Individual tree species identification using Dense Convolutional Network (DenseNet) on multitemporal RGB images from UAV

2020 ◽  
Vol 8 (4) ◽  
pp. 310-333
Author(s):  
Sowmya Natesan ◽  
Costas Armenakis ◽  
Udayalakshmi Vepakomma
Keyword(s):  
High Resolution ◽  
Species Identification ◽  
Tree Species ◽  
Tree Canopy ◽  
Tree Level ◽  
Eastern Canada ◽  
Convolutional Network ◽  
Individual Tree ◽  
Rgb Images ◽  
The Individual

Tree species identification at the individual tree level is crucial for forest operations and management, yet its automated mapping remains challenging. Emerging technology, such as the high-resolution imagery from unmanned aerial vehicles (UAV) that is now becoming part of every forester’s surveillance kit, can potentially provide a solution to better characterize the tree canopy. To address this need, we have developed an approach based on a deep Convolutional Neural Network (CNN) to classify forest tree species at the individual tree-level that uses high-resolution RGB images acquired from a consumer-grade camera mounted on a UAV platform. This work explores the ability of the Dense Convolutional Network (DenseNet) to classify commonly available economic coniferous tree species in eastern Canada. The network was trained using multitemporal images captured under varying acquisition parameters to include seasonal, temporal, illumination, and angular variability. Validation of this model using distinct images over a mixed-wood forest in Ontario, Canada, showed over 84% classification accuracy in distinguishing five predominant species of coniferous trees. The model remains highly robust even when using images taken during different seasons and times, and with varying illumination and angles.

scholarly journals Comparison of Tree Species Classifications at the Individual Tree Level by Combining ALS Data and RGB Images Using Different Algorithms

2016 ◽  
Vol 8 (12) ◽  
pp. 1034 ◽  
Author(s):  
Songqiu Deng ◽  
Masato Katoh ◽  
Xiaowei Yu ◽  
Juha Hyyppä ◽  
Tian Gao
Keyword(s):  
Tree Species ◽  
Tree Level ◽  
Individual Tree ◽  
Rgb Images ◽  
The Individual

scholarly journals RESNET-BASED TREE SPECIES CLASSIFICATION USING UAV IMAGES

2019 ◽  
Vol XLII-2/W13 ◽  
pp. 475-481 ◽  
Author(s):  
S. Natesan ◽  
C. Armenakis ◽  
U. Vepakomma
Keyword(s):  
Neural Networks ◽  
High Resolution ◽  
Tree Species ◽  
Classification Accuracy ◽  
Forest Tree ◽  
Tree Level ◽  
Species Classification ◽  
Individual Tree ◽  
Tree Species Classification ◽  
Rgb Images

<p><strong>Abstract.</strong> Tree species classification at individual tree level is a challenging problem in forest management. Deep learning, a cutting-edge technology evolved from Artificial Intelligence, was seen to outperform other techniques when it comes to complex problems such as image classification. In this work, we present a novel method to classify forest tree species through high resolution RGB images acquired with a simple consumer grade camera mounted on a UAV platform using Residual Neural Networks. We used UAV RGB images acquired over three years that varied in numerous acquisition parameters such as season, time, illumination and angle to train the neural network. To begin with, we have experimented with limited data towards the identification of two pine species namely red pine and white pine from the rest of the species. We performed two experiments, first with the images from all three acquisition years and the second with images from only one acquisition year. In the first experiment, we obtained 80% classification accuracy when the trained network was tested on a distinct set of images and in the second experiment, we obtained 51% classification accuracy. As a part of this work, a novel dataset of high-resolution labelled tree species is generated that can be used to conduct further studies involving deep neural networks in forestry.</p>

scholarly journals AGB Estimation in a Tropical Mountain Forest (TMF) by Means of RGB and Multispectral Images Using an Unmanned Aerial Vehicle (UAV)

2019 ◽  
Vol 11 (12) ◽  
pp. 1413 ◽  
Author(s):  
Víctor González-Jaramillo ◽  
Andreas Fries ◽  
Jörg Bendix
Keyword(s):  
High Resolution ◽  
Unmanned Aerial Vehicle ◽  
Tree Level ◽  
Mountain Forest ◽  
Multispectral Images ◽  
Individual Tree ◽  
Tropical Mountain ◽  
Aerial Vehicle ◽  
Rgb Images ◽  
Very High

