A knowledge augmented image deblurring method with deep learning for in-situ quality detection of yarn production

Author(s):  
Chuqiao Xu ◽  
Junliang Wang ◽  
Jing Tao ◽  
Jie Zhang ◽  
Ray Y. Zhong
Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1031
Author(s):  
Joseba Gorospe ◽  
Rubén Mulero ◽  
Olatz Arbelaitz ◽  
Javier Muguerza ◽  
Miguel Ángel Antón

Deep learning techniques are being increasingly used in the scientific community as a consequence of the high computational capacity of current systems and the increase in the amount of data available as a result of the digitalisation of society in general and the industrial world in particular. In addition, the immersion of the field of edge computing, which focuses on integrating artificial intelligence as close as possible to the client, makes it possible to implement systems that act in real time without the need to transfer all of the data to centralised servers. The combination of these two concepts can lead to systems with the capacity to make correct decisions and act based on them immediately and in situ. Despite this, the low capacity of embedded systems greatly hinders this integration, so the possibility of being able to integrate them into a wide range of micro-controllers can be a great advantage. This paper contributes with the generation of an environment based on Mbed OS and TensorFlow Lite to be embedded in any general purpose embedded system, allowing the introduction of deep learning architectures. The experiments herein prove that the proposed system is competitive if compared to other commercial systems.


Sensors ◽  
2021 ◽  
Vol 21 (16) ◽  
pp. 5312
Author(s):  
Yanni Zhang ◽  
Yiming Liu ◽  
Qiang Li ◽  
Jianzhong Wang ◽  
Miao Qi ◽  
...  

Recently, deep learning-based image deblurring and deraining have been well developed. However, most of these methods fail to distill the useful features. What is more, exploiting the detailed image features in a deep learning framework always requires a mass of parameters, which inevitably makes the network suffer from a high computational burden. We propose a lightweight fusion distillation network (LFDN) for image deblurring and deraining to solve the above problems. The proposed LFDN is designed as an encoder–decoder architecture. In the encoding stage, the image feature is reduced to various small-scale spaces for multi-scale information extraction and fusion without much information loss. Then, a feature distillation normalization block is designed at the beginning of the decoding stage, which enables the network to distill and screen valuable channel information of feature maps continuously. Besides, an information fusion strategy between distillation modules and feature channels is also carried out by the attention mechanism. By fusing different information in the proposed approach, our network can achieve state-of-the-art image deblurring and deraining results with a smaller number of parameters and outperform the existing methods in model complexity.


2021 ◽  
Vol 13 (9) ◽  
pp. 1715
Author(s):  
Foyez Ahmed Prodhan ◽  
Jiahua Zhang ◽  
Fengmei Yao ◽  
Lamei Shi ◽  
Til Prasad Pangali Sharma ◽  
...  

Drought, a climate-related disaster impacting a variety of sectors, poses challenges for millions of people in South Asia. Accurate and complete drought information with a proper monitoring system is very important in revealing the complex nature of drought and its associated factors. In this regard, deep learning is a very promising approach for delineating the non-linear characteristics of drought factors. Therefore, this study aims to monitor drought by employing a deep learning approach with remote sensing data over South Asia from 2001–2016. We considered the precipitation, vegetation, and soil factors for the deep forwarded neural network (DFNN) as model input parameters. The study evaluated agricultural drought using the soil moisture deficit index (SMDI) as a response variable during three crop phenology stages. For a better comparison of deep learning model performance, we adopted two machine learning models, distributed random forest (DRF) and gradient boosting machine (GBM). Results show that the DFNN model outperformed the other two models for SMDI prediction. Furthermore, the results indicated that DFNN captured the drought pattern with high spatial variability across three penology stages. Additionally, the DFNN model showed good stability with its cross-validated data in the training phase, and the estimated SMDI had high correlation coefficient R2 ranges from 0.57~0.90, 0.52~0.94, and 0.49~0.82 during the start of the season (SOS), length of the season (LOS), and end of the season (EOS) respectively. The comparison between inter-annual variability of estimated SMDI and in-situ SPEI (standardized precipitation evapotranspiration index) showed that the estimated SMDI was almost similar to in-situ SPEI. The DFNN model provides comprehensive drought information by producing a consistent spatial distribution of SMDI which establishes the applicability of the DFNN model for drought monitoring.


