检索结果-内蒙古大学图书馆

Research on transformer fault diagnosis: Based on improved firefly algorithm optimized LPboost-Classified regression tree

引用

IET GENERATION TRANSMISSION & DISTRIBUTION 2021年第20期15卷 2926-2942页

作者： Zhang, Xiaoxing Fang, Rongxing Zhang, Guozhi Fang, Yaqi Zhou, Xiu Ma, Yunlong Wang, Kun Chen, Kang Hubei Univ Technol Hubei Engn Res Ctr Safety Monitoring New Energy & Wuhan 430068 Peoples R China State Grid Ningxia Elect Power Res Inst Yinchuan 750002 Ningxia Peoples R China

The information of dissolved gas in transformer oil can reflect the potential fault in oil immersed power transformer. In order to improve the accuracy of transformer fault diagnosis, a transformer fault diagnosis model based on IFA-LPboost-CART is proposed here. First, a LPboost-CART model is established. The classification and regression tree (CART) are used as the weak classifiers, and the linear programming boosting (LPboost) ensemble learning method is used to adjust the weight of each weak classifier to construct a strong classifier. Then the improved firefly algorithm (IFA) is adopted to optimize the number of CART and the maximum number of splits of CART in LPboost-CART to obtain the IFA-LPboost-CART model. The experimental results show that, compared with the existing methods, such as CART and support vector machine (SVM), the proposed IFA-LPboost-CART model has higher fault diagnosis accuracy, which can provide technical support for transformer fault diagnosis.

关键词： Organic insulation Optimisation techniques computer vision and image processing techniques Optimisation techniques Combinatorial mathematics Transformers and reactors

来源：评论

学校读者我要写书评

暂无评论

Accurate and efficient vehicle detection framework based on SSD algorithm

引用

IET image processing 2021年第13期15卷 3094-3104页

作者： Zhao, Min Zhong, Yuan Sun, Dihua Chongqing Univ Sch Automat Chongqing 400044 Peoples R China

Vehicle detection plays an important role in intelligent transportation systems and security. Using the original Single Shot MultiBox Detector (SSD) directly for vehicle detection, lacks accuracy and stability. Moreover, most of the state-of-the-art methods need cost a lot of time to inference. Vehicle detection is often used in complex traffic environments. Therefore, faster detection speed and higher detection accuracy are required. This study is aimed at developing a trade-off between accuracy and speed vehicle detection framework based on the SSD algorithm. To improve the multi-scale detection performance of SSD, semantic information, detailed features and receptive fields are combined to propose the feature pyramid enhancement strategy (FPES). On the other hand, the cascade detection mechanism is proposed to strengthen the positioning capability of SSD and an adaptive threshold acquisition method for object detection module (ODM) stage to improve model accuracy. Finally, a more efficient convolutional network is deployed through network slimming. Experimental results demonstrate that the proposed framework achieves state-of-the-art performance on UA-DETRAC and Udacity benchmarks. Interestingly, the inference time is the lowest for the proposed method than the state-of-the-art methods, promising its application for fast and effective vehicle detection.

关键词： Optical, image and video signal processing computer vision and image processing techniques Traffic engineering computing Neural nets

来源：评论

学校读者我要写书评

暂无评论

Series-parallel pipeline architecture for high-resolution catadioptric panoramic unwrapping

引用

IET image processing 2010年第5期4卷 403-412页

作者： Chen, L. -D. Zhang, M. -J. Xiong, Z. -H. Natl Univ Def Technol Coll Informat Syst & Management Changsha 410073 Hunan Peoples R China

To implement high-speed panoramic unwrapping of high-resolution catadioptric omnidirectional images on field-programmable gate array (FPGA), a novel design technique of pipeline architecture is proposed, named a 'series-parallel pipeline'. Based on the strategy of 'block prefetching', catadioptric omnidirectional images are divided into image blocks before loading into the pipeline. Multiple functional sub-modules are copied to carry out the relatively time-consuming steps in parallel whereas fewer sub-modules or only one sub-module is created to carry out those less time-consuming steps. The number of copies is determined by the proportion of execution time of each step, and several neighbouring basic units are combined to form a 'unit package' before loading into the pipeline. The basic units in one 'unit package' are processed in series while carrying out the less time-consuming steps, but processed in parallel while carrying out the more time-consuming steps. A hardware pipeline design of series-parallel architecture is implemented on Xilinx Spartan-3 FPGA, which is able to unwrap one catadioptric omnidirectional image with size 1024 x 1024 into one cylindrical panorama with size 3200 x 768 at 12.480 ms per frame when the system clock is 100 MHz.

