检索结果-内蒙古大学图书馆

real-time Large-Motion Deblurring for Gimbal-Based Imaging Systems

IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL processing 2024年第3期18卷 346-357页

作者： Varghese, Nisha Rajagopalan, A. N. Ansari, Zahir Ahmed Indian Inst Technol Madras Dept Elect Engn Chennai 600036 India IRDE DRDO Dehra Dun 248001 India

Robotic systems employed in tasks such as navigation, target tracking, security, and surveillance often use camera gimbal systems to enhance their monitoring and security capabilities. These camera gimbal systems undergo fast to-and-fro rotational motion to surveil the extended field of view (FOV). A high steering rate (rotation angle per second) of the gimbal is essential to revisit a given scene as fast as possible, which results in significant motion blur in the captured video frames. real-time motion deblurring is essential in surveillance robots since the subsequent image-processing tasks demand immediate availability of blur-free images. Existing deep learning (DL) based motion deblurring methods either lack real-time performance due to network complexity or suffer from poor deblurring quality for large motion blurs. In this work, we propose a Gyro-guided Network for real-time motion deblurring (GRNet) which makes effective use of existing prior information to improve deblurring without increasing the complexity of the network. The steering rate of the gimbal is taken as a prior for data generation. A contrastive learning scheme is introduced for the network to learn the amount of blur in an image by utilizing the knowledge of blur content in images during training. To the GRNet, a sharp reference image is additionally given as input to guide the deblurring process. The most relevant features from the reference image are selected using a cross-attention module. Our method works in real-time at 30 fps. As a first, we propose a Gimbal Yaw motion real-wOrld (GYRO) dataset of infrared (IR) as well as color images with significant motion blur along with the inertial measurements of camera rotation, captured by a gimbal-based imaging setup where the gimbal undergoes rotational yaw motion. Both qualitative and quantitative evaluations on our proposed GYRO dataset, demonstrate the practical utility of our method.

关键词： Robotic systems gimbal-based imaging real-time motion deblurring gyro-aided motion deblurring video surveillance reference-based motion deblurring contrastive learning Robotic systems gimbal-based imaging real-time motion deblurring gyro-aided motion deblurring video surveillance reference-based motion deblurring contrastive learning

来源：评论

学校读者我要写书评

暂无评论

WEEPING AND GNASHING OF TEETH: TEACHING deep learning IN image AND VIDEO processing CLASSES

WEEPING AND GNASHING OF TEETH: TEACHING DEEP LEARNING IN IMA...

引用

IEEE Southwest Symposium on image Analysis and Interpretation (SSIAI)

作者： Bovik, Al Univ Texas Austin Lab Image & Video Engn Austin TX 78712 USA

ISBN: (纸本)9781728157450

In this rather informal paper and talk I will discuss my own experiences, feelings and evolution as an image processing and Digital Video educator trying to navigate the deep learning revolution. I will discuss my own ups and downs of trying to deal with extremely rapid technological changes, and how I reacted to, and dealt with consequent dramatic changes in the relevance of the topics I've taught for three decades. I arranged the discussion in terms of the stages, over time, of my progression dealing with these sea changes.

关键词： image processing Education Digital Video Education deep learning Machine learning

来源：评论

学校读者我要写书评

暂无评论

Complementary spatial transformer network for real-time 3D object recognition

引用

JOURNAL OF real-time image processing 2023年第5期20卷 88页

作者： Krishna Kumar, K. P. Paul, Varghese APJ Abdul Kalam Technol Univ CET Campus Thiruvananthapuram 695016 Kerala India Rajagiri Sch Engn & Technol Dept Comp Sci & Engn Kochi 682039 Kerala India

Tiny deep learning Models offer many advantages in various applications. From the perspective of statistical machine learning theory the contributions of this paper is to complement the research advances and results obtained so far in real-time 3D object recognition. We propose a Tiny deep learning Model named Complementary Spatial Transformer Network (CSTN) for real-time 3D object recognition. It turns out that CSTN's working, and analysis are much simplified in a target space setting. We make algorithmic enhancements to perform CSTN computations faster and keep the learning part of CSTN in minimal size. Finally, we provide the experimental verifications of the results obtained in publicly available point cloud data sets ModelNet40 and ShapeNetCore with our model performing 1.65-2 times better in DPS (Detections/s) rate on GPU hardware for 3D object recognition, when compared to state-of-the-art networks. Complementary Spatial Transformer Network architecture requires only 10-35% of trainable parameters, when compared to state-of-the-art networks, making the network easier to deploy in edge AI devices.

