The BP Neural Network for Improvement of Classification Accuracy in Remote Sensing Image

Ming Yu; He-Rong Wang; Ting Lan

doi:doi:10.11648/j.ijepp.20160403.17

| Peer-Reviewed

The BP Neural Network for Improvement of Classification Accuracy in Remote Sensing Image

Ming Yu, He-Rong Wang, Ting Lan

Published in International Journal of Environmental Protection and Policy (Volume 4, Issue 3)

Received: 6 June 2016 Accepted: Published: 7 June 2016

Views: Downloads:

Download PDF

Share This Article

Twitter
Linked In
Facebook

Abstract

Remote sensing (RS) data classification is one of the core functions of the system of remote sensing image processing. In this study, back propagation (BP) neural network was introduced into the application of remote sensing image with implementation of MATLAB. To improve measurement accuracy, the BP neural network application includes two schemes of different transfer functions; and 3, 5 and 7 bands of RS images of Landsat 8 OLI were used for validate the accuracy of classification. The experimental results proves that this algorithm is better than tradition classification of supervise and non - supervise methods. Classification accuracy increases as more band information is given; scheme 2 has high classification accuracy than scheme 1. The research results have a certain reference value for the rational use of land resources.

Published in	International Journal of Environmental Protection and Policy (Volume 4, Issue 3)
DOI	10.11648/j.ijepp.20160403.17
Page(s)	93-97
Creative Commons	This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.
Copyright	Copyright © The Author(s), 2024. Published by Science Publishing Group

Keywords

BP neural Network, Remote Sensing Image Classification, Network Parameters, Maximum Likelihood Classification Method

References

[1]	Atkinson, P. M. and A. R. L. Tattnall, Neural Networks in Remote Sensing, international journal of Remote Sensing, 1997, 18 (4): 699-709.
[2]	JIAO Li-min, Wu Su. Analyzing the characteristics of the Expansion of the Metropolises in china from 1990 to 2010 Using Self-organizing Neural Network [J]. Geomatics and Information science of Wuhan University. 2014. 39 (12): 1435-1440, 1471.
[3]	Ming Yu, Ting-hua AI. Study of RS data classification based on rough sets and C4.5 algorithm. 2009 Proceedings of SPIE, 2009.10.13-2009.10.14.
[4]	LI CHUN-HUA, SHA Jin-Min. Knowledge Based Self-Organizing Neural Network Remote Sensing Image Classification Approach， Remote Sensing Technology and Application, 2006, 21 (6): 507-511.
[5]	Xu Lei, Lin Jian, et al. Classifying Remote Sensing Image Based on BP Neural Network [J]. Geospatial Information, 2012, 10 (4): 83-85.
[6]	Zhang S L, Chang T C. A Study of Image Classification of Remote Sensing Based on Back-Propagation Neural Network with Extended Delta Bar Delta [J]. Mathematical Problems in Engineering, 2015, 501: 178598.
[7]	Y. Du, S. Zhou, and Q. Si. Application and contrast research on remote sensing image classification base on ANN [J]. Journal of Science of Surveying and Mapping, 2010, 35 (4): 121-125.
[8]	Xiao Jincheng, Ou Weixin, et al. Land cover classification of Yancheng Coastal Natural Wetlands based on BP neural network and ETM+ remote sensing data [J]. Acta Ecologica Sinica, 2013, 33 (23): 7496-7504.
[9]	Wu Chuang Ju, Song Shuang Jie, et al. Research of new method of RS Image classification Based on neural network [J]. China Science and Technology Review, 2014 (7): 321-322.
[10]	Li Haiyang, Fan Wenyi. Matlab Realization of Sensing Image Classification Based on Probabilistic Neural Network [J]. Journal of Northeast Forestry University, 2008, 36 (6): 55-56.
[11]	Jensen, J. R., Qiu, F. and K. Patterson, A Neural Network Image Interpretation System to Extract Rural and Urban Land U se and Land Cover Information from Remote Sensor Data. Geocarto International. 2001, 16 (1): 19-28.
[12]	Ke Huaming, CHEN Chaozhen, et al. Application of BP Neural Network Classification with Optimization of Genetic Algorithm for Remote Sensing Imagery Based on Matlab [J]. Journal of Southwest University of Science and Technology, 2010, 25 (3): 55-59.
[13]	Burks T F, Shearer S A, Gates R S, et al. Backpropagation neural network design and evaluation for classifying weed species using color image texture [J]. Transactions of the ASAE, 2000, 43 (4): 1029-1037.
[14]	Sexton R S, Dorsey R E. Reliable classification using neural networks: a genetic algorithm and backpropagation comparison [J]. Decision Support Systems, 2000, 30 (1): 11-22.
[15]	Li Shuang, Ding Shengyan, et al. The Comparative Study of Remote Sensing Image Classification. Journal of Henan University (Natural Science), 2002, 02: 70-73.

