检索结果-内蒙古大学图书馆

14th IEEE International Conference on Electronics Information and Emergency Communication, ICEIEC 2024

作者： Hu, Zijian Wang, Chenxing Southeast University School of Automation Nanjing210096 China Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing210096 China

ISBN: (纸本)9798350361889

In this paper, we propose a pylon reconstruction method based on Neural Radiance Fields (NeRF) technology. The advantage of this method lies in its ability to reconstruct pylons from images, with a multi-view model maintaining good performance even under complex lighting and occlusion conditions. We demonstrate the process of using NeRF to reconstruct electric power towers through experiments. During the experimental process, we collect images of electric power towers from different environments and angles, then apply NeRF to process these images, using deep learning to learn and generate a network model capable of expressing the scene. The experimental results show that our method can complete the reconstruction of scenes with only image inputs, and the reconstructed models have a certain accuracy in terms of geometric details and textures. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Driving behaviour recognition from still images by using multi-stream fusion CNN

Driving behaviour recognition from still images by using mul...

引用

作者： Hu, Yaocong Lu, Mingqi Lu, Xiaobo School of Automation Southeast University Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing210096 China

Abnormal driving behaviour is a leading cause of serious traffic accidents threatening human life and public property globally. In this paper, we investigate the use of a deep learning approach to automatically recognize driving behaviour (such as normal driving, driving with hands off the wheel, calling, playing mobile phone, smoking and talking with passengers) in a single image. The task of driving behaviour recognition can be regarded as a multi-class classification problem, and we resolve this problem from two aspects in our study: (1) Employ multi-stream CNN to extract multi-scale features by filtering images with receptive fields of different kernel sizes and (2) investigate different fusion strategies to combine the multi-scale information and generate the final decision for driving behaviour recognition. The effectiveness of our proposed method is validated by extensive experiments carried out on our self-created simulated driving behaviour dataset, as well as a real driving behaviour dataset, and the experiment results demonstrate that the proposed multi-stream CNN-based method achieves the significant performance improvements compared to the state of the art. © 2018, Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Smoky vehicle detection algorithm based on improved transfer learning 6

Smoky vehicle detection algorithm based on improved transfer...

引用

6th International Conference on systems and Informatics, ICSAI 2019

作者： Zhang, Guangming Zhang, Dexiong Lu, Xiaobo Cao, Yichao School of Automation Southeast University Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing210096 China

ISBN: (纸本)9781728152561

With the demand for pollution prevention has increased. Establishing a smoky vehicle inspection and evidence collection system will help to supervise the problem of excessive emissions of vehicles. Because the sample in the training data set is insufficient and unbalanced, the existing methods cannot obtain sufficient classification accuracy in the classification task of the smoky vehicle. This paper uses the transfer learning method to compare the effects of smoky car classification tasks on the five basic networks of DenseNet, NasNet, Inception, VGG19, MobileNet. In addition, for the classification task of the smoke vehicle, it is necessary to consider both the global information of the tail of the vehicle and the detailed information of the smoke area. In this paper, the global average pooling layer is changed to the spatial pyramid pooling layer, and it has achieved better results. Finally, the classification Precision nearly 0.1, Recall 0.3 are obtained, which is much better than the traditional classification method and the shallow non-transfer deep learning method. © 2019 IEEE.

关键词： Smoke

来源：评论

学校读者我要写书评

暂无评论

Hybrid Dynamic Variables-Dependent Event-Triggered Fuzzy Model Predictive control

引用

IEEE/CAA Journal of Automatica Sinica 2024年第3期11卷 723-733页

作者： Xiongbo Wan Chaoling Zhang Fan Wei Chuan-Ke Zhang Min Wu IEEE the School of Automation China University of Geosciencesthe Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systemsand the Engineering Research Center of Intelligent Technology for Geo-ExplorationMinistry of EducationWuhan 430074China

This article focuses on dynamic event-triggered mechanism(DETM)-based model predictive control(MPC) for T-S fuzzy systems.A hybrid dynamic variables-dependent DETM is carefully devised,which includes a multiplicative dynamic variable and an additive dynamic *** addressed DETM-based fuzzy MPC issue is described as a “min-max” optimization problem(OP).To facilitate the co-design of the MPC controller and the weighting matrix of the DETM,an auxiliary OP is proposed based on a new Lyapunov function and a new robust positive invariant(RPI) set that contain the membership functions and the hybrid dynamic variables.A dynamic event-triggered fuzzy MPC algorithm is developed accordingly,whose recursive feasibility is analysed by employing the RPI *** the designed controller,the involved fuzzy system is ensured to be asymptotically *** examples show that the new DETM and DETM-based MPC algorithm have the advantages of reducing resource consumption while yielding the anticipated performance.

