检索结果-内蒙古大学图书馆

12th conference on Reconnaissance and Electronic Warfare systems (CREWS)

作者： Jakubowski, Jacek Solarczyk, Maciej Wisnios, Michal Mil Univ Technol Fac Elect Witold Urbanowicz St 2 PL-00908 Warsaw Poland

ISBN: (数字)9781510627864

ISBN: (纸本)9781510627864

The article presents the concept of how to use convolutional networks as a method for processing digital images acquired in visible region of light for the needs of smoke detection in large open area. The meaning and consequences of massive blaze were underlined on the basis of statistical data concerning the forest fires. The proposal to overcome the difficulties in using traditional methods for detection of fire threat by image processing techniques was discussed. The idea, inner structure and properties of a convolutional neural network as a tool for automatic feature generation and image recognition were presented. The algorithms of data processing used in vision systems for fire detection were analyzed including the solutions implementing the networks. On the basis of the analysis the proposal to develop a neural network for smoke detection with the use of the strategy called transfer learning was presented. Using the image base of fires available on the web, the quantified assessment of the proposed approach was conducted. In the research the AlexNet framework was adopted to recognize smoke in images. The processing of the net was illustrated with examples of activations of selected layers when fed with images containing smoke. The 99% sensitivity reached by the proposed processing together with the 1% of false alarm rate seems to be very promising for the system of fire surveillance based on watchtowers or air vessels monitoring large open areas.

关键词： image processing smoke detection convolutional networks deep learning

来源：评论

学校读者我要写书评

暂无评论

Predicting the association between fine-grained attributes and black-boxed perceptual performance*

Predicting the association between fine-grained attributes a...

引用

Youth Academic Annual conference of Chinese Association of Automation (YAC)

作者： Biyao Shang Chi Zhang Yuehu Liu Le Wang Li Li Institute of Artificial Intelligence and Robotics Xi’ an Jiaotong University Xi’ an China Shaanxi Key Lab of Digital Technology and Intelligent Systems Xi’ an China BNRist Tsinghua University Beijing China

ISBN: (数字)9781728176840

ISBN: (纸本)9781728176857

Per-image performance of a certain visual perception algorithm is the combination of per-task performances in the image. Based on the black box test, we address to discover and explain the potential shortness of the evaluated intelligent algorithms/systems at the fine-grained task-level by human knowledge. By assuming the domain knowledge in visual tasks could be represented by a latent vector which is a sparse embedding of the catenated object-level and image-level features, we propose a latent dictionary learning framework for joint latent knowledge representation and knowledge-output regression at task level. In this way, so we can use semantic concepts to explain the relationship between test cases and test results. The experiments validate the idea of task-level explainable AI evaluation initially as well as the effectiveness of proposed method.

关键词： Visualization Semantics Machine learning Knowledge representation Predictive models Task analysis Visual perception

来源：评论

学校读者我要写书评

暂无评论

A Provable Secure image Encryption Schema Based on Fractional Order Chaotic systems 23

A Provable Secure Image Encryption Schema Based on Fractiona...

引用

23rd International conference on Electronics

作者： Aydin, Yilmaz Ozkaynak, Fatih Firat Univ Dept Software Engn TR-23119 Elazig Turkey

ISBN: (纸本)9781728122090

In the literature, many chaotic systems have been used in the design of image encryption algorithms. In this study, an application of fractional order chaotic systems is investigated. The aim of the study is to improve the disadvantageous aspects of existing methods based on discrete and continuous time chaotic systems by utilizing the features of fractional order chaotic systems. The most important advantage of the study compared to the literature is that the proposed encryption algorithm is designed with a provable security approach. Analyses results have been shown that the proposed method can be used successfully in many information security applications.

关键词： Chaos Cryptography Fractional order chaos image encryption Nonlinear signal processing

来源：评论

学校读者我要写书评

暂无评论

Blind image Zero-Watermarking Algorithm Based on Radial Krawtchouk Moments and Chaotic System

Blind Image Zero-Watermarking Algorithm Based on Radial Kraw...

引用

Intelligent systems and Computer Vision (ISCV)

作者： M. Yamni H. Karmouni A. Daoui O. El ogri M. Sayyouri H. Qjidaa Laboratory of Electronic Signals and Systems of Information (LESSI) Dhar El Mahrez Faculty of Science Sidi Mohamed Ben Abdellah-Fez University Fez Morocco Engineering Systems and Applications Laboratory National School of Applied Sciences Sidi Mohamed Ben Abdellah-Fez University Fez Morocco

ISBN: (数字)9781728180410

ISBN: (纸本)9781728180427

image watermarking systems are frequently used tools for copyright protection against unauthorized use of images in unsecured spaces. The conventional method is to embed a copyright mark (watermark) in the original image. However, this strategy is not suitable for sensitive images such as medical, satellite, texture and remote sensing images, etc., because the integrated watermark strongly affects the results of its application tasks. For copyright protection of this type of images, this paper proposes a robust blind zero-watermarking algorithm based on Krawtchouk Radial Moments and a chaotic system. This algorithm does not integrate any information into the original image and satisfactorily ensures robustness against various common image processing attacks and geometric distortions. The experimental study uses different categories of images to evaluate and compare the proposed algorithm with other watermarking and zero-watermarking algorithms in terms of robustness against various image attacks.

