Individual tree identification using different LIDAR and optical imagery data processing methods

Smits, Ingus; Priedītis, G.; Dagis, Salvis; Dubrovskis, D.

doi:10.11592/bit.121103

Cited by 15 publications

(9 citation statements)

References 15 publications

(19 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Clarks and Roberts [ 97 ] also used hyperspectral data for successful classification of seven tree species to a high level of accuracy in the tropical forests of Costa Rica. Other studies have utilized a combination of hyperspectral data, LiDAR, and conventional aerial imagery for mapping of tree species in temperate forests [ 99 , 100 ]. Given a choice between hyperspectral and aerial imagery, the former is clearly preferable for tree species mapping on a landscape scale in a tropical forest ecosystem.…”

Section: Discussionmentioning

confidence: 99%

Mapping and Characterizing Selected Canopy Tree Species at the Angkor World Heritage Site in Cambodia Using Aerial Data

et al. 2015

View full text Add to dashboard Cite

At present, there is very limited information on the ecology, distribution, and structure of Cambodia’s tree species to warrant suitable conservation measures. The aim of this study was to assess various methods of analysis of aerial imagery for characterization of the forest mensuration variables (i.e., tree height and crown width) of selected tree species found in the forested region around the temples of Angkor Thom, Cambodia. Object-based image analysis (OBIA) was used (using multiresolution segmentation) to delineate individual tree crowns from very-high-resolution (VHR) aerial imagery and light detection and ranging (LiDAR) data. Crown width and tree height values that were extracted using multiresolution segmentation showed a high level of congruence with field-measured values of the trees (Spearman’s rho 0.782 and 0.589, respectively). Individual tree crowns that were delineated from aerial imagery using multiresolution segmentation had a high level of segmentation accuracy (69.22%), whereas tree crowns delineated using watershed segmentation underestimated the field-measured tree crown widths. Both spectral angle mapper (SAM) and maximum likelihood (ML) classifications were applied to the aerial imagery for mapping of selected tree species. The latter was found to be more suitable for tree species classification. Individual tree species were identified with high accuracy. Inclusion of textural information further improved species identification, albeit marginally. Our findings suggest that VHR aerial imagery, in conjunction with OBIA-based segmentation methods (such as multiresolution segmentation) and supervised classification techniques are useful for tree species mapping and for studies of the forest mensuration variables.

show abstract

Section: Discussionmentioning

confidence: 99%

Mapping and Characterizing Selected Canopy Tree Species at the Angkor World Heritage Site in Cambodia Using Aerial Data

et al. 2015

View full text Add to dashboard Cite

show abstract

“…N Eps (p) and MinPts are mandatory thresholds to classify the point dispersion into core, border and noise points (Ester et al 1996;Smits et al 2012). The core point consists of a high density of points based on MinPts (N Eps (p) ≥ MinPts); the border is a point out of the core point but easy to be reachable (p ∈ N Eps (q)); the noise point is an isolated point far away form the core point (Figure 4).…”

Section: Step 3 -Tree Detection and Segmentationmentioning

confidence: 99%

“…The core point consists of a high density of points based on MinPts (N Eps (p) ≥ MinPts); the border is a point out of the core point but easy to be reachable (p ∈ N Eps (q)); the noise point is an isolated point far away form the core point (Figure 4). To define the core, border and noise points, the DBSCAN algorithm plays an internal validation based on the densityreachability and density-connectivity (Figure 4) (Ester et al 1996;Smits et al 2012).…”

Section: Step 3 -Tree Detection and Segmentationmentioning

confidence: 99%

Unsupervised algorithms to detect single trees in a mixed-species and multilayered Mediterranean forest using LiDAR data

et al. 2021

View full text Add to dashboard Cite

Accurate measurement of forest growing stock is a prerequisite for implementing Climate-Smart Forestry strategies. This study deals with the use of Airborne Laser Scanning data to assess carbon stock at the tree level. It aims to demonstrate that the combined use of two unsupervised techniques will improve the accuracy of estimation supporting sustainable forest management. Based on the heterogeneity of tree height and point cloud density, we classified 31 forest stands into four complexity categories. The point cloud of each stand was further splitted in three horizontal layers improving the accuracy of tree detection at tree level for which we calculated volume and carbon stock. The average accuracy of tree detection was 0.48. The accuracy was higher for forest stands with lower tree density and higher frequency of large trees, as well as dense point cloud (0.65). The prediction of carbon stock was higher with a bias ranging from -0.3 % to 1.5 % and the RMSE ranging from 0.14 % to 1.48 %.

show abstract

“…There is a large body of work on tree identification using LiDAR data, but most of it focuses on identifying trees in forested environments, with little emphasis given to urban environments. Most of these methods are derivatives of the canopy height model (CHM) [6,7,8,9,10].…”

Section: Introductionmentioning

confidence: 99%

Tree Annotations in LiDAR Data Using Point Densities and Convolutional Neural Networks

Gupta¹,

Byrne²,

Moloney³

et al. 2020

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

LiDAR provides highly accurate 3D point clouds. However, data needs to be manually labelled in order to provide subsequent useful information. Manual annotation of such data is time consuming, tedious and error prone, and hence in this paper we present three automatic methods for annotating trees in LiDAR data. The first method requires high density point clouds and uses certain LiDAR data attributes for the purpose of tree identification, achieving almost 90% accuracy. The second method uses a voxel-based 3D Convolutional Neural Network on low density LiDAR datasets and is able to identify most large trees accurately but struggles with smaller ones due to the voxelisation process. The third method is a scaled version of the PointNet++ method and works directly on outdoor point clouds and achieves an Fscore of 82.1% on the ISPRS benchmark dataset, comparable to the state-of-the-art methods but with increased efficiency.

show abstract

Individual tree identification using different LIDAR and optical imagery data processing methods

Cited by 15 publications

References 15 publications

Mapping and Characterizing Selected Canopy Tree Species at the Angkor World Heritage Site in Cambodia Using Aerial Data

Mapping and Characterizing Selected Canopy Tree Species at the Angkor World Heritage Site in Cambodia Using Aerial Data

Unsupervised algorithms to detect single trees in a mixed-species and multilayered Mediterranean forest using LiDAR data

Tree Annotations in LiDAR Data Using Point Densities and Convolutional Neural Networks

Contact Info

Product

Resources

About