检索结果-内蒙古大学图书馆

11th IEEE Asia-Pacific Conference on Antennas and Propagation, APCAP 2023 - Proceedings

作者： Xu, Xiaochun Shen, Yifan Lei, Jiaxing Wang, Xin Guo, Ente Minjiang University College of Computer and Control Engineering Fuzhou350108 China Minjiang University International Digital Economy College Fuzhou350108 China

ISBN: (纸本)9798350326277

This paper proposes a novel mean pyramid strategy for binary pattern family. The mean pyramid strategy can help the binary pattern family to capture robust multilayer local texture structure instead of the traditional single pixel value. To validate the effectiveness of the proposed strategy, we apply the mean pyramid strategy to the classical completed local binary pattern and present the completed mean pyramid local binary pattern for texture classification tasks. The experimental results on Outex database show that the proposed mean pyramid strategy can significantly enhances the classification performance of binary pattern family. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Automatic Object Attention Likelihood Map Correlation Filter for Visual Tracking 11

An Automatic Object Attention Likelihood Map Correlation Fil...

引用

11th IEEE Asia-Pacific Conference on Antennas and Propagation, APCAP 2023 - Proceedings

作者： Tang, Leinuo Xu, Xiaochun Wang, Xin Feng, Huibin Lin, Nixuan Minjiang University International Digital Economy College Fuzhou350108 China Minjiang University College of Computer and Control Engineering Fuzhou350108 China

ISBN: (纸本)9798350326277

Discriminative correlation filter-based trackers have achieved excellent performance. However, they are still suffered from the inherent boundary effect. To alleviate it, this paper proposes an automatic object attention likelihood map correlation filter. Specifically, an automatic object attention searching window is developed to highlight the object more precisely and suppress the background more appropriately, which divides the searching area into three regions and applies different object attention strategies on each area. Furthermore, combining it with the spatially regularized discriminative correlation filter, we propose the automatic object attention likelihood map correlation filter tracker. It further alleviates the boundary effect and adaptively generates a more precise tracking model frame by frame. The experimental evaluations on the popular OT2015 benchmark demonstrate that our proposed tracker gains outstanding tracking performance and offers a satisfying robustness to complex tracking scenarios. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Completed Gaussian Extended Binary Pattern for Texture Image Classification 2

A Completed Gaussian Extended Binary Pattern for Texture Ima...

引用

2nd International Conference on Signal Processing, computer Networks and Communications, SPCNC 2023

作者： Xu, Xiaochun Lin, Weizheng Chen, Dingrong Su, Nanling Tang, Leinuo Cai, Changxu College of Computer and Control Engineering Minjiang University Fuzhou350108 China International Digital Economy College Minjiang University Fuzhou350108 China

ISBN: (纸本)9798400716430

Texture image classification is a fundamental and challenging visual task and has wide range of applications. Binary pattern methods play an important role in texture feature extraction due to its ease of implementation and promising performance. To extract completed texture feature representation and improve the classification performance, this paper proposes a completed gaussian extend binary pattern for texture image classification. First, instead of the original pixel value, this paper uses the mean of local range to encode the binary pattern. Second, this paper introduces a novel gaussian sign pattern to fully represent the macro texture structure. Third, to achieve completed texture feature description, this paper presents a completed gaussian extended binary pattern, which combines the novel gaussian sign pattern, the local sign and magnitude pattern extracted from mean-processing texture image. To validate the effectiveness of the proposed completed gaussian extend binary pattern, experimental evaluations are conducted on three test subsets from Outex database. The evaluation results show that the proposed completed gaussian extended binary pattern achieves the state-pf-the-art classification performance. © 2023 ACM.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

An adaptive enhanced windowed correlation filter for visual tracking 11

An adaptive enhanced windowed correlation filter for visual ...

