检索结果-内蒙古大学图书馆

4th International Conference on Electronic Information and Communication Engineering, EICE 2025

作者： Wang, Haoxu Li, Bingjie Liu, Ming Yang, Dezhen Chen, Zhijie Liu, Xu Wan, Peiyuan Beijing Embedded System Key Lab School of Information Science and Technology Beijing University of Technology Beijing China National Key Laboratory of Infrared Detection Technologies Beijing China

This article offers a detailed exploration of the Normalized Least Mean Squares (NLMS) algorithm, highlighting its enhanced adaptive filtering capabilities and robust performance in managing input signal correlations. It delves into the foundational principles of the NLMS algorithm and outlines the essential modules required for its implementation in Verilog HDL. The implementation and simulation of the NLMS adaptive filter are studied. The simulation outcomes indicate that the convergence rate of the algorithm is superior to that of the conventional LMS algorithm. © 2025 Institute of Physics Publishing. All rights reserved.

关键词： Adaptive filtering

来源：评论

学校读者我要写书评

暂无评论

infrared small target detection based on spatial attention density peaks searching

引用

Optoelectronics Letters 2025年第2期21卷 90-96页

作者： RAO Junmin LU Siyu LIU Shijian LI Fanming CAS Key Laboratory of Infrared System Detection and Imaging Technology Shanghai Institute of Technical PhysicsShanghai 200083China University of Chinese Academy of Sciences Beijing 100049China Shanghai Institute of Technical Physics Chinese Academy of SciencesShanghai 200083China School of Information Science and Technology ShanghaiTech UniversityShanghai 201210China

The detection of small targets poses a significant challenge for infrared search and tracking (IRST) systems,as they must strike a delicate balance between accuracy and *** this paper,we propose a detection algorithm based on spatial attention density peaks searching (SADPS) and an adaptive window selection ***,the difference-of-Gaussians (DoG) filter is introduced for preprocessing raw infrared ***,the image is processed by ***,an adaptive window selection scheme is applied to obtain window templates for the target scale ***,the small target feature is used to enhance the target and suppress the ***,the true targets are segmented through a *** experimental results show that compared with the seven state-of-the-art small targets detection baseline algorithms,the proposed method not only has better detection accuracy,but also has reasonable time consumption.

关键词： template searching infrared

来源：评论

学校读者我要写书评

暂无评论

infrared aircraft few-shot classification method based on cross-correlation network

引用

红外与毫米波学报 2025年第1期44卷 103-111页

作者： HUANG Zhen ZHANG Yong GONG Jin-Fu Key Laboratory of Infrared System Detection and Imaging Technology Chinese Academy of SciencesShanghai 200083China University of Chinese Academy of Sciences Beijing 100049China Shanghai Institute of Technical Physics Chinese Academy of SciencesShanghai 200083China

In response to the scarcity of infrared aircraft samples and the tendency of traditional deep learning to overfit,a few-shot infrared aircraft classification method based on cross-correlation networks is *** method combines two core modules:a simple parameter-free self-attention and *** analyzing the self-correlation and cross-correlation between support images and query images,it achieves effective classification of infrared aircraft under few-shot *** proposed cross-correlation network integrates these two modules and is trained in an end-to-end *** simple parameter-free self-attention is responsible for extracting the internal structure of the image while the cross-attention can calculate the cross-correlation between images further extracting and fusing the features between *** with existing few-shot infrared target classification models,this model focuses on the geometric structure and thermal texture information of infrared images by modeling the semantic relevance between the features of the support set and query set,thus better attending to the target *** results show that this method outperforms existing infrared aircraft classification methods in various classification tasks,with the highest classification accuracy improvement exceeding 3%.In addition,ablation experiments and comparative experiments also prove the effectiveness of the method.

关键词： infrared imaging aircraft classification few-shot learning parameter-free attention cross attention

来源：评论

学校读者我要写书评

暂无评论

Evaluation of occlusion immunities of free-space orbital angular momentum shift keying

引用

Optics Express 2025年第6期33卷 13494-13505页

作者： Yang, Jinyu Zhang, Shurui Li, Lang Gao, Mingwei Gao, Chunqing Fu, Shiyao School of Optics and Photonics Beijing Institute of Technology Beijing100081 China Key Laboratory of Information Photonics Technology Ministry of Industry and Information Technology of the People’s Republic of China Beijing100081 China Key Laboratory of Photoelectronic Imaging Technology and System Ministry of Education of the People’s Republic of China Beijing100081 China National Key Laboratory on Near-Surface Detection Beijing100072 China

Orbital angular momentum (OAM) provides a new high-dimensional degree-of-freedom for lasers enabling high-dimensional shift keying, thus showing huge potential in free-space optical data-transmissions. Ensuring the accuracy of data transmission is of concern in any communication system. However, in the free-space OAM shift keying link, interferences from environmental occlusions will broaden the OAM spectrum and thus affect the correctness of information received. In this paper, the occlusion immunities of two commonly used OAM shift keying strategies—OAM-encoding-symbols and OAM-encoding-bits—are evaluated under different occlusion scenarios. We introduce radial, azimuthal, and random occlusions into the link and then analyze the bit error rate (BER) of various OAM shift keying strategies. The results illustrate that the strategy of OAM-encoding-symbols exhibits stronger occlusion immunity with zero BER than OAM-encoding-bits. Moreover, proof-of-concept experiments are done to transmit grayscale images under occlusions. The final decoding results show identical data-transmission performance with simulations. © 2025 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement.

