检索结果-内蒙古大学图书馆

UAV maneuvering decision-making algorithm based on deep reinforcement learning under the guidance of expert experience

引用

Journal of Systems Engineering and electronics 2024年第3期35卷 644-665页

作者： ZHAN Guang ZHANG Kun LI Ke PIAO Haiyin School of Electronics and Information Northwestern Polytechnical UniversityXi’an 710072China Science and Technology on Electro-Optic Control Laboratory Luoyang 471009China

Autonomous umanned aerial vehicle(UAV) manipulation is necessary for the defense department to execute tactical missions given by commanders in the future unmanned battlefield. A large amount of research has been devoted to improving the autonomous decision-making ability of UAV in an interactive environment, where finding the optimal maneuvering decisionmaking policy became one of the key issues for enabling the intelligence of UAV. In this paper, we propose a maneuvering decision-making algorithm for autonomous air-delivery based on deep reinforcement learning under the guidance of expert experience. Specifically, we refine the guidance towards area and guidance towards specific point tasks for the air-delivery process based on the traditional air-to-surface fire control ***, we construct the UAV maneuvering decision-making model based on Markov decision processes(MDPs). Specifically, we present a reward shaping method for the guidance towards area and guidance towards specific point tasks using potential-based function and expert-guided advice. The proposed algorithm could accelerate the convergence of the maneuvering decision-making policy and increase the stability of the policy in terms of the output during the later stage of training process. The effectiveness of the proposed maneuvering decision-making policy is illustrated by the curves of training parameters and extensive experimental results for testing the trained policy.

关键词： unmanned aerial vehicle(UAV) maneuvering decision-making autonomous air-delivery deep reinforcement learning reward shaping expert experience

来源：评论

学校读者我要写书评

暂无评论

Optical Design of Transmission/Reflection Common Aperture Infrared/Laser Composite Seeker

Optical Design of Transmission/Reflection Common Aperture In...

引用

2024 Applied Optics and Photonics China: Optical Sensing, Imaging technology, and Applications, AOPC 2024

作者： Tang, Changzheng Yu, Shaoying Wu, Lequn Science and Technology on Electro-optic Control Laboratory Luoyang471000 China Luoyang Institute of Electro-optical Equipment Luoyang471000 China

ISBN: (数字)9781510687820

ISBN: (纸本)9781510687813

In order to realize the miniaturization and low cost of infrared/laser dual-mode seeker imaging system and simplify the optical system structure, a transmission/reflection common aperture infrared/laser composite seeker optical system is designed. Firstly, the structure, overall scheme and working principle of the system are studied. The optical system uses the common aperture design at the front, and the infrared and laser signals are separated by the spectroscope at the backend to enter the respective detectors[1]. The whole optical system shares the same receiving aperture, the structure is compact, and meets the requirements of miniaturization of the seeker. The system can not only meet the requirements of large field of view in the target searching stage, but also meet the requirements of accurate recognition and tracking of the target. Based on the design metrics and parameters, the infrared optical system and laser optical system are designed and analyzed respectively. Through the analysis of action distance, the aperture and focal length of infrared and semi-active laser subsystems are designed. Simulation results show that the transfer function MTF and optical transmittance of the infrared optical system meet the design requirements, and the spot energy, linear region and optical transmittance of the semi-active laser subsystem meet the requirements. © 2024 SPIE.

关键词： Infrared transmission

来源：评论

学校读者我要写书评

暂无评论

Design Method of Off-axis Infrared Television Composite Optical System for Seekers

Design Method of Off-axis Infrared Television Composite Opti...

引用

2024 Applied Optics and Photonics China: Optical Sensing, Imaging technology, and Applications, AOPC 2024

作者： Tang, Changzheng Zhang, Hao Li, Anran Pang, Yibo Science and Technology on Electro-optic Control Laboratory Luoyang471000 China Luoyang Institute of Electro-optical Equipment Luoyang471000 China

ISBN: (数字)9781510687820

ISBN: (纸本)9781510687813

In the traditional coaxial infrared television optical system, the central aperture of the infrared imaging system will be blocked by the television imaging system, which will cause obvious loss of luminous flux and decrease of diffraction *** television imaging system is in the infrared channel, the infrared and television system size, configuration, performance, assembly will affect each other, which increases the design and assembly difficulty, as well as processing assembly and maintenance *** this paper, an off-axis infrared television composite optical system is designed. The infrared and television systems are decoupled from each other without interference. Two tilt lenses are added in front of the lens to correct the aberration of the television. The results show that the performance of off-axis infrared television composite optical system is better than that coaxial infrared television composite optical system. © 2024 SPIE.

