检索结果-内蒙古大学图书馆

The analysis of Iris image acquisition and real-time detection system using convolutional neural network

JOURNAL OF SUPERCOMPUTING 2024年第4期80卷 4500-4532页

作者： Liu, Yanru Xu, Jiali Yee, Austin Lin Inner Mongolia Univ Sci & Technol Baotou Med Coll Baotou 014040 Peoples R China Shanghai Univ Finance & Econ Sch Math Shanghai 200433 Peoples R China Med & Technol Co Ltd Chengdu 613000 Peoples R China

The purpose is to explore the effect of iris image acquisition and real-time detection systems based on Convolutional Neural Network (CNN) and improve the efficiency of iris real-time detection. Based on existing iris data acquisition and detection systems, this study uses the light field focusing algorithm to collect iris data in live, introduces CNN in deep learning (DL) algorithm, and designs an iris image acquisition and live detection system based on CNN. Afterward, Radial Basis Function (RBF)-Support Vector Machines (SVM) algorithm is used to classify iris feature information. Based on Field Programmable Gate Array (FPGA), a system for iris image acquisition, processing, and display is constructed. Finally, the performance of the constructed system and algorithm are analyzed through simulation experiments. The research results show that the proposed algorithm can automatically select the qualified iris images in live, significantly improve the recognition accuracy of the whole iris recognition system, and the average time of live quality evaluation for each frame image is less than 0.05 s. The focal point of the investigation involves the exploration of a CNN-based iris image acquisition and real-time detection system, with an emphasis on enhancing the efficiency of real-time iris detection. The innovation of this research lies in the integration of deep learning algorithms and light-field focusing techniques, applied to the reconstruction of a FPGA system. Further, the proposed algorithm is compared with Super-Resolution Using Very deep Convolutional Networks (VDSR), deeply Recursive Convolutional Network (DRCN), Residual Dense Network (RDN), and Bicubic. The comparison analysis suggests that the recognition accuracy of the proposed algorithm is the highest, close to 100%. Additionally, the proposed algorithm is compared with the image Quality Evaluation-based Algorithm (IQA) and the Feature Extraction-based Algorithm (FEA), showing that the proposed RBF-SVM

关键词： deep learning Convolutional neural network Iris image acquisition real-time detection Recurrent neural network Smart city

来源：评论

学校读者我要写书评

暂无评论

An Affordable Intelligent Navigation Backpack for the Visually Impaired: deep learning-Based Obstacle Detection and real-time Navigation with RGB-D Integration

引用

JOURNAL OF INTERNET TECHNOLOGY 2025年第2期26卷 265-271页

作者： Luo, Cheng-Li Xu, Hai Liu, Min Chu, Shu-Chuan Yango Univ Sch Informat Engn Mawei Peoples R China Nanjing Univ Informat Sci & Technol Sch Artificial Intelligence Nanjing Peoples R China

According to the World Health Organization (WHO), approximately 285 million people worldwide suffer from some form of visual impairment, including 39 million who are blind and an additional 246 million experiencing severe visual impairment. Existing navigation aids often fail to provide a user-centric perspective, relying on secondary judgment and leading to inconvenience. Hightech devices, such as smart glasses and robots, offer more effective solutions but are frequently cost-prohibitive. This study presents an affordable, first-person perspective intelligent navigation backpack for the visually impaired, utilizing deep learning. The system integrates RGB images and depth maps via alignment algorithms, extracts obstacle contours through binary image processing, and detects obstacles in real-time using the YOLO model. Experimental results demonstrate that the navigation depth camera significantly outperforms traditional ultrasonic and LiDAR sensors, achieving up to 98% measurement accuracy.

关键词： Assistive navigation system image recognition deep learning image morphology

来源：评论

学校读者我要写书评

暂无评论

Research on Water Gauge Recognition Based on deep learning and image processing 4

Research on Water Gauge Recognition Based on Deep Learning a...