引用

11th IEEE Asia-Pacific Conference on Antennas and Propagation, APCAP 2023 - Proceedings

作者： Xu, Xiaochun Feng, Huibin Wu, Qihang Guo, Ente Wang, Xinxin Minjiang University College of Computer and Control Engineering Fuzhou350108 China Minjiang University International Digital Economy College Fuzhou350108 China

ISBN: (纸本)9798350326277

Boundary effect, as an inherent drawback of discriminative correlation filter (DCF) trackers, cannot be handled well in most existing studies. This paper proposes an adaptive enhanced windowed correlation filter tracker (AEWCF), which can alleviate boundary effect adaptively and capture more reliable target information effectively. Firstly, a target enhanced likelihood map is introduced to extract reliable target information from searching window. Then, this paper further proposes an adaptive parted searching window including two sub-windows: the object region window depended on object likelihood maximization strategy and the background window generated by background suppression scheme. The extensive evaluation on OTB2015 benchmarks demonstrate that the AWCF tracker performs favorably against some popular trackers and keeps real-time speed. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improved SqueezeNet-Based Method for Automotive Paint Film Defect Detection

Improved SqueezeNet-Based Method for Automotive Paint Film D...

引用

2024 International Conference on Artificial Intelligence and Digital Technology, ICAIDT 2024

作者： Yan, Shengnan Shen, Yihui Minjiang University School of Computer and Control Engineering Fujian China Fujian Medical University College of Arts and Sciences Fujian China

ISBN: (纸本)9798350386905

To address the issues of lacking datasets and low recognition accuracy for paint film defects, this paper proposes a denoising diffusion implicit model (DDIM) for data augmentation of paint film defects and innovatively suggests a classification method combining Selective Kernel Networks (SKNet) with SqueezeNet model. Initially, the DDIM is used for dataset expansion, followed by an evaluation of the similarity between generated and captured paint film defect images using multiscale structural similarity (MS-SSIM). The training and generation effects of DDIM are then compared with those of DCGAN. In the SqueezeNet model, a Selective Kernel module is added following the fire7 module to enhance the model's attention mechanism. The results show that all types of paint film defect images generated by DDIM have MS-SSIM indices above 0.64, with most exceeding 0.7. The combined approach of Selective Kernel Networks(SKNet) and SqueezeNet outperforms other attention mechanisms, achieving an accuracy above 96.3%. The method demonstrates promising prospects for paint film defect detection, enhancing identification efficiency and accuracy while reducing detection costs, and is applicable to mobile or embedded devices. © 2024 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

PDEGAN: A Panoramic Style Transfer Based on Generative Adversarial Networks

Journal of Network Intelligence

引用

Journal of Network Intelligence 2024年第4期9卷 2112-2121页

作者： Wang, Qinghua Long, Xinling Huang, Jingwei Chen, Yang Yang, Lirong Zhang, Fuquan College of Computer and Big Data Minjiang University Fuzhou350108 China Fuzhou Technology Innovation Center of intelligent Manufacturing information System Minjiang University Fuzhou350108 China Fujian Province University Fuzhou350300 China College of Computer and Control Engineering Minjiang University Fuzhou350108 China College of Computer and Big Data Fuzhou University Fuzhou China School of Mechanical and Automotive Engineering Fujian University of Technology Fuzhou China College of foreign languages Dalian Jiaotong University Dalian116028 China Digital Media Art Key Laboratory of Sichuan Province Sichuan Conservatory of Music Chengdu610021 China

