Home > Research > Publications & Outputs > Identifying and mapping individual plants in a ...

Electronic data

  • ISPRS_paramo_paper_20200930_accepted

    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, 169, 2020 DOI: 10.1016/j.isprsjprs.2020.09.025

    Accepted author manuscript, 7.76 MB, Word 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

Identifying and mapping individual plants in a highly diverse high-elevation ecosystem using UAV imagery and deep learning

Research output: Contribution to journalJournal articlepeer-review

Published

Standard

Identifying and mapping individual plants in a highly diverse high-elevation ecosystem using UAV imagery and deep learning. / Zhang, Ce; Atkinson, Peter; George, Charles ; Wen, Zhaofei; Diazgranados, Mauricio; Gerard, France.

In: ISPRS Journal of Photogrammetry and Remote Sensing, Vol. 169, 01.11.2020, p. 280-291.

Research output: Contribution to journalJournal articlepeer-review

Harvard

Zhang, C, Atkinson, P, George, C, Wen, Z, Diazgranados, M & Gerard, F 2020, 'Identifying and mapping individual plants in a highly diverse high-elevation ecosystem using UAV imagery and deep learning', ISPRS Journal of Photogrammetry and Remote Sensing, vol. 169, pp. 280-291. https://doi.org/10.1016/j.isprsjprs.2020.09.025

APA

Zhang, C., Atkinson, P., George, C., Wen, Z., Diazgranados, M., & Gerard, F. (2020). Identifying and mapping individual plants in a highly diverse high-elevation ecosystem using UAV imagery and deep learning. ISPRS Journal of Photogrammetry and Remote Sensing, 169, 280-291. https://doi.org/10.1016/j.isprsjprs.2020.09.025

Vancouver

Author

Zhang, Ce ; Atkinson, Peter ; George, Charles ; Wen, Zhaofei ; Diazgranados, Mauricio ; Gerard, France. / Identifying and mapping individual plants in a highly diverse high-elevation ecosystem using UAV imagery and deep learning. In: ISPRS Journal of Photogrammetry and Remote Sensing. 2020 ; Vol. 169. pp. 280-291.

Bibtex

@article{82afaae49a2f4ec0b799a1eddac7433c,
title = "Identifying and mapping individual plants in a highly diverse high-elevation ecosystem using UAV imagery and deep learning",
abstract = "The identification and counting of plant individuals is essential for environmental monitoring. UAV based imagery offer ultra-fine spatial resolution and flexibility in data acquisition, and so provide a great opportunity to enhance current plant and in-situ field surveying. However, accurate mapping of individual plants from UAV imagery remains challenging, given the great variation in the sizes and geometries of individual plants and in their distribution. This is true even for deep learning based semantic segmentation and classification methods. In this research, a novel Scale Sequence Residual U-Net (SS Res U-Net) deep learning method was proposed, which integrates a set of Residual U-Nets with a sequence of input scales that can be derived automatically. The SS Res U-Net classifies individual plants by continuously increasing the patch scale, with features learned at small scales passing gradually to larger scales, thus, achieving multi-scale information fusion while retaining fine spatial details of interest. The SS Res U-Net was tested to identify and map frailejones (all plant species of the subtribe Espeletiinae), the dominant plants in one of the world{\textquoteright}s most biodiverse high-elevation ecosystems (i.e. the p{\'a}ramos) from UAV imagery. Results demonstrate that the SS Res U-Net has the ability to self-adapt to variation in objects, and consistently achieved the highest classification accuracy (91.67% on average) compared with four state-of-the-art benchmark approaches. In addition, SS Res U-Net produced the best performances in terms of both robustness to training sample size reduction and computational efficiency compared with the benchmarks. Thus, SS Res U-Net shows great promise for solving remotely sensed semantic segmentation and classification tasks, and more general machine intelligence. The prospective implementation of this method to identify and map frailejones in the p{\'a}ramos will benefit immensely the monitoring of their populations for conservation assessments and management, among many other applications.",
keywords = "Multi-scale deep learning, Residual U-Net, Scale sequence, Semantic segmentation, P{\'a}ramos",
author = "Ce Zhang and Peter Atkinson and Charles George and Zhaofei Wen and Mauricio Diazgranados and France Gerard",
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, 169, 2020 DOI: 10.1016/j.isprsjprs.2020.09.025",
year = "2020",
month = nov,
day = "1",
doi = "10.1016/j.isprsjprs.2020.09.025",
language = "English",
volume = "169",
pages = "280--291",
journal = "ISPRS Journal of Photogrammetry and Remote Sensing",
issn = "0924-2716",
publisher = "Elsevier Science B.V.",