Cite This Article

Plain Text BibTeX RIS

APA Style

Ming Yu, He-Rong Wang, Ting Lan. (2016). The BP Neural Network for Improvement of Classification Accuracy in Remote Sensing Image. International Journal of Environmental Protection and Policy, 4(3), 93-97. https://doi.org/10.11648/j.ijepp.20160403.17

Copy | Download

ACS Style

Ming Yu; He-Rong Wang; Ting Lan. The BP Neural Network for Improvement of Classification Accuracy in Remote Sensing Image. Int. J. Environ. Prot. Policy 2016, 4(3), 93-97. doi: 10.11648/j.ijepp.20160403.17

Copy | Download

AMA Style

Ming Yu, He-Rong Wang, Ting Lan. The BP Neural Network for Improvement of Classification Accuracy in Remote Sensing Image. Int J Environ Prot Policy. 2016;4(3):93-97. doi: 10.11648/j.ijepp.20160403.17

Copy | Download

@article{10.11648/j.ijepp.20160403.17,
  author = {Ming Yu and He-Rong Wang and Ting Lan},
  title = {The BP Neural Network for Improvement of Classification Accuracy in Remote Sensing Image},
  journal = {International Journal of Environmental Protection and Policy},
  volume = {4},
  number = {3},
  pages = {93-97},
  doi = {10.11648/j.ijepp.20160403.17},
  url = {https://doi.org/10.11648/j.ijepp.20160403.17},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ijepp.20160403.17},
  abstract = {Remote sensing (RS)  data classification is one of the core functions of the system of remote sensing image processing. In this study, back propagation (BP) neural network was introduced into the application of remote sensing image with implementation of MATLAB. To improve measurement accuracy, the BP neural network application includes two schemes of different transfer functions; and 3, 5 and 7 bands of RS images of Landsat 8 OLI were used for validate the accuracy of classification. The experimental results proves that this algorithm is better than tradition classification of supervise and non - supervise methods. Classification accuracy increases as more band information is given; scheme 2 has high classification accuracy than scheme 1. The research results have a certain reference value for the rational use of land resources.},
 year = {2016}
}

Copy | Download

TY  - JOUR
T1  - The BP Neural Network for Improvement of Classification Accuracy in Remote Sensing Image
AU  - Ming Yu
AU  - He-Rong Wang
AU  - Ting Lan
Y1  - 2016/06/07
PY  - 2016
N1  - https://doi.org/10.11648/j.ijepp.20160403.17
DO  - 10.11648/j.ijepp.20160403.17
T2  - International Journal of Environmental Protection and Policy
JF  - International Journal of Environmental Protection and Policy
JO  - International Journal of Environmental Protection and Policy
SP  - 93
EP  - 97
PB  - Science Publishing Group
SN  - 2330-7536
UR  - https://doi.org/10.11648/j.ijepp.20160403.17
AB  - Remote sensing (RS)  data classification is one of the core functions of the system of remote sensing image processing. In this study, back propagation (BP) neural network was introduced into the application of remote sensing image with implementation of MATLAB. To improve measurement accuracy, the BP neural network application includes two schemes of different transfer functions; and 3, 5 and 7 bands of RS images of Landsat 8 OLI were used for validate the accuracy of classification. The experimental results proves that this algorithm is better than tradition classification of supervise and non - supervise methods. Classification accuracy increases as more band information is given; scheme 2 has high classification accuracy than scheme 1. The research results have a certain reference value for the rational use of land resources.
VL  - 4
IS  - 3
ER  -

