检索结果-内蒙古大学图书馆

GMDIC: a digital image correlation measurement method based on global matching for large deformation displacement fields

引用

JOURNAL OF THE OPTICAL SOCIETY OF AMERICA A-OPTICS image SCIENCE AND VISION 2024年第11期41卷 2263-2276页

作者： Wang, Linlin Shao, Jing Wang, ZhuJun Gao, Qian Wang, ChuanYun Yan, Zhuo Li, ZhongYi Zhang, Tong ShenYang Aerosp Univ Coll Artificial Intelligence Shenyang 110136 Liaoning Peoples R China ShenYang Aerosp Univ Sch Automat Shenyang 110136 Liaoning Peoples R China

The digital image correlation method is a non-contact optical measurement method, which has the advantages of full-field measurement, simple operation, and high measurement accuracy. The traditional DIG method can accurately measure displacement and strain fields, but there are still many limitations. (i) In the measurement of large displacement deformations, the calculation accuracy of the displacement field and strain field needs to be improved due to the unreasonable setting of parameters such as subset size and step size. (ii) It is difficult to avoid under-matching or over-matching when reconstructing smooth displacement or strain fields. (iii) When processing large-scale image data, the computational complexity will be very high, resulting in slow processing speeds. In recent years, deep-learning-based DIG has shown promising capabilities in addressing the aforementioned issues. We propose a new, to the best of our knowledge, DIG method based on deep learning, which is designed for measuring displacement fields of speckle images in complex large deformations. The network combines the multi-head attention Swin-Transformer and the high-efficient channel attention module EGA and adds positional information to the features to enhance feature representation capabilities. To train the model, we constructed a displacement field dataset that conformed to the real situation and contained various types of speckle images and complex deformations. The measurement results indicate that our model achieves consistent displacement prediction accuracy with traditional DIG methods in practical experiments. Moreover, our model outperforms traditional DIG methods in cases of large displacement scenarios. (c) 2024 Optica Publishing Group. All rights, including for text and data mining (TDM), Artificial Intelligence (AI) training, and similar technologies, are reserved.

关键词： Computational imaging deep learning Imaging techniques Machine vision Neural networks Speckle imaging

来源：评论

学校读者我要写书评

暂无评论

Steel surface roughness parameter prediction from laser reflection data using machine learning models

引用

INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY 2024年第9-10期132卷 4645-4662页

作者： Milne, Alex Xie, Xianghua Swansea Univ Dept Comp Sci Swansea SA2 8PP Wales

Control of surface texture in strip steel is essential to meet customer requirements during galvanizing and temper rolling processes. Traditional methods rely on post-production stylus measurements, while on-line techniques offer non-contact and real-time measurements of the entire strip. However, ensuring accurate measurement is imperative for their effective utilization in the manufacturing pipeline. Moreover, accurate on-line measurements enable real-time adjustments of manufacturing processing parameters during production, ensuring consistent quality and the possibility of closed-loop control of the temper mill. In this study, we formulate the manufacturing issue into a time Series Extrinsic Regression problem and a Machine Vission problem and leverage state-of-the-art machine learning models to enhance the transformation of on-line measurements into a significantly more accurate Ra surface roughness metric. By comparing a selection of data-driven approaches, including both deep learning such as convolutional, recurrent, and transformer networks and non-deep learning methods such as Rocket and XGBoost, to the close-form transformation, we evaluate their potential using Root Mean Squared Error (RMSE) and correlation for improving surface texture control in temper strip steel manufacturing.

关键词： Machine learning On-line measurement Surface roughness Temper rolling time Series Extrinsic Regression (TSER)

来源：评论

学校读者我要写书评

暂无评论

Color image denoising: a hybrid approach for mixed Gaussian and impulsive noise

Color image denoising: a hybrid approach for mixed Gaussian ...

