989 Hits in 5.0 sec

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

Ananya Gupta, Jonathan Byrne, David Moloney, Simon Watson, Hujun Yin
2019 IEEE Transactions on Geoscience and Remote Sensing  
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  ...  The first method requires high density point clouds and uses certain LiDAR data attributes for the purpose of tree identification, achieving almost 90% accuracy.  ...  1 Tree Annotations in LiDAR Data Using Point Densities and Convolutional Neural Networks Ananya Gupta*, Jonathan Byrne, David Moloney, Simon Watson, Hujun Yin* Abstract-LiDAR provides highly accurate 3D  ... 
doi:10.1109/tgrs.2019.2942201 fatcat:sbwb4enm3nf5riin2te2buonlq

Editorial for the Special Issue "Frontiers in Spectral Imaging and 3D Technologies for Geospatial Solutions"

Eija Honkavaara, Konstantinos Karantzalos, Xinlian Liang, Erica Nocerino, Ilkka Pölönen, Petri Rönnholm
2019 Remote Sensing  
This Special Issue hosts papers on the integrated use of spectral imaging and 3D technologies in remote sensing, including novel sensors, evolving machine learning technologies for data analysis, and the  ...  The presented results showed improved results when multimodal data was used in object analysis.  ...  Special thanks are due to the community of distinguished reviewers for their valuable and insightful inputs.  ... 
doi:10.3390/rs11141714 fatcat:jmyg2y523jfyhm5ykkc3jsqbpa

Three-Dimensional Convolutional Neural Network Model for Early Detection of Pine Wilt Disease Using UAV-Based Hyperspectral Images

Run Yu, Youqing Luo, Haonan Li, Liyuan Yang, Huaguo Huang, Linfeng Yu, Lili Ren
2021 Remote Sensing  
three-dimensional convolutional neural network (3D-CNN) is able to collect this information from raw hyperspectral data.  ...  However, the commonly used methods, such as the two-dimensional convolutional neural network (2D-CNN), fail to simultaneously extract and fully utilize the spatial and spectral information, whereas the  ...  Acknowledgments: The authors would like to thank H.N.L. and L.Y.Y. for the field investigation and Y.Q.L., H.G.H., L.F.Y. and L.L.R. for their suggestion and modification to this paper.  ... 
doi:10.3390/rs13204065 fatcat:cdahgwcrvjcnfld7j2qzi73dpq

Improved Prototypical Network Model for Forest Species Classification in Complex Stand

Xiaomin Tian, Long Chen, Xiaoli Zhang, Erxue Chen
2020 Remote Sensing  
classification and mapping of tree species.  ...  In this study, an improved prototypical network is proposed (by adding L2 regularization to the convolutional layer and dropout to the maximum pooling layer) to address the problem of overfitting in small-sample  ...  Acknowledgments: The authors would like to thank Lei Zhao, Yanshuang Wu, Lin Zhao, Zhengqi Guo and Wenting Guo for their assistance on data collection.  ... 
doi:10.3390/rs12223839 fatcat:parvhpchwnaptoog77oi4g552a

Tree species classification from airborne hyperspectral and LiDAR data using 3D convolutional neural networks

Janne Mäyrä, Sarita Keski-Saari, Sonja Kivinen, Topi Tanhuanpää, Pekka Hurskainen, Peter Kullberg, Laura Poikolainen, Arto Viinikka, Sakari Tuominen, Timo Kumpula, Petteri Vihervaara
2021 Remote Sensing of Environment  
tree species classification from hyperspectral data with high spatial and spectral resolution.  ...  We compared the performance of three-dimensional convolutional neural networks (3D-CNNs) with the support vector machine, random forest, gradient boosting machine and artificial neural network in individual  ...  Also, the authors would like to thank the editors and reviewers for their thorough comments and suggestions which greatly helped us to improve the final manuscript.  ... 
doi:10.1016/j.rse.2021.112322 fatcat:x4mgwkoytva53leu2w5otm3gte

