671 Hits in 6.2 sec

Fall Prevention from Ladders Utilizing a Deep Learning-based Height Assessment Method

Sharjeel Anjum, Numan Khan, Rabia Khalid, Muhammad Khan, Dongmin Lee, Chansik Park
2022 IEEE Access  
Deep learning-based computer vision technology has the potential to capture a large amount of useful information from a digital image.  ...  Therefore, this paper presents a deep learning-based height assessment method using a single known value in an image to measure working height, monitor compliance to safety rules, and ensure worker safety  ...  All objects have been identified using an SSD-based deep learning model.  ... 
doi:10.1109/access.2022.3164676 fatcat:n2yhauah7jb2zimgmhdtfty6oq

A Systematic Review of Deep Learning for Silicon Wafer Defect Recognition

Uzma Batool, Mohd Ibrahim Shapiai, Muhammad Tahir, Zool H. Ismail, Noor Jannah Zakaria, Ahmed Elfakharany
2021 IEEE Access  
As deep learning has proved to be a perfect tool for image processing and pattern recognition, it is best suited to identify defect patterns in such images.  ...  For example, to represent 'deep learning', three search terms were identified as 'deep learning', 'deep network', and 'deep architecture'.  ... 
doi:10.1109/access.2021.3106171 fatcat:tjpdwnv4wzhi3fbaelpo7ewewy

Hilbert ID Considering Multi-window Feature Extraction for Transformer Deep Vision Fault Positioning

Xiaoxin Wu, Yigang He, Chenyuan Wang, Wenjie Wu, Chuankun Wang, Jiajun Duan
2020 IEEE Access  
Finally, it is used to conduct transfer learning on the convolutional neural network.  ...  INDEX TERMS Convolutional neural network (CNN), deep transfer learning (DTL), fault positioning, Hilbert visualization, multi-window feature extraction, power transformer, sweep frequency response analysis  ...  TRANSFER LEARNING AND POSITIONING RESULTS OF THE DEEP NETWORK At present, there are dozens of CNN image recognition models pre-trained for large image databases.  ... 
doi:10.1109/access.2020.2991844 fatcat:pifglumgcrhxreaklbjpbnwdea

A Deep Learning Framework for Detection of Targets in Thermal Images to Improve Firefighting [article]

Manish Bhattarai, Manel Martínez-Ramón
2020 arXiv   pre-print
To accomplish this, we use a trained deep Convolutional Neural Network (CNN) system to classify and identify objects of interest from thermal imagery in real time.  ...  We have explored state of the art machine/deep learning techniques to achieve this objective.  ...  Work [28] uses deep learning to detect people with a semi-supervised approach that takes advantage of a large quantity of nonlabeled images containing humans.  ... 
arXiv:1910.03617v3 fatcat:poq7sqifyvddnotnys523enffq

Integrating Deep Learning and Augmented Reality to Enhance Situational Awareness in Firefighting Environments [article]

Manish Bhattarai
2021 arXiv   pre-print
First, we used a deep Convolutional Neural Network (CNN) system to classify and identify objects of interest from thermal imagery in real-time.  ...  With these ad-hoc deep learning structures, we built the artificial intelligence system's backbone for firefighters' situational awareness.  ...  Objects are identified and tracked in images from the thermal imaging dataset using Faster R-CNN, and then instances of significant objects are masked and shaded using Mask R-CNN.  ... 
arXiv:2107.11043v2 fatcat:3jm5zawelze7dhx37luja7mly4

A Deep Learning Framework for Detection of Targets in Thermal Images to Improve Firefighting

Manish Bhattarai, Manel Martinez-Ramon
2020 IEEE Access  
To accomplish this, we use a trained deep Convolutional Neural Network (CNN) system to classify and identify objects of interest from thermal imagery in real-time.  ...  We have explored state-of-the-art machine/deep learning techniques to achieve this objective.  ...  thank the UNM Center for Advanced Research Computing, supported in part by the National Science Foundation, for providing the highperformance computing, large-scale storage, and visualization resources used  ... 
doi:10.1109/access.2020.2993767 fatcat:vjlnonzp5neopmozotpuazxzmq

Single- and multi-label classification of construction objects using deep transfer learning methods

Nipun D. Nath, Theodora Chaspari, Amir H. Behzadan
2019 Journal of Information Technology in Construction  
In this paper, we present deep learning (particularly, transfer learning) algorithms to annotate construction imagery from unconstrained real-world settings with high fidelity.  ...  While these images can be sorted using date and time tags, the task of searching an image dataset for specific visual content is not trivial.  ...  DEEP TRANSFER LEARNING In the following Subsections, the primary building blocks of the developed methodology, i.e., CNN and transfer learning, are briefly described.  ... 
doi:10.36680/j.itcon.2019.028 fatcat:thwa4uhggngrpjyi5ej2jat7ci

Ensemble Manifold Segmentation for Model Distillation and Semi-supervised Learning [article]

Dengxin Dai, Wen Li, Till Kroeger, Luc Van Gool
2018 arXiv   pre-print
However, learning modern CNNs with manifold structures has not raised due attention, mainly because of the inconvenience of imposing manifold structures onto the architecture of the CNNs.  ...  CNNs are trained on these ensembles under a multi-task learning framework to conform to the manifold. ManifoldNet can be trained with only the pseudo labels or together with task-specific labels.  ...  Seed Image Selection In each trial ∀t ∈ [1, ..., T ], we first identify a small set of seed images for the segmentation.  ... 
arXiv:1804.02201v1 fatcat:pdcy5tyoorf23kmnsa6blpmgty

