Abstract
Exploration of the effectiveness of multi-type features and multi-seasonal data of remote sensing images and selection of an optimal feature set from all extracted features are popular research topics in tree species classification. Eight typical image feature sets, namely, spectral band, digital surface model (DSM), texture (TEX), tassel cap transformation (TC), hue, saturation and value colour space (HSV), principal component analysis, minimum noise fraction (MNF) and spectral index (SI), were extracted in this study from images of four seasons acquired using the RedEdge-MX sensor, and maximum likelihood and random forest classifiers were used to categorise 32 typical urban tree species. Experimental results revealed the following: (1) the tree species recognition accuracy determined using the texture set (87.89%) was higher than that determined using other types of feature sets; (2) the optimal feature set containing 20 features comprised 4 DSMs, 11 TEXs, 2 TCs, 1 HSV (S), 1 SI and 1 MNF, and the classification accuracy determined using the set of features was 89.53% and (3) the classification accuracy for tree species identification determined using multi-seasonal spectral data was higher than that determined using individual seasonal data. The major contribution of this study to relevant literature is that it proves that urban greening tree species can be accurately identified using multiple features and seasonal images acquired through UAV-based sensors. The multi-feature-based approach also performs substantially well in practical applications for mapping tree species in a general urban environment considering the effects of a heterogeneous environment on tree species classification and comprehensive image processing and classification methods.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Agarwal A, Kumar S, Singh D (2021) An adaptive technique to detect and remove shadow from drone data. J Indian Soc Remote Sens 49:491–498. https://doi.org/10.1007/s12524-020-01227-z
Åkerblom M, Raumonen P, Mäkipää R, Kaasalainen M (2017) Automatic tree species recognition with quantitative structure models. Remote Sens Environ 191:1–12. https://doi.org/10.1016/j.rse.2016.12.002
Apostol B, Petrila M, Lorenţ A, Ciceu A, Gancz V, Badea O (2020) Species discrimination and individual tree detection for predicting main dendrometric characteristics in mixed temperate forests by use of airborne laser scanning and ultra-high-resolution imagery. Sci Total Environ 698:134074. https://doi.org/10.1016/j.scitotenv.2019.134074
Ben LN (2018) Study on plant species and landscape evaluation of park green space in Luoyang (in Chinese). Master’s Thesis, Henan University of science and technology, Luoyang, China
Chew WC, Lau AMS, Kanniah KD (2016) Multi-level adaptive support vector machine classification for tropical tree species. Int J geoinformatics 22:17–25
Cotrozzi L (2022) Spectroscopic detection of forest diseases: a review (1970–2020). J For Res 33:21–38. https://doi.org/10.1007/s11676-021-01378-w
Cross MD, Scambos T, Pacifici F, Marshall WE (2019) Determining effective meter-scale image data and spectral vegetation indices for tropical forest tree species differentiation. IEEE J Sel Top Appl Earth Obs Remote Sens 12:2934–2943. https://doi.org/10.1109/JSTARS.2019.2918487
Dymond CC, Mladenof DJ, Radelof V (2002) Phenological differences in tasseled cap indices improve deciduous forest classification. Remote Sens Environ 80:460–472. https://doi.org/10.1016/S0034-4257(01)00324-8
Ferreira MP, Wagner FH, Aragão LEOC, Shimabukuro YE, Filho CRDS (2019) Tree species classification in tropical forests using visible to shortwave infrared WorldView-3 images and texture analysis. ISPRS J Photogramm Remote Sens 149:119–131. https://doi.org/10.1016/j.isprsjprs.2019.01.019
Ghosh A, Joshi PK (2014) A comparison of selected classification algorithms for mapping bamboo patches in lower Gangetic plains using very high resolution WorldView-2 imagery. Int J Appl Earth Obs Geoinf 26:298–311. https://doi.org/10.1016/j.jag.2013.08.011
Gong P, Pu RL, Yu B (1998) Conifer species recognition with seasonal hyperspectral data (in chinese). J Remote Sens 2:211–217
Hamraz H, Jacobs NB, Contreras MA, Clark C (2019) Deep learning for conifer/deciduous classification of airborne LiDAR 3D point clouds representing individual trees. ISPRS J Photogramm Remote Sens 158:219–230. https://doi.org/10.1016/j.isprsjprs.2019.10.011
Han W, Zhang S, Jiao Q, Wu H (2019) Dominant tree species mapping based on multi-temporal CHRIS hyperspectral satellite data (in chinese). For Inventory Plann 44:1–6
Hughes G (1968) On the mean accuracy of statistical pattern recognizers. Inf Theory IEEE Trans 14:55–63. https://doi.org/10.1109/TIT.1968.1054102
