检索结果-内蒙古大学图书馆

IEEE International Symposium on Information (IT) in Medicine and Education, ITME

作者： Xiaogen Zhou Zuoyong Li Chuansheng Wang Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou P.R. China College of Mathematics and Computer Science Fuzhou University Fuzhou P.R. China School of Computer Science and Technology Harbin University of Science and Technology Harbin P.R. China

In this paper, we propose a novel method based on color space volume and multimodal histogram thresholding (MHT) for leukocyte segmentation in human blood smear images under the rapid staining condition. The proposed method first defines a new color space volume to highlight the leukocyte's nucleus region, and it then uses the MHT method to extract the nucleus. Then, the proposed method takes the central region in the superpixel segmentation result as an initial leukocyte region, and it then uses the MHT method to extract the leukocyte region. Finally, the cytoplasm is obtained by subtracting the nucleus region from the leukocyte region. Experimental results on a dataset containing 300 leukocyte images under rapid staining condition show that the proposed method provides a higher segmentation accuracy than the counterparts.

关键词： image segmentation image color analysis Histograms White blood cells Clustering algorithms Shape

来源：评论

学校读者我要写书评

暂无评论

Tongue image segmentation via color decomposition and thresholding

Tongue image segmentation via color decomposition and thresh...

引用

作者： Li, Zuoyong Yu, Zhaochai Liu, Weixia Xu, Yong Zhang, Daoqiang Cheng, Yong Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou350121 China The Fujian College's Research Base of Humanities and Social Science for Internet Innovation Research Center Minjiang University Fuzhou350121 China Straits Institute Minjiang University Fuzhou350121 China Bio-Computing Research Center Shenzhen Graduate School Harbin Institute of Technology Shenzhen518055 China Department of Computer Science and Engineering Nanjing University of Aeronautics and Astronautics Nanjing210016 China School of Communication Engineering Nanjing Institute of Technology Nanjing211167 China

Tongue image segmentation is a crucial step in developing an automatic tongue diagnosis system. After exploring characteristics of image thresholding in different color spaces, we propose a simple and effective tongue image segmentation method. Specifically, the proposed method first extracts an initial tongue body region by performing image thresholding on the transformed hue component in HSI (Hue, Saturation, and Intensity) color space. Then, one of two image thresholding results on the red component of an original tongue image is adaptively selected to find the gap region between the tongue body root and the upper lip. Finally, the initial tongue body region is refined by removing fake object regions such as the upper lip to obtain final tongue image segmentation result. Experimental results on a tongue image dataset containing 200 subjects demonstrate the effectiveness of the proposed method. © 2018 John Wiley & Sons, Ltd.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Sandwich control of Some Nonlinear Systems with a Number of Stochastically Occurring Impulses

Fuzzy Sandwich Control of Some Nonlinear Systems with a Numb...

引用

International Conference on Information Science and Technology (ICIST)

作者： Babatunde Oluwaseun Onasanya Yuming Feng Xiangguang Dai Wei Zhang School of Computer Science and Engineering Chongqing Three Gorges University Wanzhou Chongqing China Department of Mathematics University of Ibadan Ibadan Nigeria Three Gorges Institute of Artificial Intelligence Chongqing Three Gorges University Wanzhou Chongqing China Chongqing Engineering Research Center of Internet of Things and Intelligent Control Technology Chongqing Three Gorges University Wanzhou Chongqing China Key Laboratory of Intelligent Information Processing and Control Chongqing Three Gorges University Wanzhou Chongqing China