关键词： image resolution field programmable gate arrays Logic circuits Parallel architecture Logic and switching circuits parallel architectures computer vision and image processing techniques storage management Xilinx Spartan-3 FPGA File organisation series-parallel pipeline architecture block prefetching strategy high-resolution catadioptric omnidirectional images high-resolution catadioptric panoramic unwrapping Optical, image and video signal processing

来源：评论

学校读者我要写书评

暂无评论

Segmentation of noisy colour images using Cauchy distribution in the complex wavelet domain

引用

IET image processing 2011年第2期5卷 159-170页

作者： Wan, T. Canagarajah, N. Achim, A. Beijing Normal Univ Sch Informat Sci & Technol Beijing 100875 Peoples R China Univ Bristol Dept Elect & Elect Engn CCR Bristol BS8 1UB Avon England

This study proposes a novel image segmentation technique for noisy colour images, in which the heavy-tailed characteristics of the image are modelled by Cauchy distributions. First, the RGB colour bands of the noisy image are decomposed into multiresolution representations using the dual-tree complex wavelet transform. For each wavelet subband, a model is built assuming that the input coefficients are contaminated with signal-independent additive white Gaussian noise. Hence, the authors derive an estimation rule in the wavelet domain to obtain the noise-free coefficients based on the bivariate Cauchy distribution. The bivariate model makes it possible to exploit the inter-scale dependencies of wavelet coefficients. Subsequently, the image is roughly segmented into textured and non-textured regions using the bivariate model parameters corresponding to the denoised coefficients. A multiscale segmentation is then applied to the resulting regions. Finally, a novel statistical region merging algorithm is introduced by measuring the Kullback-Leibler distance between the estimated Cauchy models for the neighbouring segments. The experiments demonstrate that the authors algorithm yields robust segmentation results for noisy images containing artificial or natural noise.

关键词： multiscale segmentation image colour analysis wavelet subband denoised coefficient wavelet coefficient multiresolution representation signal-independent additive white Gaussian noise noise-free coefficient computer vision and image processing techniques RGB colour bands statistical region merging algorithm bivariate Cauchy distribution Optical, image and video signal processing Integral transforms Cauchy model image segmentation complex wavelet domain noisy colour image segmentation wavelet transforms bivariate model parameter Kullback-Leibler distance robust segmentation dual-tree complex wavelet transform

来源：评论

学校读者我要写书评

暂无评论

Radar target classification considering unknown classes using deep convolutional neural network ensemble

引用

IET RADAR SONAR AND NAVIGATION 2021年第10期15卷 1325-1339页

作者： Lee, Byeong-ho Lee, Seongwook Kang, Seokhyun Kim, Seong-Cheol Kim, Yong-Hwa Seoul Natl Univ Dept Elect & Comp Engn Seoul South Korea Seoul Natl Univ Inst New Media & Commun Seoul South Korea Korea Aerosp Univ Coll Engn Sch Elect & Informat Engn Goyang Si Gyeonggi Do South Korea Hyundai Mobis Uiwang Si Gyeonggi Do South Korea Korea Natl Univ Transportat Dept Data Sci Uiwang Si 16106 Gyeonggi Do South Korea

The target classification of unknown classes using radar sensor data is discussed. The neural network-based classifier shows high classification accuracy for the learned class targets. However, there is a risk of false decision for the untrained class target owing to an overconfidence problem. The output confidence of the classifier is calibrated using the deep convolutional neural network ensemble structure to propose a method to set the proper threshold for output confidence to decide unknown class targets. When using the proposed method, the accuracy of the learned target is maintained similar to that of the existing single neural network-based classifier, whereas the unknown class target is better identified. Further analysis verifies the effectiveness of the proposed method using commercial automotive radar. The proposed method can classify learned targets with an accuracy of 95% and distinguish unknown class targets with an accuracy of at least 85%. Based on the interaction with other sensors, individual sensors need to make reserved decisions about uncertain information. It is expected that the proposed ensemble network will be efficient in designing the classifier to perform target classification including unknown class decision.

