检索结果-内蒙古大学图书馆

2024 Multimedia University Engineering Conference, MECON 2024

作者： Khatoon, Amna Ullah, Asad Ahmed, Ishfaq Aslam, Ayesha Roslee, Mardeni Bin Ahmad, Shabeer School of Information Engineering Chang'An University Xi'an710064 China School of Information Engineering Xi'an Eurasia University Shaanxi Xi'an710065 China School of Marine Science Northwestern Polytechnical University Xi'an China Multimedia University University Faculty of Engineering Multimedia Cyberjaya63100 Malaysia School of Electronic Engineering Beijing University of Posts and Telecommunications China

ISBN: (纸本)9798331530747

Computer Vision (CV) analysis on constrained devices plays a crucial role in enhancing road safety and mitigating traffic congestion. This study demonstrates the integration of image segmentation and classification techniques into traffic monitoring systems on devices with limited computational power, such as dashboard cameras, smartphones, and IoT sensors. These technologies enable efficient real-time data collection and processing in densely populated urban areas, facilitating the immediate detection of irregular traffic patterns and potential collision points by leveraging edge computing and optimized algorithms. By implementing these analyses directly on constrained devices strategically placed within traffic systems, our approach provides timely responses to dynamic conditions, significantly reducing accident risks through early warnings and adaptive route suggestions. Our research also shows that CV systems can monitor driver behavior, detect attention or weariness, and give timely signals to improve driver response times. The data supports improving traffic signal timings, which might reduce vehicle idle times and improve traffic flow, thus increasing road safety and reducing environmental impact. The study provides a comprehensive methodology for implementing high-quality CV technologies in resource-constrained environments, highlighting advancements in edge computing and energy-efficient hardware. These advances underscore the importance of CV in building sustainable, resilient transport networks and its versatility in municipal and vehicle traffic management, enabling proactive measures to reduce accidents. © 2024 IEEE.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

Key Technologies on High-capacity Satellite imagery Compression 11

Key Technologies on High-capacity Satellite Imagery Compress...

引用

2023 IEEE 11th International Conference on Information, Communication and Networks, ICICN 2023

作者： Fang, Huoneng Han, Pengfei xiao, Huachao Xi'An Institute of Space Radio Technology Information Processing Technology Research Lab Xi'an China Xi'an China

ISBN: (纸本)9798350314014

With the continuous progress of science and technology, the accuracy of satellite remote sensing, detection and reconnaissance technologies is getting higher and higher, and the amount of data generated by them is also getting larger and larger. The amount of image data generated by high-resolution satellite imaging systems often reaches hundreds of Gb/s, which, coupled with the limited transmission bandwidth and storage space constraints, puts great pressure on data caching and transmission. The upper limit of transmission rate provided by traditional satellite data transmission methods has been difficult to meet the demand of inter-satellite and satellite-ground high-speed communication. To address this, a high-capacity satellite image data compression algorithm is proposed. Firstly, for the problem of redundancy of handover satellite image data, image fusion or stitching technology is used to extract valuable information from different images and synthesize high-quality images to reduce data redundancy. Secondly, to address the problem of repeated transmission of re-entry satellite data, multi-temporal data is analyzed to determine the change process of re-entry satellite image features and segment the change region in the image. In the re-entry process, only the information of the change region needs to be transmitted, avoiding multiple transmissions of duplicate information. Finally, to solve the problem of low compression efficiency of existing on-satellite compression algorithms, a new 'image-information-image' data compression strategy is explored to achieve high compression ratio and high fidelity of satellite image compression. In order to achieve high capacity compression and efficient transmission of satellite images with limited bandwidth and storage space, and to lay the foundation for fast and efficient intelligent services for all-day, all-weather observation of the Earth. © 2023 IEEE.

关键词： image compression

来源：评论

学校读者我要写书评

暂无评论

Ultra-high spatio-temporal resolution imaging with parallel acquisition-readout structured illumination microscopy(PAR-SIM)

引用

Light(Science & Applications) 2024年第6期13卷 1140-1158页

作者： xinzhu Xu Wenyi Wang Liang Qiao Yunzhe Fu xichuan Ge Kun Zhao Karl Zhanghao Meiling Guan xin Chen Meiqi Li Dayong Jin Peng xi Department of Biomedical Engineering College of Future TechnologyPeking UniversityBeijing100871China Wallace H.Coulter Dept.of Biomedical Engineering Georgia Institute of Technology and Emory UniversityAtlanta30332GAUSA National Biomedical Imaging Center Peking UniversityBeijing100871China Department of Biomedical Engineering College of EngineeringSouthern University of Science and TechnologyShenzhen518055GuangdongChina Airy Technologies Co. Ltd.Beijing100086China Eastern Institute for Advanced Study Eastern Institute of TechnologyNingboZhejiang315200China School of Life Science Peking UniversityBeijing100871China Institute for Biomedical Materials and Devices(IBMD) Faculty of ScienceUniversity of Technology SydneySydneyNSW2007Australia

