scholarly journals Quantification of the suitable rooftop area for solar panel installation from overhead imagery using Convolutional Neural Networks

2021 ◽  
Vol 2042 (1) ◽  
pp. 012002
Author(s):  
Roberto Castello ◽  
Alina Walch ◽  
Raphaël Attias ◽  
Riccardo Cadei ◽  
Shasha Jiang ◽  
...  
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Neural Networks ◽  
Computer Vision ◽  
State Of The Art ◽  
Solar Panel ◽  
Post Processing ◽  
Processing Step ◽  
Recent Method

Abstract The integration of solar technology in the built environment is realized mainly through rooftop-installed panels. In this paper, we leverage state-of-the-art Machine Learning and computer vision techniques applied on overhead images to provide a geo-localization of the available rooftop surfaces for solar panel installation. We further exploit a 3D building database to associate them to the corresponding roof geometries by means of a geospatial post-processing approach. The stand-alone Convolutional Neural Network used to segment suitable rooftop areas reaches an intersection over union of 64% and an accuracy of 93%, while a post-processing step using building database improves the rejection of false positives. The model is applied to a case study area in the canton of Geneva and the results are compared with another recent method used in the literature to derive the realistic available area.

scholarly journals ColNet: Embedding the Semantics of Web Tables for Column Type Prediction

2019 ◽  
Vol 33 ◽  
pp. 29-36 ◽  
Author(s):  
Jiaoyan Chen ◽  
Ernesto Jiménez-Ruiz ◽  
Ian Horrocks ◽  
Charles Sutton
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Neural Networks ◽  
State Of The Art ◽  
Column Type ◽  
Basic Understanding ◽  
Word Representation ◽  
Meta Information ◽  
A Cell ◽  
Multiple Cells

Automatically annotating column types with knowledge base (KB) concepts is a critical task to gain a basic understanding of web tables. Current methods rely on either table metadata like column name or entity correspondences of cells in the KB, and may fail to deal with growing web tables with incomplete meta information. In this paper we propose a neural network based column type annotation framework named ColNet which is able to integrate KB reasoning and lookup with machine learning and can automatically train Convolutional Neural Networks for prediction. The prediction model not only considers the contextual semantics within a cell using word representation, but also embeds the semantics of a column by learning locality features from multiple cells. The method is evaluated with DBPedia and two different web table datasets, T2Dv2 from the general Web and Limaye from Wikipedia pages, and achieves higher performance than the state-of-the-art approaches.

scholarly journals ThriftyNets: Convolutional Neural Networks with Tiny Parameter Budget

IoT ◽  
2021 ◽  
Vol 2 (2) ◽  
pp. 222-235
Author(s):  
Guillaume Coiffier ◽  
Ghouthi Boukli Hacene ◽  
Vincent Gripon
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Neural Networks ◽  
Convolutional Neural Network ◽  
Spatial Resolution ◽  
Network Architecture ◽  
Deep Neural Networks ◽  
State Of The Art ◽  
Feature Maps ◽  
Neural Network Architecture

Deep Neural Networks are state-of-the-art in a large number of challenges in machine learning. However, to reach the best performance they require a huge pool of parameters. Indeed, typical deep convolutional architectures present an increasing number of feature maps as we go deeper in the network, whereas spatial resolution of inputs is decreased through downsampling operations. This means that most of the parameters lay in the final layers, while a large portion of the computations are performed by a small fraction of the total parameters in the first layers. In an effort to use every parameter of a network at its maximum, we propose a new convolutional neural network architecture, called ThriftyNet. In ThriftyNet, only one convolutional layer is defined and used recursively, leading to a maximal parameter factorization. In complement, normalization, non-linearities, downsamplings and shortcut ensure sufficient expressivity of the model. ThriftyNet achieves competitive performance on a tiny parameters budget, exceeding 91% accuracy on CIFAR-10 with less than 40 k parameters in total, 74.3% on CIFAR-100 with less than 600 k parameters, and 67.1% On ImageNet ILSVRC 2012 with no more than 4.15 M parameters. However, the proposed method typically requires more computations than existing counterparts.

scholarly journals Identification of Baikal phytoplankton inferred from computer vision methods and machine learning

2021 ◽  
pp. 1143-1146
Author(s):  
A.V. Lysenko ◽  
◽  
◽  
M.S. Oznobikhin ◽  
E.A. Kireev ◽  
...  
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Neural Networks ◽  
Computer Vision ◽  
Object Recognition ◽  
Light Microscope ◽  
Optimal Size ◽  
Optimal Parameters ◽  
The Neural Network

