检索结果-内蒙古大学图书馆

International Conference on control, Automation and Information sciences (ICCAIS)

作者： Xinwei Wei Linxiu Chen Chenyu Zhang Yiru Lin Linao Zhang Xiaokai Liu Jixiang Jiang Wei Yi School of Information and Communication Engineering University of Electronic Science and Technology of China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Research Institute of Electronic Science and Technology University of Electronic Science and Technology of China

Multi-target Tracking (MTT) is the process of processing received measurements to maintain estimates of the current status of multiple targets, with important applications to autonomous driving, aerial reconnaissance, underwater operations, and others. In the model-based setting, Bayesian filtering can provide the theoretical optimal estimate in a single target scenario. However, in complex situations, uncertain factors such as changes in the number of targets will cause the amount of calculation to increase exponentially, resulting in a decline in tracking accuracy. To solve that problem, model-free methods based on deep-learning provide an attractive alternative, especially the state-of-the-art architecture Transformer based encoder-decoder prediction model, which outperforms the Bayesian filters in the single frame prediction tasks. However, when switching to continuous tracking, these algorithms need to be trained separately frame by frame to adapt to the new tasks. Still, there is no correlation between their predictions from different frames, which prevents them from fully utilizing all the measurements. In this paper, we propose an end-to-end Transformer based MTT method with state autoregression, which allows the model to have the capability of online continuous tracking and make total use of the entire trajectory. The results show that the proposed model is a great extension from single-frame prediction to online continuous tracking.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Meta-ZSDETR: Zero-shot DETR with Meta-learning

Meta-ZSDETR: Zero-shot DETR with Meta-learning

引用

International Conference on Computer Vision (ICCV)

作者： Lu Zhang Chenbo Zhang Jiajia Zhao Jihong Guan Shuigeng Zhou Shanghai Key Lab of Intelligent Information Processing and School of Computer Science Fudan University China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory China Department of Computer Science & Technology Tongji University China

Zero-shot object detection aims to localize and recognize objects of unseen classes. Most of existing works face two problems: the low recall of RPN in unseen classes and the confusion of unseen classes with background. In this paper, we present the first method that combines DETR and meta-learning to perform zero-shot object detection, named Meta-ZSDETR, where model training is formalized as an individual episode based meta-learning task. Different from Faster R-CNN based methods that firstly generate class-agnostic proposals, and then classify them with visual-semantic alignment module, Meta-ZSDETR directly predict class-specific boxes with class-specific queries and further filter them with the predicted accuracy from classification head. The model is optimized with meta-contrastive learning, which contains a regression head to generate the coordinates of class-specific boxes, a classification head to predict the accuracy of generated boxes, and a contrastive head that utilizes the proposed contrastive-reconstruction loss to further separate different classes in visual space. We conduct extensive experiments on two benchmark datasets MS COCO and PASCAL VOC. Experimental results show that our method outperforms the existing ZSD methods by a large margin.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Gm-APD LiDAR Reconstruction Algorithm with Improved Matched Filtering Based on Negative Binomial Distribution

Gm-APD LiDAR Reconstruction Algorithm with Improved Matched ...

引用

Academic International Symposium on Optoelectronics and Microelectronics technology (AISOMT)

作者： Hengchang Ou Jianfeng Sun Le Ma Peng Jiang National Key Laboratory of Laser Spatial Information Harbin Institute of Technology Harbin Heilongjiang China Zhengzhou Research Institute Harbin Institute of Technology Zhengzhou Henan China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China

ISBN: (数字)9798331542283

ISBN: (纸本)9798331542290

This article addresses the challenges faced by Gm-APD detectors in lidar systems when detecting weak signals. We use a triggering model based on the negative binomial distribution, which replaces the traditional Poisson distribution model, allowing for a more accurate description of the echo characteristics from rough surface targets. Building on this foundation, we have improved the conventional matched filtering algorithm by integrating the laser pulse waveform with the actual triggering response of the detector, thereby enhancing the detection rate. Experimental results demonstrate that the improved algorithm significantly increases the detection probability under low signal-to-noise ratios and with a limited number of frames, confirming the effectiveness of the new triggering model and the enhanced algorithm.