引用

Conference on real-time image processing and deep learning

作者： Smolka, Bogdan Kusnik, Damian Smolka, Milena Kawulok, Michal Cyganek, Boguslaw Silesian Tech Univ Gliwice Poland AGH Univ Sci & Technol Krakow Poland

ISBN: (纸本)9781510673878;9781510673861

This paper tackles the problem of mixed Gaussian and impulsive noise suppression in color images. The proposed method comprises two essential steps. Firstly, we detect impulsive noise through an approach based on the concept of digital path exploring the local pixel neighborhood. Each pixel is assigned a cost of a path connecting the boundary of a local processing window with its center. When the central pixel exhibits a high value of the path with lowest cost, it is identified as an impulse. To achieve this, we use a thresholding procedure for detecting corrupted pixels. Analyzing the distribution of minimum path costs, we employ the k-means technique to classify pixels into three distinct categories: those nearly undistorted, those corrupted by Gaussian noise, and those affected by impulsive noise. Subsequently, we employ the Laplace interpolation technique to restore the impulsive pixels - a fast and effective method yielding satisfactory denoising results. In the second step, we address the residual Gaussian noise using the Non-Local Means method, which selectively considers pixels from the local window that have not been flagged as impulsive. The experimental results confirm that our proposed hybrid method consistently yields superior outcomes compared to state-of-the-art denoising techniques. Moreover, its computational complexity remains low, rendering it suitable for real-time applications.

关键词： image enhancement color imaging mixed noise reduction impulsive noise

来源：评论

学校读者我要写书评

暂无评论

A lightweight real-time algorithm for plum harvesting detection in orchards under complex conditions

引用

SIGNAL image AND VIDEO processing 2025年第4期19卷 1-12页

作者： Zhang, Dongyan Chen, Nuo Mao, Siyu Wu, Chenxv Gu, Dandan Zhang, Lanxiang Univ Northeast Forestry Coll Comp & Control Engn Harbin 150040 Peoples R China

Accurate and efficient algorithms for detection are essential technologies utilized by robots for plum harvesting. To facilitate effective implementation on edge computing devices that have restricted processing capabilities, this research introduces a lightweight plum detection algorithm derived from YOLOv5s. Initially, the backbone network of the original architecture is substituted with the Revcol network. Subsequently, the feature space pyramid pooling (SPPF) is refined by integrating a Large Separable Kernel Attention (LSKA) mechanism, and the C3 module of the original model is improved through the use of Distributed Shift Convolutions (DSConv). Finally, a custom-designed lightweight detection head is employed to construct the lightweight plum detection model. The results show that the average mAP of the improved detection model is 96.3%, and the number of floating point operations (FLOPs) and parameters are reduced to 84.8% and 91.2% respectively. On edge computing devices, the inference speed reaches 44.64 frames per millisecond. This algorithm features high accuracy, lightweight design, and fast inference speed, providing valuable references for real-time object detection deployment of plum harvesting robots on edge computing devices.

关键词： deep learning Plum detection Target detection Smart picking real-time

来源：评论

学校读者我要写书评

暂无评论

RESEARCH ON real-time DETECTION OF LARGE-GRANULARITY GREEN PELLETS BASED ON YOLOV3 ALGORITHM

引用

METALURGIJA 2024年第3-4期63卷 329-332页

作者： Yang, Z. Univ Sci & Technol Liaoning Coll Appl Technol Anshan Liaoning Peoples R China

In order to realize the real-time detection of abnormal green pellet particle size. First, image data of large-granularity green balls at different disk pelletizing machine material disk speeds and different camera angles are collected on site;then LabelImg software is used to label the image data of large-granularity green balls;and finally based on the YOLOv3 algorithm under the Pytorch deep learning framework train and detect large-grained ball image data. The experimental results show that: under the condition of high rotation speed of the material disk of the disc pelletizing machine, the detection accuracy can reach more than 90,58 % for the image data of a single large-grained green ball, and the comprehensive detection rate can reach more than 85 %.

