Home > Research > Publications & Outputs > A hybrid MLP-CNN classifier for very fine resol...

Electronic data

  • PHOTO_2017_21_Accepted_Version

    Rights statement: This is the author’s version of a work that was accepted for publication in ISPRS Journal of Photogrammetry and Remote Sensing. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in ISPRS Journal of Photogrammetry and Remote Sensing, 140, 2018 DOI: 10.1016/j.isprsjprs.2017.07.014

    Accepted author manuscript, 1.79 MB, PDF document

    Available under license: CC BY-NC-ND: Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License

Links

Text available via DOI:

View graph of relations

A hybrid MLP-CNN classifier for very fine resolution remotely sensed image classification

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

A hybrid MLP-CNN classifier for very fine resolution remotely sensed image classification. / Zhang, Ce; Pan, Xin; Li, Huapeng et al.
In: ISPRS Journal of Photogrammetry and Remote Sensing, Vol. 140, 06.2018, p. 133-144.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

Zhang, C, Pan, X, Li, H, Gardiner, A, Sargent, I, Hare, J & Atkinson, PM 2018, 'A hybrid MLP-CNN classifier for very fine resolution remotely sensed image classification', ISPRS Journal of Photogrammetry and Remote Sensing, vol. 140, pp. 133-144. https://doi.org/10.1016/j.isprsjprs.2017.07.014

APA

Zhang, C., Pan, X., Li, H., Gardiner, A., Sargent, I., Hare, J., & Atkinson, P. M. (2018). A hybrid MLP-CNN classifier for very fine resolution remotely sensed image classification. ISPRS Journal of Photogrammetry and Remote Sensing, 140, 133-144. https://doi.org/10.1016/j.isprsjprs.2017.07.014

Vancouver

Zhang C, Pan X, Li H, Gardiner A, Sargent I, Hare J et al. A hybrid MLP-CNN classifier for very fine resolution remotely sensed image classification. ISPRS Journal of Photogrammetry and Remote Sensing. 2018 Jun;140:133-144. Epub 2017 Aug 2. doi: 10.1016/j.isprsjprs.2017.07.014

Author

Zhang, Ce ; Pan, Xin ; Li, Huapeng et al. / A hybrid MLP-CNN classifier for very fine resolution remotely sensed image classification. In: ISPRS Journal of Photogrammetry and Remote Sensing. 2018 ; Vol. 140. pp. 133-144.

Bibtex

@article{254337583dd547e7af6cdc9a05d64359,
title = "A hybrid MLP-CNN classifier for very fine resolution remotely sensed image classification",
abstract = "The contextual-based convolutional neural network (CNN) with deep architecture and pixel-based multilayer perceptron (MLP) with shallow structure are well-recognized neural network algorithms, representing the state-of-the-art deep learning method and the classical non-parametric machine learning approach, respectively. The two algorithms, which have very different behaviours, were integrated in a concise and effective way using a rule-based decision fusion approach for the classification of very fine spatial resolution (VFSR) remotely sensed imagery. The decision fusion rules, designed primarily based on the classification confidence of the CNN, reflect the generally complementary patterns of the individual classifiers. In consequence, the proposed ensemble classifier MLP-CNN harvests the complementary results acquired from the CNN based on deep spatial feature representation and from the MLP based on spectral discrimination. Meanwhile, limitations of the CNN due to the adoption of convolutional filters such as the uncertainty in object boundary partition and loss of useful fine spatial resolution detail were compensated. The effectiveness of the ensemble MLP-CNN classifier was tested in both urban and rural areas using aerial photography together with an additional satellite sensor dataset. The MLP-CNN classifier achieved promising performance, consistently outperforming the pixel-based MLP, spectral and textural-based MLP, and the contextual-based CNN in terms of classification accuracy. This research paves the way to effectively address the complicated problem of VFSR image classification.",
keywords = "Convolutional neural network, Multilayer perceptron, VFSR remotely sensed imagery, Fusion decision, Feature representation",
author = "Ce Zhang and Xin Pan and Huapeng Li and Andy Gardiner and Isabel Sargent and Jonathon Hare and Atkinson, {Peter M.}",
note = "This is the author{\textquoteright}s version of a work that was accepted for publication in ISPRS Journal of Photogrammetry and Remote Sensing. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in ISPRS Journal of Photogrammetry and Remote Sensing, 140, 2018 DOI: 10.1016/j.isprsjprs.2017.07.014",
year = "2018",
month = jun,
doi = "10.1016/j.isprsjprs.2017.07.014",
language = "English",
volume = "140",
pages = "133--144",
journal = "ISPRS Journal of Photogrammetry and Remote Sensing",
issn = "0924-2716",
publisher = "Elsevier Science B.V.",