关键词： 3D object recognition Spatial transformer network Spatial entropy Target space real-time tiny deep learning models

来源：评论

学校读者我要写书评

暂无评论

Motion training recognition based on thermal radiation imaging system and object detection: Human motion thermal image monitoring

引用

THERMAL SCIENCE AND ENGINEERING PROGRESS 2025年 60卷

作者： Zhao, Jie Liu, Chang Hou, Huisheng Minzu Univ China Sch Phys Educ Beijing 100081 Peoples R China

A human motion monitoring method based on thermal radiation image system and target detection technology is developed. The heat distribution of human body in motion is captured by thermal image, and the real-time recognition and analysis of human motion is realized by combining image processing and target detection algorithm. A complete set of thermal radiation optical image monitoring system is designed in this study. A highsensitivity thermal imaging camera is used to capture the thermal radiation images of the human body in the process of motion, and these images are then transmitted to the data acquisition unit for preliminary data collation and storage. The image processing module preprocesses the acquired thermal images, and the preprocessed images are fed into the object detection algorithm, which is based on the deep learning framework and can recognize and classify different movements of the human body. The thermal radiation image monitoring system can accurately capture the thermal image of the human body in different motion states, and identify the movement type of the athlete in real time through the target detection algorithm. The system has a strong ability to capture the details of actions, and can identify the beginning, progress and end stages of actions. Compared with traditional monitoring methods, the thermal radiation light image monitoring system has obvious advantages in terms of data accuracy and real-time performance. This method can not only provide high precision movement recognition, but also has the advantages of non-contact and real-time monitoring, which greatly improves the efficiency and accuracy of sports training monitoring.

关键词： Thermal radiation Optical image system Target detection Recognition of sports training Human movement Thermal image monitoring

来源：评论

学校读者我要写书评

暂无评论

A novel real-time quality control system for 3D printing: A deep learning approach using data efficient image transformers

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 273卷

作者： Singh, Manveer Sharma, Pradyun Sharma, Satish Kumar Singh, Jasmeet Thapar Inst Engn & Technol Dept Elect & Commun Engn Patiala India Thapar Inst Engn & Technol Dept Mech Engn Patiala India Thapar Inst Engn & Technol Dept Comp Sci & Engn Patiala India

Fused Deposition Modeling (FDM), an 3D printing technique being popular for rapidly fabricating polymeric prototypes as well as functional components with gradient structures such as scaffolds still faces significant hurdles in quality control and defect management. To overcome these limitations, a comprehensive approach has been proposed integrating advanced deep learning models with an Internet of Things (IoT) based quality control system. The research proposes a framework using Data-efficient image Transformer (DeiT) model, engineered to identify and classify three high-impact FDM defects: warping, layer delamination, and gaps in raster lines. The model has been fine-tuned on a curated dataset of original images, enhanced through pre-processing techniques. The DeiT model combined with a proposed Weighted Classification Accuracy (WCA) approach achieves an accuracy of 99.3%. Furthermore, the response time of the entire system is calculated to be 0.1121 s, providing real time monitoring and control. The research represents a significant step towards intelligent and optimized manufacturing systems in the context of Industry 4.0, addressing current challenges in FDM printing while paving the way for more autonomous and efficient 3D printing processes in the future.

关键词： deep learning Fused deposition modeling Vision transformers DeiT Quality control system Smart manufacturing IoT

来源：评论

学校读者我要写书评

暂无评论

Evaluating image DNA Techniques for Filtering Unauthorized Content in Large-Scale Social Platforms

引用

APPLIED SCIENCES-BASEL 2025年第8期15卷 4539-4539页

作者： Cho, Kyungwoon Bahn, Hyokyung Ewha Womans Univ Embedded Software Res Ctr Seoul 03760 South Korea Ewha Womans Univ Dept Comp Engn Seoul 03760 South Korea

