Behnia, N., Zare, M., Moosavi, V., Khajeddin, S.I. (2020). Evaluation of a Hierarchical Classification Method and Statistical Comparison with Pixel-Based and Object-Oriented Approaches. , 8(4), 209-219.
N. Behnia; M. Zare; V. Moosavi; S.I. Khajeddin. "Evaluation of a Hierarchical Classification Method and Statistical Comparison with Pixel-Based and Object-Oriented Approaches". , 8, 4, 2020, 209-219.
Behnia, N., Zare, M., Moosavi, V., Khajeddin, S.I. (2020). 'Evaluation of a Hierarchical Classification Method and Statistical Comparison with Pixel-Based and Object-Oriented Approaches', , 8(4), pp. 209-219.
Behnia, N., Zare, M., Moosavi, V., Khajeddin, S.I. Evaluation of a Hierarchical Classification Method and Statistical Comparison with Pixel-Based and Object-Oriented Approaches. , 2020; 8(4): 209-219.

Evaluation of a Hierarchical Classification Method and Statistical Comparison with Pixel-Based and Object-Oriented Approaches

ECOPERSIA
Article 3, Volume 8, Issue 4 - Serial Number 34, 2020, Pages 209-219    PDF (2.17 M)
Document Type: Original Research
Authors
N. Behnia1; M. Zare* 1; V. Moosavi2; S.I. Khajeddin3
1Department of Arid Lands Management, Faculty of Natural Resources, Yazd University, Yazd, Iran
2Department of Watershed Management Engineering, Faculty of Natural Resources, Tarbiat Modares University, Tehran, Iran
3Department of Range and Watershed Management, Faculty of Natural Resources, Isfahan University of Technology, Isfahan, Iran
Abstract
Aims: Producing a land use/land cover map is a fundamental step in different studies. This study aimed to assess the ability of hierarchical, pixel-based and object-oriented classification methods to produce land use/cover maps.

Materials & Methods: This study was conducted in the Harat-Marvast basin of Yazd Province, Iran using Landsat imagery of 2016 (paths 161 and 162, row 39). The hierarchical image classification method was tested for land use/cover mapping. A statistical comparison between three algorithms, namely pixel-based, object-oriented and hierarchical image classification was performed using the McNemar test. An intensive field survey was also accomplished to obtain training and test samples.

Findings: The kappa coefficients for pixel-based, hierarchical and object-oriented techniques were 0.76, 0.83 and 0.94, respectively. Results also showed that the performance of SVM and hierarchical algorithms are significantly different with aχ2f 112.3 which shows the superior performance of the hierarchical algorithm.

Conclusion: It was shown that the object-oriented approach performed significantly better than the two above-mentioned methods (χ2= 149.6). As the computational costs of object-oriented methods are relatively high, the hierarchical algorithm can be suggested when there are limitations in time or computational infrastructures. Therefore, the hierarchical algorithm can be used instead of simple pixel-based algorithms for land use/cover mapping.
Keywords
Hierarchical Classification; Land Use/Cover Mapping; Object-Oriented Approach; SVM
References
Statistics
Article View: 15,239
PDF Download: 23,355
Statistics
Number of Journals45
Number of Issues2,171
Number of Articles24,674
Article View24,449,166
PDF Download17,555,692