关键词： Dynamic event-triggered mechanism(DETM) hybrid dynamic variables model predictive control(MPC) robust positive invariant(RPI)set T-S fuzzy systems

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Smart Energy System Based on Machine Learning 10

Evaluation of Smart Energy System Based on Machine Learning

引用

10th IEEE Data Driven control and Learning systems Conference, DDCLS 2021

作者： Cheng, Xuran Chai, Lin School of Automation Southeast University Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering and School of Automation Southeast University Nanjing210096 China

ISBN: (纸本)9781665424233

In the context of the gradual shortage of fossil energy and serious pollution, the voice of energy transformation is increasing year by year. With the development of Internet and artificial intelligence, the smart energy is getting more and more attention, and it is also the key direction of the upgrading of the world energy industry. In this process, in order to better understand its development and effectively guide the future construction and development of smart energy, appropriate and reasonable evaluation is essential. In the past few years, some researchers have put forward some evaluation methods for smart energy systems, and have achieved some good results. However, only traditional evaluation methods are used which are more subjective. Therefore, the application of machine learning method in the evaluation of smart energy system is worth trying and studying. Starting from the requirements of energy system and human development, this paper first introduces the emergence and development of smart energy and its evaluation methods. Simultaneously indicating the necessity of evaluation. Then the formation of the evaluation index system is briefly introduced. Secondly, machine learning algorithm models such as support vector machines, decision trees, and BP neural networks used are introduced respectively. Finally, experiments are carried out to train the model, and then comparing and analyzing the results. The final results show that the machine learning method plays a good role in the research of smart energy system evaluation, which is worthy of further research. © 2021 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Ensuring Port Safety: Improved YOLOX and DeepSORT for Accurate Detection and Tracking of Trucks and Truck Drivers 42

Ensuring Port Safety: Improved YOLOX and DeepSORT for Accura...

引用

42nd Chinese control Conference, CCC 2023

作者： Zheng, Xueqin Su, Jinya Yang, Jun School of Automation Southeast University Nanjing210096 China Ministry of Education Key Laboratory of Measurement and Control of Complex Systems of Engineering Southeast University Nanjing210096 China

ISBN: (纸本)9789887581543

An optimized YOLOX+DeepSORT method is proposed to accurately detect and track container trucks and truck drivers at the working position of automated rubber tire gantries in ports, while ensuring their safety during the whole working process. In the proposed method, the improved YOLOX performs object detection and its output is used as the input for multi -object tracking using DeepSORT. The improved YOLOX model is developed through replacing standard convolution with depthwise separable convolution, adding the convolutional block attention module to enhance feature extraction, and using Focal Loss in the loss function to address sample imbalances. Comparative experiments were carried out on a self-built dataset, showing a 4.32% increase in mAP and improved reasoning speed for improved YOLOX compared to the original YOLOX. Furthermore, the optimized method shows a 3.57% increase in Multi-Object Tracking Accuracy and a 1.73% increase in Multi-Object Tracking Precision compared to the benchmark YOLOX+DeepSORT. © 2023 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Robust Speed Regulation of PMSM Under Disturbances and Noises Using Composite Model Predictive control 42

Robust Speed Regulation of PMSM Under Disturbances and Noise...

