检索结果-内蒙古大学图书馆

HRPose: Real-Time High-Resolution 6D Pose Estimation Network Using Knowledge Distillation

Chinese Journal of Electronics 2023年第1期32卷 189-198页

作者： GUAN Qi SHENG Zihao XUE Shibei Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Engineering Research Center of Intelligent Control and Management

Real-time six degrees-of-freedom(6D)object pose estimation is essential for many real-world applications, such as robotic grasping and augmented reality. To achieve an accurate object pose estimation from RGB images in real-time, we propose an effective and lightweight model, namely high-resolution 6D pose estimation network(HRPose). We adopt the efficient and small HRNetV2-W18 as a feature extractor to reduce computational burdens while generating accurate 6D poses. With only 33% of the model size and lower computational costs, our HRPose achieves comparable performance compared with state-of-the-art models. Moreover, by transferring knowledge from a large model to our proposed HRPose through output and feature-similarity distillations, the performance of our HRPose is improved in effectiveness and efficiency. Numerical experiments on the widely-used benchmark LINEMOD demonstrate the superiority of our proposed HRPose against state-of-the-art methods.

关键词： Knowledge engineering Computational modeling Pose estimation Grasping Benchmark testing Feature extraction Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Multiple-instance CNN Improved by S3TA for Colon Cancer Classification with Unannotated Histopathological images 11

Multiple-instance CNN Improved by S3TA for Colon Cancer Clas...

引用

11th International Conference on intelligent control and Information processing, ICICIP 2021

作者： Ye, Tiange Lan, Rushi Luo, Xiaonan Guilin University of Electronic Technology Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin China

ISBN: (纸本)9781665425155

In this paper, we propose a new method for colon cancer classification from histopathological images, which can automatically analyze a given whole slide image (WSI). We usually classify cancer classification by referring a WSI, which is typically 20000 × 20000 pixels. The cost of obtaining WSIs with annotating cancer regions is very high. Multiple-instance learning (MIL) is a variant of supervised learning in which the instances in a bag share a single class label. That is, MIL only needs unannotated WSI. In recent years, MIL has developed a hard attention mechanism which has achieved good performance. However, this hard attention mechanism cannot notice the interior of each patch, i.e., it lacks soft attention mechanism. In this paper, a soft, sequential, spatial, top-down attention mechanism (which we abbreviate as S3TA) is used to make up for the lack of MIL attention mechanism. Finally, our experiments show that by varying the number of attention steps in S3TA, we achieved a better accuracy of 93.6% than the old model. © 2021 IEEE.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

Facial Recognition-Based Classroom Attendance System Utilizing Deep Learning 1

Facial Recognition-Based Classroom Attendance System Utilizi...

引用

1st IEEE International Conference on Data Intelligence and Innovative Application, DIIA 2024

作者： Zhou, Cong Luo, Xiaonan Guilin University of Electronic Technology Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin China

ISBN: (纸本)9798331504434

In recent years, artificial intelligence technologies, especially facial recognition, have made significant strides. With its high precision and efficiency, facial recognition has shown great potential and advantages in areas such as identity verification and behavior analysis. Classroom learning is the main channel through which students acquire knowledge, develop skills, and improve their competencies. A well-organized classroom attendance system is essential for ensuring the effective implementation and smooth execution of teaching plans. This system is based on an OpenCV and PyQt5 facial recognition client, utilizing the LBPH algorithm to achieve efficient facial recognition. In addition to providing a simple check-in function, the system offers a complete registration process and data management features. In practical use, students simply need to check in by facing the camera, allowing the system to automatically recognize the student's face and record the attendance data. This significantly simplifies the check-in process for both teachers and students, thereby improving classroom management efficiency. © 2024 IEEE.