Panoramic image plays an extremely important role in the application of 3D, but in some special scenarios, the depth information is also needed as an auxiliary, but to obtain the panoramic depth information needs a high cost, it is extremely difficult to obtain. Therefore, this paper proposes a panoramic depth estimation method called PDEGAN (Panoramic Depth Estimation Generative Adversarial Network). This method first enhances the style migration, transfers the input panoramic image to a style closer to the panoramic depth image domain, and then combines the conversion results with the original panoramic image as the input data for further depth estimation training. By using the style closer to the depth estimation, the texture, color and other characteristics of the image can be adjusted, so as to better highlight the depth information of the object in the image, so that the generator network is more focused on performing the image translation task, reduce the impact of style differences on the image translation task, and improve the generalization ability of the model. At the same time, the model will also use multi-scale feature fusion, combined with the attention mechanism, to better capture the depth information of different scales, viewing angles and channels. Not only that, but also by introducing depth gradient loss, surface normal loss to improve the accuracy and stability of depth estimation. To this end, we also made a set of related datasets for the related experiments of PDEGAN, and named it PDE Images. Finally, it is shown that the method proposed in this paper has more accurate estimation results than the traditional Pix2Pix image conversion model. © 2024, Taiwan Ubiquitous Information CO LTD. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

An Improved YOLOv8-Based Method for Real-Time Detection of Harmful Tea Leaves in Complex Backgrounds

引用

Phyton-International Journal of Experimental Botany 2024年第11期93卷 2963-2981页

作者： Xin Leng Jiakai Chen Jianping Huang Lei Zhang Zongxuan Li College of Computer and Control Engineering Northeast Forestry UniversityHarbin150040China

Tea,a globally cultivated crop renowned for its uniqueﬂavor proﬁle and health-promoting properties,ranks among the most favored functional beverages ***,diseases severely jeopardize the production and quality of tea leaves,leading to signiﬁcant economic *** early and accurate identiﬁcation coupled with the removal of infected leaves can mitigate widespread infection,manual leaves removal remains time-con-suming and *** robots for pruning can signiﬁcantly enhance efﬁciency and reduce ***-ever,the accuracy of object detection directly impacts the overall efﬁciency of pruning *** complex tea plantation environments,complex image backgrounds,the overlapping and occlusion of leaves,as well as small and densely harmful leaves can all introduce interference *** algorithms perform poorly in detecting small and densely packed *** address these challenges,this paper collected a dataset of 1108 images of harmful tea leaves and proposed the YOLO-DBD *** model excels in efﬁciently identifying harmful tea leaves with various poses in complex backgrounds,providing crucial guidance for the posture and obstacle avoidance of a robotic arm during the pruning *** improvements proposed in this study encompass the Cross Stage Partial with Deformable Convolutional Networks v2(C2f-DCN)module,Bi-Level Routing Atten-tion(BRA),Dynamic Head(DyHead),and Focal Complete Intersection over Union(Focal-CIoU)Loss function,enhancing the model’s feature extraction,computation allocation,and perception *** to the baseline model YOLOv8s,mean Average Precision at IoU 0.5(mAP0.5)increased by 6%,and Floating Point Operations Per second(FLOPs)decreased by 3.3 G.

关键词： Harmful tea leaves YOLO-DBD Focal-CIoU Loss dynamic head Bi-Level Routing Attention

来源：评论

学校读者我要写书评

暂无评论

UAV 3D Trajectory Planning Based on Improved A* Algorithm and Differential Evolution

Journal of Network Intelligence

引用

Journal of Network Intelligence 2023年第4期8卷 1150-1163页

作者： Yang, Li Tan, Liang Zhang, Fuquan Department of information engineering Sichuan Vocational and Technical College of Communications Chengdu611130 China Thai-Chinese International College Assumption University of Thailand Bangkok100027 Thailand College of Computer and Control Engineering Minjiang University Fuzhou350108 China

