检索结果-内蒙古大学图书馆

IEEE International Conference on Unmanned systems (ICUS)

作者： Jin Cheng Donghui Wei Wanchun Chen Wang Gao Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing Electro-Mechanical Engineering Institute Beijing China School of Astronautics Beihang University Beijing China

ISBN: (纸本)9781728137933

This paper focuses on the problem of ultra-low-altitude flight obstacle distance estimation for monocular vision-assisted aircraft. First, the basic error model of distance estimation using sequence images is derived and the phenomenon of "epipole dead zone" is revealed. Then the distance estimation algorithm based on pairs of coplanar points is proposed as well as its error model. This algorithm is proved to be a solution of the "epipole dead zone" problem theoretically. Finally, numerical simulations show that the proposed distance estimation algorithm can effectively improve the accuracy of distance estimation in the "epipole dead zone".

关键词： Ultra-low altitude flight Monocular vision Distance estimation Monocular Vision error model flight altitude flight Death Dead

来源：评论

学校读者我要写书评

暂无评论

Transformer based Online Continuous Multi-Target Tracking with State Regression

Transformer based Online Continuous Multi-Target Tracking wi...

引用

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

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

Point Cloud Preprocessing on 3D LiDAR data for Unmanned Surface Vehicle in Marine Environment

Point Cloud Preprocessing on 3D LiDAR data for Unmanned Surf...

引用

Information technology,Big Data and Artificial Intelligence (ICIBA), International Conference on IEEE International Conference on

作者： Xianzhi Qi Wenxing Fu Pei An Bingli Wu Jie Ma National Key Laboratory of Science and Technology on Multispectral Information Processing School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China

ISBN: (数字)9781728152240

ISBN: (纸本)9781728152257

Point cloud preprocessing is still a challenging task in the marine environment, for it is difficult to filter out non-obstacle points while avoiding damage to the obstacle completeness. In this paper, we propose a novel data preprocessing method on 3D LiDAR data for the unmanned surface vehicle in the marine environment. It consists of two tasks: outlier removal and wake filtering. As the spatial resolution of LiDAR changes with distance, we exploit distance normalization on statistical outlier filter for robust outlier removal. Considering the gradient difference between wave wake and obstacle surface near the water, we define and calculate the vertical state of point cloud on the range image to obtain the pre-filtering point set, and then use the RANSAC method to filter out the wake points. Experiments on real data has demonstrated the effectiveness of the proposed algorithm both in terms of feasibility and accuracy.

关键词： Three-dimensional displays Laser radar Filtering Filtering algorithms Spatial resolution Task analysis Measurement by laser beam

来源：评论

学校读者我要写书评

暂无评论

A summary of the development of cooperative and intelligent technology for multi-UAV systems

A summary of the development of cooperative and intelligent ...

引用

2019 IEEE International Conference on Unmanned systems and Artificial Intelligence, ICUSAI 2019

作者： Zhou, Huan Su, Qian Fu, Wenxing Xu, Cheng Zheng, Meiyun Yang, Jingguang Aeronautical Engineering College Air Force Engineering University Xi'an China School of Astronautics Northwest Polytechnical University Xi'an China Unmanned System Research Institute Northwest Polytechnical University Xi'an China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China School of Marine Science and Technology Northwest Polytechnical University Xi'an China Aviation Maintenance Sergeant School of Air Force Engineering University Xinyang China

ISBN: (纸本)9781728158594

In the process of formation cooperative autonomous flight and mission execution, multi-UAV systems have the characteristics of large disturbance, strong coupling of multi variables, high degree of uncertainty and complex cooperative factors, so there are many difficulties in the design of cooperative and intelligent control system. How to effectively develop the cooperative and intelligent technology of multi-UAV systems has become an urgent problem in the field of unmanned system and artificial intelligence. This paper first introduces the key technologies involved in UAV system at present, and then analyzes the challenges faced by the development of UAV system. Finally, it focuses on the development trend of multi-UAV systems cooperation and intelligent technology in the future. The research results have strong theoretical guidance significance for the cooperation and intelligent development of multi-UAV systems in China. © 2019 IEEE.