关键词： computer vision and image processing techniques existing single neural network-based classifier learning (artificial intelligence) high classification accuracy pattern classification unknown classes unknown class decision radar sensor data Radar equipment, systems and applications untrained class target deep convolutional neural network ensemble structure Automobile electronics unknown class target road vehicle radar ensemble network neural nets output confidence learned class targets image recognition learned target image classification radar target classification Other topics in statistics

来源：评论

学校读者我要写书评

暂无评论

Non-parametric Bayesian super-resolution

引用

IET RADAR SONAR AND NAVIGATION 2010年第4期4卷 639-648页

作者： Lane, R. O. QinetiQ Malvern Technol Ctr Malvern WR14 3PS Worcs England

Super-resolution of signals and images can improve the automatic detection and recognition of objects of interest. However, the uncertainty associated with this process is not often taken into consideration. This is important because the processing of noisy signals can result in spurious estimates of the scene content. This study reviews a variety of super-resolution techniques and presents two non-parametric Bayesian super-resolution algorithms that not only take uncertainty into account, but also retain knowledge about the output uncertainty in the form of a full probability distribution. One of the two Bayesian techniques is based on an analytical calculation re-interpreted as super-resolution, and the other is a novel numerical algorithm. Although the algorithms are presented as stand-alone techniques for image analysis, such Bayesian super-resolution algorithms can increase automatic target recognition performance over standard super-resolution.

关键词： nonparametric Bayesian superresolution image analysis probability automatic object detection object recognition computer vision and image processing techniques object detection numerical analysis probability distribution image recognition signal superresolution numerical algorithm automatic object recognition Other numerical methods image superresolution image resolution Other topics in statistics

来源：评论

学校读者我要写书评

暂无评论

image resolution and contrast enhancement with optimal brightness compensation using wavelet transforms and particle swarm optimization

引用

IET image processing 2021年第12期15卷 2833-2840页

作者： Tirumani, V. Hyma Lakshmi Tenneti, Madhu Srikavya, K. Ch. Kotamraju, Sarat Kumar SRKR Engn Coll ECE Dept Guntur Andhra Pradesh India Educ Consultancy Bhimavaram Andhra Pradesh India KLEF Guntur Andhra Pradesh India

Improving the image resolution and contrast along with uniform brightness distribution over the entire image helps to retrieve the vital realistic information necessary for human perception and interpretation. A new procedure to improve these parameters is implemented and tested. Initially, the image is super resolute using discrete wavelet transform (DWT), stationary wavelet transform (SWT) image decomposition and bicubic interpolation. The resolute image is used for contrast enhancement by using SWT and contrast limited adaptive histogram equalization (CLAHE) approach. The optimized brightness compensation technique, which uses particle swarm optimization (PSO), is applied to the resolution and contrast-enhanced image to obtain uniform brightness distribution over the entire image. The proposed approach is tested on three data sets of images and it is found that the visual results, as well as the resolution and contrast levels of the tested images, are significantly superior to subjective and objective results.

关键词： Optical, image and video signal processing Optimisation techniques computer vision and image processing techniques Integral transforms Optimisation techniques Integral transforms Patient diagnostic methods and instrumentation Biology and medical computing

来源：评论

学校读者我要写书评

暂无评论

Fractional-order generalized Laguerre moments and moment invariants for grey-scale image analysis

引用

IET image processing 2021年第2期15卷 523-541页

作者： Benouini, Rachid Batioua, Imad Zenkouar, Khalid Najah, Said Univ Sidi Mohamed Ben Abdellah Fac Sci & Technol Lab Intelligent Syst & Applicat LSIA Fes Morocco

