Filters








24 Hits in 6.7 sec

Application of a semantic segmentation convolutional neural network for accurate automatic detection and mapping of solar photovoltaic arrays in aerial imagery [article]

Joseph Camilo, Rui Wang, Leslie M. Collins, Kyle Bradbury, Jordan M. Malof
2018 arXiv   pre-print
In this work, we employ a state-of-the-art convolutional neural network architecture, called SegNet (Badrinarayanan et. al., 2015), to semantically segment (or map) PV arrays in aerial imagery.  ...  We consider the problem of automatically detecting small-scale solar photovoltaic arrays for behind-the-meter energy resource assessment in high resolution aerial imagery.  ...  We would like to thank the Duke University Energy Initiative for their support for this work.  ... 
arXiv:1801.04018v1 fatcat:26d42kh5erbqdjgx7t3jfxg3va

Combined Multi-Layer Feature Fusion and Edge Detection Method for Distributed Photovoltaic Power Station Identification

Yongshi Jie, Xianhua Ji, Anzhi Yue, Jingbo Chen, Yupeng Deng, Jing Chen, Yi Zhang
2020 Energies  
In this paper, a deep convolutional neural network was used to extract distributed photovoltaic power stations from high-resolution remote sensing images automatically, accurately, and efficiently.  ...  Further, to solve the problems of blurred edges in the segmentation results and that adjacent photovoltaic panels can easily be adhered, this work combines an edge detection network and a semantic segmentation  ...  Acknowledgments: The authors sincerely thank the editors and reviewers. We also sincerely thank the authors of the Duke California Solar Array data set.  ... 
doi:10.3390/en13246742 fatcat:bniu7o7fgzbidp4mx6dxftgsyi

Mapping solar array location, size, and capacity using deep learning and overhead imagery [article]

Jordan M. Malof, Boning Li, Bohao Huang, Kyle Bradbury, Artem Stretslov
2019 arXiv   pre-print
We propose a general framework for accurately and cheaply mapping individual PV arrays, and their capacities, over large geographic areas.  ...  At the core of this approach is a deep learning algorithm called SolarMapper - which we make publicly available - that can automatically map PV arrays in high resolution overhead imagery.  ...  ACKNOWLEDGEMENTS We thank the NVIDIA corporation for donating a GPU for this work, and the XSEDE and the Duke Compute Clusters for providing computing resources.  ... 
arXiv:1902.10895v1 fatcat:lsb5zpqu6bgp5jfbrp3ecsejwe

An Artificial Intelligence Dataset for Solar Energy Locations in India [article]

Anthony Ortiz, Dhaval Negandhi, Sagar R Mysorekar, Joseph Kiesecker, Shivaprakash K Nagaraju, Caleb Robinson, Priyal Bhatia, Aditi Khurana, Jane Wang, Felipe Oviedo, Juan Lavista Ferres
2022 arXiv   pre-print
Thus, with a mean accuracy of 92\% this method permits the identification of the factors driving land suitability for solar projects and will be of widespread interest for studies seeking to assess trade-offs  ...  To expedite development of solar energy, land use planners will need access to up-to-date and accurate geo-spatial information of PV infrastructure.  ...  To overcome this limitation, and generate semantic labels at scale we first pre-trained a convolutional neural network to cluster pixels from Sentinel 2 satellite imagery by color in an unsupervised manner  ... 
arXiv:2202.01340v1 fatcat:yzvikvzypvck3n47b75lwrlf24

A deep convolutional encoder-decoder architecture for autonomous fault detection of PV plants using multi-copters

Amirmohammad Moradi Sizkouhi, Mohammadreza Aghaei, Sayyed Majid Esmailifar
2021 Solar Energy  
As a crucial prerequisite, a data-set of aerial imageries of the PV strings affected by bird's drops were collected through several experimental flight by multi-copters in order to train an accurate fully  ...  Later on, extracted feature maps of images are imported into a decoder network to map the low resolution features to full resolution ones for pixel-wise segmentation.  ...  Section 3 presents a fault detection method in PV systems and addresses the method of preparing aerial imagery data for training an accurate FCN.  ... 
doi:10.1016/j.solener.2021.05.029 fatcat:6iv5rm5lkbch5onzziqi5jkhs4

DetEEktor: Mask-R CNN based neural network for energy plant identification on aerial photographs

Maximilian Schulz, Bilel Boughattas, Frank Wendel
2021 Energy and AI  
neural network.  ...  To address this, we developed the novel model 'DetEEktor', with which six different RE plant types can be simultaneously detected and characterized on aerial photographs by means of a Mask R convolutional  ...  Acknowledgments The authors gratefully acknowledge the support of the Ministry of the Environment, Climate Protection and the Energy Sector Baden-Württemberg and the support of their institute.  ... 
doi:10.1016/j.egyai.2021.100069 fatcat:ytptwzzhvbc2zh6xnadihnyyuu

Segmentation of cell-level anomalies in electroluminescence images of photovoltaic modules

Urtzi Otamendi, Iñigo Martinez, Marco Quartulli, Igor G. Olaizola, Elisabeth Viles, Werther Cambarau
2021 Solar Energy  
In this article, we propose an end-to-end deep learning pipeline that detects, locates and segments cell-level anomalies from entire photovoltaic modules via EL images.  ...  In the operation & maintenance (O&M) of photovoltaic (PV) plants, the early identification of failures has become crucial to maintain productivity and prolong components' life.  ...  Acknowledgment This publication resulted (in part) from the PROMISE (Advances in Photovoltaic Solar Energy Operation and Maintenance Research) project (KK2019/00088), which is financed by the ELKARTEK  ... 
doi:10.1016/j.solener.2021.03.058 fatcat:hypflsf6kffnfcngyky3ocuytm

