检索结果-内蒙古大学图书馆

International Conference on Communications and Signal processing

作者： Y R Sanjay Kumar P Raja Venkatesan M Ramanathan S Saranya Department of Electronics and Communication Engineering Sri Sairam Engineering College Chennai India

ISBN: (数字)9798350353068

ISBN: (纸本)9798350353075

Drones are everywhere, from war to pharmacy delivery. Drones can also be used in surveillance, rescuing people from remote areas. Modern technologies like artificial Intelligence and deep learning must be implemented in our defence systems. Organisations and Institutes under the Defence Ministry require Drones to locate other countries’ soldiers, weapons, camps, ships, aircraft, etc. In this project, we are going to develop a drone that can detect people or soldiers, guns, grenades, ships, aircraft, weapons, etc., including face recognition. Using face recognition and objection detection algorithms, we will train models that can be used in real-time. The video data from the drone camera is sent to the servers. The video or image will be processed by the servers. Face recognition and object detection outputs will be given in the form of text messages and images. This drone technology can be used in anti-drone systems and anti-aircraft missiles to destroy other countries’ drones or missiles. Drones can be made autonomous. So, they can communicate with each other for better performance. Therefore, using this technology, better surveillance can be done. It can help national and state police officers and rescue teams locate victims of natural disasters like floods, tsunamis, etc.

关键词： deep learning Missiles Surveillance Face recognition Object detection Streaming media Servers

来源：评论

学校读者我要写书评

暂无评论

deep learning of Spatiotemporal Filtering for Fast Super-Resolution Ultrasound Imaging

引用

IEEE TRANSACTIONS ON ULTRASONICS FERROELECTRICS AND FREQUENCY CONTROL 2020年第9期67卷 1820-1829页

作者： Brown, Katherine G. Ghosh, Debabrata Hoyt, Kenneth Univ Texas Dallas Dept Bioengn Richardson TX 75080 USA Thapar Inst Engn & Technol Dept Elect & Commun Engn Patiala 147004 Punjab India

Super-resolution ultrasound (SR-US) imaging is a new technique that breaks the diffraction limit and allows visualization of microvascular structures down to tens of micrometers. The image processingmethods for the spatiotemporal filtering needed in SR-US, such as singular value decomposition (SVD), are computationally burdensome and performed offline. deep learning has been applied to many biomedical imaging problems, and trained neural networks have been shown to process an image in milliseconds. The goal of this study was to evaluate the effectiveness of deep learning to realize a spatiotemporal filter in the context of SR-US processing. A 3-D convolutional neural network (3DCNN) was trained on in vitro and in vivo data sets using SVD as ground truth in tissue clutter reduction. In vitro data were obtained from a tissue-mimicking flow phantom, and in vivo data were collected from murine tumors of breast cancer. Three training techniques were studied: training with in vitro data sets, training with in vivo data sets, and transfer learning with initial training on in vitro data sets followed by fine-tuning with in vivo data sets. The neural network trained with in vitro data sets followedby fine-tuningwith in vivo data sets had the highest accuracy at 88.0%. The SR-US images produced with deep learning allowed visualization of vessels as small as 25 mu m in diameter, which is below the diffraction limit (wavelength of 110 mu m at 14 MHz). The performance of the 3DCNN was encouraging for real-time SR-US imaging with an average processing frame rate for in vivo data of 51 Hz with GPU acceleration.

关键词： Contrast agents contrast-enhanced ultrasound (CEUS) deep learning microbubbles (MBs) super-resolution ultrasound (SR-US)

来源：评论

学校读者我要写书评

暂无评论

deep Distillation Hashing for Unconstrained Palmprint Recognition

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2021年 70卷 1-13页

作者： Shao, Huikai Zhong, Dexing Du, Xuefeng Xi An Jiao Tong Univ Sch Automat Sci & Engn Xian 710049 Peoples R China Nanjing Univ State Key Lab Novel Software Technol Nanjing 210093 Peoples R China Univ Wisconsin Dept Comp Sci Milwaukee WI 53201 USA