Abstract. This study discusses the problem of phytoplankton classification using computer vision methods and convolutional neural networks. We created a system for automatic object recognition consisting of two parts: analysis and primary processing of phytoplankton images and development of the neural network based on the obtained information about the images. We developed software that can detect particular objects in images from a light microscope. We trained a convolutional neural network in transfer learning and determined optimal parameters of this neural network and the optimal size of using dataset. To increase accuracy for these groups of classes, we created three neural networks with the same structure. The obtained accuracy in the classification of Baikal phytoplankton by these neural networks was up to 80%.

scholarly journals Traffic Sign Classification Using Convolutional Neural Networks and Computer Vision

2021 ◽  
Vol 12 (3) ◽  
pp. 4244-4250
Author(s):  
Anuraag Velamati Et.al
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Neural Networks ◽  
Computer Vision ◽  
Deep Learning ◽  
Image Classification ◽  
Human Beings ◽  
Traffic Sign ◽  
The World ◽  
Traffic Sign Classification

The world is quickly and continuously advancing towards better technological advancements that will make life quite easier for us, human beings [22]. Humans are looking for more interactive and advanced ways to improve their learning. One such dream is making a machine think like a computer, which lead to innovations like AI and deep learning [25]. The world is running at a higher pace in the domain of AI, deep learning, robotics and machine learning Using this knowledge and technology, we could develop anything right now [36]. As a part of sub-domain, the introduction of Convolution Neural Networks made deep learning extensively strong in the domain of image classification and detection [1]..The research that we have conducted is one of its kind. Our research used Convolution Neural Network, TensorFlow and Keras.

Methods and technologies of machine learning in neural network for computer vision purposes

2021 ◽  
Author(s):  
A.A. Adamova ◽  
V.A. Zaykin ◽  
D.V. Gordeev
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Neural Networks ◽  
Computer Vision ◽  
Human Life ◽  
Learning Technologies ◽  
Convolutional Networks ◽  
Emergency Situations ◽  
Control Functions ◽  
The Moment

This article is devoted to an overview of the current state and development prospects in the field of machine learning technologies application in computer vision problems. The article discusses the types of architectures of deep convolutional networks used for image processing, discusses their application in the space industry and provides an analysis of the element base for the implementation of computer vision platforms. The aim was to research the machine learning methods in computer vision problems. Consideration of options for using neural networks in solving problems related to astronautics. The authors considered various methods and technologies of machine learning using both domestic and foreign devices. The study showed that at the moment there are several domestic companies that are engaged in the development of microprocessors, on which it is possible to implement a neural network and train it. Also, the prospects of machine learning in computer vision problems, their possibility and feasibility of application at the present time and in the near future were identified. The results of the work can be used to create various types of neural networks. Based on the above overview of neural processors, you can begin to design a neural network. The processing and dumping of incoming information, necessary for machine learning, is able to control functions, solve emergency situations and protect human life.

scholarly journals Development of an Optimised Dataset for Training a Deep Neural Network

2021 ◽  
Author(s):  
Callum Newman ◽  
Jon Petzing ◽  
Yee Mey Goh ◽  
Laura Justham
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Neural Networks ◽  
Computer Vision ◽  
Light Intensity ◽  
Test Performance ◽  
Deep Neural Network ◽  
Training Dataset ◽  
Multiple Factors

Artificial intelligence in computer vision has focused on improving test performance using techniques and architectures related to deep neural networks. However, improvements can also be achieved by carefully selecting the training dataset images. Environmental factors, such as light intensity, affect the image’s appearance and by choosing optimal factor levels the neural network’s performance can improve. However, little research into processes which help identify optimal levels is available. This research presents a case study which uses a process for developing an optimised dataset for training an object detection neural network. Images are gathered under controlled conditions using multiple factors to construct various training datasets. Each dataset is used to train the same neural network and the test performance compared to identify the optimal factors. The opportunity to use synthetic images is introduced, which has many advantages including creating images when real-world images are unavailable, and more easily controlled factors.

scholarly journals Conquering the CNN Over-Parameterization Dilemma: A Volterra Filtering Approach for Action Recognition

