检索结果-内蒙古大学图书馆

Intelligent Technology and Embedded systems (ICITES), International Conference on

作者： Xiaolou Sun Fei Xie Qi Wang Yuncong Yao Hao Wang Wei Wang Wankou Yang Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education School of Automation Southeast University Nanjing China School of Automation Nanjing University of Information Science and Technology Nanjing China

Most of the existing Siamese-type trackers usually adopt pre-defined anchor boxes or anchor-free schemes to accurately estimate the bounding box of targets. Unfortunately, they suffer from complicated hand-designed components and tedious post-processings. It is not easy to adjust parameters for unique scenes in real applications. So, we propose a new scheme by formulating visual tracking as a direct set prediction problem to alleviate this issue. The main component is a transformer attached to the Siamese-type feature extraction networks. Thus, our new framework can be summarized as Siamese Network with Transformers (SiamTFR). With a fixed small set of learned object queries, we force the final set of predictions via bipartite matching, significantly reducing hyper-parameters associated with the candidate boxes. Due to the unique predictions of this framework, we significantly ease the heavy burden of hyper-parameters search of post-processings in visual tracking. Extensive experiments on visual tracking benchmarks, including GOT-10K, demonstrate that SiamTFR achieves competitive performance and runs at 50 FPS. Specifically, SiamTFR outperforms leading anchor-based tracker SiamRPN++ in the GOT-10K benchmark, confirming its effectiveness and efficiency. Furthermore, SiamTFR is deployed on the embedded device in which the algorithm can be run at 30FPS or 54FPS with TensorRT meeting the real-time requirements. In addition, we design the complete tracking system demo that can work in the real road to narrow the gap between the academic models and industrial deployments.

关键词： Performance evaluation Visualization Target tracking Embedded systems Roads Force Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

An Improved YOLOv5 Detection Algorithm with Pruning and OpenVINO Quantization

An Improved YOLOv5 Detection Algorithm with Pruning and Open...

引用

Chinese Automation Congress (CAC)

作者： Cheng Chen Yahui Gan Zao Han Huan Gao Ang Li Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education School of Automation Southeast University NanJing China Nanjing YingQi Intelligent Technology Co. Ltd. Intel Joint Research Institute on Intelligent Edge Computing NanJing China Nanjing YingQi Intelligent Technology Co. Ltd. Intel Joint Research Institute on Intelligent Edge Computing NanJing China

In order to address the problem of current object detection models being too large to be deployed on robot controllers, this paper proposes improvements to YOLOv5 for real-time detection. The YOLOv5s model is pruned at the Batch Normalization (BN) layer, and further optimized using the OpenVINO tool for quantization. The results demonstrate that our improvements effectively improve the model's inference speed while maintaining its accuracy. Compared to the original YOLOv5 model, the pruned model achieves the same accuracy without degradation, with a 36.6% reduction in parameter count and a 35% reduction in weight storage file size. Furthermore, after optimization with OpenVINO, the final model achieves a FPS of 56.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Continuous finite-time TSM control for electronic throttle system

Continuous finite-time TSM control for electronic throttle s...

引用

2019 Jiangsu Annual Conference on Automation, JACA 2019

作者： Agbaje, Oluwatoyin Timothy Li, Shihua Sun, Hao Zhang, Lu Key Laboratory of Measurement and Control of Complex Systems of Engineering School of Automation Southeast University Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education China

This article examines the position tracking difficulties of the electronic throttle (ET) system and presents a continuous finite-time terminal sliding mode (TSM) control method. The development of this control method involves two procedures: (i) designing a global finite-time observer to estimate the derivative and higher order derivatives of the ET system output, and the total disturbances;and (ii) construction of a continuous finite-time TSM controller based on observer estimations, to ensure the realisation of fast finite-time convergence of system output with a comparatively smooth control action. Comprehensive stability proof, simulation study, and experimental implementation are provided to affirm the applicability of the proposed method. © 2019 Institution of engineering and Technology. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Composite Single-Loop Model Predictive control Design for PMSM Servo System Speed Regulation Based on Disturbance Observer

Composite Single-Loop Model Predictive Control Design for PM...