引用

42nd Chinese control Conference, CCC 2023

作者： Mao, Linxuan Su, Jinya Li, Shihua School of Automation Southeast University Nanjing210096 China Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing210096 China

ISBN: (纸本)9789887581543

This paper presents a single-loop Model Predictive control strategy that incorporates a reduced-order Generalized Proportional Integral Observe and a Kalman filter to enhance the speed regulation of Permanent Magnet Synchronous Motor systems in the presence of complex disturbances and measurement noises. The proposed controller design seamlessly integrates the predictive control, disturbance observer, and state filter components, and it was evaluated through simulation comparisons. The performance of the proposed method is evaluated using various metrics, including maximum velocity drop, recovery time, and variance of steady-state error, which demonstrate its superior response performance and anti-disturbance ability when compared to other existing methods without state filtering. © 2023 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

DOUBLE WAVELET THRESHOLD FILTER DESIGN FOR REAL-TIME ADAPTIVE DENOISING IN OA-ICOS

DOUBLE WAVELET THRESHOLD FILTER DESIGN FOR REAL-TIME ADAPTIV...

引用

2024 Jiangsu Annual Conference on Automation, JACA 2024

作者： Deng, Yixin Wang, Zairan Chen, Yang-Yang Liu, Qin Wang, Xiangyu School of Automation Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing China School of Cyber Science and Engineering Southeast University Nanjing China

ISBN: (纸本)9781837242689

In the Off-Axis Integrated Cavity Output Spectroscopy (OA-ICOS) technique, single-stage filters are commonly used to reduce noise and improve the signal-to-noise ratio, enabling more precise CO2 concentration detection. However, these filters often underperform under real-time conditions. To enhance real-time performance, this paper proposes a novel framework based on Double Wavelet Threshold Filter (DWTF) that adaptively suppresses noise while preserving key features of CO2 concentration signal. Firstly, one wavelet threshold filter (WT) is introduced to calculate the mean of the current sequence, providing an initial denoising step. Secondly, another WT is employed to extract features from a longer sequence for adaptive computation of the discount factor. Finally, an exponential moving average filter (EMA) is applied to combine both current and historical data to produce a smoother aggregated output. To validate the effectiveness, DWTF was compared with other conventional algorithms for a CO2 dataset with three distinct states: smooth, ship and mutant, obtained by OA-ICOS. The experimental results demonstrate that DWTF performs effectively in all three states. © The Institution of engineering & Technology 2024.

关键词： Adaptive filters

来源：评论

学校读者我要写书评

暂无评论

An attention convolutional neural network for forest fire smoke recognition 6

An attention convolutional neural network for forest fire sm...

引用

6th International Conference on systems and Informatics, ICSAI 2019

作者： Zhang, Dexiong Cao, Yichao Zhang, Guangming Lu, Xiaobo School of Automation Southeast University Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing210096 China

ISBN: (纸本)9781728152561

In order to find forest fire in time and accurately, the identification of forest fire smoke based on computer vision has become an important research direction. In this paper, a convolutional neural network model based on the attention mechanism is designed for forest fire smoke recognition. By focusing on the regions with obvious discrimination in the image, more precise local features are extracted for fire smoke identification with the auxiliary of backbone network. The performance of network on the unbalanced forest fire dataset is improved by optimizing the cross-entropy loss function with weights. The experimental results show that attention convolutional neural network improves the accuracy of the model which reached 89.3% while reducing false positives and false negatives. © 2019 IEEE.

关键词： Deforestation

来源：评论

学校读者我要写书评

暂无评论

Improved particle filter for object tracking

Improved particle filter for object tracking

引用

作者： Zhang, Tao Fei, Shu-Min College of Automation Electronic Engineering Qingdao University of Sciences and Technology Qingdao China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing China

ISBN: (纸本)9781424487363

Robust real-time tracking of non-rigid objects is a challenging task. Color is a powerful feature for tracking deformable objects in image sequences with complex backgrounds. Color distribution is applied, as it is robust to partial occlusion, is rotation and scale invariant and computationally efficient. Particle filter has been proven very successful for non-linear and non-Gaussian estimation tracking problems. The article presents the integration of color distributions into particle filtering. A target is tracked with a particle filter by comparing its histogram with the histograms of the sample positions using the Bhattacharyya distance. Additionally, to solve the sample impoverishment (all particles collapse to a single point within a few iterations) in the particle-filter algorithm, a new resampling algorithm is proposed to tackle sample impoverishment. The performance of the proposed filter is evaluated qualitatively on various real-world video sequences. The experimental results show that the improved color-based particle filter algorithm can reduce sample impoverishment effectively and track the moving object very well. © 2011 IEEE.

关键词： Color

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：