检索结果-内蒙古大学图书馆

A Hardware Accelerator for Contour Tracing in Real-Time imaging

IEEE SENSORS JOURNAL 2024年第18期24卷 29156-29166页

作者： Gupta, Sonal Goel, Shubh Kumar, Ayush Kar, Subrat IIT Delhi Dept Elect Engn New Delhi 110016 India

Contour tracing is a critical technique in image analysis and computer vision, with applications in medical imaging, big data analytics, machine learning, and robotics. We introduce a novel hardware accelerator based on the adapted and segmented (AnS) vertex following (VF) and run-data-based-following (RDBF) families of fast contour tracing algorithms implemented on the Zynq-7000 field-programmable gate array (FPGA) platform. Our algorithmic implementation utilizing a mesh-interconnected multiprocessor architecture is at least 55x faster than the existing implementations. With input-output overheads, it is up to 12.5x faster. Our hardware accelerator for contour tracing is benchmarked on mesh-interconnected hardware, all three families of contour tracing algorithms, and a random image from the imagenet database. Our implementation is, thus, faster for FPGA, application-specific integrated circuit (ASIC), graphics processing unit (GPU), and supercomputer hardware in comparison to the central processing unit (CPU)-GPU collaborative approach and offers a better solution for those systems where the input-output overheads can be minimized, such as parallel processing arrays and mesh-connected sensor networks.

关键词： Accelerated contour tracing field-programmable gate array (FPGA) graphics processing unit (GPU) image processing multiprocessors parallel algorithms parallel processing array torus

来源：评论

学校读者我要写书评

暂无评论

algorithms to Speed up Contour Tracing in Real Time image processing systems

引用

IEEE ACCESS 2022年 10卷 127365-127376页

作者： Gupta, Sonal Kar, Subrat Indian Inst Technol Delhi IIT Delhi Dept Elect Engn New Delhi 110016 India

Contour tracing is an important pre-processing step in many image-processing applications such as feature recognition, biomedical imaging, security and surveillance. As single-processor architectures reach their performance limits, parallel processing architectures offer energy-efficient and high-performance solutions for real-time applications. parallel processing architectures are thus used for several real-time image processing applications. Among the several interconnection schemes available, Cayley graph-based interconnections offer easy routing and symmetric implementation capabilities. For parallel processing systems with a Cayley graph-based interconnection scheme, torus, we developed three accelerated algorithms corresponding to three existing families of contour tracing algorithms. We simulated these algorithms on a parallel processing framework to quantify the normalized speed-up possible in any torus-connected parallel processing system. We also compared our best-performing algorithm with the existing parallel processing implementations for Nvidia GPUs. We observed a speed-up of up to 468 times using our algorithms on a parallel processing architecture in comparison to the corresponding algorithm on a single processor architecture. We evaluated a speedup of 194 (and 47) compared to the existing parallel processing contour tracing implementation on Tesla K40c (and Quadro RTx 5000 GPU hardware, respectively). We observe that for torus-connected parallel processing architectures used for image processing, our algorithms can speed up contour tracing without any hardware modification.

关键词： parallel processing Computer architecture Hardware Graphics processing units image processing Random access memory image segmentation Accelerated contour tracing image processing parallel algorithms multiprocessors torus GPU

来源：评论

学校读者我要写书评

暂无评论

Efficient Polarization Demosaicking Via Low-Cost Edge-Aware and Inter-Channel Correlation

IEEE PHOTONICS JOURNAL

引用

IEEE PHOTONICS JOURNAL 2025年第1期17卷

作者： Liu, Guangsen Rao, Peng Chen, xin Li, Yao Jiang, Haixin Univ Chinese Acad Sci Beijing 100049 Peoples R China Chinese Acad Sci Key Lab Intelligent Infrared Percept Shanghai 200083 Peoples R China Chinese Acad Sci Shanghai Inst Tech Phys Shanghai 200083 Peoples R China

Efficient and high-fidelity polarization demosaicking is critical for the industrial applications of division of focal plane (DoFP) polarization imaging systems. However, existing methods often struggle to balance speed, accuracy, and complexity. This study introduces a novel polarization demosaicking algorithm that interpolates DoFP images within a three-stage basic demosaicking framework. Our method incorporates a DoFP low-cost edge-aware technique (DLE) to guide the interpolation process. Furthermore, inter-channel correlation is used to calibrate the initial estimate in the polarization difference domain. The proposed algorithm is available in both lightweight and full versions, designed for different application requirements. Experiments on simulated and real DoFP images demonstrated that both versions achieve the highestt interpolation accuracy and speed, respectively, among existing interpolation-based algorithms and significantly enhanced visuals. The lightweight and full versions efficiently processed a 1024 x 1024 image on an AMD Ryzen 5600x CPU in 0.1402s and 0.2693s, respectively. Additionally, as our methods operate within a 5 x 5 window, parallel acceleration on graphics processing units (GPUs) or field-programmable gate arrays (FPGAs) is highly feasible.