deep palmprint recognition has become an emerging issue with great potential for personal authentication on handheld and wearable consumer devices. Previous studies of palmprint recognition are mainly based on constrained data sets collected by dedicated devices in controlled environments, which has to reduce the flexibility and convenience. In addition, general deep palmprint recognition algorithms are often too heavy to meet the real-time requirements of embedded system. In this article, a new palmprint benchmark is established, which consists of more than 20 000 images collected by five brands of smartphones in an unconstrained manner. Each image has been manually labeled with 14 key points for the region of interest (ROI) extraction. Furthermore, a novel deep distillation hashing (DDH) algorithm is proposed as a benchmark for efficient deep palmprint recognition. Palmprint images are converted to binary codes to improve the efficiency of feature matching. Derived from knowledge distillation, new distillation lass functions are constructed to compress the deep model to further improve the efficiency of feature extraction on the light network. Comprehensive experiments are conducted on both constrained and unconstrained palmprint databases. Using DDH, the accuracy of palmprint identification can be increased by up to 11.37%, and the equal error rate (EER) of palmprint verification can be reduced by up to 3.11%. The results indicate the potential of our database, and DDH can outperform other baselines to achieve the state-of-the-art performance. The collected data set is publicly available at http://***/web/bell/resource.

关键词： Biometrics deep hash learning knowledge distillation (KD) palmprint database palmprint recognition

来源：评论

学校读者我要写书评

暂无评论

Passenger Surveillance Using deep learning in Post-COVID-19 Intelligent Transportation System

引用

Transactions of the Indian National Academy of Engineering : an international journal of engineering and technology 2022年第3期7卷 927-941页

作者： Srimanta Kundu Ujjwal Maulik Jadavpur University Kolkata India. Techno Main Salt Lake Kolkata India.

Intelligent Transport System should be renovated in many aspects in post-pandemic situation like COVID-19. The passenger-count inside a car will be restricted based on the vehicle capacity and the COVID-19 hot-spot zone. Traffic rules will be impacted to align with a similar contagious outbreak. The on-road 'Yellow-Vulture' cameras need to incorporate such surveillance rules to monitor related anomalies for preventing contamination. To maintain safe-distance, an automatic surveillance system will be preferred by the Government very soon. Moreover, facial mask usage during the journey has become an essential habit to stop the spread of the infection. In this article, we have proposed a deep-learning based framework that employs an augmented image data set to provide proper surveillance in the transport system to maintain the health protocols. Fast and accurate detection of the number of passengers inside a car and their face masks from the traffic inspection camera feed has been demonstrated. We have exploited the advantages of the popular Transfer learning approach with novel variations of images while performing the training. To the best of our knowledge, this is the first attempt to watch over in-vehicle social-distancing in post-pandemic circumstances through deep-learning based image analysis. The superiority of the proposed framework has been established over several state-of-the-art techniques using different numerical metrics and visual comparisons along with a support of statistical hypothesis test. Our technique has achieved testing accuracy in various adverse conditions. Zero-shot evaluation has been explored for the real-time-Medical-Mask-Detection data set Wang et al. (real-time-Medical-Mask-Detection, 2020a https://***/TheSSJ2612/real-time-Medical-Mask-Detection/, Accessed 14 Nov 2020), where we have attained accuracy that manifests the generalization of the network.

关键词： COVID-19 Inception-V3 Mask detection Passenger counting Transfer learning Vehicle surveillance

来源：评论

学校读者我要写书评

暂无评论

Optimizing CNN performance on CIFAR-10: a study on multi-core processing, batching techniques, and future network architectures

Optimizing CNN performance on CIFAR-10: a study on multi-cor...

引用

2nd International Conference on Mechatronic Automation and Electrical Engineering (ICMAEE 2024)

作者： Datong Jin College of art and science The Ohio State University Columbus 43210 USA

ISBN: (数字)9781837242672

The performance of Convolutional Neural Networks (CNNs) is critically dependent on the underlying computational configurations, particularly in terms of processing capabilities and data handling techniques. As deep learning models become increasingly complex and data-intensive, the choice between single-core and multi-core processing, along with strategies such as batching, becomes pivotal. These configurations directly impact the efficiency and speed of model training and inference, which are essential for applications requiring real-time processing and high accuracy, such as image recognition and automated systems. Study Contributions:This research focuses on comparing the effects of single-core versus multi-core processing configurations on CNN performance, integrating batching techniques to observe their combined influence on reducing latency and increasing throughput. The study reveals that leveraging multi-core processing with batching substantially enhances CNN operations. Additionally, it addresses the deployment challenges of the YOLOv5 architecture, emphasizing the necessity for further architectural improvements. The paper suggests that future enhancements could include adopting deeper network structures to elaborate on complex features and employing methods like ResNet to counteract gradient vanishing problems. Moreover, it advocates for the fine-tuning of models with pre-trained datasets such as imageNet to boost robustness and accuracy, particularly demonstrated on the CIFAR-10 dataset. These recommendations aim to refine CNN capabilities, thereby advancing the broader field of machine learning and computer vision.