Here, a new set of fractional-order moments, named fractional-order generalized Laguerre moments (FGLM), is introduced. These proposed moments are defined on the Cartesian coordinate system and their basis functions are represented by the fractional-order generalized Laguerre polynomials. Contrary to the classical Chebyshev, Legendre and Gegenbauer moments, which provide only global feature, our proposed FGLM have the ability to extract both global and local features. Moreover, a new set of rotation, scale and translation invariants of the FGLM, is derived and introduced for image classification and invariant pattern recognition. Just as important, we have presented a systematic parameter selection method for finding the optimal fractional parameter values with respect to pattern recognition applications. Finally, several recursive methods for reducing the computation time of our proposed invariants are also provided in this study. Therefore, to demonstrate the performance of the introduced fractional-order moments and moment invariants, a number of experimental analysis are performed in terms of global and local features extraction, robustness to noise, invariance to geometric deformations, object recognition and computational speed. The presented theoretical and experimental results clearly show that the proposed fractional-order moments and their corresponding invariants could be extremely useful in the field of image analysis.

关键词： Optical, image and video signal processing image recognition computer vision and image processing techniques

来源：评论

学校读者我要写书评

暂无评论

Some results on characteristics of bistatic high-range resolution profiles for target classification

引用

IET RADAR SONAR AND NAVIGATION 2012年第5期6卷 379-388页

作者： Ai, X. Li, Y. Wang, X. Xiao, S. Natl Univ Def Technol Sch Elect Sci & Engn Changsha Hunan Peoples R China

This study focuses on the bistatic high-range resolution profiles (HRRPs) of high-speed and manoeuvring targets and considers how to utilise the length of the bistatic HRRP for target classification. The bistatic HRRP of a high-speed and manoeuvring target is obtained via stretch processing and motion compensation, and its distortion caused by target translation is analysed quantitatively. It is demonstrated that the distortion of bistatic HRRPs is quite different from the monostatic case. The conventional length of the bistatic HRRP cannot reflect the target length, as in the monostatic case, so a new length is defined - the bistatic bisector HRRP length - which corresponds to the length of the target's projection on the bisector of the bistatic angle. Additionally, the sensitivity of the bistatic HRRP to the target aspect and location is discussed and the bistatic bisector HRRP length is proved to be applicable for target classification through computer simulation and electromagnetic calculation.

关键词： target-s projection computer vision and image processing techniques high-speed target manoeuvring target motion compensation Optical, image and video signal processing image classification stretch processing computer simulation target translation target classification electromagnetic calculation bistatic high-range resolution profiles

来源：评论

学校读者我要写书评

暂无评论

Towards accurate coronary artery calcium segmentation with multi-scale attention mechanism

引用

IET image processing 2021年第6期15卷 1359-1370页

作者： Ning, Yang Zhang, Yunfeng Li, Xuemei Zhang, Caiming Shandong Univ Sch Software Jinan Peoples R China Shandong Univ Finance & Econ Sch Comp Sci & Technol Jinan Peoples R China Shandong Univ Finance & Econ Shandong Prov Key Lab Digital Media Technol Jinan Peoples R China Shandong Coinnovat Ctr Future Intelligent Comp Yantai Peoples R China

Coronary artery calcium is a strong and independent marker of atherosclerosis and cardiovascular disease. Typically, the accurate segmentation of computed tomography images of the chest is an important prerequisite and basis for coronary artery calcium identification and analysis. However, this is very challenging in practice because the boundaries of coronary artery calcium, the small lesions with large shape variation, are very blurry, resulting in poor performance in existing studies. To tackle this challenge, we present a novel Attention-based Multi-Scale Network called AMSN, which can process information through both the main and boundary branches in parallel. Key to our AMSN is a new non-local multi-scale context encoder module, which is mainly composed of the multi-scale attention mechanism and local global long short-term memory module. By aggregating the multi-scale context information, i.e. high-resolution low-level and low-resolution high-level features, the model's feature representative capability and deployment ability are improved effectively. Besides, we introduce a new boundary preserving loss, which can consider the boundary information of all coronary artery calcium together and establish links for the segmentation of different coronary artery calcium simultaneously. Extensive experiments demonstrate our AMSN enables reliable accurate coronary artery calcium segmentation for assisted cardiovascular disease diagnosis clinically.

关键词： X-rays and particle beams (medical uses) Patient diagnostic methods and instrumentation Optical, image and video signal processing Other topics in statistics computer vision and image processing techniques Biology and medical computing

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：