关键词： Interpolation image edge detection Correlation Channel estimation image reconstruction imaging Polarization Accuracy Real-time systems Estimation Polarization demosaicking polarization remote sensing division of focal plane (DoFP) interpolation edge-aware inter-channel correlation polarization image dataset

来源：评论

学校读者我要写书评

暂无评论

Optimized algorithms and Hardware Implementation of Median Filter for image processing

引用

CIRCUITS systems AND SIGNAL processing 2023年第9期42卷 5545-5558页

作者： Draz, H. H. Elashker, N. E. Mahmoud, Mervat M. A. Elect Res Inst Microelect Dept Cairo Egypt Cairo Univ Fac Engn Commun & Elect Dept Cairo Egypt British Univ Egypt Elect Engn Dept Cairo Egypt

image processing algorithms are essential for clarifying the image and improving the ability to recognize distinct characteristics of the image. The field of digital image processing is widespread in several research and technology applications. In many of these applications, the existence of impulsive noise in the obtained images is one of the most frequent problems. The median filter is a strong method to remove the impulsive noise;it effectively eliminates salt and pepper noise from the image. The main target of this paper is to investigate efficient median filter units to be connected to a general-purpose processor (GPP) for FPGA-based embedded systems. The paper exposes three novel techniques, two of them specially for median filtering techniques and the third one is used to get the maximum number of any 9 elements array. The proposed algorithms are inspired by the Median Of Median (MOM) algorithm. The first two techniques are tested for filtering 3 x 3 image windows and optimized for producing the expected result in high accuracy, short time, and reduced number of comparisons. The last technique is tested for a 9 elements array for extracting the maximum number in same high efficiency manner. Furthermore, the three proposed techniques are implemented leveraging the advantage of the parallel processing and the FPGA flexible resources to satisfy the real-time processing constraints. A comparison between the first two proposed filtering units and their counterparts in the literature is included. The comparison reveals the superiority of the first technique in terms of accuracy with fewer comparators than previously published techniques. Besides, the paper illustrates how the concept beyond the proposed techniques can be used to perform the maximum pooling for convolution neural networks.

关键词： Embedded systems FPGA image de-noising Median filter Median of medians

来源：评论

学校读者我要写书评

暂无评论

Enhancing 2-D Electrical Impedance Tomography Throughput With a Combined FPGA and Edge GPU-Based Hardware Accelerator

引用

IEEE SENSORS JOURNAL 2024年第20期24卷 32378-32388页

作者： Tiwari, Varun Kumar Meribout, Mahmoud Khalifa Univ Dept Elect & Comp Sci Abu Dhabi U Arab Emirates Dubai Elect & Water Author DEWA Res & Dev Ctr Dubai U Arab Emirates

This article addresses the demands of high-resolution 2-D electrical impedance tomography (EIT) systems, which necessitate an increased number of electrodes and finer mesh structures compared to their traditional counterparts. These requirements lead to higher data acquisition and computational loads. Given the inherently inverse and ill-posed nature of EIT, achieving a high signal-to-noise ratio (SNR) and precision hardware acceleration is essential. This article introduces a field-programmable gate array (FPGA)-based data acquisition system equipped with a tunable single-frequency current source, achieving acquisition speeds exceeding 500 and 2400 frames per second (fps) for 32 and 16 electrodes, respectively, with a 500-kHz excitation signal frequency. Data processing and reconstruction utilize the latest embedded graphics processing unit (GPU), specifically NVIDIA Jetson Orin, leveraging multiple CUDA cores for parallel high-speed 2-D image reconstruction. Comparative evaluations of five algorithms, namely, linear back projection (LBP), Tikhonov (TK) regularization, one-step Gauss-Newton (GN), Landweber (LW), and iterative Tikhonov (ITK), show a speed gain of at least fourfold compared to traditional implementations on standard computers. Experimental results reveal that the proposed system can achieve over 2500 fps throughput for a 16-electrode setup with approximately 8192 mesh elements. This advancement opens new possibilities for high-speed imaging and large-scale 3-D EIT applications.

