Automatic detection of root rot and resin in felled Scots pine stems using convolutional neural networks

References

• Abadi M, Agarwal A, Barham P, Brevdo E, Chen Z, Citro C, Corrado GS, Davis A, Dean J, Devin M, et al. 2016. TensorFlow: large-scale machine learning on heterogeneous distributed systems. arXivorg. https://arxiv.org/abs/1603.04467.
   Google Scholar
• Abdulridha J, Ehsani R, de Castro A. 2016. Detection and differentiation between Laurel Wilt disease, phytophthora disease, and salinity damage using a hyperspectral sensing technique. Agriculture. 6(4):56. doi: 10.3390/agriculture6040056.
   Google Scholar
• Alpaydin E. 2016. Introduction to machine learning. Cambridge, MA, USA: MIT Press.
   Google Scholar
• Burdekin DA. 1972. A study of losses in scots pine caused by fomes annosus. Forestry. 45(2):189–196. doi: 10.1093/forestry/45.2.189.
   Web of Science ®Google Scholar
• Chollet F. 2015. Keras. https://keras.io.
   Google Scholar
• Chollet F 2017. Xception: deep learning with depthwise separable convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; Honolulu, USA. p. 1251–1258.
   Google Scholar
• Fabijańska A, Danek M. 2018. DeepDendro – a tree rings detector based on a deep convolutional neural network. Comp Electr Agr. 150:353–363. doi: 10.1016/j.compag.2018.05.005.
   Web of Science ®Google Scholar
• Garbelotto M, Gonthier P. 2013. Biology, epidemiology, and control of heterobasidion species worldwide. Ann Rev Phyt. 51(1):39–59. doi: 10.1146/annurev-phyto-082712-102225.
   PubMedGoogle Scholar
• Goodfellow I, Bengio Y, Courville A. 2016. Deep learning. Cambridge: MIT Press. https://www.deeplearningbook.org/.
   Google Scholar
• Greig BJW. 1995. Butt-rot of scots pine in Thetford Forest caused by heterobasidion annosum: a local phenomenon. For Path. 25(2):95–99. doi: 10.1111/j.1439-0329.1995.tb00323.x.
   Web of Science ®Google Scholar
• He K, Zhang X, Ren S, Sun J. 2016. Identity mappings in deep residual networks. Computer Vision - ECCV; Amsterdam, The Netherlands. p. 630–645.
   Google Scholar
• Holmström E, Raatevaara A, Pohjankukka J, Korpunen H, Uusitalo J. 2023. Tree log identification using convolutional neural networks. Smart Agric Technol. 4:100201. doi: 10.1016/j.atech.2023.100201.
   Google Scholar
• Huang G, Liu Z, van der Maaten L, Weinberger KQ. 2017. Densely connected convolutional networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; Honolulu, USA. p. 4700–4708.
   Google Scholar
• Kingma DP, Ba J. 2014. Adam: a method for stochastic optimization. arXivorg. https://arxiv.org/abs/1412.6980.
   Google Scholar
• Laine L. 1976. The occurrence of Heterobasidion annosum (Fr.) Bref. In woody plants in Finland. Metsant Julk. 90(3).
   Google Scholar
• Liaghat S, Ehsani R, Mansor S, Shafri HZM, Meon S, Sankaran S, Azam SHMN. 2014. Early detection of basal stem rot disease (Ganoderma) in oil palms based on hyperspectral reflectance data using pattern recognition algorithms. Int J Rem Sens. 35(10):3427–3439. doi: 10.1080/01431161.2014.903353.
   Web of Science ®Google Scholar
• Müller MM, Sievänen R, Beuker E, Meesenburg H, Kuuskeri J, Hamberg L, Korhonen K, Sturrock RN. 2014. Predicting the activity of Heterobasidion parviporum on Norway spruce in warming climate from its respiration rate at different temperatures. For Path. 44(4):325–336. doi: 10.1111/efp.12104.
   Web of Science ®Google Scholar
• Mäkinen H, Korpunen H, Raatevaara A, Heikkinen J, Alatalo J, Uusitalo J. 2019. Predicting knottiness of Scots pine stems for quality bucking. Eur J W W Prod. 78(1):143–150. doi: 10.1007/s00107-019-01476-x.