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

Short-Term Building Load Forecast Based on Patch Learning with Long Short-Term Memory Network and Support Vector Regression 1

引用

2nd International Conference on Neural Computing for Advanced Applications, NCAA 2021

作者： Dan, Zhaohui Wang, Bo Fan, Huijin Liu, Lei Key Laboratory of Ministry of Education for Image Processing and Intelligent Control Artificial Intelligence and Automation School Huazhong University of Science and Technology Wuhan430074 China

ISBN: (数字)9789811651885

ISBN: (纸本)9789811651878

This paper proposes a novel short-term building load forecasting approach under the framework of patch learning, a novel data-driven model that aggregates a global model and several patch models to further reduce forecasting errors. A PL-LSTM-SVR model is hereby employed to address such a time-series based forecasting problem, where the long short-term memory network is considered as the global model and the support vector regression is selected as the patch model. To obtain satisfying performances, an infinity norm measurement is selected to evaluate load forecasting errors and identify patch locations. Furthermore, a genetic algorithm with elitist preservation strategy is introduced for hyperparameter tuning. The performances of the proposed PL-LSTM-SVR model are tested and verified on two different data sets, and compared with four advanced building load forecasting models on several common metrics. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Prostate surgery path planning based on simplified delay-PCNN

Prostate surgery path planning based on simplified delay-PCN...

引用

2011 IEEE International conference on intelligent Computation and Bio-Medical Instrumentation, ICBMI 2011

作者： Li, He Zhang, Xuming Hou, Wenguang Ding, Mingyue Life School of Science and Technology Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9780769546230

This paper presents an algorithm to find the shortest path in 3D(three-dimensional) prostate surgery planning. Using a simplified delay pulse coupled neural network(S-DPCNN) model, a shortest path can be drawn automatically from the target position to the puncture point. Compared to the traditional pulse coupled neural network(PCNN), S-DPCNN needs much fewer neurons and therefore decreases complexity of computation. Experiments on computer simulations show the validity of this method. © 2011 IEEE.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Geometric active contour model and its application to carotid plaque detection

Geometric active contour model and its application to caroti...

引用

2011 IEEE International conference on intelligent Computation and Bio-Medical Instrumentation, ICBMI 2011

作者： Cheng, Jieyu Ding, Mingyue Zhang, Xuming Life School of Science and Technology Huazhong University of Science and Technology Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Wuhan China

ISBN: (纸本)9780769546230

This paper gives an overview of three different geometric active contour models with the focus on the application to carotid plaque detection from cross-sectional ultrasound images of the carotid artery. On one hand, basic principles of these geometric active contour models are presented. On the other hand, performance of these models are tested on 16 images and compared with the manual delineations. © 2011 IEEE.

关键词： Ultrasonic applications

来源：评论

学校读者我要写书评

暂无评论

Circadian Rhythms Recovery Based on Slide Mode controller 34

Circadian Rhythms Recovery Based on Slide Mode Controller

引用

第三十四届中国控制会议

作者： ZHOU Ren REN Haipeng HUANG Xiaona Department of Information and Control Engineering Xi'an University of Technology Shaanxi Key Laboratory for Complex System Control and Intelligent Information Processing

ISBN: (纸本)9781467374439

Disrupting the circadian rhythms will cause health problems such as sleep disorders, memory disorders and obesity. Finding the suitable external stimulation to synchronize a model with a desired phase is a biologically significant issue. The phase control of circadian rhythms for Drosophila is considered from control engineering viewpoint in this paper. If all parameters of the model are known, we can use the feedback linearization to design a tracking controller for the phase ***, in practice, parameters uncertainties always exist. To deal with this problem, a slide-mode controller is proposed for the phase tracking control of circadian rhythms. The simulation results show the effectiveness of the proposed method.

关键词： Circadian rhythms,Circadian phase,Parameter uncertainty,Slide mode control

来源：评论

学校读者我要写书评

暂无评论

An approach with nested partition for resource-constrained project scheduling problem

An approach with nested partition for resource-constrained p...