关键词： Watermarking Signal processing algorithms Robustness Copyright protection image processing Distortion

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of algorithms and Methods for Facial Expression Recognition 13

A Comparative Study of Algorithms and Methods for Facial Exp...

引用

13th Annual IEEE International systems conference (SysCon)

作者： Al-Omair, Osamah M. Huang, Shihong Florida Atlantic Univ Comp & Elect Engn & Comp Sci Boca Raton FL 33431 USA

ISBN: (纸本)9781538683965

Emotion Recognition is a critical component in the evolution of Human Computer Interaction (HCI). The advancement of Artificial Intelligent (AI) has enabled human and computer to achieve a symbiotic partnership where computers can understand human emotions (e.g., happy or sad) so that computer systems can adapt to human emotion reaction. Detecting and recognizing optimum human emotion is the first step towards this human and computer symbiosis. This paper first studies and compares different emotion recognition Machine Learning algorithms. It then proposes the application of personalized emotion recognition learning;where a machine learns the emotions of a specific user to achieve higher emotion recognition accuracy.

关键词： emotion recognition facial expression recognition human-computer interaction machine emotional intelligence image processing machine learning

来源：评论

学校读者我要写书评

暂无评论

Small Ball Tracking with Trajectory Prediction

Small Ball Tracking with Trajectory Prediction

引用

IEEE International conference on Signal and image processing (ICSIP)

作者： Shambel Ferede Xuemei xie Chen Zhang Jiang Du Guangming Shi School of Artificial Intelligence Xidian University Xi’an China College of Computing and Informatics Assosa University Assosa Ethiopia

ISBN: (数字)9781728168968

ISBN: (纸本)9781728168975

We propose small ball tracking with trajectory prediction to track them when the athletes playing with balls at sports field, as shown in Figure 1. This is a challenging task and important for intelligent physical education, especially for the coaches to grasp the accuracy of actions by the players based on the pre-defined rules. The proposed method achieves a good performance on small ball tracking since the designed algorithm incorporates motion, temporal and directional information to predict the trajectory. Experimental results show that the proposed method effectively reduces the number of identity switches and decreases track fragmentation. With the integration of motion, directional information and frames storage, this framework efficiently track small balls when the athletes playing with them.

关键词： Tracking image processing Education Prediction algorithms Trajectory Task analysis Sports

来源：评论

学校读者我要写书评

暂无评论

image processing and machine learning applications in mining industry: Mine 4.0 3

Image processing and machine learning applications in mining...

引用

3rd International conference on Intelligent systems and Advanced Computing Sciences, ISACS 2019

作者： Ouanan, Hamid Abdelwahed, El Hassan National School of Applied Sciences Sultan Moulay Slimane University Beni Mellal Morocco CSEHS Mohammed VI Polytechnic University Marrakesh Morocco

ISBN: (纸本)9781728148137

Recently, image processing (IP) and Machine learning (ML) algorithms have been successfully used in a wide variety of industry sectors. In this paper, we first provide mining engineers with the state of the art about IP and ML applications in the mining industry. furthermore, we propose a real time application for froth image analysis in the context of mineral processing. Finally, we propose some future directions, including suggestions on mining data collection and development of an exploration tool based on IP and ML algorithms by taking advantage of cloud computing technology to analyze geoscience data in order identify target areas with high prospectively potential. © 2019 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Addressing Irregularity in Sparse Neural Networks Through a Cooperative Software/Hardware Approach

引用

IEEE TRANSACTIONS ON COMPUTERS 2020年第7期69卷 968-985页

作者： Zeng, xi Zhi, Tian Zhou, Xuda Du, Zidong Guo, Qi Liu, Shaoli Wang, Bingrui Wen, Yuanbo Wang, Chao Zhou, Xuehai Li, Ling Chen, Tianshi Sun, Ninghui Chen, Yunji Chinese Acad Sci Inst Comp Technol ICT State Key Lab Comp Architecture Beijing 100864 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China Cambricon Technol Beijing Peoples R China Univ Sci & Technol China Hefei 230052 Peoples R China Chinese Acad Sci Inst Software Beijing 100864 Peoples R China CAS Ctr Excellence Brain Sci & Intelligence Techn Shanghai Res Ctr Brian Sci & Brain Inspired Intel Inst Brain Intelligence Technol Zhangjiang Lab BITZJLab Shanghai Peoples R China

