检索结果-内蒙古大学图书馆

Surface-PMSM Sensorless Control Strategy Based on Reduced-Order Linear Kalman Filter Cooperating with Prediction Error Rolling Compensation

引用

IEEE Transactions on Power Electronics 2025年第8期40卷 10804-10815页

作者： Xu, Sang Shen, Anwen Tang, Qipeng Wang, Miaomiao Luo, Pan Luo, Xin Xu, Jinbang National Key Laboratory of Science and Technology on Multispectral Information Processing Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Wuhan430074 China Science and Technology on Reactor System Design Technology Laboratory Chengdu China

Kalman filter (KF) is increasingly attracted for sensorless control of surface permanent magnet synchronous motors (SPMSMs) due to its strong robustness against measurement and system noise. However, conventional method suffers from poor position and speed estimation accuracy under dynamic conditions, and high computational cost. In order to solve these problems, an enhanced sensorless control strategy based on reduced-order linear Kalman filter (RLKF) cooperating with prediction error rolling compensation is introduced in this paper. Differing from conventional method, a reduced-order linear state equation encompassing rotor position, speed and torque disturbance is constructed. Then, by obtaining the prediction error of system output using the motor current equation in the predictive reference frame, the optimal estimation of rotor position and speed in KF algorithm is achieved based on the reduced-order model. This not only simplifies the calculation process, but also enhances the position and speed estimation accuracy under dynamic conditions. Meanwhile, a prediction error rolling compensation algorithm is developed to minimize the estimation deviations caused by motor parameters variations. Additionally, the system's dynamic performance is further improved with an adopted speed controller based on torque disturbance feedforward and acceleration feedback. Finally, experimental results verify the effectiveness and feasibility of the proposed strategy.1 © 1986-2012 IEEE.

关键词： Permanent magnets

来源：评论

学校读者我要写书评

暂无评论

Enhancing Thermal Infrared Object Detection Using SimAM-Integrated YOLOX for Improved Feature Representation

Enhancing Thermal Infrared Object Detection Using SimAM-Inte...

引用

IEEE International Conference on Consumer Electronics (ICCE)

作者： Jaehong Yoon Heegwang Kim Chanyeong Park Junbo Jang Jiyoon Lee Joonki Paik Image Processing and Intelligent System Laboratory Graduate School of Advanced Imaging Science Multimedia and Film Chung-Ang University Seoul Korea Image Processing and Intelligent System Laboratory Graduate School of Artificial Intelligence Chung-Ang University Seoul Korea

ISBN: (数字)9798331521165

ISBN: (纸本)9798331521172

Object detection with thermal infrared images is vital for applications like autonomous driving in low-light and adverse environmental conditions. While TIRDet has improved thermal-only object detection through a Thermal-To-Visible (T2V) translation model, this module can suffer from information loss in certain scenarios. To address this, we propose enhancing the CSPDarknet53 backbone of YOLOX within TIRDet by incorporating SimAM, a parameter-free attention mechanism. SimAM enhances feature representation by inferring 3D attention weights based on an energy function inspired by neuroscience theories, without increasing model parameters. By strengthening feature extraction within the backbone, our approach compensates for the T2V module's information loss, thereby improving detection performance under challenging conditions. Experiments on the LLVIP and FLIR datasets demonstrate superior performance, underscoring the effectiveness of parameter-free attention mechanisms for advancing thermal object detection.

关键词： Solid modeling Translation Attention mechanisms Three-dimensional displays Neuroscience Object detection Feature extraction Text to video Autonomous vehicles Consumer electronics

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Privacy Protection Solution: Enhancing Face Obscuring Techniques with Automated Identification, Mobile Integration, and Scalable Services

A Comprehensive Privacy Protection Solution: Enhancing Face ...