The present investigation evaluates the accuracy of estimating above-ground biomass (AGB) by means of two different sensors installed onboard an unmanned aerial vehicle (UAV) platform (DJI Inspire I) because the high costs of very high-resolution imagery provided by satellites or light detection and ranging (LiDAR) sensors often impede AGB estimation and the determination of other vegetation parameters. The sensors utilized included an RGB camera (ZENMUSE X3) and a multispectral camera (Parrot Sequoia), whose images were used for AGB estimation in a natural tropical mountain forest (TMF) in Southern Ecuador. The total area covered by the sensors included 80 ha at lower elevations characterized by a fast-changing topography and different vegetation covers. From the total area, a core study site of 24 ha was selected for AGB calculation, applying two different methods. The first method used the RGB images and applied the structure for motion (SfM) process to generate point clouds for a subsequent individual tree classification. Per the classification at tree level, tree height (H) and diameter at breast height (DBH) could be determined, which are necessary input parameters to calculate AGB (Mg ha−1) by means of a specific allometric equation for wet forests. The second method used the multispectral images to calculate the normalized difference vegetation index (NDVI), which is the basis for AGB estimation applying an equation for tropical evergreen forests. The obtained results were validated against a previous AGB estimation for the same area using LiDAR data. The study found two major results: (i) The NDVI-based AGB estimates obtained by multispectral drone imagery were less accurate due to the saturation effect in dense tropical forests, (ii) the photogrammetric approach using RGB images provided reliable AGB estimates comparable to expensive LiDAR surveys (R2: 0.85). However, the latter is only possible if an auxiliary digital terrain model (DTM) in very high resolution is available because in dense natural forests the terrain surface (DTM) is hardly detectable by passive sensors due to the canopy layer, which impedes ground detection.

scholarly journals A Comparison of Three Airborne Laser Scanner Types for Species Identification of Individual Trees

Sensors ◽  
2021 ◽  
Vol 22 (1) ◽  
pp. 35
Author(s):  
Jean-François Prieur ◽  
Benoît St-Onge ◽  
Richard A. Fournier ◽  
Murray E. Woods ◽  
Parvez Rana ◽  
...  
Keyword(s):  
Species Identification ◽  
Laser Scanning ◽  
Time Series Data ◽  
Single Photon ◽  
Series Data ◽  
Tree Level ◽  
Potential Contribution ◽  
Individual Tree ◽  
Airborne Laser ◽  
The Individual

Species identification is a critical factor for obtaining accurate forest inventories. This paper compares the same method of tree species identification (at the individual crown level) across three different types of airborne laser scanning systems (ALS): two linear lidar systems (monospectral and multispectral) and one single-photon lidar (SPL) system to ascertain whether current individual tree crown (ITC) species classification methods are applicable across all sensors. SPL is a new type of sensor that promises comparable point densities from higher flight altitudes, thereby increasing lidar coverage. Initial results indicate that the methods are indeed applicable across all of the three sensor types with broadly similar overall accuracies (Hardwood/Softwood, 83–90%; 12 species, 46–54%; 4 species, 68–79%), with SPL being slightly lower in all cases. The additional intensity features that are provided by multispectral ALS appear to be more beneficial to overall accuracy than the higher point density of SPL. We also demonstrate the potential contribution of lidar time-series data in improving classification accuracy (Hardwood/Softwood, 91%; 12 species, 58%; 4 species, 84%). Possible causes for lower SPL accuracy are (a) differences in the nature of the intensity features and (b) differences in first and second return distributions between the two linear systems and SPL. We also show that segmentation (and field-identified training crowns deriving from segmentation) that is performed on an initial dataset can be used on subsequent datasets with similar overall accuracy. To our knowledge, this is the first study to compare these three types of ALS systems for species identification at the individual tree level.

scholarly journals Accuracy of a LiDAR-Based Individual Tree Detection and Attribute Measurement Algorithm Developed to Inform Forest Products Supply Chain and Resource Management