Featured Application This work can be applied to enhance the robustness of image filtering systems in large-scale content platforms, specifically for detecting unauthorized images and their transformed versions, preventing the dissemination of manipulated *** image filtering systems have become essential in large-scale content platforms to prevent the dissemination of unauthorized data. While extensive research has focused on identifying images based on categories or visual similarity, the filtering problem addressed in this study presents distinct challenges. Specifically, it involves a predefined set of filtering images and requires real-time detection of whether a distributed image is derived from an unauthorized source. Although three major approaches-bitmap-based, image processing-based, and deep learning-based techniques-have been explored, no comprehensive comparison has been conducted. To bridge this gap, we formalize the concept of image equivalence and introduce performance metrics tailored for fair evaluation. Through extensive experiments, we derive the following key findings. First, bitmap-based methods are practically viable in real-world scenarios, offering reasonable detection rates and fast search speeds even under resource constraints. Second, despite their success in tasks such as image classification, deep learning-based methods underperform in our problem domain, highlighting the need for customized models and architectures. Third, image processing-based techniques demonstrate superior performance across all key metrics, including execution time and detection rates. These findings provide valuable insights into designing efficient image filtering systems for diverse content platforms, particularly for detecting unauthorized images and their transformations effectively.

关键词： image DNA fingerprinting unauthorized content image filtering system image equivalence

来源：评论

学校读者我要写书评

暂无评论

Innovative Quantum PlasmoVision-Based Imaging for real-time deepfake Detection

引用

PLASMONICS 2025年 1-17页

作者： Maheshwari, R. Uma Jayasudha, A. R. Pandey, Binay Kumar Pandey, Digvijay Hindusthan Inst Technol Dept Elect & Commun Engn Coimbatore India Hindusthan Coll Engn & Technol Dept Comp Applicat Coimbatore India Govind Ballabh Pant Univ Agr & Technol Pantnagar Coll Technol Dept Informat Technol Pantnagar Udham Singh Nagar Uttarakhand India Dept Tech Educ Uttar Pradesh Kanpur India

In recent years, the proliferation of deepfake images has posed a substantial threat to media credibility, security, and privacy. Contemporary detection techniques, predominantly reliant on deep learning algorithms, fail to identify the nuanced pixel-level discrepancies inherent in deepfake material. This study introduces PlasmoVision, an innovative quantum-enhanced plasmonic imaging technology that incorporates AI-driven deep learning for highly sensitive real-time deepfake detection. deepfakes alter digital images and videos to produce very persuasive fraudulent content, rendering traditional detection methods ineffective. Plasmonic surface resonance technology, in conjunction with quantum dots, has the capacity to capture intricate image features that can disclose such alterations. Integrating deep learning into this detection system improves the accuracy and velocity of analysis. The PlasmoVision technology employs quantum dot-enhanced plasmonic arrays to detect sub-pixel-level resonance shifts resulting from light interaction with the image surface. The optical signals are analyzed with a sophisticated convolutional neural network (CNN) that categorizes images according to the plasmonic resonance data. The AI model is trained on a varied dataset of genuine and deepfake photos, attaining an ideal equilibrium between detection sensitivity and speed. real-time picture analysis is accomplished by swift plasmonic scanning and AI-driven classification. The suggested device attained an accuracy rate of 98.6% in identifying deepfakes within a test dataset, exhibiting a false positive rate of 1.2% and a false negative rate of 0.5%. The quantum-enhanced plasmonic system identified pixel abnormalities with a sensitivity of up to 10 nm, markedly surpassing conventional deepfake detection technologies. PlasmoVision real-time analysis capacity decreased processing time by 35% relative to traditional approaches, rendering it exceptionally appropriate for extensive and real-ti

关键词： Quantum dots Plasmonic surface resonance deepfake detection AI-driven deep learning Convolutional neural networks image authentication real-time analysis Sub-pixel detection Media security Optical sensing

来源：评论

学校读者我要写书评

暂无评论

deep learning and Machine learning for Malaria Detection: Overview, Challenges and Future Directions

引用

INTERNATIONAL JOURNAL OF INFORMATION TECHNOLOGY & DECISION MAKING 2024年第5期23卷 1745-1776页

作者： Jdey, Imen Hcini, Hazala Ltifi, Hela Sidi Bouzid Univ Kairouan Fac Sci & Technol Kairouan Tunisia Univ Sfax Natl Engn Sch Sfax ENIS ReGIM Lab Res Grp Intelligent Machines LR11ES48 Sfax Tunisia

