检索结果-内蒙古大学图书馆

IEEE International Conference on Utility and Cloud Computing (UCC)

作者： Meghna Rai Bhawna Khosla Yash Dhawan Himanshi Kharotia Neeraj Kumar Ajay Bandi Department of Computer Science and Engineering Thapar Institute of Engineering and Technology Patiala India Northwest Missouri State University USA

In this modern era, the popularity of autonomous systems has increased manifold because they are replacing people in various jobs and are expected to become the backbone of modern society. Specifically, self-driving vehicles and robots are gaining popularity in a wide range of applications. However, traffic sign detection, a critical component of intelligent transportation systems, remains quite challenging since it needs to be done quickly, with high precision, and with high dependability. A fast, real-time, robust automatic traffic sign detection and recognition can support and relieve the driver and significantly increase driving safety and comfort. Out of many algorithms and frameworks available for traffic sign identification, i.e., object detection, one of the most popular ones is You Only Look Once (YOLO) since it provides accurate results with minimal background errors in most real-time processing tasks and has excellent learning capabilities. Motivated by this, this research article provides a novel framework, CLEAR, for traffic sign identification in adverse climate conditions using YOLOv5. We compare different models’ speed, accuracy, and other metrics on a Traffic Sign Dataset obtained from the Open image Dataset v6. Experimental results demonstrated that the proposed CLEAR model achieved the best performance with a Mean Average Precision of 0.73392 and Recall of 0.74194 compared to the existing schemes.

关键词： Training Measurement Real-time systems Data models Usability Task analysis Tuning

来源：评论

学校读者我要写书评

暂无评论

Performance comparison of recent optimization algorithm Jaya with particle swarm optimization for digital image watermarking in complex wavelet domain

引用

MULTIDIMENSIONAL systems AND SIGNAL processing 2019年第4期30卷 1769-1791页

作者： Thakkar, Falgun N. Srivastava, vinay Kumar GH Patel Coll Engn & Technol Elect & Commun Engn Dept V V Nagar 388120 Gujarat India MNNIT Allahabad ECED Allahabad Uttar Pradesh India

Nowadays copyright protection is mandatory in the field of image processing to removes the illegitimate utilization and imitation of digital images. The digital image watermarking is one of the most reliable methods for protecting the illegal validation of data. In this paper, singular value decomposition based digital image watermarking scheme is proposed in complex wavelet transform (CWT) domain using intelligence algorithms like particle swarm optimization (PSO) and recently proposed Jaya algorithm. The watermark image is embedded into high frequency CWT subband of cover image. At the time of watermark embedding and extraction, optimization algorithms Jaya and PSO are applied to improve the robustness and imperceptibility by assessing the fitness function. The perceptual quality of watermarked image and robustness of extracted watermark image are verified under the filtering, rotation, scaling, Gaussian noise and JPEG compression attacks. From the comparative analysis it is proved that Jaya algorithm is better as compared to PSO algorithm under most types of attacks with higher magnitudes whereas identical under the lower magnitude of applied attacks. Moreover, using variety of cover images, it is found that, the elapse time and value of fitness function given by Jaya algorithm are also better as compared to PSO.

关键词： Complex wavelet domain watermarking Particle swarm optimization Jaya algorithm Singular value decomposition Elapse time Fitness function

来源：评论

学校读者我要写书评

暂无评论

Development and analysis methods of images quality improvement with violation of contrast

Development and analysis methods of images quality improveme...

引用

2020 Wave Electronics and its Application in Information and Telecommunication systems, WECONF 2020

作者： Baldin, M.I. Kozyrev, N.A. Gorshunov, I.A. Kolomoitcev, v.S. ITMO University St.-Petersburg Russia Saint-Petersburg State University of Economics St.-Petersburg Russia Saint-Petersburg State University of Aerospace Instrumentation St. Peterburg Russia

Method is proposed to improve the visual quality of images based on algorithms based on histogram equalization. The work examined widely used algorithms of histograms equalization, described their advantages and disadvantages. The classification of images with contrast violation has been introduced. A focus of the work is the development of a new method of image processing with different types of contrast violations. This approach provides improved images quality, regardless of classification and characteristics. © 2020 IEEE.

关键词： Equalizers

来源：评论

学校读者我要写书评

暂无评论

Principles of Organization of the Strategies of Content-Based Analysis of Aerospace images 4th

Principles of Organization of the Strategies of Content-Base...

引用

4th International Scientific Conference on Intelligent Information Technologies for Industry (IITI)

作者： Kasimov, Denis R. Kuchuganov, valeriy N. Kuchuganov, Aleksandr, v Kalashnikov Izhevsk State Tech Univ Izhevsk Russia

ISBN: (纸本)9783030500979

The infinite variety of image subjects, the dependence of analysis algorithms and decision rules on the shooting conditions and image quality lead to the need to configure and retrain the computer vision system for almost every next series of images. The paper proposes the principles of organization and high-level language for description of strategies of content-based analysis of aerospace images. The decision maker specifies the strategy for processing and analyzing the image as a sequence of points of selection of actions or subtasks. In general, each action can be performed by different software modules, which require their own data structures, restrictions and rules. Accordingly, the results of the action will vary. The solver, which is controlled by the given strategy, selects variants of actions, data and constraints for each subtask, builds a decision tree, and monitors the progress of the decision. Examples of object detection strategies and results of their work on urban area aerial images characterized by a very high spatial resolution are given. Applied semantic models of actions and resources make the process of structuring and describing more visual and, at the same time, machine-readable. The process of describing the image analysis strategy is transferred from the level of specifying instructions/commands to the level of planning works and resources.