引用

IEEE International Conference on Consumer Electronics (ICCE)

作者： Ilhwan Kim Hyeongseok Oh Sangwoo Yun Heunseung Lim Jaeseok Ryu Joonki Paik Image Processing and Intelligent System Laboratory Graduate School of Advanced Imaging Science Multimedia and Film Chung-Ang University Seoul Korea Image Processing and Intelligent System Laboratory Graduate School of Artificial Intelligence Chung-Ang University Seoul Korea

ISBN: (数字)9798331521165

ISBN: (纸本)9798331521172

We propose a novel application aimed at protecting personal privacy. With the proliferation of various media platforms, issues related to personal portraits have emerged. To address these problems, previous applications propose methods for either Mosaic or replace it with another object. However, existing methods suffer from issues such as high time costs and unnatural rendering. To address these problems, we propose designing an automatic face identification and replacement system by combining face detection, super-resolution, and face replacement models. This approach aims to reduce processing time and enhance natural rendering. In addition to the technological advancements, we suggest expanding this system into a mobile service, allowing users to easily protect their privacy on the go. This mobile platform would provide a user-friendly interface and seamless integration with various social media and communication apps, making it accessible to a broader audience. Furthermore, we explore potential expansion opportunities, such as cloud-based processing for scalability and the development of APIs that other developers can integrate into their own applications, thereby broadening the service's reach and impact. We demonstrate that our approach is simpler and more natural compared to traditional handcrafted tasks by applying it to diverse scenarios.

关键词： Privacy Accuracy Scalability Superresolution Media Rendering (computer graphics) Face detection Protection Usability Faces

来源：评论

学校读者我要写书评

暂无评论

ViSeNet: A Visual-Semantic Fusion Network for Enhancing Few-Shot Classification

ViSeNet: A Visual-Semantic Fusion Network for Enhancing Few-...

引用

IEEE International Conference on Consumer Electronics (ICCE)

作者： Dongheon Lee Sangwoo Yun Joonki Paik Image Processing and Intelligent & System Laboratory Graduate School of Artificial Intelligence Chung-Ang University Seoul Korea Image Processing and Intelligent & System Laboratory Graduate School of Advanced & Imaging Science Multimedia and Film Chung-Ang University Seoul Korea

ISBN: (数字)9798331521165

ISBN: (纸本)9798331521172

Few-shot learning addresses the challenge of recognizing novel classes with only a few labeled examples, a critical issue in limited data scenarios. This paper proposes a multi-modal Visual and Semantic Network (ViSeNet), which enhances few-shot classification by mining linguistic features and fusing weighted vectors. ViSeNet generates enriched class prototypes by leveraging both visual and semantic information. The linguistic feature mining process utilizes image-to-text models to produce class-specific textual descriptions, which are then transformed into representative semantic embeddings. For visual feature extraction, we employ a pretrained Swin Transformer, while text embeddings are integrated for each class using weighted factors. By combining these modalities, ViSeNet constructs class prototypes that capture both visual and semantic characteristics. Experimental results on benchmark datasets, particularly CIFAR-FS, demonstrate that ViSeNet achieves performance comparable to state-of-the-art approaches.

关键词： Visualization Semantics Prototypes Linguistics Transformers Feature extraction Vectors Data mining Few shot learning Consumer electronics

来源：评论

学校读者我要写书评

暂无评论

Autonomous Path Planning via Sand Cat Swarm Optimization With Multi-Strategy Mechanism for Unmanned Aerial Vehicles in Dynamic Environment

引用

IEEE Internet of Things Journal 2025年

作者： Deng, Wu Feng, Jiayi Zhao, Huimin Civil Aviation University of China College of Electronic Information and Automation Tianjin300300 China Civil Aviation University of China Tianjin Key Lab Intelligent Signal and Image Processing Tianjin300300 China State Key Laboratory of Rail Transit Vehicle System of Southwest Jiaotong University Chengdu610031 China

