Individual tree detection based on variable and fixed window size local maxima filtering applied to IKONOS imagery for even-aged Eucalyptus plantation forests

Individual tree detection (ITD) locates plants from images to estimate monitoring parameters, helping the management of forestry and agriculture systems. As a low-cost solution to help farm monitoring, digital surface models are increasingly involved together with mathematical morphology techniques within the framework of ITD tasks. However, morphology-based approaches are prone to omission and commission errors due to the shape and size of structuring elements. To reduce the error rate in ITD tasks, we introduce a morphological transform that is based on the local maxima segmentation (Cumulative Summation of Extended Maxima transform (SEMAX)) with the aim to enhance the seed selection by extracting information collected from different heights. Validation is performed on data collected from the plantations of citrus and avocado using different measures of precision. The results obtained by the SEMAX approach show that the devised ITD algorithm provides enough accuracy, and achieves the lowest false-negative rate than other compared state-of-art approaches do.

Download Full-text

Individual tree detection using UAV-lidar and UAV-SfM data: A tutorial for beginners

Open Geosciences ◽

10.1515/geo-2020-0290 ◽

2021 ◽

Vol 13 (1) ◽

pp. 1028-1039

Author(s):

Midhun Mohan ◽

Rodrigo Vieira Leite ◽

Eben North Broadbent ◽

Wan Shafrina Wan Mohd Jaafar ◽

Shruthi Srinivasan ◽

...

Keyword(s):

Accuracy Assessment ◽

Low Cost ◽

Stem Volume ◽

Biomass Estimation ◽

Visual Interpretation ◽

Individual Tree ◽

Local Maxima ◽

Tree Detection ◽

High Resolution Imagery ◽

Lm Algorithm

Abstract Applications of unmanned aerial vehicles (UAVs) have proliferated in the last decade due to the technological advancements on various fronts such as structure-from-motion (SfM), machine learning, and robotics. An important preliminary step with regard to forest inventory and management is individual tree detection (ITD), which is required to calculate forest attributes such as stem volume, forest uniformity, and biomass estimation. However, users may find adopting the UAVs and algorithms for their specific projects challenging due to the plethora of information available. Herein, we provide a step-by-step tutorial for performing ITD using (i) low-cost UAV-derived imagery and (ii) UAV-based high-density lidar (light detection and ranging). Functions from open-source R packages were implemented to develop a canopy height model (CHM) and perform ITD utilizing the local maxima (LM) algorithm. ITD accuracy assessment statistics and validation were derived through manual visual interpretation from high-resolution imagery and field-data-based accuracy assessment. As the intended audience are beginners in remote sensing, we have adopted a very simple methodology and chosen study plots that have relatively open canopies to demonstrate our proposed approach; the respective R codes and sample plot data are available as supplementary materials.

Download Full-text

Individual Tree Detection in a Eucalyptus Plantation Using Unmanned Aerial Vehicle (UAV)-LiDAR

Remote Sensing ◽

10.3390/rs12050885 ◽

2020 ◽

Vol 12 (5) ◽

pp. 885 ◽

Cited By ~ 4

Author(s):

Juan Picos ◽

Guillermo Bastos ◽

Daniel Míguez ◽

Laura Alonso ◽

Julia Armesto

Keyword(s):