Forests ◽  
2021 ◽  
Vol 13 (1) ◽  
pp. 3
Author(s):  
Aaron M. Sparks ◽  
Alistair M.S. Smith
Keyword(s):  
Supply Chain ◽  
Tree Species ◽  
Coniferous Forest ◽  
Canopy Cover ◽  
Forest Products ◽  
Tree Canopy ◽  
Tree Level ◽  
Individual Tree ◽  
Tree Detection ◽  
Canopy Position

Individual Tree Detection (ITD) algorithms that use Airborne Laser Scanning (ALS) data can provide accurate tree locations and measurements of tree-level attributes that are required for stand-to-landscape scale forest inventory and supply chain management. While numerous ITD algorithms exist, few have been assessed for accuracy in stands with complex forest structure and composition, limiting their utility for operational application. In this study, we conduct a preliminary assessment of the ability of the ForestView® algorithm created by Northwest Management Incorporated to detect individual trees, classify tree species, live/dead status, canopy position, and estimate height and diameter at breast height (DBH) in a mixed coniferous forest with an average tree density of 543 (s.d. ±387) trees/hectare. ITD accuracy was high in stands with lower canopy cover (recall: 0.67, precision: 0.8) and lower in stands with higher canopy cover (recall: 0.36, precision: 0.67), mainly owing to omission of suppressed trees that were not detected under the dominant tree canopy. Tree species that were well-represented within the study area had high classification accuracies (producer’s/user’s accuracies > ~60%). The similarity between the ALS estimated and observed tree attributes was high, with no statistical difference in the ALS estimated height and DBH distributions and the field observed height and DBH distributions. RMSEs for tree-level height and DBH were 0.69 m and 7.2 cm, respectively. Overall, this algorithm appears comparable to other ITD and measurement algorithms, but quantitative analyses using benchmark datasets in other forest types and cross-comparisons with other ITD algorithms are needed.

scholarly journals SISFLOR: A COMPUTATIONAL SYSTEM TO DETERMINE THE OPTIMAL TREE BUCKING

2020 ◽  
Vol 28 ◽  
pp. 192-201
Author(s):  
Rodrigo Freitas Silva ◽  
Marcelo Otone Aguiar ◽  
Mayra Luiza Marques Da Silva ◽  
Gilson Fernandes Da Silva ◽  
Adriano Ribeiro De Mendonça
Keyword(s):  
Optimization Technique ◽  
Wood Products ◽  
Tree Level ◽  
Economic Losses ◽  
Computational System ◽  
Individual Tree ◽  
Optimal Tree ◽  
Cutting Pattern ◽  
Forest Enterprises ◽  
The Individual

A continuously competitive forest market and tied to the demands for wood products promotes the study and development of applications that increase the revenue of the forest enterprises. At harvesting, the cutting pattern (forest assortment) in which the trees are traced is traditionally determined by the experience of the chainsaw operator without using any optimization technique, which may result in economic losses in relation to the commercialized products. In general, there are numerous distinct assortments that can be chosen and hardly processed by a brute-force algorithm. This is the forest assortment problem at the individual tree level with the objetice of maximizing the commercial values of the felled trees. stem-level bucking optimization problem. The aim is to maximize the sales value of harvested trees. Dynamic Programming (DP) is an efficient optimization technique to determine the optimum bucking tree as it significantly reduces the number of calculations to be made. Thus, the objective of this work was to develop a modern and intuitive computational system that is able to find the optimum tree stem bucking through DP to help companies over the bole tracing, therefore, characterizing itself as a tool that supports decision making. After the execution of the system, the optimum assortment is shown by sequentially detailing all products that should be removed from the analyzed bole as well as their respective volumes and revenue.

scholarly journals Finer Resolution Estimation and Mapping of Mangrove Biomass Using UAV LiDAR and WorldView-2 Data

Forests ◽  
2019 ◽  
Vol 10 (10) ◽  
pp. 871 ◽  
Author(s):  
Qiu ◽  
Wang ◽  
Zou ◽  
Yang ◽  
Xie ◽  
...  
Keyword(s):  
Tree Level ◽  
Inference Method ◽  
Mangrove Species ◽  
Individual Tree ◽  
Model Method ◽  
Lower Accuracy ◽  
Field Samples ◽  
The Individual ◽  
Mangrove Biomass ◽  
Grid Based

