检索结果-内蒙古大学图书馆

Knowledge Distillation Facilitates the Lightweight and Efficient Plant Diseases Detection Model

Plant Phenomics 2023年第3期5卷 501-519页

作者： Qianding Huang Xingcai Wu Qi Wang Xinyu Dong Yongbin Qin Xue Wu Yangyang Gao Gefei Hao State Key Laboratory of Public Big Data College of Computer Science and TechnologyGuizhou UniversityGuiyang 550025China Text Computing&Cognitive Intelligence Engineering Research Center of National Education Ministry Guizhou UniversityGuiyang 550025China National Key Laboratory of Green Pesticide Guizhou UniversityGuiyang 550025China

Plant disease diagnosis in time can inhibit the spread of the disease and prevent a large-scale drop in production,which benefits food *** detection-based plant disease diagnosis methods have attracted widespread attention due to their accuracy in classifying and locating ***,existing methods are still limited to single crop disease *** importantly,the existing model has a large number of parameters,which is not conducive to deploying it to agricultural mobile ***,reducing the number of model parameters tends to cause a decrease in model *** solve these problems,we propose a plant disease detection method based on knowledge distillation to achieve a lightweight and efficient diagnosis of multiple diseases across multiple *** detail,we design 2 strategies to build 4 different lightweight models as student models:the YOLOR-Light-v1,YOLOR-Light-v2,Mobile-YOLOR-v1,and Mobile-YOLOR-v2 models,and adopt the YOLOR model as the teacher *** develop a multistage knowledge distillation method to improve lightweight model performance,achieving 60.4%mAP@.5 in the PlantDoc dataset with small model parameters,outperforming existing ***,the multistage knowledge distillation technique can make the model lighter while maintaining high *** only that,the technique can be extended to other tasks,such as image classification and image segmentation,to obtain automated plant disease diagnostic models with a wider range of lightweight applicability in smart *** code is available at https://***/QDH/MSKD.

关键词： Plant diagnosis image

来源：评论

学校读者我要写书评

暂无评论

Self-Contrastive Learning Fault Diagnosis Network for Signal Imaging: A Case Study

Self-Contrastive Learning Fault Diagnosis Network for Signal...

引用

2024 China Automation Congress, CAC 2024

作者： He, Wenbin Mao, Jianxu Wang, Yaonan Li, Zhe Yan, Feng Liu, Kexin College of Electrical & Information Engineering National Engineering Research Center of Robot Visual Perception & Control Technology Hunan University Hunan China College of Control Science & Engineering State Key Laboratory of Industrial Control Technology Zhejiang University Zhejiang China

ISBN: (纸本)9798350368604

The deep convolution method based on MSDP signal imaging has been proven to be an effective means of monitoring the robot grinding process. This method has very high requirements on the quality of imaging and requires a lot of computing resources. This paper proposes an image self-contrastive learning network that can effectively extract fault information from low-pixel fuzzy images and achieve efficient and accurate condition monitoring. The network first calculates the correlation distance matrix between two identical modified symmetrized dot pattern (MSDP) images and uses the generated similarity labels to calculate the contrast loss to extract the embedded features of the image. Finally, the classification network is trained using the cross entropy loss to achieve the classification of fault images. The method was verified on a robotic grinding platform to significantly reduce the calculation time while maintaining the recognition accuracy, which provides reliable technical support for the real-time monitoring of the robotic grinding process. © 2024 IEEE.

