Individual Tree Crown Segmentation and Classification of 13 Tree Species Using Airborne Hyperspectral Data

Maschler, Julia; Atzberger, Clement; Immitzer, Markus

doi:10.3390/rs10081218

Cited by 130 publications

(113 citation statements)

References 76 publications

Supporting

Mentioning

108

Contrasting

Unclassified

Order By: Relevance

“…We found that the use of vegetation indices improved the classification performance compared to the sole use of spectral signatures. Similar results were reported by Puletti et al [28] and Maschler et al [12]. The most relevant vegetation indices were based on the same bands, which show high importance in the models based only on spectral bands.…”

Section: Sentinel-2 Bands and Vegetation Indicessupporting

confidence: 90%

“…As a result, data with higher spatial, spectral and temporal resolutions are available. Analysis of hyperspectral data demonstrated the added value of the dense spectral sampling for the separation of tree species [10][11][12][13]. Multi-spectral, very high resolution (VHR) satellite data were successfully used for mapping tree species distribution for up to ten different species [14][15][16][17].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Optimal Input Features for Tree Species Classification in Central Europe Based on Multi-Temporal Sentinel-2 Data

et al. 2019

Self Cite

View full text Add to dashboard Cite

Detailed knowledge about tree species composition is of great importance for forest management. The two identical European Space Agency (ESA) Sentinel-2 (S2) satellites provide data with unprecedented spectral, spatial and temporal resolution. Here, we investigated the potential benefits of using high temporal resolution data for classification of five coniferous and seven broadleaved tree species in a diverse Central European Forest. To run the classification, 18 cloud-free S2 acquisitions were analyzed in a two-step approach. The available scenes were first used to stratify the study area into six broad land-cover classes. Subsequently, additional classification models were created separately for the coniferous and the broadleaved forest strata. To permit a deeper analytical insight in the benefits of multi-temporal datasets for species identification, classification models were developed taking into account all 262,143 possible permutations of the 18 S2 scenes. Each model was fine-tuned using a stepwise recursive feature reduction. The additional use of vegetation indices improved the model performances by around 5 percentage points. Individual mono-temporal tree species accuracies range from 48.1% (January 2017) to 78.6% (June 2017). Compared to the best mono-temporal results, the multi-temporal analysis approach improves the out-of-bag overall accuracy from 72.9% to 85.7% for the broadleaved and from 83.8% to 95.3% for the coniferous tree species, respectively. Remarkably, a combination of six–seven scenes achieves a model quality equally high as the model based on all data; images from April until August proved most important. The classes European Beech and European Larch attain the highest user’s accuracies of 96.3% and 95.9%, respectively. The most important spectral variables to distinguish between tree species are located in the Red (coniferous) and short wave infrared (SWIR) bands (broadleaved), respectively. Overall, the study highlights the high potential of multi-temporal S2 data for species-level classifications in Central European forests.

show abstract

Section: Sentinel-2 Bands and Vegetation Indicessupporting

confidence: 90%

Section: Introductionmentioning

confidence: 99%

Optimal Input Features for Tree Species Classification in Central Europe Based on Multi-Temporal Sentinel-2 Data

et al. 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…Hyperspectral features for tree species classification are relatively common (e.g. Maschler et al, 2018), but few papers have focused on integrating hyperspectral data into tree detection alongside other sensors. Hyperspectral data is available for all NEON sites, and we utilized a three-band composite image to assist in annotating the Eastern Deciduous site (Figure 9), illustrating the usefulness of hyperspectral data to distinguish adjacent tree crowns with human vision.…”