To estimate mangrove biomass at finer resolution, such as at an individual tree or clump level, there is a crucial need for elaborate management of mangrove forest in a local area. However, there are few studies estimating mangrove biomass at finer resolution partly due to the limitation of remote sensing data. Using WorldView-2 imagery, unmanned aerial vehicle (UAV) light detection and ranging (LiDAR) data, and field survey datasets, we proposed a novel method for the estimation of mangrove aboveground biomass (AGB) at individual tree level, i.e., individual tree-based inference method. The performance of the individual tree-based inference method was compared with the grid-based random forest model method, which directly links the field samples with the UAV LiDAR metrics. We discussed the feasibility of the individual tree-based inference method and the influence of diameter at breast height (DBH) on individual segmentation accuracy. The results indicated that (1) The overall classification accuracy of six mangrove species at individual tree level was 86.08%. (2) The position and number matching accuracies of individual tree segmentation were 87.43% and 51.11%, respectively. The number matching accuracy of individual tree segmentation was relatively satisfying within 8 cm ≤ DBH ≤ 30 cm. (3) The individual tree-based inference method produced lower accuracy than the grid-based RF model method with R2 of 0.49 vs. 0.67 and RMSE of 48.42 Mg ha–1 vs. 38.95 Mg ha–1. However, the individual tree-based inference method can show more detail of spatial distribution of mangrove AGB. The resultant AGB maps of this method are more beneficial to the fine and differentiated management of mangrove forests.

scholarly journals Deep Learning Approaches for the Mapping of Tree Species Diversity in a Tropical Wetland Using Airborne LiDAR and High-Spatial-Resolution Remote Sensing Images

Forests ◽  
2019 ◽  
Vol 10 (11) ◽  
pp. 1047 ◽  
Author(s):  
Ying Sun ◽  
Jianfeng Huang ◽  
Zurui Ao ◽  
Dazhao Lao ◽  
Qinchuan Xin
Keyword(s):  
Remote Sensing ◽  
Deep Learning ◽  
Species Diversity ◽  
Spatial Resolution ◽  
Tree Species ◽  
High Spatial Resolution ◽  
Diversity Index ◽  
Tree Species Diversity ◽  
Individual Tree ◽  
Rgb Images

The monitoring of tree species diversity is important for forest or wetland ecosystem service maintenance or resource management. Remote sensing is an efficient alternative to traditional field work to map tree species diversity over large areas. Previous studies have used light detection and ranging (LiDAR) and imaging spectroscopy (hyperspectral or multispectral remote sensing) for species richness prediction. The recent development of very high spatial resolution (VHR) RGB images has enabled detailed characterization of canopies and forest structures. In this study, we developed a three-step workflow for mapping tree species diversity, the aim of which was to increase knowledge of tree species diversity assessment using deep learning in a tropical wetland (Haizhu Wetland) in South China based on VHR-RGB images and LiDAR points. Firstly, individual trees were detected based on a canopy height model (CHM, derived from LiDAR points) by the local-maxima-based method in the FUSION software (Version 3.70, Seattle, USA). Then, tree species at the individual tree level were identified via a patch-based image input method, which cropped the RGB images into small patches (the individually detected trees) based on the tree apexes detected. Three different deep learning methods (i.e., AlexNet, VGG16, and ResNet50) were modified to classify the tree species, as they can make good use of the spatial context information. Finally, four diversity indices, namely, the Margalef richness index, the Shannon–Wiener diversity index, the Simpson diversity index, and the Pielou evenness index, were calculated from the fixed subset with a size of 30 × 30 m for assessment. In the classification phase, VGG16 had the best performance, with an overall accuracy of 73.25% for 18 tree species. Based on the classification results, mapping of tree species diversity showed reasonable agreement with field survey data (R2Margalef = 0.4562, root-mean-square error RMSEMargalef = 0.5629; R2Shannon–Wiener = 0.7948, RMSEShannon–Wiener = 0.7202; R2Simpson = 0.7907, RMSESimpson = 0.1038; and R2Pielou = 0.5875, RMSEPielou = 0.3053). While challenges remain for individual tree detection and species classification, the deep-learning-based solution shows potential for mapping tree species diversity.

Sign in / Sign up

Export Citation Format

Share Document