关键词：

来源：评论

学校读者我要写书评

暂无评论

learning Self-Supervised Space-time CNN for Fast Video Style Transfer

引用

IEEE TRANSACTIONS ON image processing 2021年 30卷 2501-2512页

作者： Xu, Kai Wen, Longyin Li, Guorong Qi, Honggang Bo, Liefeng Huang, Qingming Univ Chinese Acad Sci Sch Comp Sci & Technol Beijing 100864 Peoples R China JD Finance Amer Corp Mountain View CA 94043 USA

Style transfer on images has achieved significant advances in recent years, with the deep convolutional neural network (CNN). Directly applying image style transfer algorithms to each frame of a video independently often leads to flickering and unstable results. In this work, we present a self-supervised space-time convolutional neural network (CNN) based method for online video style transfer, named as VTNet, which is end-to-end trained from nearly unlimited unlabeled video data to produce temporally coherent stylized videos in real-time. Specifically, our VTNet transfer the style of a reference image to the source video frames, which is formed by the temporal prediction branch and the stylizing branch. The temporal prediction branch is used to capture discriminative spatiotemporal features for temporal consistency, pretrained in an adversarial manner from unlabeled video data. The stylizing branch is used to transfer the style image to a video frame with the guidance from the temporal prediction branch to ensure temporal consistency. To guide the training of VTNet, we introduce the style-coherence loss net (SCNet), which assembles the content loss, the style loss, and the new designed coherence loss. These losses are computed based on high-level features extracted from a pretrained VGG-16 network. The content loss is used to preserve high-level abstract contents of the input frames, and the style loss introduces new colors and patterns from the style image. Instead of using optical flow to explicitly redress the stylized video frames, we design the coherence loss to make the stylized video inherit the dynamics and motion patterns from the source video to remove temporal flickering. Extensive subjective and objective evaluations on various styles demonstrate that the proposed method achieves favorable results against the state-of-the-arts with high efficiency.

关键词： Training Spatiotemporal phenomena Streaming media Feature extraction Two dimensional displays Testing Optimization Video style transfer space-time CNN self-supervised

来源：评论

学校读者我要写书评

暂无评论

GTAW熔池激光条纹动态行为与熔透预测方法研究

引用

机械工程学报 2024年第6期60卷 236-244页

作者：李春凯王嘉昕石玗代悦兰州理工大学省部共建有色金属先进材料加工与再利用国家重点实验室兰州730050 兰州理工大学温州泵阀工程研究院温州325100

熔透状态是影响焊缝质量的关键因素之一,可靠传感并实时预测焊缝熔透状态对于提升焊接质量以及焊接智能化水平具有非常重要的意义。利用激光视觉法对低频脉冲钨极氩弧焊(Pulsed gas tungsten arc welding,P-GTAW)不同熔透状态下的反射... 详细信息

熔透状态是影响焊缝质量的关键因素之一,可靠传感并实时预测焊缝熔透状态对于提升焊接质量以及焊接智能化水平具有非常重要的意义。利用激光视觉法对低频脉冲钨极氩弧焊(Pulsed gas tungsten arc welding,P-GTAW)不同熔透状态下的反射激光条纹进行了检测,通过建立熔池表面标准模型分析了激光条纹图像动态行为与三种熔透状态熔池自由表面之间(未熔透、临界熔透、全熔透)的相关性,并基于深度学习卷积神经网络建立了GTAW熔透预测模型。研究表明:P-GTAW激光条纹的动态行为与熔池背面熔透状态、熔池表面振荡模式之间存在明确的光学对应关系,所建立从激光条纹图像到GTAW背面熔透状态的端到端卷积神经网络模型能够准确分类未熔透、临界熔透和全熔透三种状态,且分类准确率可达到98.1%,能够实现焊缝熔透状态实时传感及预测。

关键词：熔透检测激光视觉法深度学习熔池振荡端到端神经网络 GTAW

来源：评论

学校读者我要写书评

暂无评论

A Convolutional Recurrent Mixer Network For Radar Meteorological image Super-Resolution

A Convolutional Recurrent Mixer Network For Radar Meteorolog...