}

RIS

TY - JOUR

T1 - Identifying and mapping individual plants in a highly diverse high-elevation ecosystem using UAV imagery and deep learning

AU - Zhang, Ce

AU - Atkinson, Peter

AU - George, Charles

AU - Wen, Zhaofei

AU - Diazgranados, Mauricio

AU - Gerard, France

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, 169, 2020 DOI: 10.1016/j.isprsjprs.2020.09.025

PY - 2020/11/1

Y1 - 2020/11/1

N2 - The identification and counting of plant individuals is essential for environmental monitoring. UAV based imagery offer ultra-fine spatial resolution and flexibility in data acquisition, and so provide a great opportunity to enhance current plant and in-situ field surveying. However, accurate mapping of individual plants from UAV imagery remains challenging, given the great variation in the sizes and geometries of individual plants and in their distribution. This is true even for deep learning based semantic segmentation and classification methods. In this research, a novel Scale Sequence Residual U-Net (SS Res U-Net) deep learning method was proposed, which integrates a set of Residual U-Nets with a sequence of input scales that can be derived automatically. The SS Res U-Net classifies individual plants by continuously increasing the patch scale, with features learned at small scales passing gradually to larger scales, thus, achieving multi-scale information fusion while retaining fine spatial details of interest. The SS Res U-Net was tested to identify and map frailejones (all plant species of the subtribe Espeletiinae), the dominant plants in one of the world’s most biodiverse high-elevation ecosystems (i.e. the páramos) from UAV imagery. Results demonstrate that the SS Res U-Net has the ability to self-adapt to variation in objects, and consistently achieved the highest classification accuracy (91.67% on average) compared with four state-of-the-art benchmark approaches. In addition, SS Res U-Net produced the best performances in terms of both robustness to training sample size reduction and computational efficiency compared with the benchmarks. Thus, SS Res U-Net shows great promise for solving remotely sensed semantic segmentation and classification tasks, and more general machine intelligence. The prospective implementation of this method to identify and map frailejones in the páramos will benefit immensely the monitoring of their populations for conservation assessments and management, among many other applications.

AB - The identification and counting of plant individuals is essential for environmental monitoring. UAV based imagery offer ultra-fine spatial resolution and flexibility in data acquisition, and so provide a great opportunity to enhance current plant and in-situ field surveying. However, accurate mapping of individual plants from UAV imagery remains challenging, given the great variation in the sizes and geometries of individual plants and in their distribution. This is true even for deep learning based semantic segmentation and classification methods. In this research, a novel Scale Sequence Residual U-Net (SS Res U-Net) deep learning method was proposed, which integrates a set of Residual U-Nets with a sequence of input scales that can be derived automatically. The SS Res U-Net classifies individual plants by continuously increasing the patch scale, with features learned at small scales passing gradually to larger scales, thus, achieving multi-scale information fusion while retaining fine spatial details of interest. The SS Res U-Net was tested to identify and map frailejones (all plant species of the subtribe Espeletiinae), the dominant plants in one of the world’s most biodiverse high-elevation ecosystems (i.e. the páramos) from UAV imagery. Results demonstrate that the SS Res U-Net has the ability to self-adapt to variation in objects, and consistently achieved the highest classification accuracy (91.67% on average) compared with four state-of-the-art benchmark approaches. In addition, SS Res U-Net produced the best performances in terms of both robustness to training sample size reduction and computational efficiency compared with the benchmarks. Thus, SS Res U-Net shows great promise for solving remotely sensed semantic segmentation and classification tasks, and more general machine intelligence. The prospective implementation of this method to identify and map frailejones in the páramos will benefit immensely the monitoring of their populations for conservation assessments and management, among many other applications.

KW - Multi-scale deep learning

KW - Residual U-Net

KW - Scale sequence

KW - Semantic segmentation

KW - Páramos

U2 - 10.1016/j.isprsjprs.2020.09.025

DO - 10.1016/j.isprsjprs.2020.09.025

M3 - Journal article

VL - 169

SP - 280

EP - 291

JO - ISPRS Journal of Photogrammetry and Remote Sensing

JF - ISPRS Journal of Photogrammetry and Remote Sensing

SN - 0924-2716

ER -