Section: Discussionmentioning

confidence: 99%

Geographic Generalization in Airborne RGB Deep Learning Tree Detection

Marconi

Bohlman

Zare

et al. 2019

Preprint

View full text Add to dashboard Cite

11Tree detection is a fundamental task in remote sensing for forestry and ecosystem 12 ecology applications. While many individual tree segmentation algorithms have been 13 proposed, the development and testing of these algorithms is typically site specific, with 14 few methods evaluated against data from multiple forest types simultaneously. This 15 makes it difficult to determine the generalization of proposed approaches, and limits tree 16 detection at broad scales. Using data from the National Ecological Observatory Network 17 we extend a recently developed semi-supervised deep learning algorithm to include 18 data from a range of forest types, determine whether information from one forest can be 19 used for tree detection in other forests, and explore the potential for building a universal 20 tree detection algorithm. We find that the deep learning approach works well for 21 Discovery Initiative through grant GBMF4563 to E.P. White and by the National Science 464 Foundation through grant 1926542 to E.P. White, S.

show abstract

“…Maschler et al [36] applied mean shift to airborne hyperspectral image twice: Firstly to differentiate short and tall stands, and secondly to segment individual tree crowns, to classify a temperate forest.…”

Section: Related Workmentioning

confidence: 99%

Mean Shift Segmentation Assessment for Individual Forest Tree Delineation from Airborne Lidar Data

et al. 2019

View full text Add to dashboard Cite

Airborne lidar has been widely used for forest characterization to facilitate forest ecological and management studies. With the availability of increasingly higher point density, individual tree delineation (ITD) from airborne lidar point clouds has become a popular yet challenging topic, due to the complexity and diversity of forests. One important step of ITD is segmentation, for which various methodologies have been studied. Among them, a long proven image segmentation method, mean shift, has been applied directly onto 3D points, and has shown promising results. However, there are variations among those who implemented the algorithm in terms of the kernel shape, adaptiveness and weighting. This paper provides a detailed assessment of the mean shift algorithm for the segmentation of airborne lidar data, and the effect of crown top detection upon the validation of segmentation results. The results from three different datasets revealed that a crown-shaped kernel consistently generates better results (up to 7 percent) than other variants, whereas weighting and adaptiveness do not warrant improvements. and angle in the form of 3D points [9,10]. They are usually mounted on airplanes for a large coverage while maintaining a good (cm) level of accuracy. The point density is dependent upon a few factors, e.g., scanner measurement rate and scanning mechanism, flight height and speed, swath width, and strip overlaps, hence it may vary from less than 1 point per m 2 to more than 50 points per m 2 . But in general, the maximum point density is getting higher with the development of airborne laser scanners.Early studies have mostly focused on the characteristics at stand-level, such as canopy cover and height, from airborne lidar data, due to limited point density [11][12][13]. Now the point density is high enough to capture a sufficient number of points on each individual tree, so that individual tree detection or delineation (ITD), including tree location, size, shape and number, has drawn considerable attention [5,[14][15][16]. Vertical distribution, above ground biomass and other secondary properties, can be derived from those accurate delineation parameters. Therefore, ALS has been increasingly used for precise forest mapping and monitoring at landscape or regional scale [10].Although ITD from airborne lidar is an important research topic for forest studies, it still remains as a challenge due to the complexity and heterogeneity of the forest structure and its composition. The main difficulty of ITD is tree segmentation, a step to segment the overall points into clusters that represent individual trees. There are two main strategies for tree segmentation: Raster-based and point-based [17,18]. Earlier methods mostly adopted the first strategy, converting the 3D point clouds into canopy height models (CHMs), a raster image, then detecting tree tops using 2D image processing techniques such as local maxima, region growing and watershed [5]. The second strategy segments the trees based directly on 3D points [14,19]. Exam...

show abstract

Individual Tree Crown Segmentation and Classification of 13 Tree Species Using Airborne Hyperspectral Data

Cited by 130 publications

References 76 publications

Optimal Input Features for Tree Species Classification in Central Europe Based on Multi-Temporal Sentinel-2 Data

Optimal Input Features for Tree Species Classification in Central Europe Based on Multi-Temporal Sentinel-2 Data

Geographic Generalization in Airborne RGB Deep Learning Tree Detection

Mean Shift Segmentation Assessment for Individual Forest Tree Delineation from Airborne Lidar Data

Contact Info

Product

Resources

About