   Web of Science ®Google Scholar
• Nowell TC. 2019. Detection and quantification of rot in harvested trees using convolutional neural networks. Norway: Norwegian University of Life Sciences, Ås.
   Google Scholar
• Ojala T, Pietikainen M, Maenpaa T. 2002. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans Pat An Mach Intel. 24(7):971–987. doi: 10.1109/TPAMI.2002.1017623.
   Web of Science ®Google Scholar
• Ostovar A, Talbot B, Puliti S, Astrup R, Ringdahl O. 2019. Detection and classification of root and butt-rot (RBR) in stumps of Norway spruce using RGB images and machine learning. Sensors. 19(7):1579. doi: 10.3390/s19071579.
   PubMed Web of Science ®Google Scholar
• Pitkänen TP, Piri T, Lehtonen A, Peltoniemi M. 2021. Detecting structural changes induced by heterobasidion root rot on scots pines using terrestrial laser scanning. For Ecol Manag. 492:119239. doi: 10.1016/j.foreco.2021.119239.
   Web of Science ®Google Scholar
• Puliti S, Talbot B, Astrup R. 2018. Tree-stump detection, segmentation, classification, and measurement using unmanned aerial vehicle (UAV) imagery. Forests. 9(3):102. doi: 10.3390/f9030102.
   Web of Science ®Google Scholar
• Robert M, Dallaire P, Giguère P. 2020. Tree bark re-identification using a deep-learning feature descriptor. 17th Conference on Computer and Robot Vision (CRV); Ottawa, Canada.
   Google Scholar
• Ruotsalainen S. 2014. Increased forest production through forest tree breeding. Scand J For Res. 29(4):333–344. doi: 10.1080/02827581.2014.926100.
   Google Scholar
• Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M, et al. 2015. ImageNet Large Scale Visual Recognition Challenge. Int J Comp V. 115(3):211–252. doi:10.1007/s11263-015-0816-y.
   Web of Science ®Google Scholar
• Sandler M, Howard A, Zhu M, Zhmoginov A, Chen L-C. 2018. MobileNetV2: Inverted Residuals and Linear Bottlenecks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; Salt Lake City, USA. p. 4510–4520.
   Google Scholar
• Seidl R, Thom D, Kautz M, Martin-Benito D, Peltoniemi M, Vacchiano G, Wild J, Ascoli D, Petr M, Honkaniemi J, et al. 2017. Forest disturbances under climate change. Nat Clim Chan. 7(6):395–402. doi:10.1038/nclimate3303.
   PubMed Web of Science ®Google Scholar
• Simonyan K, Zisserman A. 2014. Very deep convolutional networks for large-scale image recognition. arXivorg. https://arxiv.org/abs/1409.1556.
   Google Scholar
• Syrjälä E, Jiang M, Pahikkala T, Salanterä S, Liljeberg P. 2019. Skin Conductance Response to Gradual-Increasing Experimental Pain. 41st Annual International Conference; Berlin.
   Google Scholar
• Tan M, Le Q. 2019. EfficientNet: rethinking model scaling for convolutional neural networks. PMLR. 97:6105–6114.
   Google Scholar
• van der Walt S, Schönberger JL, Nunez-Iglesias J, Boulogne F, Warner JD, Yager N, Gouillart E, Yu T. 2014. Scikit-image: image processing in python. PeerJ. 2:e453. doi: 10.7717/peerj.453.
   PubMed Web of Science ®Google Scholar
• Vihlman M, Kulovesi J, Visala A. 2019. Tree log identity matching using convolutional correlation networks. International Conference on Digital Image Computing: Techniques and Applications; Perth, Australia.
   Google Scholar
• Wang L, Zhang J, Drobyshev I, Cleary M, Rönnberg J. 2014. Incidence and impact of root infection by Heterobasidion spp., and the justification for preventative silvicultural measures on scots pine trees: a case study in southern Sweden. For Ecol And Manag. 315:153–159. doi: 10.1016/j.foreco.2013.12.023.
   Google Scholar
• Yosinski J, Clune J, Bengio Y, Lipson H. 2014. How transferable are features in deep neural networks?. Advances in Neural Information Processing Systems; Montréal, Canada.
   Google Scholar
• Zoph B, Vasudevan V, Shlens J, Le QV. 2018. Learning transferable architectures for scalable image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; Salt Lake City, USA. p. 8697–8710.
   Google Scholar