Neural networks have become the dominant algorithms rapidly as they achieve state-of-the-art performance in a broad range of applications such as image recognition, speech recognition, and natural language processing. However, neural networks keep moving toward deeper and larger architectures, posing a great challenge to hardware systems due to the huge amount of data and computations. Although sparsity has emerged as an effective solution for reducing the intensity of computation and memory accesses directly, irregularity caused by sparsity (including sparse synapses and neurons) prevents accelerators from completely leveraging the benefits, i.e., it also introduces costly indexing module in accelerators. In this article, we propose a cooperative software/hardware approach to address the irregularity of sparse neural networks efficiently. Initially, we observe the local convergence, namely larger weights tend to gather into small clusters during training. Based on that key observation, we propose a software-based coarse-grained pruning technique to reduce the irregularity of sparse synapses drastically. The coarse-grained pruning technique, together with local quantization, significantly reduces the size of indexes and improves the network compression ratio. We further design a multi-core hardware accelerator, Cambricon-SE, to address the remaining irregularity of sparse synapses and neurons efficiently. The novel accelerator have three key features: 1) selector modules to filter unnecessary synapses and neurons, 2) compress/decompress modules for exploiting the sparsity in data transmission (which is rarely studied in previous work), and 3) a multi-core architecture with elevated throughput to meet the real-time processing requirement. Compared against a state-of-the-art sparse neural network accelerator, our accelerator is 1.20x and 2.72x better in terms of performance and energy efficiency, respectively. Moreover, for real-time video analysis tasks, Cambricon-SE

关键词： Accelerator architecture deep neural networks sparsity

来源：评论

学校读者我要写书评

暂无评论

Application Analysis of RTS Smoothing on the Data Post-processing of BDS/INS Integrated Navigation

Application Analysis of RTS Smoothing on the Data Post-proce...

引用

International conference on Mechanical, Control and Computer Engineering (ICMCCE)

作者： Zhaoyang Zuo Yubin Wu Po Chen Dongrong Meng School of mechanical engineering Xijing University Xi'an Shanxi China Xi'an Research Institute of High Technology Xi'an Shanxi China

In the data post-processing of BDS/INS integrated navigation, the high precision smoothing algorithm is researched aimed at solving the problem of precision degradation caused by the loss of lock of the BDS receiver for a long time. The RTS smoothing algorithm is analyzed when the BDS signal is interrupted, and the equations are given at the same time experimental program are designed. The results show that RTS is not only able to have a smoothing effect on the navigation solution results, but also can significantly weaken the influence of BDS loss of lock to the integrated navigation system.

关键词： Degradation Smoothing methods Satellites Process control Receivers Filtering algorithms Satellite navigation systems

来源：评论

学校读者我要写书评

暂无评论

Fractional Contrast Stretching for image Enhancement of Aerial and Satellite images 18

Fractional Contrast Stretching for Image Enhancement of Aeri...

引用

18th image processing: algorithms and systems conference, IPAS 2020

作者： Trongtirakul, Thaweesak Chiracharit, Werapon Imberman, Susan Agaian, Sos Department of Electronic and Telecommunication Faculty of Engineering King Mongkut’s University of Technology Thonburi 126 Pracha Uthit Rd Bang Mot Thung Khru Bangkok10140 Thailand Department of Computer Science College of Staten Island City University of New York 2800 Victory Blvd. Staten IslandNY10314 United States Department of Computer Science City University of New York New York CityNY United States

Aerial and satellite photographs suffer from uncontrollable weather conditions. Frequently, illumination of the same region can be totally different. This is usually due to shadowing self-obstruction or light reflection. Existing image enhancement methods fail to improve hidden details and local contrast at the same visualization level. They are not developed to enhance through local dark or light regions simultaneously. Also, the current aerial and satellite image enhancement methods have several limitations. For instance, these include intensity saturation, non-uniform brightness, halo effect, blur edges, and so on. This article introduces a fractional contrast stretching concept for aerial and satellite image enhancement based on a novel automated non-uniform luminance normalization that is not provided by the user as input parameters. The introduced approach contains several new techniques: (i) no reference non-linearly fractional contrast stretching with automatic non-uniform luminance normalization and (ii) non-linearly local contrast stretching for spatial details and edge sharpening. The proposed algorithm was tested on the orthorectified aerial photograph database with a pixel resolution of 1 meter or finer from across the United States during 2000–2016. The simulation results illustrate the efficiency of the proposed algorithm and its advantages for cutting-edge aerial and satellite image enhancement, resulting in visualization quality. c Society for Imaging Science and Technology 2019

关键词： Antennas

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：