2020 ◽  
Vol 34 (07) ◽  
pp. 11948-11956
Author(s):  
Siddharth Roheda ◽  
Hamid Krim
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Neural Networks ◽  
Action Recognition ◽  
Network Architecture ◽  
Video Sequence ◽  
Spatial Information ◽  
State Of The Art ◽  
Parallel Implementation ◽  
Filtering Approach

The importance of inference in Machine Learning (ML) has led to an explosive number of different proposals in ML, and particularly in Deep Learning. In an attempt to reduce the complexity of Convolutional Neural Networks, we propose a Volterra filter-inspired Network architecture. This architecture introduces controlled non-linearities in the form of interactions between the delayed input samples of data. We propose a cascaded implementation of Volterra Filtering so as to significantly reduce the number of parameters required to carry out the same classification task as that of a conventional Neural Network. We demonstrate an efficient parallel implementation of this Volterra Neural Network (VNN), along with its remarkable performance while retaining a relatively simpler and potentially more tractable structure. Furthermore, we show a rather sophisticated adaptation of this network to nonlinearly fuse the RGB (spatial) information and the Optical Flow (temporal) information of a video sequence for action recognition. The proposed approach is evaluated on UCF-101 and HMDB-51 datasets for action recognition, and is shown to outperform state of the art CNN approaches.

scholarly journals MeshCut data augmentation for deep learning in computer vision

PLoS ONE ◽  
2020 ◽  
Vol 15 (12) ◽  
pp. e0243613
Author(s):  
Wei Jiang ◽  
Kai Zhang ◽  
Nan Wang ◽  
Miao Yu
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Computer Vision ◽  
Data Augmentation ◽  
State Of The Art ◽  
Network Models ◽  
Neural Network Models ◽  
Augmentation Strategies ◽  
Future Data ◽  
Learning In Computer Vision

To solve overfitting in machine learning, we propose a novel data augmentation method called MeshCut, which uses a mesh-like mask to segment the whole image to achieve more partial diversified information. In our experiments, this strategy outperformed the existing augmentation strategies and achieved state-of-the-art results in a variety of computer vision tasks. MeshCut is also an easy-to-implement strategy that can efficiently improve the performance of the existing convolutional neural network models by a good margin without careful hand-tuning. The performance of such a strategy can be further improved by incorporating it into other augmentation strategies, which can make MeshCut a promising baseline strategy for future data augmentation algorithms.

scholarly journals Comparative Study of Various Convolutional Neural Networks on Cifar-10

2020 ◽  
Vol 6 (12) ◽  
pp. 402-406
Author(s):  
Tushar Goyal
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Computer Vision ◽  
Comparative Study ◽  
Convolutional Neural Network ◽  
Convolutional Neural Networks ◽  
Image Recognition ◽  
State Of The Art ◽  
Fair Comparison ◽  
Develop State

Image recognition plays a foundational role in the field of computer vision and there has been extensive research to develop state-of-the-art techniques especially using Convolutional Neural Network (CNN). This paper aims to study some CNNs, heavily inspired by highly popular state-of-the-art CNNs, designed from scratch specifically for the Cifar-10 dataset and present a fair comparison between them.

scholarly journals ARCHITECTURAL HERITAGE RECOGNITION IN HISTORICAL FILM FOOTAGE USING NEURAL NETWORKS

2019 ◽  
Vol XLII-2/W15 ◽  
pp. 343-350 ◽  
Author(s):  
F. Condorelli ◽  
F. Rinaudo ◽  
F. Salvadore ◽  
S. Tagliaventi
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Neural Networks ◽  
Cultural Heritage ◽  
Architectural Heritage ◽  
Historical Film ◽  
Historical Archives ◽  
Human Effort ◽  
Over Time

<p><strong>Abstract.</strong> Researching historical archives for material suitable for photogrammetry is essential for the documentation and 3D reconstruction of Cultural Heritage, especially when this heritage has been lost or transformed over time. This research presents an innovative workflow which combines the photogrammetric procedure with Machine Learning for the processing of historical film footage. A Neural Network is trained to automatically detect frames in which architectural heritage appears. These frames are subsequently processed using photogrammetry and finally the resulting model is assessed for metric quality. This paper proposes best practises in training and validation on a Cultural Heritage asset. The algorithm was tested through a case study of the Tour Saint Jacques in Paris for which an entirely new dataset was created. The findings are encouraging both in terms of saving human effort and of improvement of the photogrammetric survey pipeline. This new tool can help researchers to better manage and organize historical information.</p>

Sign in / Sign up

Export Citation Format

Share Document