Detection of Fir Trees (Abies sibirica) Damaged by the Bark Beetle in Unmanned Aerial Vehicle Images with Deep Learning

Invasion of the Polygraphus proximus Blandford bark beetle causes catastrophic damage to forests with firs (Abies sibirica Ledeb) in Russia, especially in Central Siberia. Determining tree damage stage based on the shape, texture and colour of tree crown in unmanned aerial vehicle (UAV) images could help to assess forest health in a faster and cheaper way. However, this task is challenging since (i) fir trees at different damage stages coexist and overlap in the canopy, (ii) the distribution of fir trees in nature is irregular and hence distinguishing between different crowns is hard, even for the human eye. Motivated by the latest advances in computer vision and machine learning, this work proposes a two-stage solution: In a first stage, we built a detection strategy that finds the regions of the input UAV image that are more likely to contain a crown, in the second stage, we developed a new convolutional neural network (CNN) architecture that predicts the fir tree damage stage in each candidate region. Our experiments show that the proposed approach shows satisfactory results on UAV Red, Green, Blue (RGB) images of forest areas in the state nature reserve “Stolby” (Krasnoyarsk, Russia).

[1]  Lars T. Waser,et al.  Evaluating the Potential of WorldView-2 Data to Classify Tree Species and Different Levels of Ash Mortality , 2014, Remote. Sens..

[2]  Nataliia Kussul,et al.  Deep Learning Classification of Land Cover and Crop Types Using Remote Sensing Data , 2017, IEEE Geoscience and Remote Sensing Letters.

[3]  Eija Honkavaara,et al.  Using UAV-Based Photogrammetry and Hyperspectral Imaging for Mapping Bark Beetle Damage at Tree-Level , 2015, Remote. Sens..

[4]  Siham Tabik,et al.  A snapshot of image pre-processing for convolutional neural networks: case study of MNIST , 2017, Int. J. Comput. Intell. Syst..

[5]  N. V. Pashenova,et al.  Ophiostomatoid Fungi Associated with the Four-Eyed Fir Bark Beetle on the Territory of Russia , 2018, Russian Journal of Biological Invasions.

[6]  Johannes Breidenbach,et al.  Early Detection of Bark Beetle Green Attack Using TerraSAR-X and RapidEye Data , 2013, Remote. Sens..

[7]  I. A. Kerchev,et al.  Ecology of four-eyed fir bark beetle Polygraphus proximus Blandford (Coleoptera; Curculionidae, Scolytinae) in the west Siberian region of invasion , 2014, Russian Journal of Biological Invasions.

[8]  Marco Heurich,et al.  European spruce bark beetle (Ips typographus, L.) green attack affects foliar reflectance and biochemical properties , 2018, Int. J. Appl. Earth Obs. Geoinformation.

[9]  Francisco Herrera,et al.  Deep-learning Versus OBIA for Scattered Shrub Detection with Google Earth Imagery: Ziziphus lotus as Case Study , 2017, Remote. Sens..

[10]  C. Silva,et al.  Individual tree detection from Unmanned Aerial Vehicle (UAV) derived canopy height model in an open canopy mixed conifer forest , 2017 .

[11]  J. Hicke,et al.  Evaluating methods to detect bark beetle-caused tree mortality using single-date and multi-date Landsat imagery , 2013 .

[12]  Hulya Yalcin,et al.  Using convolutional neural networks for plant classification , 2017, 2017 25th Signal Processing and Communications Applications Conference (SIU).

[13]  Yuri Baranchikov,et al.  Bark beetle Polygraphus proximus : a new aggressive far eastern invader on Abies species in Siberia and European Russia , 2011 .

[14]  Marco Heurich,et al.  Object-orientated image analysis for the semi-automatic detection of dead trees following a spruce bark beetle (Ips typographus) outbreak , 2010, European Journal of Forest Research.

[15]  Amy Loutfi,et al.  Classification and Segmentation of Satellite Orthoimagery Using Convolutional Neural Networks , 2016, Remote. Sens..

[16]  François Chollet,et al.  Xception: Deep Learning with Depthwise Separable Convolutions , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Hemerson Pistori,et al.  Weed detection in soybean crops using ConvNets , 2017, Comput. Electron. Agric..

[18]  Jonathan P. Dash,et al.  Assessing very high resolution UAV imagery for monitoring forest health during a simulated disease outbreak , 2017 .

[19]  Hurtado Abril,et al.  Generación de un índice espectro-temporal para la identificación de zonas afectadas por deforestación usando imágenes Landsat. , 2020 .

[20]  Henrik Skov Midtiby,et al.  Plant species classification using deep convolutional neural network , 2016 .

[21]  Weijia Li,et al.  Deep Learning Based Oil Palm Tree Detection and Counting for High-Resolution Remote Sensing Images , 2016, Remote. Sens..

[22]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[23]  C. Justice,et al.  High-Resolution Global Maps of 21st-Century Forest Cover Change , 2013, Science.

[24]  Masanori Onishi,et al.  Automatic classification of trees using a UAV onboard camera and deep learning , 2018, ArXiv.

[25]  O. Sonnentag,et al.  Regional atmospheric cooling and wetting effect of permafrost thaw‐induced boreal forest loss , 2016, Global change biology.

[26]  Torsten Prinz,et al.  Analysis of Unmanned Aerial System-Based CIR Images in Forestry—A New Perspective to Monitor Pest Infestation Levels , 2015 .

[27]  G. Bonan.  Forests and Climate Change: Forcings, Feedbacks, and the Climate Benefits of Forests , 2008, Science.

[28]  David Menotti,et al.  Learning Deep Features on Multiple Scales for Coffee Crop Recognition , 2017, 2017 30th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI).

[29]  E. Honkavaara,et al.  Remote sensing of bark beetle damage in urban forests at individual tree level using a novel hyperspectral camera from UAV and aircraft , 2018 .