检索结果-内蒙古大学图书馆

2022 Conference on Infrared, Millimeter, Terahertz Waves and Applications, IMT 2022

作者： Chen, Fupu Qi, Tao Wang, Shaofei Zhang, Peng Luoyang Institute of Electro-Optical Equipment Luoyang471009 China Science and Technology on Electro-Optic Control Laboratory Luoyang471009 China

ISBN: (纸本)9781510662476

Infrared radiation characteristic measurement uses the infrared thermal imager that has been calibrated to measure and invert the infrared radiation characteristics of the target , which is a direct method to obtain the real radiation characteristics of the target. This paper proposes a method for infrared radiation characteristics based on real-time calibration of atmospheric correction parameters. This method first completes the radiation calibration of the long-wave thermal imager, then uses the surface blackbody as the standard radiation source, and uses the long-wave thermal imager to obtain the actual atmospheric transmittance. By establishing an exponential model, the correction factor between the theoretical atmospheric transmittance calculated by MODTRAN and the measured atmospheric transmittance is obtained, and the theoretical atmospheric transmittance calculated by MODTRAN is corrected by this correction factor, so that the measurement and inversion of the infrared radiation characteristics of the target to be measured can be realized. The experimental results show that the error of the target characteristic measurement result obtained by this method is less than 5%, which is higher than the traditional target radiation characteristic measurement accuracy obtained by directly using MODTRAN to correct the influence of atmospheric transmission. © 2023 SPIE.

关键词： Infrared radiation

来源：评论

学校读者我要写书评

暂无评论

Anchor-Free and Pixel-Wise Convolution for Visual Tracking

Anchor-Free and Pixel-Wise Convolution for Visual Tracking

引用

International Conference on Guidance, Navigation and control, ICGNC 2022

作者： Luo, Yihang Zhao, Zhenyu Hu, Yinji Jie, Feiran Science and Technology on Electro-Optical Control Laboratory Luoyang471000 China Luoyang Institute of Electro-Optic Equipment AVIC Luoyang471000 China

ISBN: (纸本)9789811966125

Most of the existing trackers usually rely on a multi-scale searching schemes or predefined anchor boxes to accurately estimate the scale and aspect ratio of objects. However, this operation requires tedious and heuristic configurations to obtain ideal results, which is inefficiency. To solve this problem, we introduce an anchor-free and pixel-wise convolution algorithm (named SiamAPF). SiamAPF transforms the tracking problem into a classification problem and a regression problem, and directly performs classification and bounding box regression on the target in fully convolutional network. The proposed network architecture is simple, and does not need to set responsible hyper-parameters. Meanwhile, it can improve the network's ability to express spatial information through pixel-wise convolution. It achieves state-of-the-art performance on the test datasets OTB100, UAV123 and runs at 50 FPS. In order to achieve better engineering applications, we successfully deployed SiamAPF under the NVIDIA Jetson Xavier hardware platform and recorded video for verification. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Crack Inspection of Wooden Poles based on Unmanned Aerial Vehicles 4

Crack Inspection of Wooden Poles based on Unmanned Aerial Ve...

引用

4th IEEE International Conference on Power, Intelligent Computing and Systems, ICPICS 2022

作者： Ma, Chao Zou, Jie Lei, Dawei Ye, Xigui Zang, Shaofei Ma, Jianwei School of Information Engineering Henan University of Science and Technology Science Technology on Electro-optic Control Laboratory AVIC Optronics Luoyang China Science and Technology on Electro-optic Control Laboratory AVIC Optronics Luoyang China Henan University of Science and Technology School of Information Engineering Luoyang China

ISBN: (数字)9781665467735

ISBN: (纸本)9781665467735

Wooden poles are deployed for decades. To inspect the poles, visual inspection by human experts is generally adopted. However, poles are mostly deployed in areas with bad traffic conditions, it is hard to access them. Furthermore, human inspectors tend to get tired, which lowers the inspection accuracy. In this paper, we present an unmanned aerial vehicle (UAV) based system for automatic wooden pole inspection. First, we captured the pole images by using a drone with a high resolution camera, totally we captured 600 pole images. Second, we proposed a encoder-decoder based neural network that can segment poles and cracks with high accuracy. Finally, we designed a processing scheme that can give the location and direction of each crack with high accuracy. © 2022 IEEE.

