Filters








10 Hits in 2.3 sec

Automatic Fabric Defect Detection Using Cascaded Mixed Feature Pyramid with Guided Localization

Wu, Zhang, Fang
2020 Sensors  
Generic object detection algorithms for natural images have been proven to have excellent performance. In this paper, fabric defect detection on optical image datasets is systematically studied.  ...  An improved two-stage defect detector is constructed for achieving better generalization.  ...  Thanks go to the Alibaba Group for the dataset of fabric defect images. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/s20030871 pmid:32041348 pmcid:PMC7039386 fatcat:bw6ncpas5vcubjgejal2sfnera

Transmission Line Object Detection Method Based on Label Adaptive Allocation

Lijuan Zhao, Chang'an Liu, Zheng Zhang, Hongquan Qu
2022 Mathematics  
Further improvement of detection accuracy lays a foundation for the realization of efficient real-time patrol inspection.  ...  Experimental results show that this method can eliminate the background interference in the GT (ground truth) as much as possible in object detection process, and improve the detection accuracy for objects  ...  Intelligent Small Object Detection for Digital Twin in Smart Manufacturing With Industrial Cyber-Physical Systems. IEEE Trans. Ind. Inform.2022, 18, 1377–1386.  ... 
doi:10.3390/math10122150 fatcat:ht5ecw3ftncandpdargqsxfaku

Surface Defect Detection of Nonburr Cylinder Liner Based on Improved YOLOv4

Yongbin Chen, Qinshen Fu, Guitang Wang, Sang-Bing Tsai
2021 Mobile Information Systems  
Based on the characteristics of the research object in this paper, the surface defect detection algorithm based on the improved YOLOv4 model is proposed, the model framework is constructed, and the data  ...  Aiming at the bottleneck of traditional visual inspection technology in appearance inspection, this paper proposes a surface defect detection algorithm based on deep learning to realize defect location  ...  In this paper, a method of product surface defect detection based on deep learning is proposed, which is improved on the basis of YOLOv4 to make it more suitable for industrial product surface defect detection  ... 
doi:10.1155/2021/9374465 fatcat:w2oqya7yb5grdjimwjd36wq7ri

Anchor-free object detection with mask attention

He Yang, Beibei Fan, Lingling Guo
2020 EURASIP Journal on Image and Video Processing  
This is difficult to detect for objects with a large size variation and dense and overlapping objects.  ...  This method based on key point detection simplifies the process of object detection and greatly simplifies the task of the convolution network.  ...  The authors express sincere appreciation to the anonymous referees for their helpful comments to improve the quality of the paper.  ... 
doi:10.1186/s13640-020-00517-3 fatcat:rmmpnd3iizgodnxszwvstnwpf4

Underwater Target Recognition Based on Improved YOLOv4 Neural Network

Lingyu Chen, Meicheng Zheng, Shunqiang Duan, Weilin Luo, Ligang Yao
2021 Electronics  
The YOLOv4 neural network is employed for underwater target recognition.  ...  Acknowledgments: The authors would like to thank the anonymous reviewers for their constructive suggestions, which comprehensively improved the quality of the paper.  ...  The authors also would like to thank the support from Fuzhou Ocean Research Institute and the support by Fujian Provincial College Marine Engineering Equipment Design and Manufacturing Engineering Research  ... 
doi:10.3390/electronics10141634 fatcat:6drjhgvt3rhcll44qntldmoena

Autonomous Incident Detection on Spectrometers Using Deep Convolutional Models

Xuelin Zhang, Donghao Zhang, Alexander Leye, Adrian Scott, Luke Visser, Zongyuan Ge, Paul Bonnington
2021 Sensors  
Furthermore, the non-rigid property increases the difficulty of the detection of these incidents, as such that existing deep-learning-based object detection frameworks are prone to fail for this task.  ...  In this work, we propose two frameworks for the detection task of these two incidents, which not only leverage the modern deep learning architectures but also integrate with expert knowledge of the problems  ...  For example, Erhu et al. [4] introduced an automatic defect detection system for web offset printing based on modern machine vision.  ... 
doi:10.3390/s22010160 pmid:35009704 pmcid:PMC8749529 fatcat:s5qxpptrkfhlrlmbcfzticjxzi

Smart Fashion: A Review of AI Applications in the Fashion Apparel Industry [article]

Seyed Omid Mohammadi, Ahmad Kalhor
2021 arXiv   pre-print
Furthermore, we provide a list of 86 public fashion datasets accompanied by a list of suggested applications and additional information for each.  ...  For each task, a time chart is provided to analyze the progress through the years.  ...  ., 95.8% Acc Fabric defect detection Lv [561] 2018 Cartoon-texture decomposition, DCNN Fabric defect detection X.  ... 
arXiv:2111.00905v2 fatcat:6n6d62lntjfu5pxmjzgi4mpv6i

Deep Learning Serves Traffic Safety Analysis: A Forward-looking Review [article]

Abolfazl Razi, Xiwen Chen, Huayu Li, Hao Wang, Brendan Russo, Yan Chen, Hongbin Yu
2022 arXiv   pre-print
a comparative analysis of the most successful conventional and DL-based algorithms proposed for each step.  ...  estimation, event analysis, modeling and anomaly detection.  ...  Junsuo Qu and Greg Leeming for his insightful comments.  ... 
arXiv:2203.10939v2 fatcat:oml733wvjfh3blne4h7kg5y3du

Surround-View Cameras based Holistic Visual Perception for Automated Driving [article]

Varun Ravi Kumar
2022 arXiv   pre-print
The human eye is one of the most sophisticated developments of evolution, but it still has defects.  ...  The dynamics changed from a primitive organism waiting for the food to come into contact for eating food being sought after by visual sensors.  ...  In addition to camera sensors, potential vulnerabilities of LiDAR-based autonomous driving detection systems are explored in [416] .  ... 
arXiv:2206.05542v1 fatcat:cdpn6afpvvf7hnsvry7cqbjq3u

Coping with Data Scarcity in Deep Learning and Applications for Social Good

MATTEO BUSTREO
2021
Convolutional Neural Networks and Deep Learning substantially contributed to the rise and the diffusion of AI-based solutions, creating the potential for many disruptive new businesses.  ...  Hereafter, I will introduce a hardware-based data augmentation approach, which leads to a considerable performance boost taking advantage of a novel illumination setup designed for this purpose.  ...  Additionally, some of them also have side outputs that act as edge priors [41] for defects detection.  ... 
doi:10.15167/bustreo-matteo_phd2021-03-05 fatcat:enj65oe6e5cbhfmvc4mnjzvlqm