Deep Learning for IoT Big Data and Streaming Analytics: A Survey [article]

Mehdi Mohammadi, Ala Al-Fuqaha, Sameh Sorour, Mohsen Guizani
2018 arXiv   pre-print
In this paper, we provide a thorough overview on using a class of advanced machine learning techniques, namely Deep Learning (DL), to facilitate the analytics and learning in the IoT domain.  ...  We start by articulating IoT data characteristics and identifying two major treatments for IoT data from a machine learning perspective, namely IoT big data analytics and IoT streaming data analytics.  ...  Learning with Deep Models: Transfer learning, which falls in the area of domain adaptation and multi-task learning, involves the adaptation and improvement of learning in a new domain by transferring  ... 
arXiv:1712.04301v2 fatcat:kr64lst37rhlfcpaxckgzlozvu

RID—Roof Information Dataset for Computer Vision-Based Photovoltaic Potential Assessment

Sebastian Krapf, Lukas Bogenrieder, Fabian Netzler, Georg Balke, Markus Lienkamp
2022 Remote Sensing  
deep learning datasets is a major barrier.  ...  While this paper's primary use case was roof information extraction for photovoltaic potential analysis, its implications can be transferred to other computer vision applications in remote sensing and  ...  Deep learning and CV applications have become a major research interest in the remote sensing community, but the availability of annotated images has been identified as one of the biggest challenges in  ... 
doi:10.3390/rs14102299 fatcat:t3zgj3abrvbz7l2f3sgmxnuuxm

Current Status and Future Directions of Deep Learning Applications for Safety Management in Construction

Hieu T. T. L. Pham, Mahdi Rafieizonooz, SangUk Han, Dong-Eun Lee
2021 Sustainability  
The application of deep learning (DL) for solving construction safety issues has achieved remarkable results in recent years that are superior to traditional methods.  ...  Overall, applying DL can resolve important safety challenges with high reliability; therein the CNN-based method and behaviors were the most applied directions with percentages of 75% and 67%, respectively  ...  ., (2019) [88] proposed deep CNN architectures to extract human skeletons from sensor images for evaluating the ladder-climbing posture of construction workers with an accuracy of 83%.  ... 
doi:10.3390/su132413579 fatcat:le26m4fe5bhvlposl3zsl2umwy

An Adaptive Structural Learning of Deep Belief Network for Image-based Crack Detection in Concrete Structures Using SDNET2018 [article]

Shin Kamada, Takumi Ichimura, Takashi Iwasaki
2021 arXiv   pre-print
We have developed an adaptive structural Deep Belief Network (Adaptive DBN) that finds an optimal network structure in a self-organizing manner during learning.  ...  The Adaptive RBM can find the appropriate number of hidden neurons during learning. The proposed method was applied to a concrete image benchmark data set SDNET2018 for crack detection.  ...  Classification Results Table II compares classification accuracy for SDNET test data with an existing CNN and the Adaptive DBN. The CNN is transfer learning based on AlexNet [11] .  ... 
arXiv:2110.12700v1 fatcat:v55gjfedrzelpomn3mt7cso26e

Towards Autonomous Driving Using Vision Based Intelligent Systems

Julkar Nine
2021 Embedded Selforganising Systems  
Most of the research made on vision based systems are focused on image processing and artificial intelligence systems like machine learning and deep learning.  ...  As the industry moves up the ladder of automation, safety features are coming more and more into the focus.  ...  and deep learning.  ... 
doi:10.14464/ess.v8i2.496 fatcat:wrhkg7xujnhjrmlmdor3ruarf4

Fast Predictive Maintenance in Industrial Internet of Things (IIoT) with Deep Learning (DL): A Review

Thomas Rieger, Stefanie Regier, Ingo Stengel, Nathan L. Clarke
2019 Collaborative European Research Conference  
Applying Deep Learning in the field of Industrial Internet of Things is a very active research field.  ...  Especially papers discussing the area of predictions and realtime processing with DL models are selected because of their potential use for PdM applications.  ...  The papers [1] to [5] , [7] , [13] , [14] and [19] to [23] are not part of Table 1 because they are used as reference regarding basic statements and explanations made in this paper.  ... 
dblp:conf/cerc/RiegerRSC19 fatcat:fem4wa3gqbf5dnbcjcgm5hor5a

Deep Learning in Bioinformatics [article]

Seonwoo Min, Byunghan Lee, Sungroh Yoon
2016 arXiv   pre-print
To provide a useful and comprehensive perspective, we categorize research both by the bioinformatics domain (i.e., omics, biomedical imaging, biomedical signal processing) and deep learning architecture  ...  Here, we review deep learning in bioinformatics, presenting examples of current research.  ...  [132] performed transfer learning using natural images from the ImageNet database [189] as pretraining data and fine-tuned with chest X-ray images to identify chest pathologies and to classify healthy  ... 
arXiv:1603.06430v5 fatcat:xvgg7misrrcsxmshty2emnujaq
« Previous Showing results 1 — 15 out of 671 results