}

RIS

TY - JOUR

T1 - A hybrid MLP-CNN classifier for very fine resolution remotely sensed image classification

AU - Zhang, Ce

AU - Pan, Xin

AU - Li, Huapeng

AU - Gardiner, Andy

AU - Sargent, Isabel

AU - Hare, Jonathon

AU - Atkinson, Peter M.

N1 - This is the author’s version of a work that was accepted for publication in ISPRS Journal of Photogrammetry and Remote Sensing. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in ISPRS Journal of Photogrammetry and Remote Sensing, 140, 2018 DOI: 10.1016/j.isprsjprs.2017.07.014

PY - 2018/6

Y1 - 2018/6

N2 - The contextual-based convolutional neural network (CNN) with deep architecture and pixel-based multilayer perceptron (MLP) with shallow structure are well-recognized neural network algorithms, representing the state-of-the-art deep learning method and the classical non-parametric machine learning approach, respectively. The two algorithms, which have very different behaviours, were integrated in a concise and effective way using a rule-based decision fusion approach for the classification of very fine spatial resolution (VFSR) remotely sensed imagery. The decision fusion rules, designed primarily based on the classification confidence of the CNN, reflect the generally complementary patterns of the individual classifiers. In consequence, the proposed ensemble classifier MLP-CNN harvests the complementary results acquired from the CNN based on deep spatial feature representation and from the MLP based on spectral discrimination. Meanwhile, limitations of the CNN due to the adoption of convolutional filters such as the uncertainty in object boundary partition and loss of useful fine spatial resolution detail were compensated. The effectiveness of the ensemble MLP-CNN classifier was tested in both urban and rural areas using aerial photography together with an additional satellite sensor dataset. The MLP-CNN classifier achieved promising performance, consistently outperforming the pixel-based MLP, spectral and textural-based MLP, and the contextual-based CNN in terms of classification accuracy. This research paves the way to effectively address the complicated problem of VFSR image classification.

AB - The contextual-based convolutional neural network (CNN) with deep architecture and pixel-based multilayer perceptron (MLP) with shallow structure are well-recognized neural network algorithms, representing the state-of-the-art deep learning method and the classical non-parametric machine learning approach, respectively. The two algorithms, which have very different behaviours, were integrated in a concise and effective way using a rule-based decision fusion approach for the classification of very fine spatial resolution (VFSR) remotely sensed imagery. The decision fusion rules, designed primarily based on the classification confidence of the CNN, reflect the generally complementary patterns of the individual classifiers. In consequence, the proposed ensemble classifier MLP-CNN harvests the complementary results acquired from the CNN based on deep spatial feature representation and from the MLP based on spectral discrimination. Meanwhile, limitations of the CNN due to the adoption of convolutional filters such as the uncertainty in object boundary partition and loss of useful fine spatial resolution detail were compensated. The effectiveness of the ensemble MLP-CNN classifier was tested in both urban and rural areas using aerial photography together with an additional satellite sensor dataset. The MLP-CNN classifier achieved promising performance, consistently outperforming the pixel-based MLP, spectral and textural-based MLP, and the contextual-based CNN in terms of classification accuracy. This research paves the way to effectively address the complicated problem of VFSR image classification.

KW - Convolutional neural network

KW - Multilayer perceptron

KW - VFSR remotely sensed imagery

KW - Fusion decision

KW - Feature representation

U2 - 10.1016/j.isprsjprs.2017.07.014

DO - 10.1016/j.isprsjprs.2017.07.014

M3 - Journal article

VL - 140

SP - 133

EP - 144

JO - ISPRS Journal of Photogrammetry and Remote Sensing

JF - ISPRS Journal of Photogrammetry and Remote Sensing

SN - 0924-2716

ER -