Current issue: 58(4)

Scopus CiteScore 2023: 3.5
Scopus ranking of open access forestry journals: 17th
PlanS compliant
Select issue
Silva Fennica 1926-1997
1990-1997
1980-1989
1970-1979
1960-1969
Acta Forestalia Fennica
1953-1968
1933-1952
1913-1932

Articles containing the keyword 'tree detection'

Category : Climate resilient and sustainable forest management – Research article

article id 23042, category Climate resilient and sustainable forest management – Research article
Johanna Jääskeläinen, Lauri Korhonen, Mikko Kukkonen, Petteri Packalen, Matti Maltamo. (2024). Individual tree inventory based on uncrewed aerial vehicle data: how to utilise stand-wise field measurements of diameter for calibration? Silva Fennica vol. 58 no. 3 article id 23042. https://doi.org/10.14214/sf.23042
Keywords: laser scanning; calibration; mixed-effects model; single-tree detection
Highlights: A practical scheme to improve the accuracy of predicted tree and stand attributes in an uncrewed aerial vehicle based individual tree inventory; Accuracy was considerably improved with data from 2–4 sample trees from the target stand; Calibrated existing models and the construction of local models performed equally well; The laborious task of constructing a local model can be avoided by using a calibrated transferred model.
Abstract | Full text in HTML | Full text in PDF | Author Info
Uncrewed aerial vehicles (UAV) have great potential for use in forest inventories, but in practice they can be expensive for relatively small inventory areas as a large number of field measurements are needed for model construction. One proposed solution is to transfer previously constructed models to a new inventory area and to calibrate these with a small number of local field measurements. Our objective was to compare calibration of general models and the construction of new models to determine the best approach for UAV-based forest inventories. Our material included field measurements and UAV-based laser scanning data, from which individual trees were automatically identified. A general mixed-effects model for diameter at breast height (DBH) had been formulated earlier based on data from a geographically wider area. It was calibrated to the study area with field measurements from 2–10 randomly selected calibration trees. The calibrated diameters were used to calculate the diameter of a basal area median tree (DGM), tree volumes, and the volume of all trees at plot-level. Next, new DBH-models were formulated based on the 2–10 randomly selected trees and calibrated with plot-level random effects estimated during model construction. Finally, plot-specific height-diameter regression models were formulated by randomly selecting 10 trees from each plot. Calibration reduced the prediction errors of all variables. An increase in the number of calibration trees decreased error rates by 1–6% depending on the variable. Calibrated predictions from the general mixed-effects model were similar to the separately formulated mixed-effects models and plot-specific regression models.