关键词： Flight control systems

来源：评论

学校读者我要写书评

暂无评论

Credibility Evaluation of Aircraft HWIL Simulation Based on the Time-Varying Area Metric

Credibility Evaluation of Aircraft HWIL Simulation Based on ...

引用

High Performance and Smart Computing (HPSC), IEEE International Conference on

作者： Huapin Geng Ning Wang Jiahui Tong Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing Electro-mechanical Engineering Institute Beijing China Beijing Electro-mechanical Engineering Institute Beijing China

ISBN: (数字)9798350389463

ISBN: (纸本)9798350389470

Credibility evaluation of aircraft HWIL simulation is usually measured by the degree of consistency between simulation test data and the measured data. A new method for evaluating the credibility of aircraft HWIL simulation is established based on the idea of time-varying area measurement and uncertainty measurement Mainly for univariate, single simulation, multivariable and multi-simulation. The DTW distance measurement method is used to obtain the weight coefficients of correlated multiple response variables, and the effectiveness of uncertainty measurement method in obtaining the credibility of aircraft HWIL simulation at a certain level of confidence is verified through typical examples.

关键词： Weight measurement Uncertainty Correlation Area measurement Measurement uncertainty Distance measurement Indexes

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

SAR Image Registration Based on Feature Points Using Improved CSP-DenseNet

SAR Image Registration Based on Feature Points Using Improve...

引用

Pattern Recognition and Artificial Intelligence (PRAI), International Conference on

作者： Ziwei Wang Yanjiao Yang Guangzhou Qu Qingxi Chi Beijing Electro-Mechanical Engineering Institute Beijing China Beijing Electro-Mechanical Engineering Institute Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China

Synthetic aperture radar (SAR) image registration is widely used in integrated navigation system with development of guidance system in sensors and other applications. However, there exists some difficulty because of the quality and imaginary principle of SAR images. In this article, a brand-new method based on feature points using improved CSP-DenseNet is proposed to solve the problems of SAR image registration with weak and noisy texture. Deep features of interest points in SAR images are extracted using the proposed network from the crops of search image and template image respectively. The method has an advantage of preserving abundant feature information in SAR images under the influence of insufficient image information and noise of SAR images. The CSP-DenseNet architecture has a cross-stage construction optimizing fused by CSP-Net and DenseNet to extract matching features. The network is partially connected in specific convolutional layers for feature reusing and computation resources saving. Then, Brute Force Matcher and RANSAC voting are successively applied for a larger number of matching pairs and high-precise matching vertexes. Experimental results on various SAR image matching methods show that the proposed method provides better performance than other approaches compared.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An autonomous path planning method considering terrain aided navigation constraints

An autonomous path planning method considering terrain aided...

引用

Chinese Automation Congress (CAC)

作者： Min Jiang Cheng Xu Hua Ji Yuqi Wang Beijing Electro-Mechanical Engineering Institute Bejing China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing Electro-Mechanical Engineering Institute Bejing China

In order to solve the autonomous path planning problem with terrain aided navigation constraints, a navigation-first path planning method was adopted, that is, the distribution of terrain matching regions and the drift of navigation errors were given priority, and the path planning problem was transformed into the shortest path problem of single source directed graph to determine the nodes on the path. Secondly, the path planning between adjacent nodes is transformed into a path planning problem with initial direction constraint and terminal direction freedom/constraint, and the lateral path is smoothed. Finally, for the local path passing through the no-fly zone, the obstacle avoidance path planning with initial and terminal direction constraints is carried out based on convex optimization method. The simulation results show that the autonomous path planning method considering terrain aided navigation constraints can plan the shortest flight path under the constraints of navigation accuracy, maneuverability and no-fly zone.

关键词： Smoothing methods Navigation Trajectory planning Simulation Directed graphs Turning Path planning

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：