检索结果-内蒙古大学图书馆

3rd International conference on image processing and Media Computing (ICIPMC)

作者： Bai, Jiayuan Wei, Bing Zhong, Jin Anhui Univ Sch Elect Informat Engn Hefei Peoples R China Hefei Normal Univ Sch Comp Sci Hefei Peoples R China

ISBN: (纸本)9798350386660;9798350386677

Heart rate (HR) is a vital parameter for assessing human health. Currently, image photoplethysmography (iPPG) has received widespread attention for its advantages in non-contact HR detection applications. However, iPPG has poor anti-interference ability, and its application scenarios still have significant limitations. In this paper, we focused on the office environment as a typical application scenario and conducted research on human HR monitoring under different light and noise interference conditions. Experimental data was collected from facial videos of the subjects captured by normal camera. Eulerian video magnification (EVM) algorithm was used to enhance the subtle differences in pixel intensity of facial skin. The extraction of blood volume pulse (BVP) signal was realized based on the combination of improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) and second-order blind identification (SOBI) in this study. Further, the residual high-frequency noise and harmonic components in the BVP source signal were filtered out using the single value decomposition (SVD) to improve the estimation accuracy of HR. The experimental results showed that the method is highly accurate in monitoring HR of subjects under different light and noise interference environments. Also, the robustness of the method is excellent, and the further expansion of the research has a great application prospect.

关键词： image photoplethysmography (iPPG) Eulerian video magnification (EVM) improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) second-order blind identification (SOBI)

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of Railway Track Foreign Object image processing Platform Based on GUI 9

Design and Implementation of Railway Track Foreign Object Im...

引用

9th International conference on Computer and Communication Systems (ICCCS)

作者： Lei, Xiqian Xu, Tiantian Bao, Liqun Li, Ying LanZhou Inst Technol Elect Informat Engn Coll Lanzhou Peoples R China

ISBN: (纸本)9798350350227;9798350350210

Railway plays a leading role in the field of transportation in China and shoulders the important mission of driving the development of national economy. In view of the changeable environment of railway track, the processing algorithm with good real-time performance, strong robustness and high accuracy in the process of foreign body detection is the key to achieve rapid detection. In order to facilitate researchers to compare and analyze the effects of relevant algorithms intuitively and quickly, the GUI visual interactive interface was used to design the simulation platform for track foreign object image processing, conceive the design process, build the overall design of the platform, and divide the static foreign object detection and moving target detection modules according to the realization functions. In the static foreign body detection module, the image of track foreign body is input to determine whether there is track foreign body and give early warning. Meanwhile, the processing effect of different algorithms can be visually compared through the operation results. In the moving target detection module, the moving target in the input video is marked and tracked. The test results of the simulation platform show that the processing platform is simple and easy to operate, and can effectively assist researchers to deepen the understanding and application of orbital foreign object image processing.

关键词： railway track foreign object image Graphical User Interface (GUI) simulation platform design

来源：评论

学校读者我要写书评

暂无评论

time-Efficient video Anomaly Detection With Parallel Computing and Twice-Reconstruction

引用

IEEE SENSORS JOURNAL 2025年第6期25卷 9887-9901页

作者： Qi, Xiaosha Chao, Xin Ji, Genlin Li, Le Changzhou Inst Technol Sch Comp Sci & Informat Engn Changzhou 213000 Jiangsu Peoples R China Nanjing Normal Univ Sch Geog Nanjing 210023 Jiangsu Peoples R China Nanjing Normal Univ Sch Comp & Elect Informat Nanjing 210023 Jiangsu Peoples R China

To tackle two prevalent challenges in video anomaly detection, misclassification of abnormal frames as normal and the prolonged runtime of existing methods, this article proposes a time-efficient anomaly detection method utilizing twice-reconstruction and parallel computing. The proposed method integrates three key innovations: a twice-reconstruction model to amplify the reconstruction error for abnormal frames, a memory module to better capture and utilize normal distribution patterns, and a parallel computing strategy to significantly accelerate anomaly detection. By reconstructing frames twice, our method enhances the model's anomaly detection capabilities. Meanwhile, a memory module is incorporated to retain normal distribution patterns more effectively, reducing the likelihood of misclassifying abnormal frames. Furthermore, parallel computing is employed to minimize runtime and boost detection efficiency. Unlike existing methods, TPR-VAD achieves both high detection accuracy and time efficiency, making it well-suited for real-world applications such as intelligent surveillance systems. Experimental results on the UCSD Ped2, CUHK Avenue, and ShanghaiTech datasets show that our method achieves superior detection accuracy, reaching 99.01%, 91.21%, and 82.77%, respectively, while significantly reducing runtime.