关键词： green pellets detection granularity deep learning YOLOv3

来源：评论

学校读者我要写书评

暂无评论

IoT Based Meat Freshness Classification Using deep learning

引用

IEEE ACCESS 2024年 12卷 196047-196069页

作者： Bhuiyan, Zarif Wasif Haider, Syed Ali Redwanul Haque, Adiba Uddin, Mohammad Rejwan Hasan, Mahady Independent Univ Bangladesh IUB Dept Comp Sci & Engn Dhaka 1229 Bangladesh

Meat quality and safety are critical concerns in the food industry, especially for products like beef and mutton, which are susceptible to spoilage and fraud. Traditional methods of assessing meat freshness and species classification, such as manual inspection, are often inefficient and prone to error. This paper introduces a novel Internet of Things (IoT) system that integrates gas sensors and advanced machine learning models, particularly deep learning, to address these issues effectively. The system combines image-based classification using a custom Convolutional Neural Network (CNN) with gas sensor data to provide a comprehensive, real-time solution for the classification of both beef and mutton in terms of species and freshness. The custom Convolutional Neural Network (CNN) was trained on a dataset comprising 9,928 images, 6,672 of which were utilized for meat freshness classification and 3,256 for meat species classification. The model achieved a classification accuracy of 99%, surpassing the performance of other models, including ResNet-50, Support Vector Machines (SVM), and k-Nearest Neighbors (k-NN). It is important to note that identical training and validation datasets were employed across all four models, ensuring a consistent and equitable comparison of their performance. The custom CNN showed a clear advantage in handling the complex image data, particularly in distinguishing between beef and mutton species as well as their freshness levels. The system incorporates three gas sensors-MQ135, MQ4, and MQ136-to detect gases such as ammonia (NH3), methane (CH4), and hydrogen sulfide (H2S), which are released during the spoilage of meat. These gas sensor readings are utilized specifically for the classification of meat freshness. The system provides real-time feedback via LED indicators: green for fresh meat, yellow for meat that is neither fresh nor fully rotten, and red for spoiled meat. The results of the classification, based on both image data and gas r

关键词： deep learning Accuracy Convolutional neural networks Internet of Things real-time systems Nearest neighbor methods Gas detectors Support vector machines Machine learning Biological system modeling Classification meat quality MQ135 gas sensor MQ136 gas sensor MQ4 methane natural gas sensor meat freshness IoT

来源：评论

学校读者我要写书评

暂无评论

deep learning-Driven Surveillance for Intrusion Identification using Proactive Intelligent Video Recognition 20

Deep Learning-Driven Surveillance for Intrusion Identificati...

引用

20th IEEE International Conference on Advanced Video and Signal-Based Surveillance (AVSS)

作者： Challagundla, Yagnesh Parvatham, Shreeya Dheera Mohanty, Sachi Nandan Ravindra, J. V. R. VIT AP Univ Sch Comp Sci & Engn SCOPE Amaravati India Vardhaman Coll Engn Dept Elect & Commun Engn Hyderabad Telangana India

ISBN: (纸本)9798350374292;9798350374285

In today's security-conscious environment, the need for effective real-time weapon detection systems is paramount, especially in public spaces and sensitive areas. The primary objective of this research is to create a real-time system for detecting weapons utilizing advanced deep learning techniques, namely VGG16 and Faster RCNN. The system's objective is to precisely detect and categorize weapons from photos and video data, offering prompt notifications and improving security procedures. The project's backdrop explores the difficulties encountered, including data gathering, precision standards, immediate processing, confidentiality, and deployment considerations. The system achieves excellent accuracy and real-time detection capabilities by building a comprehensive dataset manually and training the models using GPUs and modern technologies. Using Python as the programming language provides flexibility and simplicity in development, making use of Python's modules such as OpenCV for image processing and Keras for deep learning models. The Tkinter framework enables the creation of a graphical user interface (GUI) that supports various user operations, such as uploading datasets, generating models, processing images and videos, detecting weapons, and visualizing results. The methodology employs a systematic approach, encompassing stages such as data preprocessing, model building, training, testing, and result analysis. The combination of VGG16 and Faster RCNN algorithms demonstrates a compromise between speed and accuracy, with Faster RCNN exhibiting greater performance in real-time detection. The project aims to achieve several objectives, including the compilation of a dataset, training a model, evaluating accuracy, implementing real-time detection, and establishing alerting methods. The system's range encompasses a wide range of surroundings, lighting situations, and orientations, allowing it to be flexible and suitable for a variety of security applications. To sum