关键词： Maximum likelihood estimation Laser radar Accuracy Filtering Detectors Filtering algorithms Surface roughness Rough surfaces Photonics Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

An Interval-Peak-Based Algorithm for Range Image Reconstruction of GM-APD Lidar

An Interval-Peak-Based Algorithm for Range Image Reconstruct...

引用

Academic International Symposium on Optoelectronics and Microelectronics technology (AISOMT)

作者： Shihang Sun Jianfeng Sun Peng Jiang Hongchao Ni Xin Zhou Le Ma Ruobin Lin National Key Laboratory of Laser Spatial Information Harbin Institute of Technology Harbin Heilongjiang China Zhengzhou Research Institute Harbin Institute of Technology Zhengzhou Henan China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China

ISBN: (数字)9798331542283

ISBN: (纸本)9798331542290

GM-APD lidar has single-photon sensitivity, so that it can obtain 3D information of distant targets. On the other hand, the laser echo of targets is easily drowned by noise. In order to solve this problem, an interval-peak-based algorithm for range image reconstruction is proposed in this paper. Firstly, in the photon counts histogram, the x-axis is divided into small intervals and the peak value of each interval is taken. This step weakens the bad characteristic caused by the trigger probability. Secondly, according to the data feature, the trigger probability ratio coefficient and the neighborhood correlation coefficient are obtainned. Finally, the range image can be extracted by the peak method after the peak value of each interval is multiplied with this two coefficients. It is verified by the experimental data that when the SNR of target echo data is 0.022, the recovery ratio of the proposed algorithm can reach 80%, which is 25% higher than the matching filter algorithm. The proposed algorithm has a good application prospect in the range image reconstruction of GM-APD lidar.

关键词： Laser radar Three-dimensional displays Sensitivity Filtering Logic gates Approximation algorithms Spatiotemporal phenomena Image reconstruction Signal to noise ratio Photonics

来源：评论

学校读者我要写书评

暂无评论

An Improved RT-DETR-Based Object Detection Algorithm for Gm-APD LiDAR

An Improved RT-DETR-Based Object Detection Algorithm for Gm-...

引用

Academic International Symposium on Optoelectronics and Microelectronics technology (AISOMT)

作者： Qianxin Wang Jianfeng Sun Peng Jiang Xin Zhou Yuanxue Ding Guanlin Chen National Key Laboratory of Laser Spatial Information Harbin Institute of Technology Harbin Heilongjiang China Zhengzhou Research Institute Harbin Institute of Technology Zhengzhou Henan China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China

ISBN: (数字)9798331542283

ISBN: (纸本)9798331542290

Gm-APD LiDAR has a high sensitivity response characteristic, enabling imaging for detecting targets at extended distances, and finds broad utility. However, the highly sensitive response characteristic also makes Gm-APD LiDAR vulnerable to noise, resulting in poor imaging quality and challenging the application of target detection algorithms to this type of LiDAR. Therefore, this paper proposes a long-range vehicle detection model DRT-DETR for Gm-APD LiDAR. DRT-DETR is based on RT-DETR and employs a dual-channel feature extraction backbone, which combines with the lightweight FasterNet Block to capture semantic features from distance and intensity images effectively. It also incorporates mixed attention modules to selectively combine and enhance key features from both types of images. Attention-based Intrascale Feature Interaction employs cascaded group attention as a replacement for multi-head attention in order to minimize computational redundancy. Finally, Dysample is used instead of nearest neighbor upsampling in the cross-scale feature fusion to align features better and minimize distortion. The improved model boosts detection accuracy by 3.8% over RT-DETR and outperforms other common object detection models on the dataset, demonstrating its effectiveness.

关键词： Laser radar Sensitivity Computational modeling Vehicle detection Semantics Redundancy Imaging Object detection Feature extraction Distortion

来源：评论

学校读者我要写书评

暂无评论

Rudder Health Monitoring and Data Visualization Based on Feature Extraction 10

Rudder Health Monitoring and Data Visualization Based on Fea...

引用

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

作者： Zhou, Yajing Sun, Mingwei Hao, Mingrui Chen, Zengqiang College of Artificial Intelligence Nankai University Tianjin300350 China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing100074 China

ISBN: (纸本)9781665424233

In order to monitor the health status of the rudder, this paper proposes a health monitoring method based on deep neural network through feature extraction. First, sufficient samples are obtained by data preprocessing. Then the feature dimension is reduced by using autoencoder, and the health monitoring can be carried out by combining with Softmax classifier. After proper tuning and comparison, proper network structure parameters can be obtained. Two kinds of images can be plotted by using the feature extraction of encoder to provide explicit contrast between the normal and abnormal rudders. The effectiveness of the proposed method can be demonstrated by numerical simulations. © 2021 IEEE.

