Deep learning methods for object detection in smart manufacturing: A survey

Ahmad, Hafiz Mughees; Rahimi, Afshin

doi:10.1016/j.jmsy.2022.06.011

Cited by 77 publications

(23 citation statements)

References 113 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the field of machine learning (ML) techniques, deep learning (DL) uses deep neural networks to deal with nonlinear problems involving big data to create predictive models. In recent years, compared to traditional ML, such as logistic regression, support vector machine, and other methods, DL has been faster and more accurate when performing under multidimensional data [ 50 ], for instance, image classification, segmentation, and localization.…”

Section: Methodsmentioning

confidence: 99%

Fast and Non-Destructive Quail Egg Freshness Assessment Using a Thermal Camera and Deep Learning-Based Air Cell Detection Algorithms for the Revalidation of the Expiration Date of Eggs

Nakaguchi

Ahamed

2022

Sensors

View full text Add to dashboard Cite

Freshness is one of the most important parameters for assessing the quality of avian eggs. Available techniques to estimate the degradation of albumen and enlargement of the air cell are either destructive or not suitable for high-throughput applications. The aim of this research was to introduce a new approach to evaluate the air cell of quail eggs for freshness assessment as a fast, noninvasive, and nondestructive method. A new methodology was proposed by using a thermal microcamera and deep learning object detection algorithms. To evaluate the new method, we stored 174 quail eggs and collected thermal images 30, 50, and 60 days after the labeled expiration date. These data, 522 in total, were expanded to 3610 by image augmentation techniques and then split into training and validation samples to produce models of the deep learning algorithms, referred to as “You Only Look Once” version 4 and 5 (YOLOv4 and YOLOv5) and EfficientDet. We tested the models in a new dataset composed of 60 eggs that were kept for 15 days after the labeled expiration label date. The validation of our methodology was performed by measuring the air cell area highlighted in the thermal images at the pixel level; thus, we compared the difference in the weight of eggs between the first day of storage and after 10 days under accelerated aging conditions. The statistical significance showed that the two variables (air cell and weight) were negatively correlated (R2 = 0.676). The deep learning models could predict freshness with F1 scores of 0.69, 0.89, and 0.86 for the YOLOv4, YOLOv5, and EfficientDet models, respectively. The new methodology for freshness assessment demonstrated that the best model reclassified 48.33% of our testing dataset. Therefore, those expired eggs could have their expiration date extended for another 2 weeks from the original label date.

show abstract

Section: Methodsmentioning

confidence: 99%

Fast and Non-Destructive Quail Egg Freshness Assessment Using a Thermal Camera and Deep Learning-Based Air Cell Detection Algorithms for the Revalidation of the Expiration Date of Eggs

Nakaguchi

Ahamed

2022

Sensors

View full text Add to dashboard Cite

show abstract

“…This manufacturing processes optimization through the use of predictive maintenance with the exploitation of industry 4.0 concepts such as artificial intelligence or internet of things, can be extrapolated to cybersecurity to increase manufacturing performance. As presented in [26], IoTs and connected objects are used in manufacturing processes to increase their performance with deep learning algorithms exploitation. Cyber-physical systems allow the integration of computational and physical processes, in which digital twins are used as a copy of the physical system to perform real-time optimization [27] [28].…”

Section: Industry 40 For the Company Performance Improvementmentioning

confidence: 99%

Enhancing Security for Legacy Factory Machines: A Continuous Key Renewal Algorithm for Securing Group of Machines

Ferry,

Dossou,

Ihowa

et al. 2023

JSEA

View full text Add to dashboard Cite

Companies are generally focused on how to improve their global performance. Concepts, methods and tools are regularly used to transform them. Key performance indicators are used to measure how performance is increased. Industry 4.0 concepts and sustainability expectations actually contribute to this performance improvement. Indeed, cybersecurity as one of these concepts is required to increase the company performance. Even if it is well-known and applied in companies through the protection of their information systems, progress is expected in research on how to ensure the security of data and factory processes in the manufacturing, as the number of cyberattacks towards industries is growing these last few years. This paper aims to increase the company performance and sustainability to enforce factory machines protection by creating private security network groups. But currently, most of the Programmable Logic Controller PLC protocols have not been securely designed. Thus, the creation of secure groups of machines by combining strong authentication, strong or lightweight ciphering, and data stream integrity is proposed. The security is enforced by a continuous key's renewal algorithm. An experiment on an industry's architecture has been led to validate the concepts of the proposition. The study is compared to existing OPC-UA and MACsec standards in terms of drawbacks and advantages. This work could be implemented in hardware for further performance improvement.

show abstract

“…The manufacturing industry is expected to increasingly adopt smart supervision technologies to increase labor efficiency and yield better productivity [1]. Towards this end, VIEXPAND project aims to build a real-time multiview video system, for AI-boosted smart supervision of industrial production processes.…”

Section: Introductionmentioning

confidence: 99%

Real-time industrial machine vision supervision using DPU-based edge devices

Ribeiro,

Figueiredo,

Assunção

et al. 2024

Fourth International Conference on Computer Vision and Information Technology (CVIT 2023)

View full text Add to dashboard Cite

In many modern industries the production lines are very fast-paced environments with repetitive and intricate motions where humans and machines often co-exist. Manufacturers are always looking for ways to minimize breakdowns and failures to improve productivity and efficiency. This work is an outcome of the collaborative R&D project VIEXPAND AI -a real-time AI-boosted solution that complements and expands human supervision with 24/7 'smart eyes' in a container glass industry application. The goal is to reduce production downtime, accidents, waste of raw materials and energy, as well as improve the industrial work conditions. To accomplish this, we propose an architecture where AI methods and techniques are implemented on the edge, to allow real-time supervision of multiple sites with centralized remote monitoring. FPGA System-on-Chip (SoC) devices are used to implement the video processing, multiplexing and encoding/decoding stages, as well as the AI engine used for object detection and classification. This heterogeneous technology allows us to distribute processing tasks over different hardware modules available on-chip (the multiprocessor unit, hard-cores and soft-cores), thus enabling real-time operation. This paper evaluates the use of YOLOX models in a Xilinx Zynq®UltraScale+ TM Multiprocessor System-on-Chip (MPSoC) Deep-Learning Processing System (DPU). It presents a study on the performance of the models when trained with different input sizes and custom datasets, obtained on the factory floor. The impact of different design choices on performance metrics is reported and discussed.

show abstract

Deep learning methods for object detection in smart manufacturing: A survey

Cited by 77 publications

References 113 publications

Fast and Non-Destructive Quail Egg Freshness Assessment Using a Thermal Camera and Deep Learning-Based Air Cell Detection Algorithms for the Revalidation of the Expiration Date of Eggs

Fast and Non-Destructive Quail Egg Freshness Assessment Using a Thermal Camera and Deep Learning-Based Air Cell Detection Algorithms for the Revalidation of the Expiration Date of Eggs

Enhancing Security for Legacy Factory Machines: A Continuous Key Renewal Algorithm for Securing Group of Machines

Real-time industrial machine vision supervision using DPU-based edge devices

Contact Info

Product

Resources

About