关键词： real-time weapon detection deep learning algorithms VGG16 Faster RCNN Speed vs accuracy tradeoff real-time detection Performance analysis

来源：评论

学校读者我要写书评

暂无评论

Joint Spatial and Frequency Domain learning for Lightweight Spectral image Demosaicing

引用

IEEE TRANSACTIONS ON image processing 2025年 34卷 1119-1132页

作者： Wu, Fangfang Huang, Tao Xu, Junwei Cao, Xun Dong, Weisheng Dong, Le Shi, Guangming Xidian Univ Sch Comp Sci & Technol Xian 710071 Peoples R China Xidian Univ Sch Artificial Intelligence Xian 710071 Peoples R China Yealink Xiamen 361009 Peoples R China Nanjing Univ Sch Elect Sci & Engn Nanjing 210093 Peoples R China

Conventional spectral image demosaicing algorithms rely on pixels' spatial or spectral correlations for reconstruction. Due to the missing data in the multispectral filter array (MSFA), the estimation of spatial or spectral correlations is inaccurate, leading to poor reconstruction results, and these algorithms are time-consuming. deep learning-based spectral image demosaicing methods directly learn the nonlinear mapping relationship between 2D spectral mosaic images and 3D multispectral images. However, these learning-based methods focused only on learning the mapping relationship in the spatial domain, but neglected valuable image information in the frequency domain, resulting in limited reconstruction quality. To address the above issues, this paper proposes a novel lightweight spectral image demosaicing method based on joint spatial and frequency domain information learning. First, a novel parameter-free spectral image initialization strategy based on the Fourier transform is proposed, which leads to better initialized spectral images and eases the difficulty of subsequent spectral image reconstruction. Furthermore, an efficient spatial-frequency transformer network is proposed, which jointly learns the spatial correlations and the frequency domain characteristics. Compared to existing learning-based spectral image demosaicing methods, the proposed method significantly reduces the number of model parameters and computational complexity. Extensive experiments on simulated and real-world data show that the proposed method notably outperforms existing spectral image demosaicing methods.

关键词： Frequency-domain analysis Imaging image reconstruction Transformers Feature extraction Correlation Fourier transforms Interpolation Three-dimensional displays Optimization Spectral image demosaicing multispectral filter array (MSFA) deep learning spatial domain frequency domain transformer

来源：评论

学校读者我要写书评

暂无评论

deep learning Approaches for Continuous Sign Language Recognition: A Comprehensive Review

引用

IEEE ACCESS 2025年 13卷 55524-55544页

作者： Khan, Asma Jin, Seyong Lee, Geon-Hee Arzu, Gul E. Dang, L. Minh Nguyen, Tan N. Choi, Woong Moon, Hyeonjoon Sejong Univ Dept Comp Sci & Engn Seoul 05006 South Korea Sejong Univ Dept Artificial Intelligence Seoul South Korea Duy Tan Univ Inst Res & Dev Da Nang 550000 Vietnam Duy Tan Univ Fac Informat Technol Da Nang 550000 Vietnam Sejong Univ Dept Informat & Commun Engn & Convergence Engn Int Seoul 05006 South Korea Sejong Univ Dept Architectural Engn Seoul 05006 South Korea Kangnam Univ Div ICT Convergence Engn Yongin 16979 South Korea