引用

International Conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Rafael Gonçalves Pires Daniel F. S Santos Roberto V. Calheiros João Paulo Papa Ik Hyun Lee Sambit Bakshi Khan Muhammad Department of Computing São Paulo State University Bauru Brasil Meteorological Research Institute São Paulo State University Bauru Brasil Dept. of Mechatronics Engineering Tech University of Korea IKLAB Inc. South Korea Dept. of CS&E National Institute of Technology Rourkela India School of Convergence Sungkyunkwan University Seoul South Korea

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

image super-resolution (SR) focuses on reconstructing high-resolution images from their low-resolution counter-parts, often affected by sensor limitations or environmental factors. Convolutional Neural Networks (CNNs) are state-of-the-art for SR tasks but computationally heavy. This paper introduces a novel CRMN (Convolutional Recurrent Mixer Network), a hybrid deep learning-based SR technique designed to address the complexity of CNNs, which is validated in the context of meteorological radar images. Experiments on public benchmark datasets (Berkley432 and T291) and our newly manually collected precipitation dataset from the Meteorological Research Institute (IPMET) show that our CRMN model provides competitive results compared to leading SR methods with significantly fewer parameters, making it a promising and practical solution for SR applications, particularly radar meteorology.

关键词： image quality Meteorological radar Convolution Computational modeling Superresolution real-time systems Complexity theory Speech processing Mixers Signal resolution

来源：评论

学校读者我要写书评

暂无评论

TATA: Throughput-Aware TAsk Placement in Heterogeneous Stream processing with deep Reinforcement learning 19

TATA: Throughput-Aware TAsk Placement in Heterogeneous Strea...

引用

19th IEEE International Symposium on Parallel and Distributed processing with Applications (IEEE ISPA)

作者： Huang, Xiao Jiang, Yu Fan, Hao Tang, Huayun Wang, Yiping Jin, Jin Wan, Hai Zhao, Xibin Tsinghua Univ Beijing Peoples R China ChinaBond Finance & Informat Technol Co Ltd Beijing Peoples R China Maple Growth Res Club Inst Toronto ON Canada

ISBN: (纸本)9781665435741

Data Stream processing (DSP) applications, which generate real-time analytics on continuous data flows, have become prevalent recently. For the deployment of DSP applications, task placement is an important and essential part. As determining the optimal task placement is an NP-hard problem, several efficient heuristics have been designed and deep Reinforcement learning (DRL) was used to train the scheduling agent. Current DRL-based approach assumes all resources including CPU, memory and networking are homogeneous. However, the available computation and network resources are heterogeneous in many scenarios. To deal with it, we devise a general DRL-based resource-aware framework, which models resources using graph embedding and attention mechanism to predict the placement. Furthermore, in order to accelerate the training process and improve the throughput, we propose an efficient throughput estimation tool, which can estimate the throughput with high accuracy. We integrated our scheduling heuristic framework into Apache Flink and conducted comprehensive testings using multiple synthetic and real DSP applications. The experimental results show that our framework increases the throughput by 64%, 42%, 29% on average respectively compared with three state-of-the-art strategies.

关键词： Data stream processing Task placement Throughput deep reinforcement learning Heterogeneous resources

来源：评论

学校读者我要写书评

暂无评论

Analysis of deep learning based path loss prediction from satellite images 29

Analysis of deep learning based path loss prediction from sa...

引用

29th IEEE Conference on Signal processing and Communications Applications (SIU)

作者： Alam, Muhammad Z. Ates, Hasan F. Baykas, Tuncer Gunturk, Bahadir K. Istanbul Medipol Univ Sch Engn & Nat Sci Istanbul Turkey Kadir Has Univ Dept Elect Elect Engn Istanbul Turkey

ISBN: (纸本)9781665436496

Determining the channel model parameters of a wireless communication system, either by measurements or by running electromagnetic propagation simulations, is a time-consuming process. Any rapid deployment of network demands faster determination of at least major channel parameters. In this paper, we investigate the idea of using deep convolutional neural networks and satellite images for channel parameters (i.e., path loss exponent n and shadowing factor sigma) prediction in a cellular network with aerial base stations. Specifically, we investigate the performance dependency of the method on three different factors: height of the transmitter antenna, quantization levels of the channel parameters and architectural design of CNN. The results presented in this paper show a high prediction accuracy of the channel parameters in real-time.

关键词： Channel parameters estimation deep CNNs image classification

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：