Unmanned Aerial Vehicles (UAVs) face critical challenges in path planning in dynamic environment. Sand Cat Swarm Optimization (SCSO) algorithm has demonstrated promise in addressing complex optimization challenges. However, SCSO is limited by slow convergence, susceptibility to local optima, and insufficient adaptability. To overcome these shortcomings, an enhanced SCSO with the spiral search, Livy flight, tent chaotic mapping, and adaptive sparrow alert mechanism, namely TSLS-SCSO is developed to propose an autonomous path planning method for UAVs in dynamic environment. In TSLS-SCSO, a new population initialization strategy with tent chaotic mapping is designed to achieve a large dynamic range and coverage capability. Then a new spiral search strategy is designed to broaden the search range in the search phase. And a new Livy flight strategy is employed to enrich the diversity of population in the attacking prey phase. A new sparrow alert mechanism with integrating the sand cat group with the sparrow alert is designed to obtain faster convergence speed and accuracy. The experiment results on CEC 2017 and CEC 2022 show that the TSLS-SCSO obtains higher accuracy and more stable solutions and exhibits better competitiveness. Furthermore, the proposed UAV path planning method successfully found effective paths with an obstacle avoidance effectiveness of 95.5%. The obtained results validate the effectiveness and competitiveness of TSLS-SCSO in UAV path planning in the dynamic environment. © 2014 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Air Pollution Monitoring By Integrating Local and Global Information in Self-Adaptive Multiscale Transform Domain

引用

IEEE Transactions on Multimedia 2025年

作者： Gu, Ke Liu, Yuchen Liu, Hongyan Liu, Bo Qiao, Junfei Lin, Weisi Zhang, Wenjun Beijing University of Technology School of Information Science and Technology Engineering Research Center of Intelligent Perception and Autonomous Control of Ministry of Education Beijing Laboratory of Smart Environmental Protection Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing Artificial Intelligence Institute Beijing100124 China Massey University School of Mathematical and Computational Sciences New Zealand Nanyang Technological University College of Computing and Data Science Singapore Shanghai Jiao Tong University Institute of Image Communication and Information Processing Shanghai China

As the deadliest form of pollution, air pollution had a prolonged severe damage to the human health and life safety of nearly 99% of the world's population. Facing to the problem that billions of tons of pollutants discharged into the air per year by industrial activities, this paper proposed a novel image-based air pollution monitor (IAPM) by incorporating local and global information in the self-adaptive multiscale transform domain, so as to achieve the timely and effective leakage detection of typical air pollutants from a single image. To be specific, this paper first developed a screen-shaped module according to two significant findings in visual neuroscience, which include the high sensitivity of human eyes to horizontal and vertical stimuli and the center-surround inhibition, by designing and fusing the square module, horizontal strip module and vertical strip module parallelly for simulating the behaviour of human eyes to extract local features. Second, the learnable weights and proportional mapping were applied to incorporate the screen-shaped module and lightweight vision transformer as backbone, towards more richly exploiting and fusing local and global information just as the way a brain perceives external stimuli. Third, a new self-adaptive multiscale transform domain method was devised based on two motivations from the visual characteristics of multiscale perception and the brain characteristics of self-adaptive domain transform to modify the backbone by using the operations of pooling and pointwise convolution. Extensive experiments implemented on the datasets of carbon particulate matters and ethylene leakage confirmed the superior monitoring performance of the proposed IAPM model beyond the state-of-the-art (SOTA) peers by an accuracy gain of about 4%. Furthermore, the proposed IAPM model only required 0.089 GFLOPs and 0.15 million model parameters, remarkably outperforming SOTA competitors in computational efficiency and storage resources. © 1999-2

关键词： Information leakage

来源：评论

学校读者我要写书评

暂无评论

Research on feature classification method of network text data based on association rules

引用

International Journal of Computers and Applications 2020年第2期42卷 157-163页

作者： Huang, Hongben Guangxi Colleges and Universities Key Laboratory of Image Processing and Intelligent Information System Wuzhou University Wuzhou China

Due to the large number of features, sparse data, low precision of feature extraction, and long time-consuming. Using the current method to classify the text data features, it is difficult to achieve better results. A method of feature classification of network text data based on association rules is proposed. A single word is used as a classification feature to extract the association feature item of text data. The feature item after dimension reduction is to construct classifier. Through the support vector machine algorithm, the network text data feature classification is realized. The highest precision ratio of Hangxia et al.’s study [Hangxia Z, Jiajun Y, Huan R. Text categorization based on deep belief network. Comput Eng Sci. 2016;38(5):871–876] is 69%, the highest precision ratio of Wenjuan et al.’s study [Wenjuan S, Shun L, Fei Y. Iterative text classification framework based on background learning. Comput Eng Applic. 2015;51(9):129–134] is 85%, and the highest precision ratio of the proposed method is 93%. The precision of this method is higher, which shows that the method can accurately reflect the feature class information of text data and reduce the error rate of text classification. Experimental results show that the proposed method can improve the accuracy of classification results and has high robustness. © 2018, © 2018 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Association rules

来源：评论

学校读者我要写书评

暂无评论

Comparison of Several Color Histogram Based Retrieval Algorithms

Comparison of Several Color Histogram Based Retrieval Algori...