Immitzer M, Atzberger C, Koukal T (2012) Tree species classification with random forest using very high spatial resolution 8-band WorldView-2 satellite data. Remote Sens 4:2661–2693. https://doi.org/10.3390/rs4092661
Immitzer M, Neuwirth M, Böck S, Brenner H, Vuolo F, Atzberger C (2019) Optimal input features for tree species classification in central europe based on multi-temporal Sentinel-2 data. Remote Sens 11:2599. https://doi.org/10.3390/rs11222599
Kamal M, Phinn S, Johansen K (2015) Object-based approach for multi-scale mangrove composition mapping using multi-resolution image datasets. Remote Sens 7:4753–4783. https://doi.org/10.3390/rs70404753
Karlson M, Ostwald M, Reese H (2015) Mapping tree canopy cover and aboveground biomass in Sudano-Sahelian woodlands using landsat 8 and Random Forest. Remote Sens 7:10017–10041. https://doi.org/10.3390/rs70810017
Karlson M, Ostwald M, Reese H, Bazié HR, Tankoano B (2016) Assessing the potential of multi-seasonal WorldView-2 imagery for mapping west african agroforestry tree species. Int J Appl Earth Obs Geoinf 50:80–88. https://doi.org/10.1016/j.jag.2016.03.004
Kemal A, Serhat K, Onur C (2019) Classification and diagnosis of cervical cancer with stacked autoencoder and softmax classification. Expert Syst Appl 115:557–564. https://doi.org/10.1016/j.eswa.2018.08.050
Kureel N, Sarup J, Matin S, Goswami S, Kureel K (2022) Modelling vegetation health and stress using hypersepctral remote sensing data. Model Earth Syst Environ 8:733–748. https://doi.org/10.1007/s40808-021-01113-8
Li D, Ke Y, Gong H, Li X (2015) Object-based urban tree species classification using bi-temporal WorldView-2 and WorldView-3 images. Remote Sens 7:16917–16937. https://doi.org/10.3390/rs71215861
Lin C, Popescu SC, Thomson G, Tsogt K, Chang CI (2015) Classification of tree species in overstorey canopy of subtropical forest using QuickBird images. PLoS ONE 10:e0125554. https://doi.org/10.1371/journal.pone.0125554
Liu H (2016) Classification of urban typical greening tree species based on WorldView-2 data (in Chinese). Ph.D Thesis, Inner Mongolia Agricultural University, Hohhot, China
Liu H, An H (2019) Urban greening tree species classification based on HSV colour space of WorldView-2. J Indian Soc Remote Sens 47:1959–1967. https://doi.org/10.1007/s12524-019-01028-z
Liu HP, An HJ, Wang B, Zhang QL (2015) Tree species classification using WorldView-2 images based on recursive texture feature elimination (in chinese). J Beijing For Univ 37:53–59
Masemola C, Cho MA, Ramoelo A (2019) Assessing the effect of seasonality on leaf and canopy spectra for the discrimination of an alien tree species, acacia mearnsii, from co-occurring native species using parametric and nonparametric classifiers. IEEE Trans Geosci Remote Sens 57:5853–5867. https://doi.org/10.1109/TGRS.2019.2902774
Masemola C, Cho MA, Ramoelo A (2020) Sentinel-2 time series based optimal features and time window for mapping invasive australian native acacia species in kwazulu natal, south africa. Int J Appl Earth Obs Geoinf 93:102207. https://doi.org/10.1016/j.jag.2020.102207
Modzelewska A, Fassnacht FE, Stereńczak K (2020) Tree species identification within an extensive forest area with diverse management regimes using airborne hyperspectral data. Int J Appl Earth Obs Geoinf 84:101960. https://doi.org/10.1016/j.jag.2019.101960
Naidoo L, Cho MA, Mathieu R, Asner GP (2012) Classification of savanna tree species, in the Greater Kruger National Park region, by integrating hyperspectral and LiDAR data in a Random Forest data mining environment. ISPRS J Photogramm Remote Sens 69:167–179. https://doi.org/10.1016/j.isprsjprs.2012.03.005
Niu JN, Sun YM, Zhang YR, Ji YF (2019) Noise-suppressing channel allocation in dynamic DWDM-QKD networks using LightGBM. Opt Express 27:31741–31756. https://doi.org/10.1364/OE.27.031741
Olofsson P, Foody GM, Herold M, Stehman SV, Woodcock CE, Wulder MA (2014) Good practices for estimating area and assessing accuracy of land change. Remote Sens Environ 148:42–57
Pu R, Landry S (2012) A comparative analysis of high resolution IKONOS and WorldView-2 imagery for mapping urban tree species. Remote Sens Environ 124:516–533. https://doi.org/10.1016/j.rse.2012.06.011
Pu R, Landry S (2020) Mapping urban tree species by integrating multi-seasonal high resolution Pléiades satellite imagery with airborne LiDAR data. Urban For Urban Gree 53:126675. https://doi.org/10.1016/j.ufug.2020.126675
Pu R, Shawn L, Yu Q (2018) Assessing the potential of multi-seasonal high resolution pléiades satellite imagery for mapping urban tree species. Int J Appl Earth Obs Geoinformation 71:144–158. https://doi.org/10.1016/j.jag.2018.05.005