关键词： Electrical impedance tomography image reconstruction Electrodes Field programmable gate arrays Throughput Voltage measurement Graphics processing units Data acquisition electrical tomography field-programmable gate array (FPGA) graphics processing unit (GPU) heterogeneous computing image reconstruction

来源：评论

学校读者我要写书评

暂无评论

image edge detection using butterfly-optimized adaptive resonance neural model

引用

Multimedia Tools and applications 2025年 1-24页

作者： Jansirani, M. Sumitra, P. Tamil Nadu Tiruchengode India

image edge detection is a crucial step in digital image processing that plays a pivotal role in various applications of computer vision. It involves identifying the abrupt changes in intensity or color that delineate boundaries between different regions in an image. Edge detection is used extensively in object recognition, image segmentation, medical imaging, autonomous vehicles, and robotics. Despite its importance, detecting edges accurately remains challenging due to noise, variations in image contrast, and complex image structures. In this research, we propose a novel approach to edge detection using the Butterfly-Optimized Adaptive Resonance Neural Model (BO-ARNM). BO-ARNM is an optimized neural network model that uses the parallel-learning capability of the Butterfly Optimization algorithm and the self-organizing properties of the Adaptive Resonance Theory (ART) neural network. Our approach uses the ART's vigilance parameter to increase the detection of edge pixels, enhancing overall edge detection accuracy. The performance of the BO-ARNM algorithm is compared with other previous edge detection algorithms such as SVM and CNN. The evaluation metrics used to assess the performance of the algorithm were accuracy, PSNR, SSIM, FAR and FRR. Experimental results on synthetic and real-world images demonstrate that the BO-ARNM achieves superior edge detection accuracy while also being more time-efficient than other compared methods. The proposed BO-ARNM approach to edge detection exhibits robustness against noise and variations in image contrast, making it suitable for real-world applications. The proposed BO-ARNM edge detection algorithm presents a novel contribution to the development of efficient and accurate edge detection systems that offer improved performance than other state-of-the-art methods. The results of this research have significant implications for the development of robust and efficient image processing methods and their applications in various fields.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Polarimetric imaging mobile phone application for large-area surface inspection 27

Polarimetric imaging mobile phone application for large-area...

引用

Conference on Novel Optical systems, Methods, and applications xxVii

作者： Martini, Carlo Hahlweg, Cornelius F. Bbw Hsch Wagner Regeny Str 21 D-12489 Berlin Germany

ISBN: (纸本)9781510679207;9781510679214

This paper is intended as a short follow-up to our last publication on the use of polarization-based imaging techniques and metrology applications. With their increasing resolution, memory availability and computing capacity, smartphones have become a common means for image and video documentation, geodetic and metrological data acquisition and similar applications in recent years. We are investigating concepts for smartphone-based polarimetric image acquisition and evaluation in field measurement campaigns. Technical applications are, for example, the mobile examination of larger areas with regard to contamination, damage to coatings, corrosion and the like, but also artistic photography, e.g. for paintings and sculptures. In addition to pure data acquisition, image pre-processing and analysis can be carried out in the field by means of mobile image processing applications. In the paper we discuss such concepts, their feasibility and robust extensions for smartphones that could lead to applications that actually take advantage of the smartphone's mobility.

关键词： polarization imaging mobile device surface inspection contamination detection dielectric layers cross- and parallel polarization

来源：评论

学校读者我要写书评

暂无评论

Smartphone Platform for Multisignal parallel Detection, processing, and Visualization in Fluorescence Biosensing

引用

IEEE SENSORS JOURNAL 2025年第10期25卷 18312-18322页

作者： Zhan, Weihe Geng, Qingfubo Wang, Baole Liu, Yian Geng, Zhaoxin Minzu Univ China Sch Informat Engn Beijing 100081 Peoples R China Minzu Univ China Key Lab Ethn Language Intelligent Anal & Secur Gov MOE Beijing 100081 Peoples R China

The fluorescence sensing method is widely used in biochemical sensing. With the development of hardware structures and software systems in smartphones, this method has gradually evolved from large laboratory equipment to smartphones. However, current methods mainly rely on single signal processing and provide few detection schemes, requiring greater flexibility and efficiency. To overcome these challenges, a new smartphone platform is proposed for signal processing in fluorescence biosensing experiments. The platform supports multisignal parallel processing and precise target localization by integrating multiple image preprocessing algorithms and a Hough transform-assisted grayscale distribution algorithm. In addition, the platform provides multiple methods for sampling and concentration curve fitting, ensuring the flexibility and verifiability of experimental design. The experimental results demonstrate that the localization algorithm achieves a hit rate of 99.48%, with an average deviation distance of only 3.595 pixels. The minimum mean square error (mse) between the average pixel value of the target signal area calculated by the platform and the actual pixel value is only 3.158, and the minimum mean absolute error (MAE) is only 1.360. Validation experiments further confirm that the sensitivity and accuracy of the platform meet the basic requirements for fluorescence sensing detection. This platform has broad applicability in biomedical engineering and point-of-care testing (POCT), improving portable diagnostic tools and paving the way for home biochemical sensing applications, such as early cancer screening and cardiovascular disease prevention.