引用

2016 IEEE Advanced Information Management,Communicates,Electronic and Automation Control Conference(IMCEC 2016)

作者： Qiuxiang Liao Wuzhou University Guangxi Colleges and University Key Laboratory of Image Processing and Intelligent Information System

ISBN: (纸本)9781509001668

As an important visual characteristic,color has been widely applied in content based image *** paper adopted the RGB color model,wherein intersection distance method,Euclidean distance method and correlation distance method based on color histogram characteristics were applied respectively in the experiments of the same sample image and the same image *** results show that the three algorithms could retrieve the sample image accurately,wherein the histogram intersection algorithm completed the retrieval most quickly;the Euclidean distance method based on simple theories can be understood easily;and the correlation distance method had the lowest recall *** experimental results have certain guidance and reference values for selecting and optimizing the content based image retrieval algorithm.

关键词： accumulative histogram histogram intersection distance euclidean distance correlation distance

来源：评论

学校读者我要写书评

暂无评论

Small Object Detection in Infrared images Using Attention Mechanism and Sigmoid Function

Small Object Detection in Infrared Images Using Attention Me...

引用

2024 IEEE International Conference on Consumer Electronics, ICCE 2024

作者： Lee, Jiyoon Kim, Heegwang Park, Chanyeong Jang, Junbo Paik, Joonki Chung-Ang University Image Processing and Intelligent System Laboratory Department of Artificial Intelligence Seoul Korea Republic of Chung-Ang University Image Processing and Intelligent System Laboratory Department of Image Seoul Korea Republic of

ISBN: (纸本)9798350324136

Infrared image-based object detection is challenging due to inherent low resolution and scarce details, especially when locating small objects that cover minimal region in the image. We present a methodology for detecting small objects in infrared imagery captured by UAVs, emphasizing the use of attention mechanisms to increase detection precision. Using YOLOX as our baseline network, we integrated a modified Recursive Feature Pyramid (RFP) to enhance vehicle detection in the VisDrone-Vehicle dataset. To amplify the spatial details of these smaller objects, we incorporated an attention module and sigmoid function, bridging the connection between the primary and secondary Feature Pyramid Networks (FPNs). The sigmoid function further refines the RFP outputs by filtering out background *** experiments demonstrate that the proposed network outperforms the baseline in detecting vehicles in infrared images. © 2024 IEEE.

关键词： infrared image object detection small object detection

来源：评论

学校读者我要写书评

暂无评论

Blur region detection and segmentation of partial blur image

Blur region detection and segmentation of partial blur image

引用

2021 International Conference on Signal processing and Communication Technology, SPCT 2021

作者： Wang, Kui-Kui Hou, Yi-Feng Lv, Mei-Ni Gong, Ping Yang, Qiu-Hui Gan, Hui Guangxi Key Laboratory of Image Processing and Intelligent Information System Wuzhou University Wuzhou543000 China

ISBN: (数字)9781510653344

ISBN: (纸本)9781510653337

In order to address the detection and segmentation of partial blur for natural images,a no-reference and training-free algorithm was proposed. Firstly, the test image was re-blurred by a Gaussian low-pass filter. Secondly, the pixel-wise singular value decomposition within N×N neighborhoods for both the test image and the re-blurred image were conducted to obtain the ratio of the end singular value to all singular value. According to the ratio,the blurriness distribution function was structured and the blurriness distribution map was drawed. Finally, combined with the K-means clustering algorithm and the erosion and dilation operations, the test image could be segmented into blur region and clear region. Experiment results show that the proposed approach can effectively detect and segment the partial blur image and behave well at precision, recall and F-score. © 2022 SPIE.

关键词： Distribution functions

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：