Published
Optimization of Fusion Method for GF-2 Satellite Remote Sensing Images based on the Classification Effect
Optimización del método de fusión para imágenes satelitales GF-2 basadas en el efecto de clasificación
DOI:
https://doi.org/10.15446/esrj.v23n2.80281Keywords:
GF-2, fusion algorithm, object-oriented classification, classification effect, (en)GF-2, algoritmo de fusión, clasificación orientada a objetos, efecto de clasificación, (es)
Downloads
With the successful launch of China’s GF series satellites, it is more important to study the image data quality, the adaptability of processing method and information extraction method. The panchromatic and multi-spectral data which is based on the GF-2 images data of Chinese sub-meter high-resolution remote sensing satellite is fused by PCA, Pansharp, Gram-Schmidt and NNDiffuse fusion. Then, the quality of the fusion images were evaluated subjectively and objectively. In order to evaluate the applicability of different classification algorithms to the classification, the object-oriented classification algorithm which is based on machine learning algorithm, such as KNN, SVM and Random Trees were used to classify the different GF-2 fusion images. The results showed that: (1) The best visual effect of GF-2 fusion image was the Pansharp fusion image; The quantitative evaluation results showed that the brightness and information retention of Gram-Schmidt fusion image was the best,while the Pansharp fusion image had the highest correlation with the original multi-spectral image; the NNDiffuse fusion image had the highest clarity, and the PCA fusion image quantitative evaluation effect was the worst; (2) According to the applicability analysis of the fusion images based on different classification algorithms with features information extraction, it could be seen that the NNDiffuse fusion method was used for the fusion of GF-2 image data, and the classification of the fusion images was more suitable by using KNN or Random Trees classification algorithm.
Con el lanzamiento exitoso de los satélites de la serie GF de China es más importante estudiar la calidad de los datos de imagen, la adaptabilidad del método de procesamiento y el método de extracción de información. Los datos pancromáticos y multiespectrales que se basan en los datos de imágenes GF-2 del satélite de teleobservación de alta resolución en el submetro chino, se fusionaron mediante PCA, Pansharp, Gram-Schmidt y NNDiffuse. Luego, la calidad de las imágenes de fusión se evaluó de manera subjetiva y objetiva. Para evaluar la aplicabilidad de diferentes algoritmos de clasificación a la clasificación, se utilizó el algoritmo de clasificación orientado a objetos que se basa en el algoritmo de aprendizaje automático, como KNN, SVM y árboles aleatorios para clasificar las diferentes imágenes de fusión de GF-2. Los resultados mostraron que: (1) El mejor efecto visual de la imagen de fusión GF-2 fue la imagen de fusión Pansharp; los resultados de la evaluación cuantitativa mostraron que el brillo y la retención de información de la imagen de fusión Gram-Schmidt fueron los mejores, mientras que la imagen de fusión Pansharp tuvo la mayor correlación con la imagen multiespectral original; la imagen de fusión NNDiffuse tuvo la mayor claridad, y el efecto de evaluación cuantitativa de la imagen de fusión PCA fue el peor; (2) De acuerdo con el análisis de aplicabilidad de las imágenes de fusión basadas en diferentes algoritmos de clasificación con características de extracción de información, se pudo ver que se usó el método de fusión NNDiffuse para la fusión de datos de imágenes GF-2, y la clasificación de las imágenes de fusión fue más apropiada utilizando el algoritmo de clasificación KNN o Random Trees.
References
Chen, J., Shao Q., Mei, X., Deng, M., & Hou, J. (2016). Object-based Urban Road Extraction From High Resolution Imagery with Space-scale Theory. Engineering of Surveying and Mapping. (12): 5-11.
Chen, M. (2016). Image Fusion of Visual and Infrared Image based on NSCT and Compressed Sensing. Journal of Image and Graphics. (01): 39-44.
Chen, X., Zhang, K., Zang, W., & Dong, L. (2016). Remote Sensing Image Fusion Based on High-Boost Filtering and àtrous Wavelet Transform. Journal of Henan University (NATURAL SCIENCE EDITION). (02): 202-206.