Author(s):  
Veerraju Gampala ◽  
M. Sunil Kumar ◽  
C. Sushama ◽  
E. Fantin Irudaya Raj

2021 ◽  
Vol 11 (21) ◽  
pp. 10373
Author(s):  
Zichen Lu ◽  
Jiabin Jiang ◽  
Pin Cao ◽  
Yongying Yang

Due to the imperfect assembly process, the unqualified assembly of a missing gasket or lead seal will affect the product’s performance and possibly cause safety accidents. Machine vision method based on deep learning has been widely used in quality inspection. Semi-supervised learning (SSL) has been applied in training deep learning models to reduce the burden of data annotation. The dataset obtained from the production line tends to be class-imbalanced because the assemblies are qualified in most cases. However, most SSL methods suffer from lower performance in class-imbalanced datasets. Therefore, we propose a new semi-supervised algorithm that achieves high classification accuracy on the class-imbalanced assembly dataset with limited labeled data. Based on the mean teacher algorithm, the proposed algorithm uses certainty to select reliable teacher predictions for student learning dynamically, and loss functions are modified to improve the model’s robustness against class imbalance. Results show that when only 10% of the total data are labeled, and the imbalance rate is 5.3, the proposed method can improve the accuracy from 85.34% to 93.67% compared to supervised learning. When the amount of annotated data accounts for 20%, the accuracy can reach 98.83%.


2021 ◽  
Author(s):  
Patrick Aravena Pelizari ◽  
Christian Geiß ◽  
Elisabeth Schoepfer ◽  
Torsten Riedlinger ◽  
Paula Aguirre ◽  
...  

<p>Knowledge on the key structural characteristics of exposed buildings is crucial for accurate risk modeling with regard to natural hazards. In risk assessment this information is used to interlink exposed buildings with specific representative vulnerability models and is thus a prerequisite to implement sound risk models. The acquisition of such data by conventional building surveys is usually highly expensive in terms of labor, time, and money. Institutional data bases such as census or tax assessor data provide alternative sources of information. Such data, however, are often inappropriate, out-of-date, or not available. Today, the large-area availability of systematically collected street-level data due to global initiatives such as Google Street View, among others, offers new possibilities for the collection of <em>in-situ</em> data. At the same time, developments in machine learning and computer vision – in deep learning in particular – show high accuracy in solving perceptual tasks in the image domain. Thereon, we explore the potential of an automatized and thus efficient collection of vulnerability related building characteristics. To this end, we elaborated a workflow where the inference of building characteristics (e.g., the seismic building structural type, the material of the lateral load resisting system or the building height) from geotagged street-level imagery is tasked to a custom-trained Deep Convolutional Neural Network. The approach is applied and evaluated for the earthquake-prone Chilean capital Santiago de Chile. Experimental results are presented and show high accuracy in the derivation of addressed target variables. This emphasizes the potential of the proposed methodology to contribute to large-area collection of <em>in-situ</em> information on exposed buildings.</p>


Sensors ◽  
2020 ◽  
Vol 20 (13) ◽  
pp. 3724
Author(s):  
Quan Zhou ◽  
Mingyue Ding ◽  
Xuming Zhang

Image deblurring has been a challenging ill-posed problem in computer vision. Gaussian blur is a common model for image and signal degradation. The deep learning-based deblurring methods have attracted much attention due to their advantages over the traditional methods relying on hand-designed features. However, the existing deep learning-based deblurring techniques still cannot perform well in restoring the fine details and reconstructing the sharp edges. To address this issue, we have designed an effective end-to-end deep learning-based non-blind image deblurring algorithm. In the proposed method, a multi-stream bottom-top-bottom attention network (MBANet) with the encoder-to-decoder structure is designed to integrate low-level cues and high-level semantic information, which can facilitate extracting image features more effectively and improve the computational efficiency of the network. Moreover, the MBANet adopts a coarse-to-fine multi-scale strategy to process the input images to improve image deblurring performance. Furthermore, the global information-based fusion and reconstruction network is proposed to fuse multi-scale output maps to improve the global spatial information and recurrently refine the output deblurred image. The experiments were done on the public GoPro dataset and the realistic and dynamic scenes (REDS) dataset to evaluate the effectiveness and robustness of the proposed method. The experimental results show that the proposed method generally outperforms some traditional deburring methods and deep learning-based state-of-the-art deblurring methods such as scale-recurrent network (SRN) and denoising prior driven deep neural network (DPDNN) in terms of such quantitative indexes as peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) and human vision.


Sign in / Sign up

Export Citation Format

Share Document