关键词： Contrastive Learning fault diagnosis robotic grinding signal imaging

来源：评论

学校读者我要写书评

暂无评论

A 7DOF redundant manipulator inverse kinematic solution algorithm based on bald eagle search optimization algorithm

引用

Soft Computing 2024年第23期28卷 13681-13699页

作者： Zhao, Guojun Sun, Ying Jiang, Du Liu, Xin Tao, Bo Jiang, Guozhang Kong, Jianyi Yun, Juntong Liu, Ying Li, Gongfa Key Laboratory of Metallurgical Equipment and Control Technology of Ministry of Education Wuhan University of Science and Technology Wuhan430081 China Research Center for Biomimetic Robot and Intelligent Measurement and Control Wuhan University of Science and Technology Wuhan430081 China Hubei Key Laboratory of Mechanical Transmission and Manufacturing Engineering Wuhan University of Science and Technology Wuhan430081 China Precision Manufacturing Research Institute Wuhan University of Science and Technology Wuhan430081 China

Solving inverse kinematics (IK) is an excellent challenge for redundant manipulators due to their highly non-linear and complex coupling, which is not amenable to analytical solutions by conventional methods. In this paper, the conventional solution was replaced by the optimization process of a fitness function. The fitness function aims to obtain a set of solutions for the desired position of the end effector (EE). The function is based on forward kinematics;hence, this method can avoid singularities and be suitable for solving redundant manipulators. For solving this optimization problem, the bald eagle search (BES) optimization algorithm was chosen due to its easy principle and excellent performance. BES integrates the advantages of evolutionary and swarm techniques. On the one hand, BES maximizes the advantages offered by swarm intelligence (SI) in terms of searching within the best position in the swarm. On the other hand, BES capitalizes on the capability of evolutionary techniques to explore the search space frequently and avoid the local optimum. In this study, two 7-degree of freedom (DOF) manipulators were used to test the performance of BES. Meanwhile, several evolutionary and SI optimization algorithms were selected to compare with BES. The experimental results demonstrate that the BES optimization algorithm can efficiently and accurately solve the IK problem of 7DOF redundant manipulators. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Inverse kinematics

来源：评论

学校读者我要写书评

暂无评论

Superresolution structured illumination microscopy reconstruction algorithms:a review

引用

Light(Science & Applications) 2023年第8期12卷 1510-1543页

作者： Xin Chen Suyi Zhong Yiwei Hou Ruijie Cao Wenyi Wang Dong Li Qionghai Dai Donghyun Kim Peng Xi Department of Biomedical Engineering College of Future TechnologyPeking UniversityBeijing 100871China National Biomedical Imaging Center Peking UniversityBeijing 100871China National Laboratory of Biomacromolecules CAS Center for Excellence in BiomacromoleculesInstitute of BiophysicsChinese Academy of SciencesBeijingChina Department of Automation Tsinghua UniversityBeijingChina Institute for Brain and Cognitive Sciences Tsinghua UniversityBeijingChina Beijing Key Laboratory of Multidimension&Multiscale Computational Photography Tsinghua UniversityBeijingChina Beijing Laboratory of Brain and Cognitive Intelligence Beijing Municipal Education CommissionBeijingChina School of Electrical and Electronic Engineering Yonsei University50 Yonsei-RoSeodaemun-GuSeoul 03722Korea

Structured illumination microscopy(SIM)has become the standard for next-generation wide-field microscopy,offering ultrahigh imaging speed,superresolution,a large fiield-of-view,and long-term *** the past decade,SIM hardware and software have flourished,leading to successful applications in various biological ***,unlocking the full potential of SIM system hardware requires the development of advanced reconstruction ***,we introduce the basic theory of two SIM algorithms,namely,optical sectioning SIM(OS-SIM)and superresolution SIM(SR-SIM),and summarize their implementation *** then provide a brief overview of existing OS-SIM processing algorithms and review the development of SR-SIM reconstruction algorithms,focusing primarily on 2D-SIM,3D-SIM,and *** showcase the state-of-the-art development of SIM systems and assist users in selecting a commercial SIM system for a specific application,we compare the features of representative off-the-shelf SIM ***,we provide perspectives on the potential future developments of SIM.

关键词： illumination hardware offering

来源：评论

学校读者我要写书评

暂无评论

Application Research of Landmarks in Path Planning Algorithms of Mobile robots 2

Application Research of Landmarks in Path Planning Algorithm...