引用

4th International Conference on E-Business, Information Management and Computer Science, EBIMCS 2021

作者： Tang, Yuehao Guo, Chong Changjiang Institute Of Technology School Of Water Conservancy And Electric Power Wuhan China Wuhan Business University Research Center For Chinese And Western Language And Culture Wuhan China

ISBN: (纸本)9781450395687

In order to improve the intellective level of water resources management, a real-time water level recognition method based on deep-learning algorithms and image-processing techniques is proposed in this paper. The recognition process is composed of four steps. Firstly, for the purpose of digit detection, YOLO-v3 model is deployed for extracting numbers from the water gauges. Then, the cropped number images are fed into the LSTM + CTC model as training samples so that digits can be recognized. In the third step, Hough transform are adopted to correct the tilt of water gauge in terms of the vertical edge feature. Morphological operation, associated with horizontal projection would position upper and lower edge of water gauge to recognize the scale lines correctly. Water level could be determined correspondingly. Model application shows that the recognition model has satisfying accuracy and efficiency, with potential being applied in practice. © 2021 ACM.

关键词： Water levels

来源：评论

学校读者我要写书评

暂无评论

Syflo: augmenting yolo for real-time health monitoring of electric assets in power transmission lines

引用

JOURNAL OF real-time image processing 2025年第1期22卷 1-15页

作者： Sankuri, Raja Sekhar Sristy, Nagesh Bhattu Karri, Sri Phani Krishna Natl Inst Technol Andhra Pradesh Dept Elect Engn Tadepalligudem India Natl Inst Technol Andhra Pradesh Dept Comp Sci & Engn Tadepalligudem India

Sustainable transmission of electrical energy to consumers across regions relies heavily on the integrity of power transmission lines and continuous monitoring of assets is crucial for maintaining system reliability. Unmanned aerial vehicles have revolutionized defect identification in real-time and accessibility, even in difficult-to-reach geographical landscapes, thereby improving image-based inspections. This work introduces semisupervised Yolo with focal loss function (SYFLo), a novel method that augments YOLO for real-time health monitoring of electric assets in power transmission lines. SYFLo integrates the focal loss function with semi-supervised learning to effectively address the lack of abundant labeled data, data imbalances and enhance detection accuracy. Additionally, it improves data generalizability across a wide range of images, ensuring robust performance despite varied image backgrounds. By leveraging YOLOv8, SYFLo significantly improves fault identification, achieving a detection accuracy of 96.5% and an FPS of 16.39. Experimental results demonstrate the impact of the proposed approach, highlighting its potential to enhance the reliability of power transmission line monitoring. These findings underscore the importance of integrating advanced deep learning techniques with innovative loss functions to address common challenges in real-time health monitoring systems.

关键词： deep learning Power grid inspection Defect detection Semi-supervised learning Focal loss function

来源：评论

学校读者我要写书评

暂无评论

Key Technologies for Machine Vision for Picking Robots:Review and Benchmarking

引用

Machine Intelligence Research 2025年第1期22卷 2-16页

作者： Xu Xiao Yiming Jiang Yaonan Wang College of Electrical and Information Engineering Hunan UniversityChangsha 410082China National Engineering Research Center for Robot Vision Perception and Control Technology Hunan UniversityChangsha 410082China

The increase in precision agriculture has promoted the development of picking robot technology,and the visual recognition system at its core is crucial for improving the level of agricultural *** paper reviews the progress of visual recognition tech-nology for picking robots,including image capture technology,target detection algorithms,spatial positioning strategies and scene *** article begins with a description of the basic structure and function of the vision system of the picking robot and em-phasizes the importance of achieving high-efficiency and high-accuracy recognition in the natural agricultural ***-sequently,various image processing techniques and vision algorithms,including color image analysis,three-dimensional depth percep-tion,and automatic object recognition technology that integrates machine learning and deep learning algorithms,were *** the same time,the paper also highlights the challenges of existing technologies in dynamic lighting,occlusion problems,fruit maturity di-versity,and real-time processing *** paper further discusses multisensor information fusion technology and discusses methods for combining visual recognition with a robot control system to improve the accuracy and working rate of *** the same time,this paper also introduces innovative research,such as the application of convolutional neural networks(CNNs)for accurate fruit detection and the development of event-based vision systems to improve the response speed of the *** the end of this paper,the future development of visual recognition technology for picking robots is predicted,and new research trends are proposed,including the refinement of algorithms,hardware innovation,and the adaptability of technology to different agricultural *** purpose of this paper is to provide a comprehensive analysis of visual recognition technology for researchers and practitioners in the field of agricul-tural rob

关键词： Picking robot visual system perception technology image processing machine learning deep learning.

