Woody Plant Encroachment: Evaluating Methodologies for Semiarid Woody Species Classification from Drone Images

被引:16
作者
Olariu, Horia G. [1 ]
Malambo, Lonesome [1 ]
Popescu, Sorin C. [1 ]
Virgil, Clifton [1 ]
Wilcox, Bradford P. [1 ]
机构
[1] Texas A&M Univ, Dept Ecol & Conservat Biol, College Stn, TX 77598 USA
关键词
deep learning; machine learning; drones; woody encroachment; semiarid; pixel-based classification; object-based classification; phenology; Texas; Edwards Plateau; VGG-19; RANDOM FOREST; VEGETATION; FUTURE; METAANALYSIS; CLASSIFIERS; DYNAMICS; SAVANNA;
D O I
10.3390/rs14071665
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Globally, native semiarid grasslands and savannas have experienced a densification of woody plant species-leading to a multitude of environmental, economic, and cultural changes. These encroached areas are unique in that the diversity of tree species is small, but at the same time the individual species possess diverse phenological responses. The overall goal of this study was to evaluate the ability of very high resolution drone imagery to accurately map species of woody plants encroaching on semiarid grasslands. For a site in the Edwards Plateau ecoregion of central Texas, we used affordable, very high resolution drone imagery to which we applied maximum likelihood (ML), support vector machine (SVM), random forest (RF), and VGG-19 convolutional neural network (CNN) algorithms in combination with pixel-based (with and without post-processing) and object-based (small and large) classification methods. Based on test sample data (n = 1000) the VGG-19 CNN model achieved the highest overall accuracy (96.9%). SVM came in second with an average classification accuracy of 91.2% across all methods, followed by RF (89.7%) and ML (86.8%). Overall, our findings show that RGB drone sensors are indeed capable of providing highly accurate classifications of woody plant species in semiarid landscapes-comparable to and even greater in some regards to those achieved by aerial and drone imagery using hyperspectral sensors in more diverse landscapes.
引用
收藏
页数:22
相关论文
共 54 条
  • [1] Exploiting machine learning algorithms for tree species classification in a semiarid woodland using RapidEye image
    Adelabu, Samuel
    Mutanga, Onisimo
    Adam, Elhadi
    Cho, Moses Azong
    [J]. JOURNAL OF APPLIED REMOTE SENSING, 2013, 7
  • [2] Transfer Learning Models for Land Cover and Land Use Classification in Remote Sensing Image
    Alem, Abebaw
    Kumar, Shailender
    [J]. APPLIED ARTIFICIAL INTELLIGENCE, 2022, 36 (01)
  • [3] [Anonymous], MACH LEARN
  • [4] Identifying species from the air: UAVs and the very high resolution challenge for plant conservation
    Baena, Susana
    Moat, Justin
    Whaley, Oliver
    Boyd, Doreen S.
    [J]. PLOS ONE, 2017, 12 (11):
  • [5] Random forest in remote sensing: A review of applications and future directions
    Belgiu, Mariana
    Dragut, Lucian
    [J]. ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2016, 114 : 24 - 31
  • [6] Ben Wu X, 2001, J RANGE MANAGE, V54, P98, DOI 10.2307/4003168
  • [7] Classification of Herbaceous Vegetation Using Airborne Hyperspectral Imagery
    Burai, Peter
    Deak, Balazs
    Valko, Orsolya
    Tomor, Tamas
    [J]. REMOTE SENSING, 2015, 7 (02) : 2046 - 2066
  • [8] Campbell J.B., 2011, INTRO REMOTE SENSING, V5th ed., P350
  • [9] Robust support vector method for hyperspectral data classification and knowledge discovery
    Camps-Valls, G
    Gómez-Chova, L
    Calpe-Maravilla, J
    Martín-Guerrero, JD
    Soria-Olivas, E
    Alonso-Chordá, L
    Moreno, J
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2004, 42 (07): : 1530 - 1542
  • [10] Xception: Deep Learning with Depthwise Separable Convolutions
    Chollet, Francois
    [J]. 30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, : 1800 - 1807