Published

2019-10-01

Fusion Method Evaluation and Classification Suitability Study of Wetland Satellite Imagery

Evaluación del método de fusión y estudio de idoneidad de clasificación de imágenes satelitales de humedales

DOI:

https://doi.org/10.15446/esrj.v23n4.84350

Keywords:

HJ-1A HIS, Landsat-8 OLI, Fusion method, Wetland classification (en)
HJ-1A HIS, Landsat-8 OLI, Método de fusión, Clasificación de humedales (es)

Downloads

Authors

  • Danyao Zhu Heilongjiang Province Key Laboratory of Geographical Environment Monitoring and Spatial Information Service in Cold Regions, Harbin Normal University, Harbin 150025, China
  • Luhe Wan Heilongjiang Province Key Laboratory of Geographical Environment Monitoring and Spatial Information Service in Cold Regions, Harbin Normal University, Harbin 150025, China
  • Wei Gao Heilongjiang Province Key Laboratory of Geographical Environment Monitoring and Spatial Information Service in Cold Regions, Harbin Normal University, Harbin 150025, China

Based on HJ-1A HSI data and Landsat-8 OLI data, RS image fusion experiments were carried out using three fusion methods: principal component (PC) transform, Gram Schimdt (GS) transform and nearest neighbor diffusion (NND) algorithm. Four evaluation indexes, namely mean, standard deviation, information entropy and average gradient, were selected to evaluate the fusion results from the aspects of image brightness, clarity and information content. Wetland vegetation was classified by spectral angle mapping (SAM) to find a suitable fusion method for wetland vegetation information extraction. The results show that PC fusion image contains the largest amount of information, GS fusion image has certain advantages in brightness and clarity maintenance, and NND fusion method can retain the spectral characteristics of the image to the maximum extent; Among the three fusion methods, PC transform is the most suitable for wetland information extraction. It can retain more spectral information while improving spatial resolution, with classification accuracy of 89.24% and Kappa coefficient of 0.86.

Con base en los datos HJ-1A HSI y Landsat-8 OLI, los experimentos de fusión de imágenes RS se llevaron a cabo utilizando tres métodos de fusión: transformación de componente principal (PC), transformación de Gram Schimdt (GS) y algoritmo de difusión vecina más cercana (NND). Se seleccionaron cuatro índices de evaluación, desviación estándar, entropía de información y gradiente promedio, para evaluar los resultados de fusión de los aspectos de brillo de imagen, claridad y contenido de información. La vegetación de humedales se clasificó por mapeo de ángulo espectral (SAM) para encontrar un método de fusión adecuado para la extracción de información de vegetación de humedales. Los resultados muestran que la imagen de fusión de PC contiene la mayor cantidad de información, la imagen de fusión GS tiene ciertas ventajas en el mantenimiento del brillo y la claridad, y el método de fusión NND puede retener las características espectrales de la imagen al máximo. Entre los tres métodos de fusión, la transformación de PC es la más adecuada para la extracción de información de humedales. Puede retener más información espectral al tiempo que mejora la resolución espacial, con una precisión de clasificación del 89,24% y un coeficiente Kappa de 0,86.

References

Adam, E., Mutanga, O., Rugege, D. (2010). Multispectral and hyperspectral remote sensing for identification and mapping of wetland vegetation: A review. Wetlands Ecology and Management, 18, 281-296.

Dong, Q. L., Lin, H., Sun, H., Qiu, L., & Zhang, Y. (2013). Application of multi-source remote sensing data fusion method in wetland classification. Journal of Central South University of Forestry and Technology, 33(1), 52-57.

Fusun, B. S., Saygin, A., Mustafa, T. E., & Filiz, S. (2017). Evaluation of image fusion methods using PALSAR, RADARSAT-1 and SPOT images for land use/ land cover classification. Journal of the Indian Society of Remote Sensing, 45(4), 591-601.

Gao, L. (2015). Landsat8 OLI remote sensing image fusion based on the nearest neighbor diffusion method. Proceedings of the 2015 Annual Conference of Jiangsu Surveying and Mapping Geographic Information Society.

Ma, X. X. & Wang, J. L. (2016). The basic research of phase retrieval algorithm. Optik-International Journal for Light & Electron Optics, 127(4), 1561-1566.

Ma, Y. P., Feng, Z. K., He, Y. J., & Zhang, Z. H. (2007). Research on image fusion of quickbird based on ERDAS IMAGINE software. Journal of Beijing Forestry University, (S2), 181-184.

Moon, W., Choi, J., Lee, S., & An, K. (2017). In situ nutrient-spiking bioassays for determining phosphorus and light limitation in a wetland ecosystem. Journal of Environmental Biology, 38(4), 631-639.

Ocalan, T., Erdogan, B., Tunalioglu, N., & Durdag, U. M. (2016). Accuracy investigation of PPP method versus relative positioning using different satellite ephemerides products near/under forest environment. Earth Sciences Research Journal, 20(4), D1-D9.

Sun, W. H., Chen, B., & David, W. (2014). Nearest-neighbor diffusion-based pan- sharpening algorithm for spectral images. Optical Engineering, 53(1), 13-17.

Wang, Z. J., Li, D. R., & Li, Q. Q. (2001). Application of multiple wavelet theory in SPOT and TM image fusion. Journal of Wuhan University (Information Science Edition), 1, 24-28.