In this paper, rather than have a fixed constant matrix in the sandwich control of the nonlinear system, a fuzzy control matrix was used. In addition, simple inequalities that do not require additional computational time and skills in computer programming were used rather than the usual LMI. The result of this method is that the period T required in the control process is shorter and the control time is also reached much faster or reduced compared to the existing sandwich methods that used constant matrices. In other words, the control time of this method is shorter than the control time achieved when using constant matrices. Besides, this method also can be used to control more nonlinear chaotic systems such as Lorenz's, Rossler's and Chen's systems. Numerical simulations were used to demonstrate the effectiveness of this method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Nonlinear dynamics in the flexible shaft rotating-lifting system of silicon crystal puller using Czochralski method

arXiv

引用

arXiv 2019年

作者： Ren, Hai-Peng Zhou, Zi-Xuan Grebogi, Celso Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi’an University of Technology Xi’anShaanxi710048 China North Minzu University Library Yinchuan Ningxia750021 China Institute for Complex System and Mathematical Biology University of Aberdeen AB24 3UE United Kingdom

Silicon crystal puller (SCP) is a key equipment in silicon wafer manufacture, which is, in turn, the base material for the most currently used integrated circuit (IC) chips. With the development of the techniques, the demand for longer mono-silicon crystal rod with larger diameter is continuously increasing in order to reduce the manufacture time and the price of the wafer. This demand calls for larger SCP with increasing height, however, it causes serious swing phenomenon of the crystal seed. The strong swing of the seed causes difficulty in the solidification and increases the risk of mono-silicon growth *** main aim of this paper is to analyze the nonlinear dynamics in the FSRL system of the SCP. A mathematical model for the swing motion of the FSRL system is derived. The influence of relevant parameters, such as system damping, excitation amplitude and rotation speed, on the stability and the responses of the system are analyzed. The stability of the equilibrium, bifurcation and chaotic motion are demonstrated, which are often observed in practical situations. Melnikov method is used to derive the possible parameter region that leads to chaotic motion. Three routes to chaos are identified in the FSRL system, including period doubling, symmetry-breaking bifurcation and interior crisis. The work in this paper explains the complex dynamics in the FSRL system of the SCP, which will be helpful for the SCP designers in order to avoid the swing phenomenon in the SCP. Copyright © 2019, The Authors. All rights reserved.

关键词： Silicon wafers

来源：评论

学校读者我要写书评

暂无评论

Seam carving algorithm based on saliency 1st

Seam carving algorithm based on saliency

引用

1st International Conference on Smart Vehicular Technology, Transportation, Communication and Applications, VTCA 2017

作者： Lin, Wen Zhang, Fuquan Lian, Renbao Xu, Lin Chen, Xueyun Kuang, Linghong School of Electronic Information Science Fujian Jiangxia University Fuzhou University Town Fuzhou350108 China School of Software Beijing Institute of Technology Beijing100081 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou350121 China Innovative Information Industry Research Institute Fujian Normal University Fuzhou350300 China Institute of Information Engineering Longyan University Town DongXiao XinLuo District Longyan364012 China School of Information Science and Engineering Fujian University of Technology Fuzhou University Town Fuzhou350118 China

ISBN: (纸本)9783319707297

This paper proposes a seam carving algorithm based on saliency. This algorithm makes saliency detection to the source image. images are classified according to the gray-scale of saliency detection. Adding different energy protection methods, it can protect the foreground area of a subject and detailed areas of the edge. Then the cumulative energy map is calculated. According to the principle of deleting the minimum energy pixel, single pixel-wide carves chosen to be deleted or copied. The experimental result shows that the algorithm avoids image restoration caused by extracting too many pixels in saliency area and non equal-ratio scaling. It reduces the deformed structures caused by displacement of edge pixel and also improves the integrity of algorithm. © Springer International Publishing AG 2018.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Sparse Prior Is Not All You Need: When Differential Directionality Meets Saliency Coherence for Infrared Small Target Detection

arXiv

引用

arXiv 2024年

作者： Zhou, Fei Fu, Maixia Qian, Yulei Yang, Jian Dai, Yimian Ministry of Education Henan Key Laboratory of Grain Photoelectric Detection and Control Henan University of Technology Zhengzhou China Nanjing Marine Radar Institute Nanjing China PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China