Identifying Tree-Related Microhabitats in TLS Point Clouds Using Machine Learning

Nataliia Rehush, Meinrad Abegg, Lars Waser, Urs-Beat Brändli
2018 Remote Sensing  
Neural Network (CNN) trained using rasterized multiview orthographic projections (MVOPs) containing top view, front view and side view of the point's local 3D neighborhood.  ...  To classify the TreMs, we applied: (1) the Random Forest (RF) classifier, incorporating frequently used local geometric features and two additional self-developed orientation features, and (2) a deep Convolutional  ...  We are also grateful to Jonas Stillhard for providing information on habitat trees in Swiss forest reserves, Christian Ginzler for fruitful discussions regarding the scanning design and Silvia Dingwall  ... 
doi:10.3390/rs10111735 fatcat:yceupdwg5bglzg7bsjs7nxorfm

Hyperspectral Imaging for Minced Meat Classification Using Nonlinear Deep Features

Hamail Ayaz, Muhammad Ahmad, Manuel Mazzara, Ahmed Sohaib
2020 Applied Sciences  
Later, these preprocessed HSI cubes are fed into a 3D-Convolutional Neural Network (3D-CNN) model for nonlinear feature extraction and classification.  ...  Recently, Hyperspectral Imaging (HSI) has been used for the classification and identification of minced meat types.  ...  (A) represents the 3D-Convolutional Neural Network (3D-CNN) framework and (B) represents the Convolution and Kernel Operation for 3D Spectral Cube.  ... 
doi:10.3390/app10217783 fatcat:b7l2coyuyvf27l2zr5ldmkjylq

Mapping Tree Species Composition Using OHS-1 Hyperspectral Data and Deep Learning Algorithms in Changbai Mountains, Northeast China

Yanbiao Xi, Chunying Ren, Zongming Wang, Shiqing Wei, Jialing Bai, Bai Zhang, Hengxing Xiang, Lin Chen
2019 Forests  
In this study, one-dimensional convolutional neural network (Conv1D), a popular deep learning algorithm, was proposed to automatically identify tree species using OHS-1 hyperspectral images.  ...  Especially for broadleaf species with similar spectral characteristics, such as Manchurian walnut and aspen, the accuracy of Conv1D-based classifier is significantly higher than RF classifier (87.15% and  ...  Author Contributions: Y.X. calculated and analyzed the data in addition to writing the paper. C.R. designed the research project and analyzed the data in addition to writing the paper.  ... 
doi:10.3390/f10090818 fatcat:s6ugsrglhrgyppfebeyegfpege

Combining Multi-Dimensional Convolutional Neural Network (CNN) With Visualization Method for Detection of Aphis gossypii Glover Infection in Cotton Leaves Using Hyperspectral Imaging

Tianying Yan, Wei Xu, Jiao Lin, Long Duan, Pan Gao, Chu Zhang, Xin Lv
2021 Frontiers in Plant Science  
Convolutional Neural Networks (CNNs) were used for identification and compared with conventional machine learning methods.  ...  in 2D and 3D CNN visualization.  ...  ACKNOWLEDGMENTS The authors want to thank Jingcheng Xu, a master student at the Agricultural College of Shihezi University in China, for providing guidance on the use of hyperspectral imaging systems.  ... 
doi:10.3389/fpls.2021.604510 pmid:33659014 pmcid:PMC7917247 fatcat:lnxseiklinffjir2pceqxnybsi

Vegetation Type Classification Based on 3D Convolutional Neural Network Model: A Case Study of Baishuijiang National Nature Reserve

Xinyao Zhou, Wenzuo Zhou, Feng Li, Zhouling Shao, Xiaoli Fu
2022 Forests  
With the development of deep learning, the convolutional neural network (CNN) has been used successfully to classify tree species in many studies, but CNN models have rarely been applied in the classification  ...  , 2D-CNN, JSSAN (joint spatial–spectral attention network) and Resnet18, using sentinel-2A data.  ...  Data Availability Statement: Not applicable. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/f13060906 fatcat:fjtesoghjzbx3nxxi4ex4antsa