引用

19th International Conference on Industrial Engineering and Engineering Management: Assistive Technology of Industrial Engineering

作者： Liu, Zhen-Yuan Yu, Wen-Min Institute of Systems Engineering Huazhong University of Science and Technology Wuhan China Key Laboratory of Education Ministry for Image Processing and Intelligent Control Wuhan China

ISBN: (纸本)9783642383908

A time-based nested partition (NP) approach is proposed to solve resource-constrained project scheduling problem (RCPSP) in this paper. In iteration, one activity is selected as the base point of which the finish time interval calculated by CPM is divided into two parts to form two subregions on the basis of the promising region of the last iteration. Then sampling is taken in both subregions and the surrounding region to determine the promising region and aggregate the other as the surrounding region of this iteration so that whether the backtracking or the moving operation being performed is determined. Double justification is also performed in iteration to improve the results. The results of numerical tests on PSPLIB show the effectiveness and time-efficient of the proposed NP method. © 2013 Springer-Verlag Berlin Heidelberg.

关键词： Scheduling

来源：评论

学校读者我要写书评

暂无评论

Knowledge-Data Fusion Based Source-Free Semi-Supervised Domain Adaptation for Seizure Subtype Classification

Knowledge-Data Fusion Based Source-Free Semi-Supervised Doma...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Peng, Ruimin An, Jiayu Wu, Dongrui School of Artificial Intelligence and Automation Huazhong University of Science and Technology Key Laboratory of the Ministry of Education for Image Processing and Intelligent Control Wuhan430074 China

ISBN: (纸本)9781665410205

Electroencephalogram (EEG)-based seizure sub-type classification enhances clinical diagnosis efficiency. Source-free semi-supervised domain adaptation (SF-SSDA), which transfers a pre-trained model to a new dataset with no source data and limited labeled target data, can be used for privacy-preserving seizure subtype classification. This paper considers two challenges in SF-SSDA for EEG-based seizure subtype classification: 1) How to effectively fuse both raw EEG data and expert knowledge in classifier design? 2) How to align the source and target domain distributions for SF-SSDA? We propose a Knowledge-Data Fusion based SF-SSDA approach, KDF-MutuaISHOT, for EEG-based seizure subtype classification. In source model training, KDF uses Jensen-Shannon Diver-gence to facilitate mutual learning between a feature-driven Decision Tree-based model and a data-driven Transformer-based model. To adapt KDF to a new target dataset, an SF-SSDA algorithm, MutualSHOT, is developed, which features a consistency-based pseudo-label selection strategy. Experiments on the public TUSZ and CHSZ datasets demonstrated that KDF-MutualSHOT outperformed other supervised and source-free domain adaptation approaches in cross-subject seizure subtype classification. © 2024 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

A new artificial immune network classifier for SAR image

A new artificial immune network classifier for SAR image

引用

MIPPR 2009 - Pattern Recognition and Computer Vision: 6th International Symposium on Multispectral image processing and Pattern Recognition

作者： Liu, Ruochen Niu, Manchun Jiao, Licheng Key Laboratory of Intelligent Perception and Image Understanding Institute of Intelligent Information Processing Xidian University Xi'an Shaanxi 710071 China

ISBN: (纸本)9780819478078

Inspired by the idiotypic network theory, a new artificial immune network classifier for SAR image is proposed in this paper. In the proposed algorithm, only one B-cell instead of many B-cells is used to denote a class so as to reduce the scale of network as well as avoid the suppression operation between B-cells;moreover, a new affinity function based on the correct rate is proposed to realize antigen priority based the evaluation strategy. The proposed algorithm has been extensively compared with Fuzzy C-means (FCM), Multiple-Valued Immune Network algorithm (MVIN), and Clonal Selection Algorithm for classifier (CSA) over two SAR images. The result of experiment indicates the superiority of the algorithm over FCM, MVIN and CSA on classification accuracy and robustness. © 2009 Copyright SPIE - The International Society for Optical Engineering.

关键词： Synthetic aperture radar

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：