Deng, S., Chen, Q., & Du, H. (2014). ENVI remote sensing image processing. Beijing: Higher Education Press (in Chinese)
Dong, S., Zang, S., Wu, C., & Li, M. (2017). Comparison of Different Image Fusion Methods Using Spot-7. Geomatics and Spatial Information Technology. (01): 75-78.
Du, T. (2015). The comparsion among fusion algorithms of Landsat 8 OLI remote sensing imagery and analysis on adaptability of the classification of land use. Northwestern University.
Fan, C. (2015). Research on Wuxi New District Information Extraction Based on Worldview2 Image. Nanjing University.
Fang, T., Huo, H., & Ma, H. (2016). Intelligent interpretation of high resolution remote sensing images. Beijing:Science Press.
Jiang, Y., & Li, S. (2016). Remote Sensing Image Classification Based on Fusion of Multiple Features with Block Feature Point Density Analysis. Computer and Modernization.(05): 1-6.
Liu, K., Fu, J., & Li, F. (2015) Evaluation Study of Four Fusion Methods of GF-1 PAN and Multi-spectral Images. Remote Sensing Technology and Application. (05): 980-986.
Liu, X. (2014). Adjustment and Protection Analysis of Permanent Basic Farmland in Longchang County of Neijiang. Chengdu University of Technology.
Liu, Y. (2016). Target Recognition of High Resolution Remote Sensing Image Based on Multi-media Neural Cognitive Computing Model. Henan University.
Luo, L., & Du, Q. (2017). Image fusion quality evaluation algorithm based on multi-scale local variance. Computer Engineering. (02): 264-267.
Meng, F., Chen, S., & Zhang, G. (2016). Image Fusion Quality Assessment of GF-2 Satellite Based on Full Reference. Spacecraft Recovery and Remote Sensing.(06): 85-94.
Ren, J. (2016). Evaluation of Data Fusion Effect Based on the PMS data of Chinese GF-2 Satellite. Chengdu, China: 2016.
Sun, W., & Messinger, D. (2014). Nearest-neighbor diffusion-based pan-sharpening algorithm for spectral images. Optical Engineering. 53(1): 13107.
Sun, X., Fu, K., & Wang, H.. (2011) High Resolution Remote Sensing Image Understanding. Beijing: Science Press.
Wang, A. (2016). The Research of Remote Sensing Image Fusion Method Optimization Based on the GF-2 Satellite in the Mountain Area. Yunnan University.
Wang, H., Li, G., Zhang, B., & Dou, X. (2015). Contrast and Analysis of different fusion algorithms for ZY-3 Satellite Images. Science of Surveying and Mapping. 40(1): 47-51.
Wang, Z. H., Meng, F., Yang, X. M., Yang, F., & Fang, Y. (2016). Study on the automatic selection of segmentation scale parameters for high spatial resolution remote sensing images. Journal of Geo-information Science, 18(5):639-648.
Wang, Z., & Zhang, Q. (2015). Study of Fusion Methods of ZY-1-02C Satellite PMS Data. SPACECRAFT RECOVERY and REMOTE SENSING.(05): 83-95.
Xie, D. F., Zhang, J. S., Sun, P. J., & Pan, Y. (2016). Remote sensing data fusion by combining STARFM and downscaling mixed pixel algorithm. Journal of Remote Sensing. 20(1): 62-72
Yang, F. (2016). Comparison and Application of High-Resolution Image Fusion from the Same or Different Sensors. Anhui University, China.
Yang, H. P., & Ming, D. P. (2016). Optimal scales based segmentation of high spatial resolution remote sensing data. Journal of Geo-information Science, 18(5):632-638.
Yang, L. (2016). Building Change Detection From Multitemporal High Resolution Remote Sensing Imagery Based on Multi-Features Fusion Using Dempster-Shafer Evidence Theory. Southwest Jiao Tong University.
Yang, Y., & Yang, W. (2015). Study on delimitation of basic farmland in Longchang County. Agriculture and technology. (07): 1-3.
Yang, Y. (2015). Comparative Study on Object-oriented Classification Technique With the World-View2 High-resolution Image. Chengdu University of Technology.
Yilihamu, Y., Xie, L., & Kong, J. (2014). Remote sensing image fusion based on PCA transform and wavelet transform. Infrared and laser engineering. (07): 2335-2340.