关键词： Fluorescence Sensors Smart phones Gray-scale Location awareness Biosensors Distortion Noise image preprocessing Cameras Fluorescence biosensing image processing multisignal detection point-of-care testing (POCT) smartphone software design

来源：评论

学校读者我要写书评

暂无评论

Performance evaluation of spatial fuzzy C-means clustering algorithm on GPU for image segmentation

引用

MULTIMEDIA TOOLS AND applications 2023年第5期82卷 6787-6805页

作者： Ali, Noureddine Ait El Abbassi, Ahmed Bouattane, Omar Moulay Ismail Univ Meknes FST Errachidia Labo ERTTI Meknes Morocco Mohammedia Hassan II Univ Casablanca SSDIA Lab ENSET Casablanca Morocco

image processing by segmentation technique is an important phase in medical imaging such as MRI. Its objective is to analyze the different tissues in human body. In research area, Fuzzy set is one of the most successful techniques that guarantees a robust classification. Spatial FCM (SFCM);one of the fuzzy c-means variants;considers spatial information to deal with the noisy images. To reduce this iterative algorithm's execution time, a hard SIMD architecture has been planted named the Graphical processing Unit (GPU). In this work, a great contribution has been done to diagnose, confront and implement three different parallel implementations on GPU. A parallel implementations' extensive study of SFCM entitled PSFCM using 3 x 3 window is presented, and the experiments illustrate a significant decrease in terms of running time of this algorithm known by its high complexity. The experimental results indicate that the parallel version's execution time is about 9.46 times faster than the sequential implementation on image segmentation. This gain in terms of speed-up is achieved on the Nvidia GeForce GT 740 m GPU.

关键词： Fuzzy C-mean SFCM SIMD architecture Clustering GPU CUDA

来源：评论

学校读者我要写书评

暂无评论

Solving Quadratic systems With Full-Rank Matrices Using Sparse or Generative Priors

引用

IEEE TRANSACTIONS ON SIGNAL processing 2025年 73卷 477-492页

作者： Chen, Junren Ng, Michael K. Liu, Zhaoqiang Univ Hong Kong Dept Math Hong Kong 852 Peoples R China Hong Kong Baptist Univ Dept Math Hong Kong 852 Peoples R China Univ Elect Sci & Technol China Sch Comp Sci & Engn Chengdu 611731 Peoples R China

The problem of recovering a signal x is an element of R-n from a quadratic system{yi=x(T)A(ix), i=1,...,m} with full-rank matrices A(i) frequently arises in applications such a sun assigned distance geometry and sub-wavelength imaging. With i.i.d. standard Gaussian matrices A(i) , this paper addresses the high-dimensional case where m << n by incorporating prior knowledge of x. First, we consider a k-sparse x and introduce the thresholded Wirtinger flow (TWF) algorithm that does not require the sparsity level k. TWF comprises two steps: the spectral initialization that identifies a point sufficiently closetox (up to a sign flip) when m=O(k(2)logn),and the thresholded gradient descent which, when provided a good initialization, produces a sequence linearly converging to x with m=O(k log n) measurements. Second, we explore the generative prior, assuming that x lies in the range of an L-Lipschitz continuous generative model with k-dimensional inputs in an l(2)-ball of radius r. With an estimate correlated with the signal, we develop the projected gradient descent (PGD)algorithm that also comprises two steps: the projected power method that provides an initial vector with O(root k log(L)/m) l(2)-error given m=O( k log(Lnr))measurements, and the projected gradient descent that refines the l(2)-error to O(delta) at a geometric rate when m=O(k log Lrn/delta(2)). Experimental results corroborate our theoretical findings and show that: (i)our approach for the sparse case notably outperforms the existing provable algorithm sparse power factorization;(ii) leveraging the generative prior allows for precise image recovery in the MNIST dataset from a small number of quadratic measurements.

关键词： Sparse matrices Complexity theory Signal processing algorithms Vectors Phase measurement Compressed sensing Standards Particle measurements image segmentation image reconstruction Generative prior projected gradient descent projected power method quadratic system sparse prior wirtinger flow

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：