Category : Research article

article id 22007, category Research article
Ilkka Korpela, Antti Polvivaara, Saija Papunen, Laura Jaakkola, Noora Tienaho, Johannes Uotila, Tuomas Puputti, Aleksi Flyktman. (2023). Airborne dual-wavelength waveform LiDAR improves species classification accuracy of boreal broadleaved and coniferous trees. Silva Fennica vol. 56 no. 4 article id 22007. https://doi.org/10.14214/sf.22007
Keywords: crown modeling; laser scanning; photogrammetry; individual tree detection; Scandinavia
Highlights: First study to assess dual-wavelength waveform data in tree species identification; New findings regarding waveform features of previously unstudied species; Waveform features correlated with tree size displaying wavelength- and species-specific differences linked to bark reflectance, height growth rate and foliage density; Effects by pulse length and beam divergence are highlighted.
Abstract | Full text in HTML | Full text in PDF | Author Info
Tree species identification constitutes a bottleneck in remote sensing applications. Waveform LiDAR has been shown to offer potential over discrete-return observations, and we assessed if the combination of two-wavelength waveform data can lead to further improvements. A total of 2532 trees representing seven living and dead conifer and deciduous species classes found in Hyytiälä forests in southern Finland were included in the experiments. LiDAR data was acquired by two single-wavelength sensors. The 1064-nm and 1550-nm data were radiometrically corrected to enable range-normalization using the radar equation. Pulses were traced through the canopy, and by applying 3D crown models, the return waveforms were assigned to individual trees. Crown models and a terrain model enabled a further split of the waveforms to strata representing the crown, understory and ground segments. Different geometric and radiometric waveform attributes were extracted per return pulse and aggregated to tree-level mean and standard deviation features. We analyzed the effect of tree size on the features, the correlation between features and the between-species differences of the waveform features. Feature importance for species classification was derived using F-test and the Random Forest algorithm. Classification tests showed significant improvement in overall accuracy (74→83% with 7 classes, 88→91% with 4 classes) when the 1064-nm and 1550-nm features were merged. Most features were not invariant to tree size, and the dependencies differed between species and LiDAR wavelength. The differences were likely driven by factors such as bark reflectance, height growth induced structural changes near the treetop as well as foliage density in old trees.
  • Korpela, University of Helsinki, Department of Forest Sciences, P.O. Box 27, FI-00014 University of Helsinki, Finland ORCID 0000-0002-1665-3984 E-mail: ilkka.korpela@helsinki.fi (email)
  • Polvivaara, University of Helsinki, Department of Forest Sciences, P.O. Box 27, FI-00014 University of Helsinki, Finland E-mail:
  • Papunen, University of Helsinki, Department of Forest Sciences, P.O. Box 27, FI-00014 University of Helsinki, Finland ORCID 0000-0001-5383-4314 E-mail: saija.papunen@outlook.com
  • Jaakkola, University of Helsinki, Department of Forest Sciences, P.O. Box 27, FI-00014 University of Helsinki, Finland E-mail: laura.jaakkola@helsinki.fi
  • Tienaho, University of Eastern Finland, Faculty of Science and Forestry, P.O. Box 111, FI-80101 Joensuu, Finland ORCID 0000-0002-6574-5797 E-mail: noora.tienaho@uef.fi
  • Uotila, University of Helsinki, Department of Forest Sciences, P.O. Box 27, FI-00014 University of Helsinki, Finland E-mail: johannes.uotila@helsinki.fi
  • Puputti, University of Helsinki, Department of Forest Sciences, P.O. Box 27, FI-00014 University of Helsinki, Finland ORCID 0000-0003-1972-1636 E-mail: tuomas.puputti@helsinki.fi
  • Flyktman, University of Helsinki, Department of Forest Sciences, P.O. Box 27, FI-00014 University of Helsinki, Finland ORCID 0000-0002-5235-317X E-mail: aleksi.flyktman@helsinki.fi
article id 10179, category Research article
Lauri Korhonen, Jaakko Repola, Tomi Karjalainen, Petteri Packalen, Matti Maltamo. (2019). Transferability and calibration of airborne laser scanning based mixed-effects models to estimate the attributes of sawlog-sized Scots pines. Silva Fennica vol. 53 no. 3 article id 10179. https://doi.org/10.14214/sf.10179
Keywords: Pinus sylvestris; LIDAR; crown base height; hierarchical data; individual tree detection; sawlog quality
Highlights: Attributes of individual sawlog-sized pines estimated by transferring ALS-based models between sites; Mixed effects models were more accurate than k-NN imputation tested earlier; Calibration with a small number of field measured trees improved the accuracy.
Abstract | Full text in HTML | Full text in PDF | Author Info

