Robust forest classification using hyperspectral imaging, laser scanning and satellite imagery

Vasilii Mosin, Roberto Aguilar, Alexander Platonov, Albert Vasiliev, Alexander Kedrov, Anton Ivanov

    Research output: Contribution to journalConference articlepeer-review

    Abstract

    Wood products are an important export for Russia. Understanding the status of trees and their classification is an ongoing task for many organizations. Currently, documentation of forests is done manually and there is a number of initiatives to implement automatic forest classification. A particular case described in the present paper showcases how aerial survey data supplements satellite imagery in order to achieve higher classification accuracy of forest tree species. Moreover, applicability of different data types, such as LiDAR and hyperspectral (NIR and VIS) for the task at hand is investigated. In the paper, we present the experiment to use hyperspectral forest classification (using a UAV), which is then used in the context of satellite imagery, airborne laser scanning, and manual identification. We actively employ machine learning algorithms for classification and recognition tasks. The project began with an expedition to the northern region of Arkhangelsk (Russia) in August 2018. The main goals of the expedition were data acquisition with the help of UAVs, as well as observing various weather conditions and their effect on the data collected. Validation of the results was performed in four separate polygons, where in-situ data was collected by manually recording tree locations and species. In this project we evaluated the precision of trees identification from UAV hyperspectral data, helped by ALS and high-resolution satellite imagery (50 cm). Supervised machine learning algorithms, namely Support Vector Machine (SVM) and Random Forest (RF), were applied and evaluated for automatic tree species classification task. An object-based classification has been performed by delineating individual tree crowns beforehand with the help of LiDAR data. Various spectral features have been identified for use in classification algorithms complemented by on-ground spectroscopic benchmark data. In this paper, we prove applicability of the proposed method and workflow in forestry operations. Results validation was done using data from the observation parcels, where trees were manually labeled. We aim at classification accuracy of 95% that will allow for change proposal for current forestry policy and legislature to enable the use of UAVs and satellites in forestry for classification purposes.

    Original languageEnglish
    Article numberIAC-19_B5_2_10_x51019
    JournalProceedings of the International Astronautical Congress, IAC
    Volume2019-October
    Publication statusPublished - 2019
    Event70th International Astronautical Congress, IAC 2019 - Washington, United States
    Duration: 21 Oct 201925 Oct 2019

    Keywords

    • Forest inventory
    • Hyperspectral imagery
    • LiDAR data
    • Machine learning
    • Tree detection
    • Tree species

    Fingerprint

    Dive into the research topics of 'Robust forest classification using hyperspectral imaging, laser scanning and satellite imagery'. Together they form a unique fingerprint.

    Cite this