关键词： Anomaly detection Computational modeling Parallel processing Training image reconstruction Memory modules Feature extraction Adaptation models Accuracy Gaussian distribution Memory module parallel computing twice-reconstructions video anomaly detection

来源：评论

学校读者我要写书评

暂无评论

On cross-layer optimization for real-time remote communication in 5G and beyond 27

On cross-layer optimization for real-time remote communicati...

引用

27th conference on Innovation in Clouds, Internet and Networks (ICIN)

作者： Dimitrovski, Toni Alexiou, Evangelos D'Acunto, Lucia Bergman, Tim Hindriks, Rick Turkovic, Belma TNO Networks The Hague Netherlands

ISBN: (纸本)9798350393767;9798350393774

The use of real-time remote communication has seen significant growth in the last few years. The need for providing the feeling of togetherness in real-time remote communication, combined with new developments in volumetric video, are expected to lead to immersive and holographic remote communication in the near future. These services will require high bandwidth, low latency and significant processing both at the sender and receiver side, and often within the network itself too. In order to fulfill these requirements, we argue that a holistic cross-layer optimization approach, that takes input from and provides optimization actions to all layers involved in the delivery of these services is necessary. In this paper we provide insights in the design and implementation of a cross-layer system orchestrator for adaptation of real-time remote communication. Based on inputs from the network and application layers, it uses a machine learning (ML) model to maximize the objective video quality metric by finding the best system configuration and taking adaptation actions in both layers. The model performance shows that it learned how to offset any system dynamics coming from the environment with the correct configuration settings.

关键词： edge computing network orchestration machine learning video conferencing cross-layer optimization immersive communication

来源：评论

学校读者我要写书评

暂无评论

Comparative evaluation of two algorithmic methods to enhance autonomous vehicle vision through de-raining imagery techniques 47

Comparative evaluation of two algorithmic methods to enhance...

引用

conference on Applications of Digital image processing XLVII

作者： Ajami, Hanieh Nigjeh, Mahdi Kargar Nigjeh, Mahsa Kargar Umbaugh, Scott E. Southern Illinois Univ Edwardsville Comp Vis & Image Proc Lab Dept Elect & Comp Engn Edwardsville IL 62026 USA

ISBN: (纸本)9781510679344;9781510679351

The effectiveness of autonomous vehicles relies on clear visual input, which rain can significantly obstruct. Rain streaks degrade the quality of captured images and videos, affecting both user perception and the functionality of outdoor vision systems, such as those in autonomous vehicles. This visual degradation impacts the vehicle's ability to interpret its environment, increasing the risk of driving in rainy conditions. Researchers have responded to this challenge by developing various rain removal algorithms, ranging from single-image to video-based approaches, each with its own strengths and weaknesses. This research aims to develop two novel, efficient single-image rain removal algorithms that strike a balance between high performance and quick execution. The proposed algorithms will address the need for an effective de-raining technique suitable for real-time use in autonomous vehicles. By improving visibility in rainy conditions, this innovation will enhance the performance and safety of autonomous vehicles, contributing to advancements in the field. A survey involving ten image processing experts and professionals, who evaluated the results of both algorithms based on perceived quality and improvement, revealed that Algorithm 1 received a higher average rating (0.58) compared to Algorithm 2 (0.43). Although Algorithm 1 is slightly preferred based on average participant ratings, Algorithm 2's superior edge preservation and image sharpness make it more favorable for applications demanding high accuracy and detailed image retention. Overall, the project meets the demand for real-time rain removal in autonomous vehicles and provides valuable insights into the effectiveness of Algorithm 1 in de-raining images compared to Algorithm

关键词： Autonomous vehicle vision Rain streaks removal Computer vision enhancement CVIPtools Python Algorithmic methods image segmentation

来源：评论

学校读者我要写书评

暂无评论

Research on real-time image processing system combining convolutional neural network and edge computing

Research on real-time image processing system combining conv...