Airborne laser scanning (ALS) data is nowadays often available for forest inventory purposes, but adequate field data for constructing new forest attribute models for each area may be lacking. Thus there is a need to study the transferability of existing ALS-based models among different inventory areas. The objective of our study was to apply ALS-based mixed models to estimate the diameter, height and crown base height of individual sawlog sized Scots pines (Pinus sylvestris L.) at three different inventory sites in eastern Finland. Different ALS sensors and acquisition parameters were used at each site. Multivariate mixed-effects models were fitted at one site and the models were validated at two independent test sites. Validation was carried out by applying the fixed parts of the mixed models as such, and by calibrating them using 1–3 sample trees per plot. The results showed that the relative RMSEs of the predictions were 1.2–6.5 percent points larger at the test sites compared to the training site. Systematic errors of 2.4–6.2 percent points also emerged at the test sites. However, both the RMSEs and the systematic errors decreased with calibration. The results showed that mixed-effects models of individual tree attributes can be successfully transferred and calibrated to other ALS inventory areas in a level of accuracy that appears suitable for practical applications.

  • Korhonen, University of Eastern Finland, School of Forest Sciences, P.O. Box 111, FI-80101 Joensuu, Finland ORCID http://orcid.org/0000-0002-9352-0114 E-mail: lauri.korhonen@uef.fi (email)
  • Repola, Natural Resources Institute of Finland (Luke), Natural resources, Eteläranta 55, FI-96300 Rovaniemi, Finland E-mail: jaakko.repola@luke.fi
  • Karjalainen, University of Eastern Finland, School of Forest Sciences, P.O. Box 111, FI-80101 Joensuu, Finland E-mail: tomikar@uef.fi
  • Packalen, University of Eastern Finland, School of Forest Sciences, P.O. Box 111, FI-80101 Joensuu, Finland E-mail: petteri.packalen@uef.fi
  • Maltamo, University of Eastern Finland, School of Forest Sciences, P.O. Box 111, FI-80101 Joensuu, Finland E-mail: matti.maltamo@uef.fi
article id 56, category Research article
Johan Holmgren, Andreas Barth, Henrik Larsson, Håkan Olsson. (2012). Prediction of stem attributes by combining airborne laser scanning and measurements from harvesters. Silva Fennica vol. 46 no. 2 article id 56. https://doi.org/10.14214/sf.56
Keywords: ALS data; pre-harvest inventory; tree detection
Abstract | View details | Full text in PDF | Author Info
In this study, a new method was validated for the first time that predicts stem attributes for a forest area without any manual measurements of tree stems by combining harvester measurements and Airborne Laser Scanning (ALS) data. A new algorithm for automatic segmentation of tree crowns from ALS data based on tree crown models was developed. The test site was located in boreal forest (64°06’N, 19°10’E) dominated by Norway spruce (Picea abies) and Scots Pine (Pinus sylvestris).The trees were harvested on field plots, and each harvested tree was linked to the nearest tree crown segment derived from ALS data. In this way, a reference database was created with both stem data from the harvester and ALS derived features for linked tree crowns. To estimate stem attributes for a tree crown segment in parts of the forest where trees not yet have been harvested, tree stems are imputed from the most similar crown segment in the reference database according to features extracted from ALS data. The imputation of harvester data was validated on a sub-stand-level, i.e. 2–4 aggregated 10 m radius plots, and the obtained RMSE of stem volume, mean tree height, mean stem diameter, and stem density (stems per ha) estimates were 11%, 8%, 12%, and 19%, respectively. The imputation of stem data collected by harvesters could in the future be used for bucking simulations of not yet harvested forest stands in order to predict wood assortments.
  • Holmgren, Swedish University of Agricultural Sciences, Forest Resource Management, Umeå, Sweden E-mail: johan.holmgren@slu.se (email)
  • Barth, The Forestry Research Institute of Sweden, Uppsala, Sweden E-mail: ab@nn.se
  • Larsson, Swedish University of Agricultural Sciences, Forest Resource Management, Umeå, Sweden E-mail: hl@nn.se
  • Olsson, Swedish University of Agricultural Sciences, Forest Resource Management, Umeå, Sweden E-mail: ho@nn.se

Register
Click this link to register to Silva Fennica.
Log in
If you are a registered user, log in to save your selected articles for later access.
Contents alert
Sign up to receive alerts of new content
Your selected articles