来源：评论

学校读者我要写书评

暂无评论

deep learning image burst stacking to reconstruct high-resolution ground-based solar observations

引用

ASTRONOMY & ASTROPHYSICS 2025年 693卷

作者： Schirninger, C. Jarolim, R. Veronig, A. M. Kuckein, C. Karl Franzens Univ Graz Inst Phys Univ Pl 5 A-8010 Graz Austria Natl Ctr Atmospher Res High Altitude Observ 3080 Ctr Green Dr Boulder CO USA Karl Franzens Univ Graz Kanzelhohe Observ Solar & Environm Res Graz Austria Inst Astrofis Canarias IAC Via Lactea S-N E-38205 San Cristobal la Laguna Tenerife Spain Univ La Laguna Dept Astrofis E-38206 San Cristobal la Laguna Tenerife Spain Max Planck Inst Sonnensystemforsch Justus Von Liebig Weg 3 D-37077 Gottingen Germany

Context. Large aperture ground-based solar telescopes allow the solar atmosphere to be resolved in unprecedented detail. However, ground-based observations are inherently limited due to Earth's turbulent atmosphere, requiring image correction techniques. Aims. Recent post-image reconstruction techniques are based on using information from bursts of short-exposure images. Shortcomings of such approaches are the limited success, in case of stronger atmospheric seeing conditions, and computational demand. real-time post-image reconstruction is of high importance to enabling automatic processing pipelines and accelerating scientific research. In an attempt to overcome these limitations, we provide a deep learning approach to reconstruct an original image burst into a single high-resolution high-quality image in real time. Methods. We present a novel deep learning tool for image burst reconstruction based on image stacking methods. Here, an image burst of 100 short-exposure observations is reconstructed to obtain a single high-resolution image. Our approach builds on unpaired image-to-image translation. We trained our neural network with seeing degraded image bursts and used speckle reconstructed observations as a reference. With the unpaired image translation, we aim to achieve a better generalization and increased robustness in case of increased image degradations. Results. We demonstrate that our deep learning model has the ability to effectively reconstruct an image burst in real time with an average of 0.5 s of processing time while providing similar results to standard reconstruction methods. We evaluated the results on an independent test set consisting of high- and low-quality speckle reconstructions. Our method shows an improved robustness in terms of perceptual quality, especially when speckle reconstruction methods show artifacts. An evaluation with a varying number of images per burst demonstrates that our method makes efficient use of the combined image info

关键词： atmospheric effects techniques: image processing telescopes Sun: atmosphere Sun: photosphere

来源：评论

学校读者我要写书评

暂无评论

A deep learning enhanced inverse scattering framework for microwave imaging of piece-wise homogeneous targets

引用

INVERSE PROBLEMS 2024年第4期40卷 045001-045001页

作者： Ruiz, Alvaro Yago Stevanovic, Maria Nikolic Cavagnaro, Marta Crocco, Lorenzo Inst Electromagnet Sensing Environm Natl Res Council Italy CNR IREA Naples Italy Singidunum Univ Belgrade Serbia Sapienza Univ Rome DIET Rome Italy

In this paper, we present a framework for the solution of inverse scattering problems that integrates traditional imaging methods and deep learning. The goal is to image piece-wise homogeneous targets and it is pursued in three steps. First, raw-data are processed via orthogonality sampling method to obtain a qualitative image of the targets. Then, such an image is fed into a U-Net. In order to take advantage of the implicitly sparse nature of the information to be retrieved, the network is trained to retrieve a map of the spatial gradient of the unknown contrast. Finally, such an augmented shape is turned into a map of the unknown permittivity by means of a simple post-processing. The framework is computationally effective, since all processing steps are performed in real-time. To provide an example of the achievable performance, Fresnel experimental data have been used as a validation.

关键词： inverse scattering microwave imaging deep learning qualitative methods orthogonality sampling method

来源：评论

学校读者我要写书评

暂无评论

Efficient NPU-GPU scheduling for real-time deep learning inference on mobile devices

引用

JOURNAL OF real-time image processing 2025年第2期22卷 1-13页

作者： Yu, Chengwu Wang, Meng Chen, Shan Wang, Wanqi Fang, Weiwei Chen, Yanming Xiong, Neal N. Beijing Jiaotong Univ Sch Comp Sci & Technol Beijing 100044 Peoples R China Hubei Engn Res Ctr Intelligent Detect & Identifica Wuhan 430205 Hubei Peoples R China Anhui Univ Sch Comp Sci & Technol Hefei 230601 Anhui Peoples R China Sul Ross State Univ Dept Comp Sci & Math Alpine TX 79830 USA

