Tree crown delineation and tree species classification in boreal forests using hyperspectral and ALS data

By Michele Dalponte, Hans Ole Ørka, Liviu Theodor Ene, Terje Gobakken, Erik Næsset. 2014

276 citations recorded by the source corpus.

Subfields: Ecology, Environmental Engineering, Nature and Landscape Conservation

View Paper: https://www.semanticscholar.org/paper/ae15020d77c01f517cd718a1b8a4a6599f18fc0b

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Ecology

In Environmental Engineering

In Nature and Landscape Conservation

Citations in the corpus

Urban tree species mapping using hyperspectral and lidar data fusion (2014, methodology): “It is necessary to train an object-level classification model using manually delineated crowns in order to assure that the full segment area is composed of one and only one known species (Dalponte et al., 2014).”
Trends in Automatic Individual Tree Crown Detection and Delineation - Evolution of LiDAR Data (2016, methodology): “, spatial g ometry nd spec al) information, the fusi of active and passive im gery was often ppli d for species- ific forest inven ory using ITCD results [114,115].”
Quantifying Boreal Forest Structure and Composition Using UAV Structure from Motion (2018, background): “Further, it is possible that tree heights, particularly under conditions of high canopy closure, could be measured more accurately with a dense point cloud compared to standard field measurements [31,32].”
Individual Tree Detection and Classification with UAV-Based Photogrammetric Point Clouds and Hyperspectral Imaging (2017, methodology): “[69] have used high resolution airborne hyperspectral imagery to classify individual trees with 93.”
Remote sensing and machine learning for tree detection and classification in forestry applications (2019, methodology): “For instance, Support Vectors Machine (SVM) algorithm was applied on hyperspectral imagery with 160 bands (410-990 nm) to classify 3 groups of trees (Spruces, Pines, and Deciduous trees) in Norway and the accuracy of 92% was achieved.(10) 89% classification accuracy was obtained when classifying 13 ”
Forest Structure Estimation from a UAV-Based Photogrammetric Point Cloud in Managed Temperate Coniferous Forests (2017, methodology): “Then, the three band values of each grid were normalized radiometrically by dividing each band value in the grid by the sum of the values of all bands in the corresponding grid, as described in previous studies [17,33,34].”