Final Program

2020 2020 17th International Conference on Electrical Engineering, Computing Science and Automatic Control (CCE)  
Registration and Publication Chair MSc. Graciela Judith Esparza Azcoitia Signatory for the non-IEEE Sponsor M.A. Andrés Hernández Pineda Logistics manager MSc.  ...  model Self-driving through a Time-distributed Convolutional Recurrent Neural Network Convolutional neural network Deep Learning Networks for Vowel Speech Imagery Convolutional neural networks Analysis  ...  Efficient Joined Pyramid Network Applied to Semantic Segmentation for GPU Embedded System Abstract: Fully Convolutional Networks (FCN) are the best methods for semantic segmentation.  ... 
doi:10.1109/cce50788.2020.9299182 fatcat:dff7ylnwrzabdcv276gbwcgkji

Machine Learning for Sustainable Energy Systems

Priya L. Donti, J. Zico Kolter
2021 Annual Review Environment and Resources  
We first provide a taxonomy of machine learning paradigms and techniques, along with a discussion of their strengths and limitations.  ...  In recent years, machine learning has proven to be a powerful tool for deriving insights from data.  ...  ACKNOWLEDGMENTS The writing of this review was supported by a US Department of Energy Computational Science Graduate Fellowship (DE-FG02-97ER25308), the Center for Climate and Energy Decision Making through  ... 
doi:10.1146/annurev-environ-020220-061831 fatcat:pplsvl4zu5arngtbrov4uod74e

Technical program

2020 2020 17th International Conference on Electrical Engineering, Computing Science and Automatic Control (CCE)  
Structural characterization of the YBa2Cu3Oσ superconductor with phases [σ=6.87,6.89 and 6.9] obtained by solid state reaction ID 59  ...  Efficient Joined Pyramid Network Applied to Semantic Segmentation for GPU Embedded System Abstract: Fully Convolutional Networks (FCN) are the best methods for semantic segmentation.  ...  Therefore, this paper proposes two neural networks to classify vowels in speech imagery signals using SRP: a Convolutional Neural Network called sCNN and a Capsule Neural Network called sCapsNet.  ... 
doi:10.1109/cce50788.2020.9299132 fatcat:xkw6xl7vvnan7enewajqfqwo4q

2021 Index IEEE Transactions on Instrumentation and Measurement Vol. 70

2021 IEEE Transactions on Instrumentation and Measurement  
-that appeared in this periodical during 2021, and items from previous years that were commented upon or corrected in 2021.  ...  The primary entry includes the coauthors' names, the title of the paper or other item, and its location, specified by the publication abbreviation, year, and article number.  ...  ., +, TIM 2021 5008010 Semantic Segmentation With Light Field Imaging and Convolutional Neural Networks.  ... 
doi:10.1109/tim.2022.3156705 fatcat:dmqderzenrcopoyipv3v4vh4ry

Applications of Unmanned Aerial Systems (UASs) in Hydrology: A Review

Mercedes Vélez-Nicolás, Santiago García-López, Luis Barbero, Verónica Ruiz-Ortiz, Ángel Sánchez-Bellón
2021 Remote Sensing  
This paper provides a comprehensive review of 122 works on the applications of UASs in surface water and groundwater research with a purpose-oriented approach.  ...  The first aim of this review is to serve as a reference or introductory document for all researchers and water managers who are interested in embracing this novel technology.  ...  The authors also want to express their gratitude to the reviewers and in particular, to Ulf Mallast, whose encouraging and insightful comments have greatly contributed to improve this review.  ... 
doi:10.3390/rs13071359 fatcat:en3b3kcksbg7xjoksug2eqqylu

Thermal and Visual Tracking of Photovoltaic Plants for Autonomous UAV inspection [article]

Luca Morando, Carmine Tommaso Recchiuto, Jacopo Callà, Paolo Scuteri, Antonio Sgorbissa
2022 arXiv   pre-print
Since photovoltaic (PV) plants require periodic maintenance, using Unmanned Aerial Vehicles (UAV) for inspections can help reduce costs.  ...  The article proposes a novel approach using an autonomous UAV equipped with an RGB and a thermal camera for PV module tracking.  ...  In [24] , a Convolutional neural network (CNN) is used for defect recognition based on aerial images obtained from UAVs.  ... 
arXiv:2202.01003v2 fatcat:e5nokxgbifbk7mko74oakgt7mm

Program

2022 2022 International Conference on Decision Aid Sciences and Applications (DASA)  
A maximum of 92.90% classification accuracy is obtained using the features of IMF-4 with 10-fold cross-validation. The results conclude that the proposed method can detect AD patients efficiently.  ...  The present study aims to develop an automatic AD detection using Electroencephalogram (EEG) signal to alleviate these problems and to support neurologists.  ...  It can detect the damaged structures in time by integrating satellite imagery and Convolutional Neural Network (CNN) transfer learning.  ... 
doi:10.1109/dasa54658.2022.9765271 fatcat:ttqppf4j3navnaxe653mrzmezi

Program

2020 2020 IEEE Canadian Conference on Electrical and Computer Engineering (CCECE)  
A comparison of using this model with three different backbone convolutional neural networks is presented.  ...  This work also evaluates applicability of various Deep Convolutional Neural Networks (DCNNs) for SLAM. pp. 102-105 16:36 Implementation Simple Fitting System Using Image Recognition for Portable Device  ...  In this paper, a feasibility and cost analysis of a PV based solar water pumping system is conducted for Pakistani conditions.  ... 
doi:10.1109/ccece47787.2020.9255763 fatcat:mpf7smikpfc77bu73ciqstdagm
« Previous Showing results 1 — 15 out of 24 results