Structured illumination microscopy(SIM)has emerged as a promising super-resolution fluorescence imaging technique,offering diverse configurations and computational strategies to mitigate phototoxicity during real-time imaging of biological *** efforts to enhance system frame rates have concentrated on processing algorithms,like rolling reconstruction or reduced frame reconstruction,or on investments in costly sCMOS cameras with accelerated row readout *** this article,we introduce an approach to elevate SIM frame rates and region of interest(ROI)coverage at the hardware level,without necessitating an upsurge in camera expenses or intricate ***,parallel acquisition-readout SIM(PAR-SIM)achieves the highest imaging speed for fluorescence imaging at currently available detector *** using the full frame-width of the detector through synchronizing the pattern generation and image exposure-readout process,we have achieved a fundamentally stupendous information spatial-temporal flux of 132.9 MPixels·s^(−1),9.6-fold that of the latest techniques,with the lowest SNR of−2.11 dB and 100 nm ***-SIM demonstrates its proficiency in successfully reconstructing diverse cellular organelles in dual excitations,even under conditions of low signal due to ultra-short exposure ***,mitochondrial dynamic tubulation and ongoing membrane fusion processes have been captured in live COS-7 cell,recorded with PAR-SIM at an impressive 408 *** posit that this novel parallel exposure-readout mode not only augments SIM pattern modulation for superior frame rates but also holds the potential to benefit other complex imaging systems with a strategic controlling approach.

关键词： hardware illumination resolution

来源：评论

学校读者我要写书评

暂无评论

Development of DNN Accelerator and Its Application in Avionics System 1

引用

10th Chinese Society of Aeronautics and Astronautics Youth Forum, 2022

作者： Yixuan, Zhao Feiyang, Liu Han, Gao Xi’an Aeronautics Computing Technique Research Institute AVIC Xi’an710068 China

ISBN: (数字)9789811976520

ISBN: (纸本)9789811976513

Future avionics systems must have high-performance intelligent data processing capability, especially for various intelligent application scenarios, such as image/radar target recognition, big data analysis, control and decision. Deep neural network (DNN) is a widely used AI algorithm due to its accurate fitness of nonlinear functions. It can introduce huge computation and memory costs as the increase of network depth. Recently, DNN hardware accelerator is proposed as a domain-specific accelerating platform. It can provide a flexible and reconfigurable operating environment for different algorithms, including convolutional neural network and recurrent neural network, with the advantages of high performance, low latency, and low power cost. The key technologies of DNN accelerators mainly include: parallel computing architecture, intelligent processing elements design, efficient memory structure, and dataflow scheduling optimization. This paper studies the design methodology of DNN accelerators, summarizes the key technologies, and discusses the prospective applications in avionics computing systems. This paper will provide some technique supports for the design of next-generation intelligent airborne computing systems. © 2023, Chinese Aeronautical Society.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhancement for Low-Contrast images with Dynamical Saturating Nonlinearity and Adaptive Stochastic Resonance 1st

Enhancement for Low-Contrast Images with Dynamical Saturatin...

引用

1st International Conference on Cognitive Computation and systems, ICCCS 2022

作者： Wang, Guodong Wang, xi Ma, Yumei Pan, Zhenkuan Zhang, Xuqun Yu, Jinpeng College of Computer Science Technology Qingdao University No. 308 Ningxia Road Qingdao266071 China Communication Dispatching Section Qingdao Emergency Center No. 120 Jinsong 3rd Road Qingdao266035 China College of Automation Qingdao University No. 308 Ningxia Road Qingdao266071 China

ISBN: (纸本)9789819927883

In recent years, image processing based on stochastic resonance has received more and more attention. In this paper, a dynamic saturated nonlinear stochastic pooling network model based on adaptive stochastic resonance is proposed. And it combines the dynamical saturating nonlinearity with the stochastic resonance, which can realize adaptive iteration and enhance low-contrast images. At the same time, a new method to solve the optimal parameters of nonlinear systems is proposed, which is used to solve the optimal parameter values of dynamical saturating nonlinearity in this paper. This new image enhancement method is tested on low-contrast images in the LOL dataset. By comparing the new model and some other image enhancement algorithms, it demonstrates that the results not only have good visual perception, but also obtain more excellent evaluation indicators value. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Adaptive algorithms