Sign language uses hand gestures as a visual mode of communication, along with body actions and facial expressions. Due to the increasing incidence of hearing deficiencies, the field of Continuous Sign Language Recognition (CSLR) has seen a considerable increase in research, which involves identifying consecutive signs in video streams without previous information of their sequential limitations. However, existing research often lacks a unified framework for integrating spatial, temporal, and alignment approaches, while critical challenges such as real-time processing, diverse datasets, and signer variability remain unresolved. This survey uniquely contributes by presenting a novel framework that integrates these dimensions into a unified taxonomy for CSLR systems. It critically analyzes numerous studies, organizing them into a comprehensive taxonomy covering aspects such as sign language, data collection, input method, gesture signals, identification methods, applied data collections, and comprehensive efficiency. The article further categorizes deep-learning CSLR models according to spatial, temporal, and alignment approaches, highlighting their benefits and drawbacks. Furthermore, it explores various research aspects, such as the challenges of CSLR, the significance of nonverbal elements in CSLR systems, and the gaps in the body of current research. By emphasizing the role of real-time processing and diverse datasets, this survey provides actionable insights for advancing CSLR systems in practical applications. This classification serves as a helpful tool for researchers developing and organizing cutting-edge CSLR methods. The study highlights the effectiveness of deep learning systems in capturing different sign language signals. On the other hand, several challenges remain, such as the need for diverse, naturalistic datasets, improved signer diversity, and real-time CSLR systems. Addressing these gaps will be essential for advancing CSLR's real-world applicatio

关键词： Sign language Feature extraction Assistive technologies Hands Accuracy deep learning Training Skeleton Hidden Markov models Visualization Continuous sign language recognition deep learning hand gesture recognition (HGR) computer vision

来源：评论

学校读者我要写书评

暂无评论

Scanning imaging through the scattering medium based on the guided filter assisted by a WTMM and NLM

引用

APPLIED OPTICS 2025年第10期64卷 2408-2418页

作者： Zhang, Yiyang Ding, Zhewen Li, Runze Meng, Xianglei Shi, Yan Zhan, Chunlian Zhao, Chunliu China Jiliang Univ Coll Opt & Elect Technol Hangzhou 310018 Zhejiang Peoples R China State Adm Market Regulat Key Lab Light Sensing & Image Metrol Hangzhou 310018 Zhejiang Peoples R China Zhejiang Prov Key Lab Optoelect Metrol & Precis In Hangzhou 310018 Zhejiang Peoples R China

In a scanning imaging system through a scattering medium, the quality of the imaging result is related to the energy distribution of the focusing point. In actual imaging, the energy of the focusing point cannot be perfectly concentrated. The scattering noise is always surrounded by the focusing point, which reduces the signal-to-noise ratio and results in poor image quality. To improve the quality of imaging, further processing of the imaging results is required, while most conventional image processing methods can only achieve one of the goals such as noise reduction, image smoothing, edge sharpening, or maintaining image integrity. In this paper, a scanning imaging system through the scattering medium based on an adaptive guided filter assisted by the wavelet transform modulus maximum (WTMM) and non-local mean (NLM) is proposed for the first time, to the best of our knowledge, which can make the imaging results simultaneously have the advantages of low noise, high contrast, and clear details. To verify the validity of the proposed method, a scanning imaging system through the scattering medium was setup. Transmissive imaging was performed at different positions from the focal plane. The experimental results show that the background noise is significantly restrained, single-pixel response and edge continuity are good, and details are clear with the proposed method. Compared with the traditional methods and the deep learning methods, the proposed method can improve the PSNR and SSIM by up to 10.68 dB, 0.75 and 5.34 dB, 0.72, respectively. Finally, the performance of the proposed method in high-noise environments, its application in the field of real-time imaging, and future improvements are discussed. The method proposed in this paper can effectively improve the quality of scanning imaging results through the scattering medium, which is expected to promote the application of this technology in endoscopic imaging and other fields. (c) 2025 Optica Publishing Group. A

关键词： deep learning Imaging systems Imaging techniques real time imaging Scattering media Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：