引用

2nd International Conference on Digital Society and Intelligent Systems, DSInS 2022

作者： Fan, Linghao Liu, Xiangde Zhang, Yi Chongqing University of Posts and Telecommunications Intelligent Systems and Robotics Laboratory Chongqing China Chongqing Information Accessibility and Service Robot Engineering Technology Research Center Chongqing China

ISBN: (纸本)9781510663244

A way of incorporating landmark information matrix QR to affect the global path planning algorithm is proposed for the use of landmarks in robot localization and navigation. It is also investigated how this method affects the pace at which the original algorithm solves problems. The reward and punishment items in this technique include dangerous locations with lots of obstacles around them, landmarks with location information connected to the ground, and the two combined. Three representative common robot path planning algorithms are also imposed as influences. Through MATLAB simulation experiment, find the optimal path planning algorithm that is appropriate for applying reward and punishment by comparing the quality of the robot's driving path and the algorithm solution speed before and after the reward and punishment. According to the simulation results, the reward and punishment approach is practical and efficient. The heuristic search algorithm is better suited for reward and punishment, and both its path quality and speed of solution have greatly increased. © 2023 SPIE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Base position planning of mobile manipulators for assembly tasks in construction environments

引用

Advances in Manufacturing 2023年第1期11卷 93-110页

作者： Dai-Jun Xie Ling-Dong Zeng Zhen Xu Shuai Guo Guo-Hua Cui Tao Song Shanghai Key Laboratory of Intelligent Manufacturing and Robotics School of Mechatronic Engineering and AutomationShanghai UniversityShanghai200444People’s Republic of China National Demonstration Center for Experimental Engineering Training Education Shanghai UniversityShanghai200444People’s Republic of China School of Mechanical and Automotive Engineering Shanghai University of Engineering ScienceShanghai201620People’s Republic of China Shanghai Collaborative Innovation Center of Intelligent Manufacturing Robot Technology for Large Components Shanghai201620People’s Republic of China

With good mobility and flexibility,mobile manipulators have shown broad applications in construction *** position(BP)planning,which refers to the robot autonomously determining its working station in the environment,is an important technique for mobile manipulators when performing the construction assembly task,especially in a large-scale construction ***,the BP planning process is tedious and time-consuming for a human worker to carry ***,to improve the efficiency of construction assembly tasks,a novel BP planning method is proposed in this paper,which can lead to appropriate BPs and minimize the number of BPs at the same ***,the feasible BP regions are generated based on the grid division and the variable workspace of the mobile ***,the positioning uncertainties of the mobile manipulator are considered in calculating the preferred BP areas using ***,a set coverage optimization model is established to obtain the minimum number of BPs using an optimization algorithm according to the greedy *** simulated experiment based on a 9-degree of free(DoF)mobile manipulator has been *** results illustrated that the time for BP planning was significantly reduced and the number of BPs was reduced by 63.41%compared to existing manual planning,which demonstrated the effectiveness of the proposed method.

关键词： Base position(BP)planning Mobile manipulators Variable workspace Positioning uncertainties Construction environments

来源：评论

学校读者我要写书评

暂无评论

Research on Lightweight Intervertebral Disc Segmentation Method for Spine Magnetic Resonance Images 4

Research on Lightweight Intervertebral Disc Segmentation Met...

引用

4th International Conference on robotics, Intelligent Control and Artificial Intelligence, RICAI 2022

作者： Li, Xianda Li, Qi Wen, James Zhiqing Luo, Huiyuan He, Siyuan School of Computer Science and Technology Changchun University of Science and Technology Jilin130022 China Intelligent Robot Engineering Research Center Ji Hua Laboratory Guangdong528437 China Intelligent Robot Engineering Research Center Ji Hua Laboratory Foshan Guangdong528200 China