关键词： Aerial image Object detection Semantic image analysis Context-sensitive strategy Decision tree Strategy Description Language Solver

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Approach in Detecting Object Applied to Automotive Traffic Roads Signs 6

An Enhanced Approach in Detecting Object Applied to Automoti...

引用

6th International Conference on Optimization and Applications, ICOA 2020

作者： Barodi, Anass Bajit, Abdrrahim Benbrahim, Mohammed Tamtaoui, Ahmed Laboratory of Electrical Systems and Telecommunication Engineering National School of Applied Sciences Ibn Tofail University Kenitra Morocco Mohammed v University SC Department Rabat Morocco

ISBN: (纸本)9781728166544

In this article, we use among and the best-known library is Open Computer vision we call it for short OpenCv. It is used for image processing, to do all operations we want, to isolate and detect a specific object, which in our case are traffic road signs. We process to find the most efficient methods of detection of traffic road signs. Our objective is to demonstrate the links the elements for optimized and powerful to computer vision algorithms that are easy to use as typing in an image and video processing. Most of the techniques they employed the color selection, edge detection, a region of interest selection, and shapes transformation of detection. Many applications require the recognition of traffic road signs in urban areas. The automation of this task is necessary, for example, ADAS systems, and the application of vision robotics or an autonomous vehicle, consist of recognizing and identifying traffic road signs as quickly as possible with errors to be minimized, in images of their type acquired by an embedded camera on board a vehicle. © 2020 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Recognition of Casting Embossed Convex and Concave Characters Based on YOLO v5 for Different Distribution Conditions

Recognition of Casting Embossed Convex and Concave Character...

引用

International Wireless Communications and Mobile Computing Conference, IWCMC

作者： Zhiyue Zhang Guang Yang Chensheng Wang Guangjian Chang Beijing University of Posts and Telecommunications Beijing China Army Academy of Armored Force Beijing China

Traditional casting character recognition algorithms need to select appropriate position features for different scenes in the character location step, so it is difficult to realize the recognition task of casting embossed concave and convex characters in the different distribution in complex scenes. In this letter, a recognition method of casting embossed characters based on YOLO v5 is proposed. The fast and reliable depth learning algorithm YOLO v5 is used to automatically extract the image features and realize the recognition of casting embossed characters (including numbers and letters) Recognition. The experimental results show that the accuracy of the network model for steel seal character recognition is higher than traditional computer vision algorithms, the average processing time of the algorithm is quickly, and the weight file volume is small, which meets the accuracy and efficiency requirements of engineering application.

关键词： Wireless communication Casting Solid modeling image recognition Seals Feature extraction Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Arbitrary Scale Super-Resolution for Medical images

引用

INTERNATIONAL JOURNAL OF NEURAL systems 2021年第10期31卷 2150037-2150037页

作者： Zhu, Jin Tan, Chuan Yang, Junwei Yang, Guang Lio, Pietro Univ Cambridge Dept Comp Sci & Technol Cambridge CB3 0FD England Royal Brompton Hosp Cardiovasc Res Ctr London SW3 6NP6 England Imperial Coll London Natl Heart & Lung Inst London SW7 2AZ England Univ Cambridge Dept Comp Sci & Technol Cambridge CB3 0FD England

Single image super-resolution (SISR) aims to obtain a high-resolution output from one low-resolution image. Currently, deep learning-based SISR approaches have been widely discussed in medical image processing, because of their potential to achieve high-quality, high spatial resolution images without the cost of additional scans. However, most existing methods are designed for scale-specific SR tasks and are unable to generalize over magnification scales. In this paper, we propose an approach for medical image arbitrary-scale super-resolution (MIASSR), in which we couple meta-learning with generative adversarial networks (GANs) to super-resolve medical images at any scale of magnification in (1, 4]. Compared to state-of-the-art SISR algorithms on single-modal magnetic resonance (MR) brain images (OASIS-brains) and multi-modal MR brain images (BraTS), MIASSR achieves comparable fidelity performance and the best perceptual quality with the smallest model size. We also employ transfer learning to enable MIASSR to tackle SR tasks of new medical modalities, such as cardiac MR images (ACDC) and chest computed tomography images (COvID-CT). The source code of our work is also public. Thus, MIASSR has the potential to become a new foundational pre-/post-processing step in clinical image analysis tasks such as reconstruction, image quality enhancement, and segmentation.