来源：评论

学校读者我要写书评

暂无评论

Adaptive HSV enhancement algorithm for high grayscale X-ray films

引用

Jisuanji Jicheng Zhizao xitong/Computer Integrated Manufacturing systems, CIMS 2025年第4期31卷 1237-1246页

作者： Li, Liangliang Wang, Peng Ren, Jia Lyu, Zhigang Luo, Cheng Li, xiaoyan School of Mechatronic Engineering Xi'an Technological University Xi'an710021 China School of Electronics and Information Engineering Xi'an Technological University Xi'an710021 China School of Information and Communication Engineering Hainan University Haikou570228 China

Aiming at the existing high grayscale image enhancement algorithms with poor robustness and insufficient adaptive capability, an enhancement algorithm capable of adaptively enhancing the processed high-bit images was proposed. To compensate for the brightness and darkness of the original film, an adaptive correction algorithm based on the grayscale prior was designed, and a new high-level HSV pseudo-color enhancement algorithm was presented. In addition, to ensure the balance of the enhanced image, an adaptive balance processing algorithm based on the brightness Channel was proposed. Finally, the enhancement effect was performed on the 12-bit X-ray negative image generated in the industrial welding manufacturing field. The experimental results showed that the proposed method could achieve the best enhancement effect on many different test samples without significantly increasing the complexity of the algorithm. © 2025 CIMS. All rights reserved.

关键词： Photointerpretation

来源：评论

学校读者我要写书评

暂无评论

Automatic Segmentation of Rectal Tumor on Magnetic Resonance images via a Deep Discriminative Model Consisting of Asymmetric U-Net and Convolutional Conditional Random Field based Post-processing 19

Automatic Segmentation of Rectal Tumor on Magnetic Resonance...

引用

19th International Conference on Natural Computation, Fuzzy systems and Knowledge Discovery, ICNC-FSKD 2023

作者： Li, xing Chen, Hao Ge, Sisi Xi'an University of Posts and Telecommunications School of Computer Science Xi'an710121 China Xi'an University of Posts and Telecommunications School of Humanities and Foreign Languages Xi'an710121 China

ISBN: (纸本)9798350304398

The process of manual delineating is frequently time-consuming and can result in low consistency. Our goal was to design a deep discriminative model (DDM) to mitigate these issues of magnetic resonance imaging (MRI) for rectal tumor lesion boundary delineation, and we proposed an asymmetric U-Net rectal tumor MR images segmentation algorithm based on multi-scale dilated convolutional inputs and convolutional conditional random fields (ConvCRFs). A multiscale convolutional input module was designed as a preprocessing step to enrich the extraction and input of global contextual semantic information;then, an asymmetric U-Net network combined with ConvCRFs was used to discriminatively fine-tune the segmentation results so as to enhance segmentation accuracy of tumors. To verify the feasibility of the algorithm, the experiments were conducted on a private dataset provided by a medical institution, and the experimental Dice coefficient reached 0.876 on T2WI images, 0.851 on DWI images, respectively, indicating the existence of an important clinical guidance value for rectal tumor image segmentation algorithms. © 2023 IEEE.

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

Point spread function modeling for coherent plane-wave compounding ultrasound imaging 15

Point spread function modeling for coherent plane-wave compo...

引用

15th International Conference on Information Optics and Photonics, CIOP 2024

作者： Zhou, Bowen Liu, Songde Tian, Chao School of Engineering Science University of Science and Technology of China Anhui Hefei230026 China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Anhui Hefei230088 China Anhui Province Key Laboratory of Biomedical Imaging and Intelligent Processing Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei230088 China

ISBN: (数字)9781510686175

ISBN: (纸本)9781510686168

Spatial resolution is a critical measure of the imaging performance of ultrasound imaging systems and is determined by various system factors. So far, no comprehensive studies have been reported to elucidate the impact of system factors on spatial resolution, which is generally defined as the full width at half maximum (FWHM) of the point spread function (PSF). This work aims to model the PSF of ultrasound imaging systems based on a linear transducer array and a coherent plane-wave compounding (CPWC) method and study how pulse-echo sequences, transducer parameters, and beamforming algorithms impact PSF. The Verasonics simulator and UltraSound ToolBox are used in numerical simulations for ultrasound signal generation and image reconstruction, respectively. Experiments are conducted to verify simulation results. Numerical and experimental results show that the value of axial resolution is negatively correlated with the center frequency of the ultrasonic transducer;the value of lateral resolution is positively correlated with the number of transmitted plane waves of the CPWC method and the element width of the ultrasonic transducer and is negatively correlated with the maximum steering angle of the CPWC method and the aperture size and center frequency of the ultrasonic transducer. Different beamforming algorithms show varying effects on spatial resolution and image quality. This work is expected to help predict and interpret the quality of ultrasound images produced by practical ultrasound imaging systems and is beneficial for the design and development of ultrasonic transducers, pulse-echo sequences, and beamforming algorithms for enhanced spatial resolution. © 2024 SPIE.