关键词： Infrared television

来源：评论

学校读者我要写书评

暂无评论

Teachers cooperation:team-knowledge distillation for multiple cross-domain few-shot learning

引用

Frontiers of Computer science 2023年第2期17卷 91-99页

作者： Zhong JI Jingwei NI Xiyao LIU Yanwei PANG School of Electrical and Information Engineering Tianjin UniversityTianjin 300072China Science and Technology on Electro-Optical Information Security Control Laboratory Tianjin 300308China Tianjin Key Laboratory of Brain-Inspired Intelligence Technology Tianjin 300072China

Although few-shot learning(FSL)has achieved great progress,it is still an enormous challenge especially when the source and target set are from different domains,which is also known as cross-domain few-shot learning(CD-FSL).Utilizing more source domain data is an effective way to improve the performance of ***,knowledge from different source domains may entangle and confuse with each other,which hurts the performance on the target ***,we propose team-knowledge distllation networks(TKD-Net)to tackle this problem,which explores a strategy to help the cooperation of multiple ***,we distill knowledge from the cooperation of teacher networks to a single student network in a meta-learning *** incorporates task-oriented knowledge distillation and multiple cooperation among teachers to train an efficient student with better generalization ability on unseen ***,our TKD-Net employs both response-based knowledge and relation-based knowledge to transfer more comprehensive and effective *** experimental results on four fine-grained datasets have demonstrated the effectiveness and superiority of our proposed TKD-Net approach.

关键词： cross-domain few-shot learning meta-learning knowledge distillation multiple teachers

来源：评论

学校读者我要写书评

暂无评论

Model-based deep learning for fiber bundle infrared image restoration

引用

Defence technology（防务技术） 2023年第9期27卷 38-45页

作者： Bo-wen Wang Le Li Hai-bo Yang Jia-xin Chen Yu-hai Li Qian Chen Chao Zuo Jiangsu Key Laboratory of Spectral Imaging and Intelligent Sense Nanjing University of Science and TechnologyNanjingJiangsu Province210094China Smart Computational Imaging(SCI)Laboratory Nanjing University of Science and TechnologyNanjingJiangsu Province210094China Science and Technology on Electro-Optical Information Security Control Lab Tianjin300308China

As the representative of flexibility in optical imaging media,in recent years,fiber bundles have emerged as a promising architecture in the development of compact visual *** to tackling the problems of universal honeycomb artifacts and low signal-to-noise ratio(SNR)imaging in fiber bundles,the iterative super-resolution reconstruction network based on a physical model is *** the constraint of solving the two subproblems of data fidelity and prior regularization term alternately,the network can efficiently“regenerate”the lost spatial resolution with deep *** building and calibrating a dual-path imaging system,the real-world dataset where paired low-resolution(LR)-high-resolution(HR)images on the same scene can be generated *** results on both the United States Air Force(USAF)resolution target and complex target objects demonstrate that the algorithm can restore high-contrast images without pixilated *** the basis of super-resolution reconstruction,compound eye image composition based on fiber bundle is also embedded in this paper for the actual imaging *** proposed work is the first to apply a physical model-based deep learning network to fiber bundle imaging in the infrared band,effectively promoting the engineering application of thermal radiation detection.

关键词： Fiber bundle Deep learning Infrared imaging Image restoration

来源：评论

学校读者我要写书评

暂无评论

Digital Detail Enhancement Method for Infrared Images Based on Gaussian Filtering

Digital Detail Enhancement Method for Infrared Images Based ...

引用

2024 Conference on Spectral technology and Applications, CSTA 2024

作者： Wang, Shaofei Zhang, Peng Pan, Xuhui Luoyang Electro-Optical Equipment Research Institute of AVIC Henan Luoyang China Science and Technology on Electro-Optical Control Laboratory Henan Luoyang China

ISBN: (纸本)9781510683082

Infrared images typically exhibit a high dynamic range, necessitating the utilization of an appropriate compression technique to prevent the loss of original information. This preservation of data is crucial for subsequent feature extraction, recognition, and tracking processes. In this paper, we introduce a digital detail enhancement technique specifically tailored for infrared images, leveraging the Gaussian filter. The Gaussian filtering process effectively separates the background layer from the detail layer of the image. Subsequently, the background layer undergoes gray level enhancement, while the detail layer undergoes detail enhancement and noise suppression. Finally, based on the overall dynamic range of the image, both the background and detail layers undergo compression and adjustment, leading to a further enhancement in image contrast. Experimental results demonstrate that the proposed method successfully improves image contrast and presents more detailed information, thus contributing to the accurate and reliable processing of infrared images. © 2024 SPIE.