关键词： Super-resolution medical image analysis image processing generative adversarial networks meta learning transfer learning

来源：评论

学校读者我要写书评

暂无评论

Contrast Limited Adaptive Histogram Equalization (CLAHE) Approach for Enhancement of the Microstructures of Friction Stir Welded Joints

Research Square

引用

Research Square 2021年

作者： Mishra, Akshansh Centre for Artificial Intelligent Manufacturing Systems Stir Research Technologies India

image processing algorithms are finding various applications in manufacturing and materials industries such as identification of cracks in the fabricated samples, calculating the geometrical properties of the given microstructure, presence of surface defects, etc. The present work deals with the application of Contrast Limited Adaptive Histogram Equalization (CLAHE) algorithm for improving the quality of the microstructure images of the Friction Stir Welded joints. The obtained results showed that the obtained value of quantitative metric features such as Entropy value and RMS Contrast value were high which resulted in enhanced microstructure images. © 2021, CC BY.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

Memory-Latency-Accuracy Trade-offs for Continual Learning on a RISC-v Extreme-Edge Node 34

Memory-Latency-Accuracy Trade-offs for Continual Learning on...

引用

34th IEEE Workshop on Signal processing systems (SiPS)

作者： Ravaglia, Leonardo Rusci, Manuele Capotondi, Alessandro Conti, Francesco Pellegrini, Lorenzo Lomonaco, vincenzo Maltoni, Davide Benini, Luca Univ Bologna DISI Bologna Italy Univ Bologna DEI Bologna Italy Univ Modena & Reggio Emilia FIM Reggio Emilia Italy Swiss Fed Inst Technol IIS Zurich Switzerland

ISBN: (纸本)9781728180991

AI-powered edge devices currently lack the ability to adapt their embedded inference models to the ever-changing environment. To tackle this issue, Continual Learning (CL) strategies aim at incrementally improving the decision capabilities based on newly acquired data. In this work, after quantifying memory and computational requirements of CL algorithms, we define a novel HW/SW extreme-edge platform featuring a low power RISC-v octa-core cluster tailored for on-demand incremental learning over locally sensed data. The presented multi-core HW/SW architecture achieves a peak performance of 2.21 and 1.70 MAC/cycle, respectively, when running forward and backward steps of the gradient descent. We report the trade-off between memory footprint, latency, and accuracy for learning a new class with Latent Replay CL when targeting an image classification task on the CORe50 dataset. For a CL setting that retrains all the layers, taking 5h to learn a new class and achieving up to 77.3% of precision, a more efficient solution retrains only part of the network, reaching an accuracy of 72.5% with a memory requirement of 300 MB and a computation latency of 1.5 hours. On the other side, retraining only the last layer results in the fastest (867 ms) and less memory hungry (20 MB) solution but scoring 58% on the CORe50 dataset. Thanks to the parallelism of the low-power cluster engine, our HW/SW platform results 25x faster than typical MCU device, on which CL is still impractical, and demonstrates an 11x gain in terms of energy consumption with respect to mobile-class solutions.

关键词： continual learning extreme edge deep learning parallel programming online learning federated learning

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Approach for Identifying User Communities Based on Geographical Preferences and Its Applications to Urban and Environmental Planning

引用

ACM TRANSACTIONS ON SPATIAL algorithms AND systems 2020年第3期6卷 1–24页

作者： Ferreira, Danielle L. Nunes, Bruno A. A. Campos, Carlos Alberto, v Obraczka, Katia Univ Calif Santa Cruz UCSC 1156 High St Santa Cruz CA 95064 USA Univ Calif San Francisco UCSF 1500 Owens St 1630 Third St San Francisco CA USA Fed Univ State Rio de Janeiro UNIRIO Av Pasteur 296 Rio De Janeiro RJ Brazil Univ Calif San Francisco UCSF Dept Cardiol San Francisco CA 94143 USA

Understanding human mobility plays a vital role in urban and environmental planning as cities continue to grow. Ubiquitous geo-location, localization technology, and availability of big-data-ready computing infrastructure have enabled the development of more sophisticated models to characterize human mobility in urban areas. In this work, our main goal is to extract spatio-temporal features that characterize user mobility and, based on the similarity of these features, identify user communities. To this end, we propose a novel approach that leverages image processing techniques to represent user geographical preferences as images and then apply deep convolutional autoencoders to extract latent spatio-temporal mobility features from these images. These features are then fed to a clustering algorithm that identifies the underlying community structures. We use a diverse urban mobility dataset to validate the proposed framework. Our results show that the proposed framework is able to significantly increase the similarity between intra-community nodes (by up to 107%) as well as dissimilarity between inter-community nodes (up to 54%) when compared against no pre-processing of the datasets, i.e without pre-processing the datasets through any feature fusion method. Moreover, it was also able to reach up to 100% improvement when compared against community identification using Principal Component Analysis (PCA). Our results also show that the proposed approach yields significant increase in contact time amongst users belonging to the same community, by up to 80% when compared to the average contact time when not considering community structures, and by up to 150% when compared to the baseline. To the best of our knowledge, our proposal is the first to consider deep convolutional autoencoding to perform automatic extraction of non-linear spatio-temporal mobility features characterizing individual users from raw mobility datasets with the goal of identifying user communities.

关键词： Deep learning autoencoder convolutional neural networks T-sne principal component analysis clustering algorithm human mobility geographical preference user community mobility feature extraction

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：