Yu, B. (2015). Geometric Correction and Fusion Research on Domestic Satellite GF-1 Data. China University of Geosciences (Beijing).
Zhang, T., Liu, J., Yang, K., & Luo, W. (2015). Fusion Algorithm for Hyperspectral Remote Sensing Image Combined with Harmonic Analysis and Gram-Schmidt Transform. Acta Geodaetica et Cartographica Sinica, 44(9):1042-1047
Zhang, X. (2016). Road Extraction of High-resolution Remote Sensing Images Based on the Time-frequency Feature and SVM. Anhui University.
Zhao, D. (2016). Research of High Resolution Remote Sensing Image Segmentation Based on Modified Watershed. China University of Geosciences (Beijing).
Zhao, X., Li, Y., & Lei, S. (2016). An Image Fusion Method with Sparse Representation Based on Genetic Algorithm Optimization. Journal of Beijing University of Posts and Telecommunications. (02): 73-76.
How to Cite
APA
ACM
ACS
ABNT
Chicago
Harvard
IEEE
MLA
Turabian
Vancouver
Download Citation
CrossRef Cited-by
1. Tao Wang, Lili Du, Weining Yi, Jin Hong, Liming Zhang, Jianyu Zheng, Chao Li, Xiaoshan Ma, Dongying Zhang, Wei Fang, Honglian Huang, Anjing Wang, Bo Song, Nan Zhou, Rufang Ti, Kaitao Li, Wenyu Cui. (2021). An adaptive atmospheric correction algorithm for the effective adjacency effect correction of submeter-scale spatial resolution optical satellite images: Application to a WorldView-3 panchromatic image. Remote Sensing of Environment, 259, p.112412. https://doi.org/10.1016/j.rse.2021.112412.
2. 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.
3. Prakash Ghimire, Deng Lei, Nie Juan. (2020). Effect of Image Fusion on Vegetation Index Quality—A Comparative Study from Gaofen-1, Gaofen-2, Gaofen-4, Landsat-8 OLI and MODIS Imagery. Remote Sensing, 12(10), p.1550. https://doi.org/10.3390/rs12101550.
4. Yu Zhang, Chaoyong Shen, Shaoqi Zhou, Ruidong Yang, Xuling Luo, Guanglai Zhu. (2022). Applicability Analysis of GF-2PMS and PLANETSCOPE Data for Ground Object Recognition in Karst Region. Land, 12(1), p.33. https://doi.org/10.3390/land12010033.
5. Wei Wang, Rongyuan Liu, Huiyun Yang, Ping Zhou, Xiangwen Zhang, Ling Ding. (2021). Urban Forest Identification from High-Resolution Images Using Deep-Learning Method. 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS. , p.5283. https://doi.org/10.1109/IGARSS47720.2021.9553362.
6. Shuying Liu. (2024). Proceedings of International Conference on Artificial Intelligence and Communication Technologies (ICAICT 2023). Smart Innovation, Systems and Technologies. 368, p.55. https://doi.org/10.1007/978-981-99-6641-7_5.
7. Zirui Wang. (2024). Proceedings of International Conference on Artificial Intelligence and Communication Technologies (ICAICT 2023). Smart Innovation, Systems and Technologies. 368, p.17. https://doi.org/10.1007/978-981-99-6641-7_2.
8. Dan Chen, Xianyun Fei, Zhen Wang, Yajun Gao, Xiaowei Shen, Tingting Han, Yuanzhi Zhang. (2022). Classifying Vegetation Types in Mountainous Areas with Fused High Spatial Resolution Images: The Case of Huaguo Mountain, Jiangsu, China. Sustainability, 14(20), p.13390. https://doi.org/10.3390/su142013390.
Dimensions
PlumX
Article abstract page views
Downloads
License
Copyright (c) 2019 Earth Sciences Research Journal
![Creative Commons License](http://i.creativecommons.org/l/by/4.0/88x31.png)
This work is licensed under a Creative Commons Attribution 4.0 International License.
Earth Sciences Research Journal holds a Creative Commons Attribution license.
You are free to:
Share — copy and redistribute the material in any medium or format
Adapt — remix, transform, and build upon the material for any purpose, even commercially.
The licensor cannot revoke these freedoms as long as you follow the license terms.