关键词： Poles

来源：评论

学校读者我要写书评

暂无评论

Cooperative attack–defense decision-making of multi-UAV using satisficing decision-enhanced wolf pack search algorithm

引用

Soft Computing 2024年第17-18期28卷 9575-9586页

作者： Zhou, Tongle Chen, Mou Wang, Yuhui Zhu, Ronggang Yang, Chenguang College of Automation Engineering Nanjing University of Aeronautics and Astronautics Nanjing211106 China Key Laboratory of Avionics System Integrated Technology Shanghai200241 China Science and Technology on Electro-optic Control Laboratory Luoyang Institute of Electro-Optical Equipment of Avic Luoyang471000 China Bristol Robotics Laboratory University of the West of England BristolBS16 1QY United Kingdom

Unmanned aerial vehicles (UAVs) have shown their superiority for applications in complicated military missions. A cooperative attack–defense decision-making method based on satisficing decision-enhanced wolf pack search (SDEWPS) algorithm is developed for multi-UAV air combat in this paper. Firstly, the multi-UAV air combat mathematical model is provided and the attack–defense decision-making constraints are defined. Besides the traditional air combat situation, the capability of UAVs and target information including target type and target intention are all considered in this paper to establish the air combat superiority function. Then, the wolf pack search (WPS) algorithm is used to solve the attack decision problem. To improve efficiency, the satisficing decision theory is employed to enhance the WPS to obtain the satisficing solution rather than optimal solution. The simulation results show that the developed method can realize the cooperative attack decision-making. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Research on Ballistic Planning Method Based on Improved DDPG Algorithm

Research on Ballistic Planning Method Based on Improved DDPG...

引用

2023 International Conference on Cyber-Physical Social Intelligence, ICCSI 2023

作者： Xue, Shuai Han, Yun Bai, Hongyang Nanjing University of Science and Technology School of Energy and Power Engineering Nanjing China Science and Technology on Electro-Optic Control Laboratory Luoyang Institute of Electro-Optical Equipment Cavic Luoyang China

ISBN: (纸本)9798350312492

Aiming at the ballistic planning problem given the target position indication under the condition of satisfying the missile capability boundary and process constraints, an improved deep deterministic policy gradient (DDPG) algorithm is proposed. This method solves the problems of the traditional trajectory planning method, such as strong dependence on model, low adaptability to environment and lack of real-time performance. The agent is firstly trained by this algorithm at the initial stage in a simple environment through a guided training based on the slow training speed of deep neural network, and then the generated strategy is adopted as an initial strategy for retraining. In the process, the sampling strategy of experience-first playback is applied to the gradient algorithm of deep deterministic strategy, and the Ornstein-Uhlenbeck (OU) noise model is employed for increasing the exploration ability of the agent. Then, this work develops a comprehensive simulation model according to an actual environment, where an improved DDPG method is thus introduced into the ballistic planning field by combining with performance indicators for planning and the trajectory can also meet the constraints. In order to verify the effectiveness of this method, the Gaussian pseudo-spectrum method is also used to compare with the proposed method in this paper. The simulation results show that the ballistic planning time of this improved algorithm is only within 10ms, which is about 8 times shorter than that of Gaussian pseudo-spectrum method. The corresponding ballistics that satisfy the constraints can be quickly generated, which has a good convergence and robustness, and is also suitable for solving online ballistic planning problems. © 2023 IEEE.

关键词： Ballistics

来源：评论

学校读者我要写书评

暂无评论

Exploiting Inductive Bias in Transformer for Point Cloud Classification and Segmentation

Exploiting Inductive Bias in Transformer for Point Cloud Cla...

引用

2023 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2023

作者： Li, Zihao Gao, Pan Yuan, Hui Wei, Ran Paul, Manoranjan College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China School of Control Science and Engineering Shandong University Jinan China Science and Technology on Electro-optic Control Laboratory Luoyang China Charles Sturt University Bathurst Australia

ISBN: (纸本)9798350313154

Discovering inter-point connection for efficient high-dimensional feature extraction from point coordinate is a key challenge in processing point cloud. Most existing methods focus on designing efficient local feature extractors while ignoring global connection, or vice versa. In this paper, we design a new Inductive Bias-aided Transformer (IBT) method to learn 3D inter-point relations, which considers both local and global attentions. Specifically, considering local spatial coherence, local feature learning is performed through Relative Position Encoding and Attentive Feature Pooling. We incorporate the learned locality into the Transformer module. The local feature affects value component in Transformer to modulate the relationship between channels of each point, which can enhance self-attention mechanism with locality based channel interaction. We demonstrate its superiority experimentally on classification and segmentation tasks. The code is available at: https://***/jiamang/IBT © 2023 IEEE.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Target Combat Intention Recognition Based on Improved Fisher Information Matrix

Target Combat Intention Recognition Based on Improved Fisher...