Unmanned Aerial Vehicle ◽

Point Cloud ◽

Single Point ◽

Tree Height ◽

Individual Tree ◽

Eucalyptus Plantation ◽

Local Maxima ◽

Eucalypt Plantations ◽

Aerial Vehicle ◽

Precision Forestry

The present study addresses the tree counting of a Eucalyptus plantation, the most widely planted hardwood in the world. Unmanned aerial vehicle (UAV) light detection and ranging (LiDAR) was used for the estimation of Eucalyptus trees. LiDAR-based estimation of Eucalyptus is a challenge due to the irregular shape and multiple trunks. To overcome this difficulty, the layer of the point cloud containing the stems was automatically classified and extracted according to the height thresholds, and those points were horizontally projected. Two different procedures were applied on these points. One is based on creating a buffer around each single point and combining the overlapping resulting polygons. The other one consists of a two-dimensional raster calculated from a kernel density estimation with an axis-aligned bivariate quartic kernel. Results were assessed against the manual interpretation of the LiDAR point cloud. Both methods yielded a detection rate (DR) of 103.7% and 113.6%, respectively. Results of the application of the local maxima filter to the canopy height model (CHM) intensely depends on the algorithm and the CHM pixel size. Additionally, the height of each tree was calculated from the CHM. Estimates of tree height produced from the CHM was sensitive to spatial resolution. A resolution of 2.0 m produced a R2 and a root mean square error (RMSE) of 0.99 m and 0.34 m, respectively. A finer resolution of 0.5 m produced a more accurate height estimation, with a R2 and a RMSE of 0.99 and 0.44 m, respectively. The quality of the results is a step toward precision forestry in eucalypt plantations.

Download Full-text

INDIVIDUAL TREE DETECTION FROM UAV LIDAR DATA IN A MIXED SPECIES WOODLAND

ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences ◽

10.5194/isprs-archives-xlii-2-w13-657-2019 ◽

2019 ◽

Vol XLII-2/W13 ◽

pp. 657-663 ◽

Cited By ~ 6

Author(s):

A. Zaforemska ◽

W. Xiao ◽

R. Gaulton

Keyword(s):

Point Cloud ◽

Voronoi Tessellation ◽

Mean Shift ◽

Region Growing ◽

Single Species ◽

Mixed Species ◽

Individual Tree ◽

Local Maxima ◽

Tree Detection ◽

Segmentation Algorithms

<p><strong>Abstract.</strong> The study evaluates five existing segmentation algorithms to determine the method most suitable for individual tree detection across a species-diverse forest: raster-based region growing, local maxima centroidal Voronoi tessellation, point-cloud level region growing, marker controlled watershed and continuously adaptive mean shift. Each of the methods has been tested twice over one mixed and five single species plots: with their parameters set as constant and with the parameters calibrated for every plot. Overall, continuous adaptive mean shift performs best across all the plots with average F-score of 0.9 with fine-tuned parameters and 0.802 with parameters held at constant. Raster-based algorithms tend to achieve higher scores in coniferous plots, due to the clearly discernible tops, which significantly aid the detection of local maxima. Their performance is also highly dependent on the moving size window used to detect the local maxima, which ideally should be readjusted for every plot. Crown overlap, suppressed and leaning trees are the most likely sources of error for all the algorithms tested.</p>

Download Full-text

Individual tree detection in digital aerial images by combining locally adaptive binarization and local maxima methods

Canadian Journal of Forest Research ◽

10.1139/x01-013 ◽

2001 ◽

Vol 31 (5) ◽

pp. 832-844 ◽

Cited By ~ 38

Author(s):

Juho Pitkänen

Keyword(s):

Digital Camera ◽

Adaptive Methods ◽

Aerial Images ◽

Detection Accuracy ◽

Image Smoothing ◽

Individual Tree ◽

Local Maxima ◽

Tree Detection ◽

Locally Adaptive ◽

Tree Data

Locating local maxima of grey levels in aerial images was used for individual tree detection in boreal, closed forest conditions in southern Finland. Image smoothing and binarization were used as preprocessing steps. Binarization was used to restrict the local maxima searching to the bright areas of the images, which were assumed to be tree crowns. Because brightness variations are typical of aerial images, both within and among images, locally adaptive methods were suggested for binarization. Aerial digital camera images and mapped tree data of eight stands in three field plots were used. Four adaptive binarization methods were compared. Differences in tree detection accuracy were small even though the appearance of the binarized images were different. Image smoothing improved the results of tree detection in the three stands that had the largest mean tree size. Tree detection worked fairly well in all seven stands with a density of less than 1500 trees/ha. In these stands, 7095% of the trees were detected, whereas only 54% were detected in the last stand, which had a density of approximately 1900 trees/ha.