Track planning technology, as a key technology for UAV mission planning, has always been a major research hotspot in the field of UAVs. In real-life applications, due to the complex and constrained UAV flight environment, how to establish an accurate environment model and how to select an efficient planning algorithm become the elements to solve the trajectory planning problem. In this work, after studying existing trajectory planning algorithms, a method using a combination of improved A* algorithm and differential evolution algorithm is proposed for 3D trajectory planning in complex environments. Firstly, the mathematical modelling of the UAV track planning related problems, including the UAV model, manoeuvrability constraints and equivalent digital maps, is carried out. Secondly, an improved sparse A* algorithm is proposed for solving the winding path problem of the sparse A* algorithm, which reduces the winding path of the trajectory by extracting path feature points and quadratic optimisation. Finally, the improved sparse A* algorithm is combined with the differential evolutionary algorithm and applied to the UAV real-time trajectory planning, where the improved sparse A* algorithm is used for the UAV global trajectory planning and the differential evolutionary algorithm is applied to the emergent threat avoidance, i.e. local trajectory planning. The results of MATLAB simulations show that the proposed method can solve the patharound problem of the sparse A* algorithm and can be flexible in complex environments to achieve dynamic trajectory planning, thus effectively guaranteeing the flight safety of UAVs in practical environments. © 2023, Taiwan Ubiquitous Information CO LTD. All rights reserved.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

An Investigation into Improved YOLOv8-based Target Detection Algorithms for UAV Aerial Imagery 2

An Investigation into Improved YOLOv8-based Target Detection...

引用

2nd International Conference on Image Processing, computer Vision and Machine Learning, ICICML 2023

作者： Ming, Rui Liu, Xinyu Lin, Yuxuan Gong, Qian Minjiang University College of Computer and Control Engineering Fuzhou350108 China Fuzhou University College of Computer and Data Science College of Software Fuzhou350108 China

ISBN: (纸本)9798350331417

In UAV imagery, the intricate backgrounds combined with the high quantity and compact distribution of minute targets have consistently made target detection a formidable challenge in the realm of computer vision. This study introduces an enhancement over the YOLOv8 algorithm, wherein a sophisticated multi-scale convolutional layer, integrating depth-separable convolution, attention mechanisms, and multi-scale processing techniques, replaces the original model's convolution. Moreover, we introduce an attention mechanism for a Bi-Level Routing within the core component of the base model, and adjustments are made to the original model's loss function. Lastly, to confirm the viability of the enhanced model proposed in this paper, we conducted a validation of the metrics using publicly accessible datasets. The findings illustrate that the improved model outlined in this research substantially enhances target recognition accuracy in UAV images. Furthermore, the model exhibits superior performance in mitigating issues of duplicate detection and target omission. © 2023 IEEE.

关键词： Multi-scale Convolutions Target Detection UAV Aerial Imagery YOLOv8-based

来源：评论

学校读者我要写书评

暂无评论

A calibration and compensation method for an industrial robot with high accuracy harmonic reducers

引用

Science China(Technological Sciences) 2024年第3期67卷 725-739页

作者： ZHAO YiYang LIU Xun CAO JiaBin LIU JinYu XU Yan YAN WeiXin School of Mechanical Engineering Shanghai Jiao Tong UniversityShanghai 200240China College of Computer and Control Engineering Northeast Forestry UniversityHarbin 150040China

Industrial serial robots need high stiffness to keep absolute pose accuracy and meet the requirements in practical applications. However, the weak stiffness feature of robot joints and the payloads affected on robot end-effector, which will also increase the pose error of robot. Especially, the existing calibration methods often consider under no-payload condition without discussing the payload state. In this paper, we report a new industrial serial robot composed by a new harmonic reducer: Model-Y, based on high accuracy and high stiffness, and a kinematic parameter calibration algorithm which is based on a harmonic reducer forcedeformation model. To decrease the accuracy effects of payload, an iterative calibration method for kinematic parameters with payload situation was proposed. Simulation and experiments are conducted to verify the effectiveness of the proposed calibration method using the self-developed industrial serial robot. The results show a remarkably improved accuracy in absolute position and orientation with the robot's payload range. The position mean error has 70% decreased to 0.1 mm and the orientation mean error diminished to less than 0.01° after calibration with compensation. Additionally, online linear and circular tests are carried out to evaluate the position error of the robot during large-scale spatial and low-speed continuous movement. The accuracy is consistent with the previous calibration results, indicating the effectiveness and advantages of the proposed strategy in this article.

关键词： industrial serial robot Model-Y harmonic calibration stiffness model online compensation

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：