Detection of Single Tree Stems in Forested Areas From High Density Als Point Clouds Using 3d Shape Descriptors

Abstract

ABSTRACT:Airborne Laser Scanning (ALS) is a widespread method for forest mapping and management purposes. While common ALS techniques provide valuable information about the forest canopy and intermediate layers, the point density near the ground may be poor due to dense overstory conditions. The current study highlights a new method for detecting stems of single trees in 3D point clouds obtained from high density ALS with a density of 300 points/m 2 . Compared to standard ALS data, due to lower flight height (150-200 m) this elevated point density leads to more laser reflections from tree stems. In this work, we propose a three-tiered method which works on the point, segment and object levels. First, for each point we calculate the likelihood that it belongs to a tree stem, derived from the radiometric and geometric features of its neighboring points. In the next step, we construct short stem segments based on high-probability stem points, and classify the segments by considering the distribution of points around them as well as their spatial orientation, which encodes the prior knowledge that trees are mainly vertically aligned due to gravity. Finally, we apply hierarchical clustering on the positively classified segments to obtain point sets corresponding to single stems, and perform 1-based orthogonal distance regression to robustly fit lines through each stem point set. The 1-based method is less sensitive to outliers compared to the least square approaches. From the fitted lines, the planimetric tree positions can then be derived. Experiments were performed on two plots from the Hochficht forest in Oberösterreich region located in Austria. We marked a total of 196 reference stems in the point clouds of both plots by visual interpretation. The evaluation of the automatically detected stems showed a classification precision of 0.86 and 0.85, respectively for Plot 1 and 2, with recall values of 0.7 and 0.67.

A Novel Approach for the Detection of Standing Tree Stems from Plot-Level Terrestrial Laser Scanning Data

“…In a forest environment, Polewski et al [38] proposed an approach that combined a point-based and a segment-based method to detect fallen tree stems from TLS datasets. Amiri et al [39] applied Polewski 's method to detect tree stems from very-high density airborne laser scanning datasets. However, they employed a supervised method in the stage of point-based classification by using multiple features, which increased the complexity of the algorithm and turned out to be a time-consuming approach.…”

ALS as Tool to Study Preferred Stem Inclination Directions

“…In recent years several methods for extracting tree stems using ALS have been developed [1,[18][19][20][21][22][23]. Due to differing objectives, differing ALS acquisition designs and differing investigated forest types and structures, the accuracy of the trunk detection methods is hard to compare.…”

“…Amiri et al [21] enhance the method of Polewski et al [19] for identifying individual tree stems using high density ALS point clouds. With a Random Forest Classifier, points associated with tree stems are classified using 3D shape descriptors, covariance features and the normalized height.…”

Reliable Estimates of Merchantable Timber Volume from Terrestrial Laser Scanning

“…Their results showed that downed dead wood volume was automatically estimated with an RMSE of 15.0 m 3 /ha (59.3%), which was reduced to 6.4 m 3 /ha (25.3%) when visual interpretation was incorporated. In another study, Amiri et al [26] used visual interpretation to identify all the reference stems, and they compared them with stems obtained through laser scanning. The evaluation of the automatically detected stems showed a classification precision of 0.86 and 0.85 and recall values of 0.7 and 0.67 for plots 1 and 2, respectively.…”