引用

2023 International Conference on Cyber-Physical Social Intelligence, ICCSI 2023

作者： Gao, Ruizhou Ma, Yunhong Zhang, Yimin Li, Xinyi Aviation Industry Cooperation of China Science and Technology on Electro-optic Control Laboratory Luoyang China Northwestern Polytechnical University School of Electronics and Information Xi'an China

ISBN: (纸本)9798350312492

Recognizing the opponent's intention is an important part in situational assessment and make the operation decision. Based on the pattern recognition technology of artificial intelligence, a combat intention recognition algorithm according to the value of Fisher information matrix is proposed. The target's combat intention knowledge rule base is constructed and the relative Fisher information matrix is designed to evaluate the target's current state information. The target combat intention recognition problem is transformed into an optimization problem according to the Fisher information matrix. The contribution index is defined to eliminate redundant information during the discrimination process, which improves the accuracy and efficiency of the target combat intention recognition. The proposed algorithm is used on multi-target combat intention recognition and the simulation results verified that the proposed algorithm is effective. © 2023 IEEE.

关键词： Fisher information matrix

来源：评论

学校读者我要写书评

暂无评论

Short-term trajectory prediction of aerial target based on LSTM model

Short-term trajectory prediction of aerial target based on L...

引用

2021 International Conference on Computational Modeling, Simulation, and Data Analysis, CMSDA 2021

作者： Chen, Yun Zou, Jie Wu, Mengjie Science and Technology on Electro-optic Control Laboratory Luoyang Institute of Electro-optical Equipment of AVIC Luoyang China

ISBN: (纸本)9781510651968

When the radar is tracking an air target, there is a short-term interruption of the track. The accurate prediction of the target track can help improve the accuracy of the track association. In response to the problem of low calculation accuracy of traditional track prediction algorithms, this article introduces and adopts a long short-term memory algorithm (Long Short - Term Memory) track prediction method. Use data to train the model, and use the mean square error (MSE) as an evaluation indicator to predict the future location of the target. The final simulation test results show that the algorithm can use the changing law of the air target's movement state to predict the target's movement state in a certain time in the future, which demonstrates the feasibility of the proposed algorithm in the problem of interrupted track prediction. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Parallelization of multi-trajectory calculation based on Runge-Kutta method 18

Parallelization of multi-trajectory calculation based on Run...

引用

18th International Conference on Computational Intelligence and Security, CIS 2022

作者： Zhou, Lin Su, Zhaobing Zhuang, Yongshi Liu, Yang Fan, Lei Science and Technology on Electro-optic Control Laboratory Luoyang471009 China School of Computer Science and Technology Xidian University Xi'an710071 China

ISBN: (纸本)9798350346275

Uncontrolled exterior ballistic calculation is a typical computing intensive problem, which plays vital roles in aircraft design and trajectory planning. Solving this problem usually involves a large amount of calculation, which is time-consuming. To accelerate the multiple trajectory calculation, we design a multi-trajectory calculation architecture based on the fourth-order Runge-Katta method using multithreading parallel computing technology. The multi-trajectory calculation tasks will be allocated to different threads through tasks division. The influences of key factors of multi-trajectory calculation were analyzed in experiments. Simulation results show that the multi-trajectory parallel acceleration architecture can effectively reduce the calculation time and improve the calculation efficiency for the complex differential equations. © 2022 IEEE.

关键词： Runge Kutta methods

来源：评论

学校读者我要写书评

暂无评论

Towards task parallelizing in scientific workflow systems 18

Towards task parallelizing in scientific workflow systems

引用

18th International Conference on Computational Intelligence and Security, CIS 2022

作者： Liu, Yang Su, Zhaobing Zhuang, Yongshi Fan, Lei Zhou, Lin School of Computer Science and Technology Xidian University Xi'an710071 China Science and Technology on Electro-optic Control Laboratory Luoyang471009 China

ISBN: (纸本)9798350346275

Task scheduling is a hot issue in computing fields, aiming at improving time efficiency of algorithms or resource utilization of computing platforms. This article mainly deals with the data processing scheduling problems in scientific workflow systems. In this paper, data processes in the scientific workflow will be analyzed based on the process activity graph. According to the dependencies between the processes, some processes will be merged before scheduling. During the execution of the scientific workflow tasks, the processes that can be performed in parallel will be recognized automatically by the proposed method, which will be further executed by the developed scheduling approach via virtual machines with the goal of minimizing the workflow run time. Experiments are conducted to evaluate the proposed methods. The results show the effectiveness and positiveness of the scheduling strategy. © 2022 IEEE.

关键词： Data handling

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：