Wei, W., Li, Z. Y., Tan, B. X., & Xun, H. S. (2011). Research on remote sensing classification method of longbaotan wetland based on multi-angle hyperspectral CHRIS image. Forest Science Research, 24(2), 159-164.

Wu, R. J., He, X. F., & Wang, J. (2015). Evaluation of fusion quality of multi-spectral and panchromatic images of wetland on resource 3 satellit. High-Tech Communication, 25(2), 157-162.

Yan, Z. (2008). Research on multi-source remote sensing image fusion technology. Wuhan University of Technology.

Zhu, Z. X. (2012). Zhalong wetland vegetation classification based on hyperspectral remote sensing image. Harbin Normal University.

How to Cite

APA

Zhu, D., Wan, L. and Gao, W. (2019). Fusion Method Evaluation and Classification Suitability Study of Wetland Satellite Imagery. Earth Sciences Research Journal, 23(4), 339–346. https://doi.org/10.15446/esrj.v23n4.84350

ACM

[1]
Zhu, D., Wan, L. and Gao, W. 2019. Fusion Method Evaluation and Classification Suitability Study of Wetland Satellite Imagery. Earth Sciences Research Journal. 23, 4 (Oct. 2019), 339–346. DOI:https://doi.org/10.15446/esrj.v23n4.84350.

ACS

(1)
Zhu, D.; Wan, L.; Gao, W. Fusion Method Evaluation and Classification Suitability Study of Wetland Satellite Imagery. Earth sci. res. j. 2019, 23, 339-346.

ABNT

ZHU, D.; WAN, L.; GAO, W. Fusion Method Evaluation and Classification Suitability Study of Wetland Satellite Imagery. Earth Sciences Research Journal, [S. l.], v. 23, n. 4, p. 339–346, 2019. DOI: 10.15446/esrj.v23n4.84350. Disponível em: https://revistas.unal.edu.co/index.php/esrj/article/view/84350. Acesso em: 14 jul. 2024.

Chicago

Zhu, Danyao, Luhe Wan, and Wei Gao. 2019. “Fusion Method Evaluation and Classification Suitability Study of Wetland Satellite Imagery”. Earth Sciences Research Journal 23 (4):339-46. https://doi.org/10.15446/esrj.v23n4.84350.

Harvard

Zhu, D., Wan, L. and Gao, W. (2019) “Fusion Method Evaluation and Classification Suitability Study of Wetland Satellite Imagery”, Earth Sciences Research Journal, 23(4), pp. 339–346. doi: 10.15446/esrj.v23n4.84350.

IEEE

[1]
D. Zhu, L. Wan, and W. Gao, “Fusion Method Evaluation and Classification Suitability Study of Wetland Satellite Imagery”, Earth sci. res. j., vol. 23, no. 4, pp. 339–346, Oct. 2019.

MLA

Zhu, D., L. Wan, and W. Gao. “Fusion Method Evaluation and Classification Suitability Study of Wetland Satellite Imagery”. Earth Sciences Research Journal, vol. 23, no. 4, Oct. 2019, pp. 339-46, doi:10.15446/esrj.v23n4.84350.

Turabian

Zhu, Danyao, Luhe Wan, and Wei Gao. “Fusion Method Evaluation and Classification Suitability Study of Wetland Satellite Imagery”. Earth Sciences Research Journal 23, no. 4 (October 1, 2019): 339–346. Accessed July 14, 2024. https://revistas.unal.edu.co/index.php/esrj/article/view/84350.

Vancouver

1.
Zhu D, Wan L, Gao W. Fusion Method Evaluation and Classification Suitability Study of Wetland Satellite Imagery. Earth sci. res. j. [Internet]. 2019 Oct. 1 [cited 2024 Jul. 14];23(4):339-46. Available from: https://revistas.unal.edu.co/index.php/esrj/article/view/84350

Download Citation

CrossRef Cited-by

CrossRef citations4

1. Hui Wang, Yu Shang, Yue Lv. (2021). Measurement and influencing factor analysis of TFEE in middle reaches of the Yellow River. Arabian Journal of Geosciences, 14(13) https://doi.org/10.1007/s12517-021-07571-9.

2. Li Hong, Songling Pang, Meiyun Geng, Sihan Wang. (2021). The GIS study on the spatial structure and visual perception of historical districts in winter cities. Arabian Journal of Geosciences, 14(12) https://doi.org/10.1007/s12517-021-07481-w.

3. Heber I. Mejia, Samuel Sanchez, Fernando J. Monja, Luz A. Cabrejos, Victor A. Tuesta, Manuel G. Forero, Andrew G. Tescher, Touradj Ebrahimi. (2021). Evaluation of panchromatic and multispectral image fusion methods using natural images. Applications of Digital Image Processing XLIV. , p.60. https://doi.org/10.1117/12.2594623.

4. Nikolay Abramov, Yulia Emelyanova, Vitaly Fralenko, Vyacheslav Khachumov, Mikhail Khachumov, Maria Shustova, Alexander Talalaev. (2024). Intelligent Methods for Forest Fire Detection Using Unmanned Aerial Vehicles. Fire, 7(3), p.89. https://doi.org/10.3390/fire7030089.

Dimensions

PlumX

Article abstract page views

400

Downloads

Download data is not yet available.