关键词： Optical transfer function

来源：评论

学校读者我要写书评

暂无评论

BIDIRECTIONAL FEATURE PYRAMID FOR FACE DETECTION IN DENSE CROWD SCENES 18

BIDIRECTIONAL FEATURE PYRAMID FOR FACE DETECTION IN DENSE CR...

引用

18th International Conference on Interfaces and Human Computer Interaction 2024, IHCI 2024, the 17th International Conference on Game and Entertainment Technologies 2024, GET 2024 and the 18th International Conference on Computer Graphics, Visualization, Computer Vision and image processing 2024, CGVCVIP 2024, Part of the 18th Multi Conference on Computer Science and Information systems 2024, MCCSIS 2024

作者： Wei, Yajuan Xu, Zhiejie Dai, Chuan Zhang, Wanju Xi’an University of Posts and Telecommunications Xi’an China University of Huddersfield United Kingdom

ISBN: (纸本)9789898704580

Face detection algorithms based on deep learning approaches have made significant advancements in the last decade. However, recognising faces in dense crowd scenes remains challenging, particularly in situations with overlapping and obscured small targets. This paper introduces a lightweight model based on YOLOv5s, which replaces the Pyramid Attention Network (PANet) in the original network neck with a bidirectional feature pyramid network (BiFPN) for effective handling of varied feature sizes. The original YOLOv5s framework has a high down sampling ratio that leads to difficulties in learning the features of small objects. The devised model has deployed an additional output head to prioritise small object detection. Based on ablation and benchmarking experiments, the original network's loss function is substituted with the SIoU Loss Function, which not only aggregates regression metrics between predicted and ground truth bounding boxes but also identifies their mismatched orientations, hence enhancing the model's detection accuracy of overlapping targets. Experiments conducted on the COCO128 and WiderFace benchmarks validate the superiority of the proposed model, resulting significant mAP accuracy improvement. © 2024 Interfaces and Human Computer Interaction. All Rights Reserved.

关键词： Bidirectional Feature Pyramid Face Detection SIoU WiderFace YOLOv5s

来源：评论

学校读者我要写书评

暂无评论

A NONLOCAL KRONECKER-BASIS-REPRESENTATION METHOD FOR LOW-DOSE CT SINOGRAM RECOVERY

引用

Journal of Computational Mathematics 2024年第4期42卷 1080-1108页

作者： Jian Lu Huaxuan Hu Yuru Zou Zhaosong Lu xiaoxia Liu Keke Zu Lin Li Shenzhen Key Laboratory of Advanced Machine Learning and Applications College of Mathematics and StatisticsShenzhen UniversityShenzhen 518060China National Center for Applied Mathematics Shenzhen(NCAMS) Shenzhen 518055China Department of Industrial and Systems Engineering University of Minnesota Twin CitiesMinneapolisMN55455USA Department of Applied Mathematics The Hong Kong Polytechnic UniversityHong Kong SARChina School of Electronic Engineering Xidian UniversityXi'an 710071China

Low-dose computed tomography(LDCT)contains the mixed noise of Poisson and Gaus-sian,which makes the image reconstruction a challenging *** order to describe the statistical characteristics of the mixed noise,we adopt the sinogram preprocessing as a stan-dard maximum a posteriori(MAP).Based on the fact that the sinogram of LDCT has non-local self-similarity property,it exhibits low-rank *** conventional way of solving the low-rank problem is implemented in matrix forms,and ignores the correlations among similar patch *** avoid this issue,we make use of a nonlocal Kronecker-Basis-Representation(KBR)method to depict the low-rank problem.A new denoising model,which consists of the sinogram preprocessing for data fidelity and the nonlocal KBR term,is developed in this *** proposed denoising model can better illustrate the generative mechanism of the mixed noise and the prior knowledge of the ***-merical results show that the proposed denoising model outperforms the state-of-the-art algorithms in terms of peak-signal-to-noise ratio(PSNR),feature similarity(FSIM),and normalized mean square error(NMSE).

关键词： Low-dose computed tomography Kronecker-basis-representation Low-rank imation.Noise-generating-mechanism

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：