Copy | Download

Author Information

Ming Yu

School of Geographical Sciences, Fujian Normal University, Fuzhou, China; Institute of Geography, Fujian Normal University, Fuzhou, China
He-Rong Wang

School of Geographical Sciences, Fujian Normal University, Fuzhou, China
Ting Lan

School of Geographical Sciences, Fujian Normal University, Fuzhou, China

Download PDF

Sections

Plain Text BibTeX RIS

APA Style

Ming Yu, He-Rong Wang, Ting Lan. (2016). The BP Neural Network for Improvement of Classification Accuracy in Remote Sensing Image. International Journal of Environmental Protection and Policy, 4(3), 93-97. https://doi.org/10.11648/j.ijepp.20160403.17

Copy | Download

ACS Style

Ming Yu; He-Rong Wang; Ting Lan. The BP Neural Network for Improvement of Classification Accuracy in Remote Sensing Image. Int. J. Environ. Prot. Policy 2016, 4(3), 93-97. doi: 10.11648/j.ijepp.20160403.17

Copy | Download

AMA Style

Ming Yu, He-Rong Wang, Ting Lan. The BP Neural Network for Improvement of Classification Accuracy in Remote Sensing Image. Int J Environ Prot Policy. 2016;4(3):93-97. doi: 10.11648/j.ijepp.20160403.17

Copy | Download

@article{10.11648/j.ijepp.20160403.17,
  author = {Ming Yu and He-Rong Wang and Ting Lan},
  title = {The BP Neural Network for Improvement of Classification Accuracy in Remote Sensing Image},
  journal = {International Journal of Environmental Protection and Policy},
  volume = {4},
  number = {3},
  pages = {93-97},
  doi = {10.11648/j.ijepp.20160403.17},
  url = {https://doi.org/10.11648/j.ijepp.20160403.17},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ijepp.20160403.17},
  abstract = {Remote sensing (RS)  data classification is one of the core functions of the system of remote sensing image processing. In this study, back propagation (BP) neural network was introduced into the application of remote sensing image with implementation of MATLAB. To improve measurement accuracy, the BP neural network application includes two schemes of different transfer functions; and 3, 5 and 7 bands of RS images of Landsat 8 OLI were used for validate the accuracy of classification. The experimental results proves that this algorithm is better than tradition classification of supervise and non - supervise methods. Classification accuracy increases as more band information is given; scheme 2 has high classification accuracy than scheme 1. The research results have a certain reference value for the rational use of land resources.},
 year = {2016}
}

Copy | Download

TY  - JOUR
T1  - The BP Neural Network for Improvement of Classification Accuracy in Remote Sensing Image
AU  - Ming Yu
AU  - He-Rong Wang
AU  - Ting Lan
Y1  - 2016/06/07
PY  - 2016
N1  - https://doi.org/10.11648/j.ijepp.20160403.17
DO  - 10.11648/j.ijepp.20160403.17
T2  - International Journal of Environmental Protection and Policy
JF  - International Journal of Environmental Protection and Policy
JO  - International Journal of Environmental Protection and Policy
SP  - 93
EP  - 97
PB  - Science Publishing Group
SN  - 2330-7536
UR  - https://doi.org/10.11648/j.ijepp.20160403.17
AB  - Remote sensing (RS)  data classification is one of the core functions of the system of remote sensing image processing. In this study, back propagation (BP) neural network was introduced into the application of remote sensing image with implementation of MATLAB. To improve measurement accuracy, the BP neural network application includes two schemes of different transfer functions; and 3, 5 and 7 bands of RS images of Landsat 8 OLI were used for validate the accuracy of classification. The experimental results proves that this algorithm is better than tradition classification of supervise and non - supervise methods. Classification accuracy increases as more band information is given; scheme 2 has high classification accuracy than scheme 1. The research results have a certain reference value for the rational use of land resources.
VL  - 4
IS  - 3
ER  -

Copy | Download