引用

2024 International conference on Physics, Photonics, and Optical Engineering, ICPPOE 2024

作者： Liang, Lu Hebei University of Architecture Hebei Zhangjiakou China

ISBN: (数字)9781510689121

ISBN: (纸本)9781510689114

With the rise of the Internet of Things (IoT) and edge computing technologies, traditional cloud-dependent convolutional neural network (CNN) image processing methods are facing the challenges of latency and bandwidth bottlenecks. In this study, we propose a real-time image processing system that combines CNN and edge computing, which enables the CNN model to run efficiently on resource-constrained edge devices through model pruning and quantisation optimisation. Experimental results show that the system significantly outperforms traditional methods in terms of inference speed, processing frame rate, and energy-efficiency ratio, especially in application scenarios requiring high real-time performance, such as intelligent surveillance, autonomous driving, and industrial inspection. In addition, the system shows good robustness and stability under different network conditions. This study provides an efficient and low-latency solution for image processing in edge computing environments and lays the foundation for future intelligent applications. © 2025 SPIE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Submerged single-photon LiDAR imaging sensor used for real-time 3D scene reconstruction in scattering underwater environments

引用

OPTICS EXPRESS 2023年第10期31卷 16690-16708页

作者： Maccarone, Aurora Rummond, Kristofer Mccarthy, Aongus Teinlehner, Ulrich K. S. Achella, Julian Arcia, Diego A. Guirre G. Pawlikowska, Agata Lamb, Robert A. Henderson, Robert K. Mclaughlin, Stephen Altmann, Yoann Buller, Gerald S. Heriot Watt Univ Sch Engn & Phys Sci Edinburgh EH14 4AS Scotland Leonardo MW Ltd Crewe Rd North Edinburgh EH5 2XS Scotland ENSL Lab Phys CNRS F-69364 Lyon France Verisk Ave Europa 2 Alcorcon 28922 Madrid Spain Univ Edinburgh Sch Engn Edinburgh EH9 3FF Scotland

We demonstrate a fully submerged underwater LiDAR transceiver system based on single-photon detection technologies. The LiDAR imaging system used a silicon single-photon avalanche diode (SPAD) detector array fabricated in complementary metal-oxide semiconductor (CMOS) technology to measure photon time-of-flight using picosecond resolution time-correlated single-photon counting. The SPAD detector array was directly interfaced to a Graphics processing Unit (GPU) for real-time image reconstruction capability. Experiments were performed with the transceiver system and target objects immersed in a water tank at a depth of 1.8 meters, with the targets placed at a stand-off distance of approximately 3 meters. The transceiver used a picosecond pulsed laser source with a central wavelength of 532 nm, operating at a repetition rate of 20 MHz and average optical power of up to 52 mW, dependent on scattering conditions. Three-dimensional imaging was demonstrated by implementing a joint surface detection and distance estimation algorithm for real-time processing and visualization, which achieved images of stationary targets with up to 7.5 attenuation lengths between the transceiver and the target. The average processing time per frame was approximately 33 ms, allowing real-time three-dimensional video demonstrations of moving targets at ten frames per second at up to 5.5 attenuation lengths between transceiver and target.

关键词： Detector arrays Diffractive optical elements Imaging systems Picosecond pulses Three dimensional image processing Three dimensional imaging

来源：评论

学校读者我要写书评

暂无评论

PVLI: potentially visible layered image for real-time ray tracing

引用

VISUAL COMPUTER 2023年第8期39卷 3359-3372页

作者： Kravec, Jaroslav Kacerik, Martin Bittner, Jiri Czech Tech Univ Prague Czech Republic