Richards JA, Jia X (2008) Using suitable neighbors to augment the training set in hyperspectral maximum likelihood classification. IEEE Geosci Remote Sens Lett 5:774–777. https://doi.org/10.1109/LGRS.2008.2005512
Schönert M, Weichelt H, Zillmann E, Jürgens C (2014) Derivation of tasseled cap coefficients for RapidEye data. Earth Resources & Environmental Remote Sensing/gis Applications V. International Society for Optics and Photonics
Shi WW, Gong YH, Tao XY, Cheng D, Zheng NN (2019) Fine-grained image classification using modified DCNNs trained by cascaded softmax and generalized large-margin losses. IEEE Trans Neural Networks Learn Syst 30:683–694. https://doi.org/10.1109/TNNLS.2018.2852721
Shi YF, Wang TJ, Skidmore AK, Heurich M (2020) Improving LiDAR-based tree species mapping in central european mixed forests using multi-temporal digital aerial colour-infrared photographs. Int J Appl Earth Obs Geoinf 84:101970. https://doi.org/10.1016/j.jag.2019.101970
Sona G, Pinto L, Pagliari D, Passoni D, Gini R (2014) Experimental analysis of different software packages for orientation and digital surface modelling from uav images. Earth Sci Inf 7:97–107. https://doi.org/10.1007/s12145-013-0142-2
Tooke TR, Coops NC, Goodwin NR, Voogt JA (2009) Extracting urban vegetation characteristics using spectral mixture analysis and decision tree classifications. Remote Sens Environ 113:398–407. https://doi.org/10.1016/j.rse.2008.10.005
Torabzadeh H, Leiterer R, Hueni A, Schaepman M, Morsdorf F (2019) Tree species classification in a temperate mixed forest using a combination of imaging spectroscopy and airborne laser scanning. Agric For Meteorol 279:107744. https://doi.org/10.1016/J.AGRFORMET.2019.107744
Van der Linden S, Rabe A, Held M, Jakimow B, Leitão PJ, Okujeni A, Schwieder M, Suess S, Hostert P (2015) The EnMAP-Box- A toolbox and application programming interface for EnMAP data processing. Remote Sens 7:11249–11266. https://doi.org/10.3390/rs70911249
Wang T, Zhang H, Lin H, Fang C (2016) Textural-spectral feature-based species classification of mangroves in Mai Po Nature Reserve from Worldview-3 imagery. Remote Sens 8:24. https://doi.org/10.3390/rs8010024
Wang X, Wang Y, Zhou C, Yin L, Feng X (2020) Urban forest monitoring based on multiple features at the single tree scale by uav. Urban For Urban Gree 58:126958. https://doi.org/10.1016/j.ufug.2020.126958
Yan S, Jing L, Wang H (2021) A new individual tree species recognition method based on a convolutional neural network and high-spatial resolution remote sensing imagery. Remote Sens 13:479. https://doi.org/10.3390/rs13030479
Yu X, Hyyppä J, Litkey P, Kaartinen H, Vastaranta M, Holopainen M (2017) Single-sensor solution to tree species classification using multispectral airborne laser scanning. Remote Sens 9:108. https://doi.org/10.3390/rs9020108
Zhang Z, Kazakova A, Moskal LM, Styers DM (2016) Object-based tree species classification in urban ecosystems using LiDAR and hyperspectral data. Forests 7:122. https://doi.org/10.3390/f7060122
Zhang HB, Qiu DD, Wu RZ, Deng YX, Ji DH, Li T (2019) Novel framework for image attribute annotation with gene selection XGBoost algorithm and relative attribute model. Appl Soft Comput 80:57–79. https://doi.org/10.1016/j.asoc.2019.03.017
Zhang B, Zhao L, Zhang X (2020) Three-dimensional convolutional neural network model for tree species classification using airborne hyperspectral images. Remote Sens Environ 247:111938. https://doi.org/10.1016/j.rse.2020.111938
Zhong LH, Hu LN, Zhou H (2019) Deep learning based multi-temporal crop classification. Remote Sens Environ 221:430–443. https://doi.org/10.1016/j.rse.2018.11.032
Zhou JH, Zhou YF, Mu WS (2011) Mathematic descriptor for identifying plant species: a case study on urban landscape vegetation (in chinese). J Remote Sens 15:524–538
Acknowledgements
This work was supported by the Natural Science Foundation of Henan Province, China (Grant No. 202300410293) and the National Nature Science Foundation of China (Grant No. 32001250). I want to thank Engineer Zhenlin Xu from China Southern Surveying and Mapping Technology Co., Ltd for his assistance in image acquisition. I also want to thank Professor Ruiliang Pu from the University of South Florida for his help in improving the manuscript and correcting the grammatical errors. I also wish to express my gratitude to the editors and anonymous reviewers.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Disclosure statement
No potential conflict of interest was reported by the authors.
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Liu, H. Classification of tree species using UAV-based multi-spectral and multi-seasonal images: a multi-feature-based approach. New Forests 55, 173–196 (2024). https://doi.org/10.1007/s11056-023-09974-w
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11056-023-09974-w