Download Full-text

A Crown Morphology-Based Approach to Individual Tree Detection in Subtropical Mixed Broadleaf Urban Forests Using UAV LiDAR Data

Remote Sensing ◽

10.3390/rs13071278 ◽

2021 ◽

Vol 13 (7) ◽

pp. 1278

Author(s):

Wenbing Xu ◽

Susu Deng ◽

Dan Liang ◽

Xiaojun Cheng

Keyword(s):

Detection Rate ◽

Window Size ◽

Test Site ◽

Lidar Data ◽

Parameter Setting ◽

Individual Tree ◽

Tree Distribution ◽

Tree Detection ◽

Crown Morphology ◽

Crown Size

Owing to the complex forest structure and large variation in crown size, individual tree detection in subtropical mixed broadleaf forests in urban scenes is a great challenge. Unmanned aerial vehicle (UAV) light detection and ranging (LiDAR) is a powerful tool for individual tree detection due to its ability to acquire high density point cloud that can reveal three-dimensional crown structure. Tree detection based on a local maximum (LM) filter, which is applied on a canopy height model (CHM) generated from LiDAR data, is a popular method due to its simplicity. However, it is difficult to determine the optimal LM filter window size and prior knowledge is usually needed to estimate the window size. In this paper, a novel tree detection approach based on crown morphology information is proposed. In the approach, LMs are firstly extracted using a LM filter whose window size is determined by the minimum crown size and then the crown morphology is identified based on local Gi* statistics to filter out LMs caused by surface irregularities contained in CHM. The LMs retained in the final results represent treetops. The approach was applied on two test sites characterized by different forest structures using UAV LiDAR data. The sensitivity of the approach to parameter setting was analyzed and rules for parameter setting were proposed. On the first test site characterized by irregular tree distribution and large variation in crown size, the detection rate and F-score derived by using the optimal combination of parameter values were 72.9% and 73.7%, respectively. On the second test site characterized by regular tree distribution and relatively small variation in crown size, the detection rate and F-score were 87.2% and 93.2%, respectively. In comparison with a variable-size window tree detection algorithm, both detection rates and F-score values of the proposed approach were higher.

Download Full-text

Influence of Agisoft Metashape Parameters on UAS Structure from Motion Individual Tree Detection from Canopy Height Models

Forests ◽

10.3390/f12020250 ◽

2021 ◽

Vol 12 (2) ◽

pp. 250

Author(s):

Wade T. Tinkham ◽

Neal C. Swayze

Keyword(s):

Structure From Motion ◽

Ponderosa Pine ◽

Point Cloud ◽

Image Resolution ◽

Canopy Height ◽

Computer Hardware ◽

Forest Monitoring ◽

Individual Tree ◽

Ponderosa Pine Forests ◽

Tree Detection

Applications of unmanned aerial systems for forest monitoring are increasing and drive a need to understand how image processing workflows impact end-user products’ accuracy from tree detection methods. Increasing image overlap and making acquisitions at lower altitudes improve how structure from motion point clouds represents forest canopies. However, only limited testing has evaluated how image resolution and point cloud filtering impact the detection of individual tree locations and heights. We evaluate how Agisoft Metashape’s build dense cloud Quality (image resolution) and depth map filter settings influence tree detection from canopy height models in ponderosa pine forests. Finer resolution imagery with minimal filtering provided the best visual representation of vegetation detail for trees of all sizes. These same settings maximized tree detection F-score at >0.72 for overstory (>7 m tall) and >0.60 for understory trees. Additionally, overstory tree height bias and precision improve as image resolution becomes finer. Overstory and understory tree detection in open-canopy conifer systems might be optimized using the finest resolution imagery that computer hardware enables, while applying minimal point cloud filtering. The extended processing time and data storage demands of high-resolution imagery must be balanced against small reductions in tree detection performance when down-scaling image resolution to allow the processing of greater data extents.

Download Full-text