Infrared small target detection is crucial for the efficacy of infrared search and tracking systems. Current tensor decomposition methods emphasize representing small targets with sparsity but struggle to separate targets from complex backgrounds due to insufficient use of intrinsic directional information and reduced target visibility during decomposition. To address these challenges, this study introduces a Sparse Differential Directionality prior (SDD) framework. SDD leverages the distinct directional characteristics of targets to differentiate them from the background, applying mixed sparse constraints on the differential directional images and continuity difference matrix of the temporal component, both derived from Tucker decomposition. We further enhance target detectability with a saliency coherence strategy that intensifies target contrast against the background during hierarchical decomposition. A Proximal Alternating Minimization-based (PAM) algorithm efficiently solves our proposed model. Experimental results on several real-world datasets validate our method’s effectiveness, outperforming ten state-of-the-art methods in target detection and clutter suppression. Our code is available at https://***/GrokCV/SDD. Copyright © 2024, The Authors. All rights reserved.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

Joint Optimization of Energy Consumption and Truck Transfer by Stack Allocation in Steel Warehouses

Joint Optimization of Energy Consumption and Truck Transfer ...

引用

Chinese Automation Congress (CAC)

作者： Hongwei Wang Zhezhuang Xu Jinlong Wang Boyu Chen Qingdong Zhang Xiuren Wu Yuxiong Xia Education Department of Fujian Province Key Laboratory of Industrial Automation Control Technology and Information Processing College of Electrical Engineering and Automation Fuzhou University Fuzhou China Sansteel Minguang Co. Ltd. Sanming China Fujian Huading Intelligent Manufacturing Technology Co. Ltd. Fuzhou China

ISBN: (数字)9798350368604

ISBN: (纸本)9798350368611

Due to the continuous growth in steel market demand and the shift towards small batches and multiple varieties, efficient storage management has become a key factor in increasing the profitability of logistics parks. However, the current storage methods, due to the unreasonable allocation of stack positions, still result in energy waste during the dispatch phase and the need for trucks to pick up goods across multiple yards. To address these challenges, this paper proposes a comprehensive optimization scheme to reduce truck transfers and energy consumption in steel product dispatch. First, we constructed an optimization problem model that integrates the spatial layout of the logistics park and order data, aiming to maximize the correlation between steel products within the same yard and reduce the total energy consumption during the dispatch phase. Subsequently, a new algorithm called Enhanced Greedy and Tabu-Assisted Adaptive Large Neighborhood Search (EGTA-ALNS) is introduced. Experimental results demonstrate that the proposed algorithm outperforms existing ones in terms of solving speed and scale. It effectively optimizes energy consumption during steel dispatch and reduces the number of truck transfers.

关键词： Lead acid batteries Energy consumption Profitability Storage management Loading Layout Steel Resource management Optimization Logistics

来源：评论

学校读者我要写书评

暂无评论

SiamCMN: Jointing cycle memory and correlation network for Siamese object tracking

引用

Optik 2023年第1期286卷

作者： Zhang, Baohua Zhang, Nianchao Li, Yongxiang Lu, Xiaoqi Gu, Yu Li, Jianjun School of Information Engineering Inner Mongolia University of Science and Technology Baotou Inner Mongolia014010 China Inner Mongolia Key Laboratory of Pattern Recognition and Intelligent Image Processing Baotou Inner Mongolia014010 China School of Information Engineering Mongolia Industrial University Hohhot Inner Mongolia010051 China College of Energy and Transportation Engineering Inner Mongolia Agricultural University Hohhot Inner Mongolia010018 China