As the need for on-device artificial intelligence (AI) has increased in recent years, mobile devices tend to be equipped with multiple heterogeneous processors, including CPU, GPU, and Neural processing Unit (NPU). While NPUs can offer low-cost and real-time AI processing capabilities for deep Neural Network (DNN) inference, its limited resources often lead to a trade-off between performance and accuracy, potentially resulting in a non-trivial accuracy drop. To address this problem, we propose a new NPU-GPU Scheduling (NGS) framework for DNN-based video analytics. The main challenge lies in determining when and how to execute inference on the NPU/GPU to satisfy the performance objectives. To make more precise scheduling decisions, we first propose a new image complexity assessment model to replace the existing normalized edge density metric. Then, we formulate the scheduling problem with the objective of maximizing inference accuracy under the given latency constraint, and introduce an adaptive solution based on dynamic programming to determine which frames should be processed on the GPU and when to exit from inference for each of them. Extensive experiments conducted on a real mobile device show that our NGS framework substantially outperforms other solutions, and achieves a close-to-oracle performance.

关键词： Edge computing DNN inference Heterogeneous processors Task scheduling Dynamic Programming

来源：评论

学校读者我要写书评

暂无评论

SoN: Selective Optimal Network for smartphone-based indoor localization in real-time

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 272卷

作者： Lee, Kyungsu Lee, Haeyun Hwang, Jae Youn Jeonbuk Natl Univ Dept Comp Sci & Artificial Intelligence Jeonju 54896 South Korea Korea Univ Technol & Educ Sch Comp Sci & Engn Cheonan 31253 South Korea Daegu Gyeongbuk Inst Sci & Technol DGIST Dept Elect Engn & Comp Sci Interdisciplinary Studies Artificial Intelligence Daegu 42988 South Korea

deep learning-based scene recognition algorithms have been developed for real-time application in indoor localization systems. However, owing to the slow calculation time resulting from the deep structure of convolutional neural networks, deep learning-based algorithms have limitations in the usage of real-time applications, despite their high accuracy in classification tasks. To significantly reduce the computation time of these algorithms and slightly improve their accuracy, we thus propose a path-selective deep learning network, denoted as Selective Optimal Network (SoN). The SoN selectively uses the depth-variable networks depending on anew indicator, denoted as the classification-complexity of a source image. The SoN reduces the prediction time by selecting optimal depth for the baseline networks corresponding to the input samples. The network was evaluated using two public datasets and two custom datasets for indoor localization and scene classification, respectively. The experimental results indicated that, compared to other deep learning models, the SoN exhibited improved accuracy and enhanced the processing speed by up to 78.59%. Additionally, the SoN was applied to a smartphone-based indoor positioning system in real-time. The results indicated that the SoN shows excellent performance for rapid and accurate classification in real-time applications of indoor localization systems.

关键词： deep learning Semi-supervised learning Efficient learning Scene recognition Indoor localization

来源：评论

学校读者我要写书评

暂无评论

Leveraging active perception for real-time high-resolution pose estimation

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 271卷

作者： Manousis, Theodoros Eleftheriadis, Emmanouil Passalis, Nikolaos Tefas, Anastasios Aristotle Univ Thessaloniki Dept Informat AIIA Lab Computat Intelligence & Deep Learning Grp Thessaloniki Greece Aristotle Univ Thessaloniki Dept Chem Engn Thessaloniki Greece

The evolution of computational intelligence, especially deep learning, has revolutionized problem-solving approaches, with human pose estimation emerging as a popular challenge that relies on RGB images captured by cameras. Advancements in hardware have made high-resolution cameras more accessible and affordable, enabling their use across a variety of applications. Although deep learning models could theoretically benefit from the increased details provided by these high-resolution images, there is a trade-off between the resolution increase and inference time. To address this challenge, an efficient approach to high-resolution image analysis has been developed for pose estimation. This method selectively focuses on key regions within an image, allowing the pose estimation model itself to identify areas of interest without requiring a separate person detection model. By leveraging features from the model's backbone, it actively identifies important regions, enhancing both efficiency and accuracy. Moreover, a sequential processing approach refines the model's focus in stages, enabling it to retain high-resolution details that might be lost with traditional downscaling. This model-agnostic technique is adaptable across various pose estimation models, offering a flexible and computationally efficient solution.

关键词： Pose estimation High resolution Active perception deep learning

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：