Novel view synthesis is frequently employed in video streaming, temporal upsampling, or virtual reality. We propose a new representation, potentially visible layered image (PVLI), that uses a combination of a potentially visible set of the scene geometry and layered color images. PVLI encodes the depth implicitly and enables cheap run-time reconstruction. Furthermore, PVLI can also be used to reconstruct pixel and layer connectivities, which is crucial for filtering and post-processing of the rendered images. We use PVLIs to achieve local and server-based real-time ray tracing. In the first case, PVLIs are used as a basis for temporal and spatial upsampling of ray-traced illumination. In the second case, PVLIs are compressed, streamed over the network, and then used by a thin client to perform temporal and spatial upsampling and to hide latency. To shade the view, we use path tracing, accounting for effects such as soft shadows, global illumination, and physically based refraction. Our method supports dynamic lighting, and up to a limited extent, it also handles view-dependent surface interactions.

关键词： real-time rendering Ray tracing Remote rendering

来源：评论

学校读者我要写书评

暂无评论

An Impact Study of Deep Learning-based Low-light image Enhancement in Intelligent Transportation Systems

An Impact Study of Deep Learning-based Low-light Image Enhan...

引用

conference on Multimodal image Exploitation and Learning

作者： Jinadu, Obafemi Rajeev, Srijith Panetta, Karen A. Agaian, Sos S. Tufts Univ Dept Elect & Comp Engn Medford MA 02155 USA City Univ New York Dept Comp Sci New York NY USA

ISBN: (纸本)9781510673854;9781510673847

images and videos captured in poor illumination conditions are degraded by low brightness, reduced contrast, color distortion, and noise, rendering them barely discernable for human perception and ultimately negatively impacting computer vision system performance. These challenges are exasperated when processing video surveillance camera footage, using this unprocessed video data as-is for real-time computer vision tasks across varying environmental conditions within Intelligent Transportation Systems (ITS), such as vehicle detection, tracking, and timely incident detection. The inadequate performance of these algorithms in real-world deployments incurs significant operational costs. Low-light image enhancement (LLIE) aims to improve the quality of images captured in these unideal conditions. Groundbreaking advancements in LLIE have been recorded employing deep-learning techniques to address these challenges, however, the plethora of models and approaches is varied and disparate. This paper presents an exhaustive survey to explore a methodical taxonomy of state-of-the-art deep learning-based LLIE algorithms and their impact when used in tandem with other computer vision algorithms, particularly detection algorithms. To thoroughly evaluate these LLIE models, a subset of the BDD100K dataset, a diverse real-world driving dataset is used for suitable image quality assessment and evaluation metrics. This study aims to provide a detailed understanding of the dynamics between low-light image enhancement and ITS performance, offering insights into both the technological advancements in LLIE and their practical implications in real-world conditions. The project Github repository can be accessed here.

关键词： low-light image enhancement deep learning image restoration computer vision

来源：评论

学校读者我要写书评

暂无评论

Deep learning model for early prediction of material fracture in tensile testing

引用

NEURAL COMPUTING & APPLICATIONS 2024年第18期36卷 10461-10474页

作者： Jubair, Fahed Alhamayel, Ahmad Aljaiose, Raed Darabkh, Khalid A. Univ Jordan Sch Engn Comp Engn Dept Amman 11942 Jordan

Tensile testing (aka tension testing) is a widely employed mechanical testing technique for analyzing materials' properties and behavior under applied stress. Tensile testing plays a pivotal role in helping engineers to make informed decision about material selection and usage. Despite its importance, there is a limited numbers of studies that explored the potential of AI techniques for real time monitoring and material behavior prediction in tensile testing. To this end, this work presents a deep learning model designed to predict the material's condition throughout tensile testing and provide an early warning prior to fracture. By leveraging a comprehensive dataset of tension test video samples, the proposed model utilizes both convolution and recurrent neural networks to extract pertinent spatial and temporal visual features, thereby predicting the frames at which material deformation and fracture occur. The evaluation results of our research showed that the proposed model achieved a predictive ability with an F1-score of 97%, on average. The implications of our research are significant for industries and researchers in the field of materials science and engineering. By accurately predicting material status, our model enables automounts, real time analysis of material behavior during tensile testing, leading to better time and cost efficiency in various applications.

关键词： Tensile testing Material deformation Material fracture Deep learning image processing EfficientNet

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：