In heterogeneous scenes with latent non-deterministic states, template features determine the performance of the Siamese network-based trackers, however, background noise is easily introduced in the search area matching process, which causes the trackers lack sufficient discrimination. To solve this problem, this paper proposes an object tracking algorithm based on the cyclic memory module. Firstly, the extracted primary features are mapped to the cyclic spatial memory network, the spatial memory unit is used to store the interference components. On this basis, the cyclic structure is used to filter out the interference components and refine the template features. Then a channel correlation network is introduced into the proposed method, which can mine semantic complementary information and capture global contextual relevance by modeling the positive and the negative correlation between the channels. The experimental results on tracking benchmarks such as OTB50, OTB100, UAV123, VOT2018, GOT10k, and LaSOT have shown that the proposed method outperforms recent representative algorithms in tracking accuracy in challenging scenarios. © 2023 Elsevier GmbH

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A Multi-Stage Goal-Driven Network for Pedestrian Trajectory Prediction

A Multi-Stage Goal-Driven Network for Pedestrian Trajectory ...

引用

Computer Vision, image and Deep Learning (CVIDL), International Conference on

作者： Xiuen Wu Tao Wang Yuanzheng Cai Lingyu Liang George Papageorgiou Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou China College of Computer and Data Science Fuzhou University Fuzhou China School of Electronic and Information Engineering South China University of Technology Guangzhou China Department of Computer Science and Engineering European University Cyprus Nicosia Cyprus

ISBN: (数字)9798350373820

ISBN: (纸本)9798350373837

Pedestrian trajectory prediction plays a pivotal role in ensuring the safety and efficiency of various applications, including autonomous vehicles and traffic management systems. This paper proposes a novel method for pedestrian trajectory prediction, called multi-stage goal-driven network (MGNet). Diverging from prior approaches relying on stepwise recursive prediction and the singular forecasting of a long-term goal, MGNet directs trajectory generation by forecasting intermediate stage goals, thereby reducing prediction errors. The network comprises three main components: a conditional variational autoencoder (CVAE), an attention module, and a multi-stage goal evaluator. Trajectories are encoded using conditional variational autoencoders to acquire knowledge about the approximate distribution of pedestrians’ future trajectories, and combined with an attention mechanism to capture the temporal dependency between trajectory sequences. The pivotal module is the multi-stage goal evaluator, which utilizes the encoded feature vectors to predict intermediate goals, effectively minimizing cumulative errors in the recursive inference process. The effectiveness of MGNet is demonstrated through comprehensive experiments on the JAAD and PIE datasets. Comparative evaluations against state-of-the-art algorithms reveal significant performance improvements achieved by our proposed method.

关键词： Deep learning Pedestrians Computational modeling Predictive models Prediction algorithms Vectors Inference algorithms

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Methods for Ship Classification: From Visible to Infrared images

Deep Learning Methods for Ship Classification: From Visible ...

引用

Robotics, intelligent control and Artificial Intelligence (RICAI), International Conference on

作者： Tianci Liu Hengjia Qin Zhuo Zhan Yunpeng Liu Chinese Academy of Sciences Shenyang Institute of Automation Shenyang China Chinese Academy of Sciences Institutes for Robotics and Intelligent Manufacturing Shenyang China University of Chinese Academy of Sciences Beijing China Key Laboratory of Opto-Electronic Information Processing Chinese Academy of Sciences Shenyang China Key Laboratory of Image Understanding and Computer Vision Shenyang Liaoning Province China The Third Military Representative Office of the Air Force Equipment Department in Shenyang Region Shenyang Liaoning Province China

Deep learning methods have achieved excellent performances on visual tasks of target recognition and classification. The rapid development of autonomous seafaring vessels comes up with the requirement to recognize other maritime ships day and night. However, the recognition of ships based on the deep neural networks may not always access the results as expectation when the ships are under the nighttime environment. To this issue, we consider the ship recognition task under the deep learning framework with paired visible images and infrared images. In this article, we propose an end-to-end convolutional network based on visible images and infrared images of the autonomous seafaring vessels. To demonstrate the effectiveness of our model, we choose the V AIS dataset to test the performance of classifying the maritime ships. Experimental results show that the proposed network outperforms the state-of-the-art methods based on the V AIS database.

关键词：

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：