引用

第32届中国控制与决策会议

作者： Mengdi Zhou Xiangyang Liu Shihua Li School of Automation Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education

In order to optimize the control performance of the permanent magnet synchronous motor（PMSM） in the presence of strong disturbances and model uncertainty,a composite single-loop model predictive control（MPC） based on disturbance observer（DOB） is studied in this ***,a DOB is employed to estimate the lumped disturbance including the uncertain parameters and the external disturbance in real ***,benefitting from model-based design,estimations are introduced into the prediction model of the PMSM,then a composite single-loop MPC is designed based on this ***,the optimal control input is obtained,by introducing Lagrange vector and solving the quadratic programming problem with *** results show that the proposed composite control method has a faster transient response and a better disturbance rejection *** addition,compared with the generally cascade structure,only the predictive horizon and the observer poles are needed to be adjusted,so it provides a more practical optimization algorithm for the engineering application.

关键词： Composite Single-Loop Model Predictive control Disturbance Observer Quadratic Programming Problem PMSM Servo System

来源：评论

学校读者我要写书评

暂无评论

Data Quality Improvement Method of Distributed PV Generation Based on Time Correlation and Spatial Correlation

Data Quality Improvement Method of Distributed PV Generation...

引用

第33届中国控制与决策会议

作者： Min CAO Zhifeng LIANG Zhi LI Yi QU Kaifeng ZHANG Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of EducationSoutheast University National Electric Power Dispatching and Control Center Department of Dispatch Center State Grid Anhui Electric Power Co. Ltd.

In order to solve the problem of data anomaly and data missing in distributed photovoltaic(PV) active power,this paper proposes a data quality improvement method based on time correlation and spatial *** terms of anomaly detection,back propagation(BP) neural network is used to establish a correlation model based on the correlation among active power and meteorological data on the time scale,and the difference method is used to detect and eliminate anomaly *** terms of missing data repair,Random Forest is used to establish a correlation model based on the spatial correlation among active power of power station to be repaired and its surrounding power station's,and the direct repair method is adopted to repair the missing *** experimental results show that the anomaly detection method based on time correlation can achieve an AUC value of more than 0.93,and the repair method based on spatial correlation can achieve more accurate repair results.

关键词： Distributed Photovoltaic Correlation Data Quality Improvement

来源：评论

学校读者我要写书评

暂无评论

Nonsingular Terminal Sliding Mode control for PMSM Servo System Based on Backlash Compensation and High-order Sliding Mode Observer

Nonsingular Terminal Sliding Mode Control for PMSM Servo Sys...

引用

第32届中国控制与决策会议

作者： Jianwei Gui Lu Zhang Shihua Li Xiangyu Wang School of Automation Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education

In this paper,the permanent magnet synchronous motor（PMSM） servo system with backlash is *** the mechanical transmission of the servo system uses gears,screw rods,on the one hand,the proper backlash can ensure the normal operation of the transmission mechanism;on the other hand,the existence of backlash nonlinearity will reduce the rigidity of the transmission mechanism,affect the tracking performance of the system,and even lead to mechanical *** order to eliminate the influence of the backlash nonlinearity,the modeling and identification of the backlash nonlinearity are introduced,and the influence of the backlash is compensated in the *** addition,in order to reject the possible model deviation and uncertain interference,reduce steady states fluctuations,a high-order sliding mode observer（HOSMO） based nonsingular terminal sliding mode control（NTSMC） is *** simulation verification,the compound controller proposed in this paper can effectively reduce the influence of the backlash nonlinearity and improve the position tracking performance of the system.

关键词： Permanent Magnet Synchronous Motor（PMSM） Servo System Backlash Nonsingular Terminal Sliding Mode control（NTSMC） High-order Sliding Mode Observer（HOSMO）

来源：评论

学校读者我要写书评

暂无评论

Multi-source Disturbance Observer Based Continuous Sliding Mode control for Fuel Quantity Actuator System

Multi-source Disturbance Observer Based Continuous Sliding M...