ISBN: (纸本)9781450398343

To address the problem of conflicting segmentation accuracy and model parametric numbers in many lumbar MR image disc segmentation methods, we propose a lightweight segmentation pipeline named Lite-snake for lumbar MR image disc instances. We use Nanodet as a lightweight target detection model, a parallel feature aggregation module to aggregate multi-scale features, and a depth-separable cyclic convolution to reconstruct deep snake. The method achieves an IoU of 79.49% and a DSC of 88.50% on the test set of lumbar MR images with only 5,670,000 parameters. The experimental results show that compared to many current deep-learning image segmentation methods, our method dramatically reduces the number of parameters of the model while ensuring segmentation accuracy. Therefore it is easy to deploy to lightweight mobile devices and has good application prospects. © 2022 ACM.

关键词： Magnetic resonance

来源：评论

学校读者我要写书评

暂无评论

Predicting and Visualizing Citrus Color Transformation Using a Deep Mask-Guided Generative Network

引用

Plant Phenomics 2023年第3期5卷 435-446页

作者： Zehan Bao Weifu Li Jun Chen Hong Chen Vijay John Chi Xiao Yaohui Chen College of Informatics Huazhong Agricultural UniversityWuhan 430070China Engineering Research Center of Intelligent Technology for Agriculture Ministry of EducationWuhanChina RIKEN Guardian robot project2-2-2 Hikaridai Seika-choSorakugun619-0288 KyotoJapan Key Laboratory of Biomedical Engineering of Hainan Province School of Biomedical EngineeringHainan UniversityHaikou 570100China College of Engineering Huazhong Agricultural University430070 WuhanChina

Citrus rind color is a good indicator of fruit development,and methods to monitor and predict color transformation therefore help the decisions of crop management practices and harvest *** work presents the complete workflow to predict and visualize citrus color transformation in the orchard featuring high accuracy and fidelity.A total of 107 sample Navel oranges were observed during the color transformation period,resulting in a dataset containing 7,535 citrus images.A framework is proposed that integrates visual saliency into deep learning,and it consists of a segmentation network,a deep mask-guided generative network,and a loss network with manually designed loss ***,the fusion of image features and temporal information enables one single model to predict the rind color at different time intervals,thus effectively shrinking the number of model *** semantic segmentation network of the framework achieves the mean intersection over a union score of 0.9694,and the generative network obtains a peak signal-to-noise ratio of 30.01 and a mean local style loss score of 2.710,which indicate both high quality and similarity of the generated images and are also consistent with human *** ease the applications in the real world,the model is ported to an Android-based application for mobile *** methods can be readily expanded to other fruit crops with a color transformation *** dataset and the source code are publicly available at GitHub.

关键词： Visual Deep network

来源：评论

学校读者我要写书评

暂无评论

Local and Global Feature-Aware Dual-Branch Networks for Plant Disease Recognition

引用

植物表型组学（英文） 2024年第4期6卷 828-840页

作者： Jianwu Lin Xin Zhang Yongbin Qin Shengxian Yang Xingtian Wen Tomislav Cernava Quirico Migheli Xiaoyulong Chen Text Computing & Cognitive Intelligence Engineering Research Center of National Education Ministry College of Computer Science and TechnologyGuizhou UniversityGuiyang 550025China State Key Laboratory of Public Big Data College of Computer Science and TechnologyGuizhou UniversityGuiyang 550025China College of Big Data and Information Engineering Guizhou UniversityGuiyang 550025China Guizhou-Europe Environmental Biotechnology and Agricultural Informatics Oversea Innovation Center in Guizhou University Guizhou Provincial Science and Technology DepartmentGuiyang 550025China Text Computing & Cognitive Intelligence Engineering Research Center of National Education Ministry College of Computer Science and TechnologyGuizhou UniversityGuiyang 550025China State Key Laboratory of Public Big Data College of Computer Science and TechnologyGuizhou UniversityGuiyang 550025China College of Big Data and Information Engineering Guizhou UniversityGuiyang 550025China Guizhou-Europe Environmental Biotechnology and Agricultural Informatics Oversea Innovation Center in Guizhou University Guizhou Provincial Science and Technology DepartmentGuiyang 550025China College of Big Data and Information Engineering Guizhou UniversityGuiyang 550025China School of Biological Sciences Faculty of Environmental and Life SciencesUniversity of SouthamptonSouthampton S017 1BJUK Dipartimento di Agraria and NRD-Nucleo di Ricerca sulla Desertificazione Università degli Studi di SassariSassariItaly Guizhou-Europe Environmental Biotechnology and Agricultural Informatics Oversea Innovation Center in Guizhou University Guizhou Provincial Science and Technology DepartmentGuiyang 550025China College of Life Sciences Guizhou UniversityGuiyang 550025China