A Convolutional Neural Network Classifier Identifies Tree Species in Mixed-Conifer Forest from Hyperspectral Imagery

Geoffrey A. Fricker, Jonathan D. Ventura, Jeffrey A. Wolf, Malcolm P. North, Frank W. Davis, Janet Franklin
2019 Remote Sensing  
In this study, we automate tree species classification and mapping using field-based training data, high spatial resolution airborne hyperspectral imagery, and a convolutional neural network classifier  ...  We publicly provide our code to apply deep learning classifiers to tree species identification from geospatial imagery and field training data.  ...  The opinions expressed in this article are the author's own and do not reflect the view of Amazon Corporation.  ... 
doi:10.3390/rs11192326 fatcat:el6nbum7pfephbmkvjz4dyjuzu

DBMF: A Novel Method for Tree Species Fusion Classification Based on Multi-Source Images

Xueliang Wang, Honge Ren
2021 Forests  
The network has two branches in the spatial branch to avoid the risk of information loss, of which, sandglass blocks are embedded into a convolutional neural network (CNN) to extract the corresponding  ...  Multi-source data remote sensing provides innovative technical support for tree species recognition.  ...  [26] applied a three-dimensional convolutional neural network (3D-CNN) to recognize three main tree species with HS data from a boreal forest in Finland, and the OA reached 0.96 on the validation dataset  ... 
doi:10.3390/f13010033 fatcat:5p7fps4tcbepfpdschqnm5syvu

A New CBAM-P-Net Model for Few-Shot Forest Species Classification Using Airborne Hyperspectral Images

Long Chen, Xiaomin Tian, Guoqi Chai, Xiaoli Zhang, Erxue Chen
2021 Remote Sensing  
High-precision automatic identification and mapping of forest tree species composition is an important content of forest resource survey and monitoring.  ...  The airborne hyperspectral image contains rich spectral and spatial information, which provides the possibility of high-precision classification and mapping of forest tree species.  ...  Acknowledgments: The authors would like to thank Lei Zhao, Yueting Wang, Lin Zhao, and Zhengqi Guo for their assistance on data collection.  ... 
doi:10.3390/rs13071269 fatcat:b6lbaa3jkfakjduhi3vhpxf6ja

HyperSeed: An End-to-End Method to Process Hyperspectral Images of Seeds

Tian Gao, Anil Kumar Nalini Chandran, Puneet Paul, Harkamal Walia, Hongfeng Yu
2021 Sensors  
The results show that the proposed 3D convolutional neural network (3D CNN) model has the highest accuracy, which is 97.5% in seed-based classification and 94.21% in pixel-based classification, compared  ...  Moreover, we conducted a classification of seeds raised in heat stress and control environments using both traditional machine learning models and neural network models.  ...  Acknowledgments: The authors would like to thank the staff members of the University of Nebraska-Lincoln's Plant Pathology Greenhouse for their help in the data collection.  ... 
doi:10.3390/s21248184 pmid:34960287 pmcid:PMC8703337 fatcat:dwpkjfn27fclzkonuqaxmkgk7i

Deep Learning Sensor Fusion in Plant Water Stress Assessment: A Comprehensive Review

Mohd Hider Kamarudin, Zool Hilmi Ismail, Noor Baity Saidi
2021 Applied Sciences  
Basically, there are eight deep learning solutions compiled for the 3D-dimensional data and plant varieties challenge, including unbalanced data that occurred due to isohydric plants, and the effect of  ...  plant water stress identification.  ...  Convolutional Neural Network Convolutional Neural Network (CNN) is a type of feedforward deep learning model most commonly used for two-dimensional input data, such as an image.  ... 
doi:10.3390/app11041403 fatcat:bt53jh7idjct7lxxjfx247gza4
« Previous Showing results 1 — 15 out of 989 results