引用

第32届中国控制与决策会议

作者： Xuming Wang Hao Sun Shihua Li Jun Yang School of Automation Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education

The fuel quantity actuator is a significant component in the position-controlled fuel injection pump,which controls the fuel quantity injected into the diesel *** the fuel quantity actuator system,there are nonlinearities and multi-source disturbances which result in significant degradations of control performance and increase the difficulty of *** researches merely consider the constant disturbance in the fuel quantity actuator system but ignore the existing harmonic disturbance,as a result,it is hard to achieve excellent control performance in the presence of harmonic *** paper analyses the working principle of system in detail,considers multiple sources of disturbances,and then establishes the nonlinear mathematical model with multi-source disturbances including constant disturbances and harmonic ***,a baseline chattering free continuous sliding mode controller is *** the baseline controller,the feedback linearization technique is applied to handle the *** order to further reduce the steady-state fluctuation,a multi-source disturbance observer composed of a disturbance observer（DOB） and a harmonic disturbance observer（HDOB） is employed to estimate the multi-source disturbances and the estimations are used for *** this end,a multi-source disturbance observer based continuous sliding mode control approach is *** guaranteeing robustness and free chattering,the steady-state fluctuation is reduced effectively since the switch function gain in the continuous control law can be selected *** simulation validates the proposed control approach.

关键词： Multi-source disturbance Harmonic disturbance observer Continuous sliding mode control Fuel quantity actuator

来源：评论

学校读者我要写书评

暂无评论

Skeleton-prompt: A cross-dataset transfer learning approach for skeleton action recognition

引用

Pattern Recognition 2026年 169卷

作者： Mingqi Lu Xiaobo Lu Jun Liu School of Automation Southeast University Nanjing 210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing 210096 China School of Computing and Communications Lancaster University UK

This paper presents Skeleton-Prompt, a novel tuning method designed to tackle cross-dataset transfer issues in skeleton action recognition models. Given the scarcity of large-scale 3D skeleton datasets and the variability in keypoint structures across datasets, existing methods often rely on training models from scratch, necessitating extensive labeled data and exhibiting high sensitivity to occlusion. Our approach aims to fine-tune pre-trained models to adapt to limited real-world skeleton data. We use 2D skeletons as inputs and leverage a large human motion dataset for 2D to 3D pose estimation to learn generalizable motion features. A lightweight prompt generator produces instance-level prompts, and we employ dynamic queries with cross-attention to refine the semantic information of the input data. Additionally, we introduce a joint-enhanced multi-stream fusion mechanism based on self-attention to improve robustness against incomplete skeletons. Skeleton-Prompt represents a significant advancement in efficient fine-tuning for skeleton action recognition, effectively addressing cross-dataset generalization challenges in a data-efficient and parameter-efficient manner.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Stochastic DoS attack allocation against collaborative estimation in sensor networks

Stochastic DoS attack allocation against collaborative estim...

引用

作者： Zhang, Ya Du, Lishuang Lewis, Frank L. School of Automation Southeast University Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing210096 China University of Texas at Arlington Research Institute Fort WorthTX76118 United States

In this paper, denial of service DoS attack management for destroying the collaborative estimation in sensor networks and minimizing attack energy from the attacker perspective is studied. In the communication channels between sensors and a remote estimator, the attacker chooses some channels to randomly jam DoS attacks to make their packets randomly dropped. A stochastic power allocation approach composed of three steps is proposed. Firstly, the minimum number of channels and the channel set to be attacked are given. Secondly, a necessary condition and a sufficient condition on the packet loss probabilities of the channels in the attack set are provided for general and special systems, respectively. Finally, by converting the original coupling nonlinear programming problem to a linear programming problem, a method of searching attack probabilities and power to minimize the attack energy is proposed. The effectiveness of the proposed scheme is verified by simulation examples. © 2014 Chinese Association of Automation.

关键词： Denial-of-service attack

来源：评论

学校读者我要写书评

暂无评论

A NEW IMAGE DENOISING METHOD BASED ON STEER KETNEL REGRESSION

A NEW IMAGE DENOISING METHOD BASED ON STEER KETNEL REGRESSIO...

引用

Jiangsu Annual Conference on Automation (JACA 2020)

作者： G. Shi L. Chai L. Jin Key Laboratory of Measurement and Control of Complex Systems of Engineering and School of Automation Southeast University Nanjing 210096 China

In this paper, we propose a new image pyramid denoising model based on the iterative steer kernel regression (ISKR) method. By introducing an image pyramid to generate images at multiple scales, it can filter out large-scale noise on low-resolution images and preserve details on the high-resolution image, and then we fuse the denoised images of multiple resolutions into a high-quality image by up-sampling noise residual. This method can improve denoising performance efficiently. and reduce the cost of calculation. Experiments show that this model reduces calculation by about 58% compared with the ISKR method while ensuring a good denoising effect.

关键词： image resolution image denoising regression analysis

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：