431161.2011.637093
67	Trimble (2015). eCognition Developer 9.1 User Guide. Munich: Trimble Documentation
68	H Van der Werff, F Van Ruitenbeek, T Zegers, F Van der Meer (2007). Geologic mapping on Mars by segmentation of OMEGA data. In: Proceedings 5th EARSeL Workshop on Imaging Spectroscopy
69	L Wang, W Sousa, P Gong (2004). Integration of object-based and pixel-based classification for mangrove mapping with IKONOS imagery. Int J Remote Sens, 25(24): 5655–5668 https://doi.org/10.1080/014311602331291215
70	B Ye, S Tian, J Ge, Y Sun (2017). Assessment of WorldView-3 Data for Lithological Mapping. Remote Sens, 9(11): 1132 https://doi.org/10.3390/rs9111132
71	A Yazdi, M A Arian, M M R Tabari (2014). Geological and geotourism study of Iran Geology Natural Museum, Hormoz Island. Open J Ecol, 4(11): 703–714 https://doi.org/10.4236/oje.2014.411060
72	C Yeomans, M Middleton, R K Shail, S Grebby, P A J Lusty (2019). Integrated Object-Based Image Analysis for semi-automated geological lineament detection in southwest England. Comput Geosci, 123: 137–148 https://doi.org/10.1016/j.cageo.2018.11.005

[1]	Xiaosong HAN, Jiayi PAN, Adam T. DEVLIN. Remote sensing study of wetlands in the Pearl River Delta during 1995---2015 with the support vector machine method[J]. Front. Earth Sci., 2018, 12(3): 521-531.
[2]	Parham PAHLAVANI, Behnaz BIGDELI. A mutual information-Dempster-Shafer based decision ensemble system for land cover classification of hyperspectral data[J]. Front. Earth Sci., 2017, 11(4): 774-783.
[3]	Jun QI, Jia WEI, Changhong SUN, Tao PAN. A comparative QSPR study on aqueous solubility of polycyclic aromatic hydrocarbons by GA-SVM, GA-RBFNN and GA-PLS[J]. Front Earth Sci, 2011, 5(3): 245-251.

Viewed

Full text

Abstract

Cited

Shared

Discussed