Public health initiatives must be made using evidence-based decision-making to have the greatest impact. Machine learning algorithms are created to gather, store, process, and analyze data to provide knowledge and guide decisions. A crucial part of any surveillance system is image analysis. The communities of computer vision and machine learning have become curious about it as of late. This study uses a variety of machine learning, and image processing approaches to detect and forecast malarial illness. In our research, we discovered the potential of deep learning techniques as innovative tools with a broader applicability for malaria detection, which benefits physicians by assisting in the diagnosis of the condition. We investigate the common confinements of deep learning for computer frameworks and organizing, including the requirement for data preparation, preparation overhead, real-time execution, and explaining ability, and uncover future inquiries about bearings focusing on these constraints.

关键词： Malaria diagnosis machine learning deep learning convolutional neural network hybrid algorithms

来源：评论

学校读者我要写书评

暂无评论

A lightweight deep learning method for real-time weld feature extraction under strong noise

引用

SIGNAL image AND VIDEO processing 2024年第11期18卷 8169-8184页

作者： Cheng, Jiaming Jin, Hui Southeast Univ Sch Civil Engn Jiangsu Key Lab Mech Anal Infrastructure & Adv Equ Nanjing Peoples R China

This paper proposes a lightweight deep learning (DL) framework for real-time accurate weld feature extraction from noisy images with light, smoke, or splash. Leveraging a two-dimensional human pose estimation paradigm, the framework follows a top-down architecture for accurate weld feature point localization. This study develops a semi-automatic annotation technique to dramatically reduce the annotation cost. Then, we design a lightweight yet faster You Only Look Once version 8 (YOLOv8) detector to rapidly detect the weld feature region in the presence of strong noise. To avoid reliance on high-resolution feature maps and achieve sub-pixel-level localization accuracy, a heatmap-free approach decomposes the feature point detection task into subtasks of horizontal and vertical coordinate classification. Comparison with mainstream DL-based weld recognition methods validates the superiority of the proposed method regarding real-time feature extraction accuracy and robustness.

关键词： Laser vision Pose estimation Weld feature extraction Coordinate classification YOLO

来源：评论

学校读者我要写书评

暂无评论

Efficient physics-based learned reconstruction methods for real-time 3D near-field MIMO radar imaging

引用

DIGITAL SIGNAL processing 2024年 144卷

作者： Manisali, Irfan Oral, Okyanus Oktem, Figen S. Middle East Tech Univ METU Dept Elect & Elect Engn TR-06800 Ankara Turkiye

Near-field multiple-input multiple-output (MIMO) radar imaging systems have recently gained significant attention. These systems generally reconstruct the three-dimensional (3D) complex-valued reflectivity distribution of the scene using sparse measurements. Consequently, imaging quality highly relies on the image reconstruction approach. Existing analytical reconstruction approaches suffer from either high computational cost or low image quality. In this paper, we develop novel non-iterative deep learning-based reconstruction methods for real-time near-field MIMO imaging. The goal is to achieve high image quality with low computational cost at compressive settings. The developed approaches have two stages. In the first approach, physics-based initial stage performs adjoint operation to back-project the measurements to the image-space, and deep neural network (DNN)-based second stage converts the 3D backprojected measurements to a magnitude-only reflectivity image. Since scene reflectivities often have random phase, DNN processes directly the magnitude of the adjoint result. As DNN, 3D U-Net is used to jointly exploit range and cross-range correlations. To comparatively evaluate the significance of exploiting physics in a learning-based approach, two additional approaches that replace the physics-based first stage with fully connected layers are also developed as purely learning based methods. The performance is also analyzed by changing the DNN architecture for the second stage to include complex-valued processing (instead of magnitude-only processing), 2D convolution kernels (instead of 3D), and ResNet architecture (instead of U-Net). Moreover, we develop a synthesizer to generate large-scale dataset for training the neural networks with 3D extended targets. We illustrate the performance through experimental data and extensive simulations. The results show the effectiveness of the developed physics based learned reconstruction approach compared to commonly used ap

关键词： Radar imaging Near-field microwave imaging deep learning 3D inverse imaging problems Sparse MIMO array

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：