关键词： Wiener filtering

来源：评论

学校读者我要写书评

暂无评论

Design and simulation of a two-stage linear inverted pendulum control system based on fuzzy LQR control 7

Design and simulation of a two-stage linear inverted pendulu...

引用

7th International Symposium on Autonomous Systems, ISAS 2024

作者： Peng, Siting Ren, Jun Li, Lei Ma, Yichao Song, Zhichao The Beijing Electro-Mechanical Engineering Institute Science and Technology On Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China

ISBN: (纸本)9798350363173

This paper introduces in detail the origin of the development of automatic control methods, applications and current research hotspots. It also introduces some control methods commonly used in industrial and agricultural production, and expounds the current application hotspots and new advanced control methods that are developing rapidly. The background, current situation and classification of the inverted pendulum platform are introduced in detail. In the first chapter, the LQR method in modern control theory is introduced in detail. The influence of parameters is analyzed through simulink space modeling and simulation control experiment. At the same time, the real-time experiment is also done in combination with the hardware platform. In the second chapter, the fuzzy control theory in intelligent control is introduced in detail. By combining fuzzy control with LQR method, suitable LQR parameters are calculated by pole assignment. After proper adjustment, reasonable fuzzy rules are adopted and adaptive fuzzy control principle is applied to adjust the control situation in real time. Using simulink space modeling, a good simulation control effect is obtained. Finally, the summary is made. © 2024 IEEE.

关键词： Fuzzy control

来源：评论

学校读者我要写书评

暂无评论

Causal reasoning in typical computer vision tasks

引用

science China(Technological sciences) 2024年第1期67卷 105-120页

作者： ZHANG KeXuan SUN QiYu ZHAO ChaoQiang TANG Yang Key Laboratory of Advanced Control and Optimization for Chemical Process Ministry of EducationEast China University of Science and TechnologyShanghai 200237China National Key Laboratory of Air based Information Perception and Fusion Luoyang 471000China Luoyang Institute of Electro Optical Equipment of Avic Luoyang 471000China

Deep learning has revolutionized the field of artificial *** on the statistical correlations uncovered by deep learning-based methods,computer vision tasks,such as autonomous driving and robotics,are growing *** being the basis of deep learning,such correlation strongly depends on the distribution of the original data and is susceptible to uncontrolled *** the guidance of prior knowledge,statistical correlations alone cannot correctly reflect the essential causal relations and may even introduce spurious *** a result,researchers are now trying to enhance deep learningbased methods with causal *** theory can model the intrinsic causal structure unaffected by data bias and effectively avoids spurious *** paper aims to comprehensively review the existing causal methods in typical vision and visionlanguage tasks such as semantic segmentation,object detection,and image *** advantages of causality and the approaches for building causal paradigms will be *** roadmaps are also proposed,including facilitating the development of causal theory and its application in other complex scenarios and systems.

关键词： causal reasoning computer vision tasks vision-language tasks semantic segmentation object detection

来源：评论

学校读者我要写书评

暂无评论

Measurement and Analysis of Infrared Radiation Characteristics of UAV 3

Measurement and Analysis of Infrared Radiation Characteristi...

引用

3rd International Computing Imaging Conference, CITA 2023

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

ISBN: (纸本)9781510671409

Studying the infrared radiation characteristics of UAV is of great significance. This paper first completes the radiation calibration of the mid-wave infrared thermal imager, and then conducts multi-angle radiation characteristics tests on the ground static UAV. MODTRAN software is used to calculate the atmospheric transmittance and path radiation, and complete the inversion calculation of the UAV radiant intensity and atmospheric transmission revision. The test results show that the infrared radiation of UAV has directionality, and the radiation characteristics of UAV in the side tail direction are the strongest, which is mainly represented by engine radiation, and the radiant intensity of UAV increases significantly with the acceleration of engine speed. © 2023 SPIE.

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

Measurement of infrared radiation based on real-time calibration of atmospheric correction parameters

Measurement of infrared radiation based on real-time calibra...

引用

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

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：