关键词： Visualization

来源：评论

学校读者我要写书评

暂无评论

An infrared Radar fusion tracking algorithm based on adaptive fault tolerant filtering 40

An infrared Radar fusion tracking algorithm based on adaptiv...

引用

40th Chinese control Conference, CCC 2021

作者： Peng, Siting Lei, Li Ma, Yichao Youcheng, Wang Beijing Electro-Mechanical Engineering Institute Beijing100074 China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing100074 China

ISBN: (纸本)9789881563804

In this paper, based on the fusion tracking of infrared and radar, a federated kalman filtering algorithm based on adaptive fault tolerance is designed. According to the observation equation of infrared and radar, a distributed fusion federated kalman filtering structure is established by using three infrared sensors and three radar sensors. The sub nodes filter their detection information respectively, and the estimation results are obtained. After that, the sub nodes filter results are sent into their part of fault-tolerant judgment respectively, then we can get the weight information of each sub node, thus it can determine the degree of dependence of each node, and the filtering results of all sub nodes are fused into calculation by their weight. The final simulation shows that the algorithm can isolate the interference in the multi-mode fusion tracking process effectively , and get a stable state estimation output. © 2021 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Tracking radar

来源：评论

学校读者我要写书评

暂无评论

Meta-ZSDETR: Zero-shot DETR with Meta-learning

arXiv

引用

arXiv 2023年

作者： Zhang, Lu Zhang, Chenbo Zhao, Jiajia Guan, Jihong Zhou, Shuigeng Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory China Department of Computer Science & Technology Tongji University China

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Tracking performance limitations of networked control systems with packet dropouts and logarithmic quantization 41

Tracking performance limitations of networked control system...

引用

第41届中国控制会议

作者： Jianhao Li Xiaowei Jiang Hao Chen Shaoying Wang Xianhe Zhang School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation of Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Fujian Provincial Key Laboratory of Intelligent Identification and Control of Complex Dynamic System College of Science Binzhou University School of Electrical Engineering and Automation Hubei Normal University

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

In this paper,we focus on the tracking performance(TP) limitations of networked control systems(NCS s).The control system considered is a multi-input and multi-output(MIMO) discrete-time network control system with time delay,channel noise,packet dropouts,and logarithmic quantization communication *** modeling the channel,we assumed the channel noise to be additive white Gaussian noise(AWGN) and used a binary random process to model packet dropouts and a logarithmic quantizer to model the quantization *** explicit expression of the TP limitations of NCSs utilizing the two-degree-of-freedom(TDOF) controller is then derived using the frequency-domain approach,coprime decomposition,and Youla parameterization *** results show that the essential characteristics of the plant(locations and directions of nonminimum phase zeros and unstable poles) and network constraints(time delay,packet dropouts,quantization,and noise power spectral density) are closely related to the TP limitations.

关键词： Networked control systems tracking performance limitations packet dropouts logarithmic quantization

来源：评论

学校读者我要写书评

暂无评论

A Method for Marine Ship Formation Intention Recognition based on BiConvLSTM-Attention

A Method for Marine Ship Formation Intention Recognition bas...

引用

Electronic Information Engineering and Computer science (EIECS), 2021 International Conference on

作者： Yunqiao Xi Junping Zhang Jian Liu Linlin Wang Hongfeng Xu Linxiu Chen Jixiang Jiang School of Electronics and Information Engineering Harbin Institute of Technology Harbin China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Institute of Electrical and Mechanical Engineering Beijing China

To solve the problem that current dynamic intention recognition methods fail to make full use of time domain variation information between multi-temporal group targets, which leads to low accuracy of intention recognition. This paper proposes a bidirectional convolutional long short term memory-attention network for marine formation target intention recognition. The network takes the multi-source trajectory data of the marine ship formation target as the input, extracts and uses the target change rule and time domain characteristics of the Marine formation data, and trains the model to have the ability to independently learn the weight of information in different time periods. The simulation results show that the method has good performance and can meet the needs of practical application.

关键词：

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：