Accurate identification of plant diseases is important for ensuring the safety of agricultural *** neural networks(CNNs)and visual transformers(VTs)can extract effective representations of images and have been widely used for the intelligent recognition of plant disease ***,CNNs have excellent local perception with poor global perception,and VTs have excellent global perception with poor local *** makes it difficult to further improve the performance of both CNNs and VTs on plant disease recognition *** this paper,we propose a local and global feature-aware dual-branch network,named LGNet,for the identification of plant *** specifically,we first design a dual-branch structure based on CNNs and VTs to extract the local and global ***,an adaptive feature fusion(AFF)module is designed to fuse the local and global features,thus driving the model to dynamically perceive the weights of different ***,we design a hierarchical mixed-scale unit-guided feature fusion(HMUFF)module to mine the key information in the features at different levels and fuse the differentiated information among them,thereby enhancing the model's multiscale perception ***,extensive experiments were conducted on the Al Challenger 2018 dataset and the self-collected corn disease(SCD)*** experimental results demonstrate that our proposed LGNet achieves state-of-the-art recognition performance on both the Al Challenger 2018 dataset and the SCD dataset,with accuracies of 88.74％and 99.08％,respectively.

关键词： global plant disease dual-branch feature-aware local networks recognition

来源：评论

学校读者我要写书评

暂无评论

DFGET: Displacement-Field Assisted Graph Energy Transmitter for Gland Instance Segmentation 17

DFGET: Displacement-Field Assisted Graph Energy Transmitter ...

引用

17th IEEE International Conference on Signal Processing, ICSP 2024

作者： Jian, Caiqing Qin, Yongbin Wang, Lihui Ye, Chen Cheng, Xinyu Guizhou University Engineering Research Center of Text Computing & Cognitive Intelligence Ministry of Education Key Laboratory of Intelligent Medical Image Analysis and Precise Diagnosis of Guizhou Province State Key Laboratory of Public Big Data College of Computer Science and Technology Guiyang China

ISBN: (纸本)9798350387384

Gland instance segmentation is an essential but challenging task in the diagnosis of adenocarcinoma. The existing models usually achieve gland instance segmentation through multi-task learning and boundary loss constraint. However, how to deal with the problems of gland adhesion and inaccurate boundary in segmenting the complex samples remains a challenge. In this work, we propose a novel geometric feature named displacement field (DF), which can represent the geometric information such as shape, size, and orientation of the glands. Based on the explicit constraint of DF, a displacement-field assisted graph energy transmitter (DFGET) framework is proposed for solving the above problems. Using such graph framework, the gland semantic segmentation map and the displacement field of the graph nodes are estimated with two graph network branches. With the constraint of DF, a graph cluster module is presented to improve the intra-class feature consistency and inter-class feature discrepancy, as well as to separate the adherent glands. Extensive comparison and ablation experiments on the GlaS dataset demonstrate the effectiveness of the displacement field and the superiority of DFGET. Compared to the best comparative model, DFGET increases the object-Dice and object-F1 score by 2.27% and 3.11% respectively, while decreases the object-HD by 15.58, achieving state-of-the-art performance, which indicates that DFGET can serve as an auxiliary tool for the diagnosis of adenocarcinoma. © 2024 IEEE.

关键词： Semantic Segmentation

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：