关键词： Bit error rate

来源：评论

学校读者我要写书评

暂无评论

infrared Dim Small Target detection Algorithm Based on Adaptive Attention Transformer Network

引用

Journal of Shanghai Jiaotong University (Science) 2025年 1-13页

作者： Ding, Leqi Xia, Yilin Wang, Biyun Cai, Yunze Department of Automation Shanghai Jiao Tong UniversityKey Laboratory of System Control and Information Processing of Ministry of Education Shanghai200240 China National Key Laboratory of Air-based Information Perception and Fusion Henan Luoyang471009 China Shanghai Institute of Aerospace Control Technology Infrared Detection Technology R & D Center of China Aerospace Science and Technology Corporation Shanghai201109 China

This paper presents a novel algorithm for detecting infrared dim small targets in complex backgrounds by integrating both global and local feature information. The proposed method employs an adaptive attention transformer network which addresses challenges associated with computational complexity and information redundancy in traditional self-attention mechanisms. A global context aggregation module is designed to address the loss of small target features in high-level feature maps. This module compensates for spatial distribution information during the multi-scale feature fusion process, ensuring the preservation of target features. Comparison experiments were conducted on two datasets, NUAA-SIRST and IRSTD-1k. The proposed algorithm achieved 0.784 for mIoU and 0.878 for F-measure on NUAA-SIRST, 0.632 for mIoU and 0.807 for F-measure on IRST-1k, all of which are the highest values. The proposed algorithm shows a significant improvement over other existing detection algorithms, demonstrating its capability to accurately extract both local and global features of targets with high recall rates and low false alarm rates across various scenarios. The ablation study results highlight the significant improvements contributed by the key modules to the proposed algorithm. (Figure presented.) © Shanghai Jiao Tong University 2025.

关键词： A adaptive attention global context aggregation module infrared dim small target detection TP391.4 Transformer network

来源：评论

学校读者我要写书评

暂无评论

Selective formation of generalized optical skyrmions

引用

Optics Letters 2025年第9期50卷 2840-2843页

作者： Zhang, Haojun Gao, Chunqing Fu, Shiyao School of Optics and Photonics Beijing Institute of Technology Beijing100081 China Key Laboratory of Information Photonics Technology Ministry of Industry and Information Technology of the People’s Republic of China Beijing100081 China Key Laboratory of Photoelectronic Imaging Technology and System Ministry of Education of the People’s Republic of China Beijing100081 China National Key Laboratory on Near-Surface Detection Beijing100072 China

Optical skyrmions, a type of topologically protected quasiparticle, have undergone various deformations in recent years. In this Letter, we present a scheme that can achieve the selective formation of generalized optical skyrmions. In our proposal, a liquid-crystal spatial light modulator and a variable liquid-crystal retarder, both of which are commonly programmable devices, are employed, allowing for the on-demand precise manipulation of topological textures of various quasiparticles including but not limited to skyrmions, antiskyrmions, and bimerons. The proof-of-concept experiments illustrate that generalized optical skyrmions whose skyrmion number up to 5 can be well generated with on-demand tailored topological textures. While maintaining a simple setup, the system demonstrates a notable capacity for the manipulation of intricate high-order textures, signifying its considerable potential for extensive and sophisticated applications in the generation and manipulation of skyrmions. © 2025 Optica Publishing Group.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Temporal multiplexing coding strategy for spatiotemporal compressed imaging 4

Temporal multiplexing coding strategy for spatiotemporal com...

引用

4th International Computational imaging Conference, CITA 2024

作者： Hao, Xiaowen Ke, Jun School of Optics and Photonics Beijing Institute of Technology Beijing100081 China Key Laboratory of Photo-electronic Imaging Technology and System Ministry of Education of China Beijing100081 China National Key Laboratory on Near-surface Detection Beijing100072 China

ISBN: (纸本)9781510688834

Spatiotemporal compressed imaging(STCI) aims to improve the spatial and temporal resolution of an imaging system simultaneously, which can effectively alleviate the mutual constraints between the two imaging resolutions. However, the development of STCI is limited by the effectively modulate target scenes in dual-domain, and by the back-end reconstruction process which doesn't work well for high compression ratio(CR). In this paper, we propose a temporal multiplexing coding strategy for STCI, which can effectively help the reconstruction algorithm for a large CR. Simulated experiments are implemented to demonstrate our idea. The proposed method can achieve nice spatiotemporal reconstructions with CR equal to 128:1, in which the spatial CR is 16:1 and the temporal CR is 8:1. © 2025 SPIE.

关键词： Image coding

来源：评论

学校读者我要写书评

暂无评论

Optimizing object classification with single-pixel imaging and transformer networks 4

Optimizing object classification with single-pixel imaging a...

引用

4th International Computational imaging Conference, CITA 2024

作者： Cheng, Yin Liao, Yusen Sun, Xin Ke, Jun School of Optics and Photonics Beijing Institute of Technology Beijing100081 China Key Laboratory of Photo-electronic Imaging Technology and System Ministry of Education of China Beijing100081 China National Key Laboratory on Near-surface Detection Beijing100072 China

ISBN: (纸本)9781510688834

Traditional computer vision tasks rely on high-quality images for classification, but single-pixel imaging (SPI) uses compressive sensing with a bucket detector to simplify hardware and reduce costs. However, factors like atmospheric turbulence can degrade SPI image quality, lowering classification accuracy. To address this, a block-based single-pixel image-free transformer classification framework is proposed. It uses a learnable binary sampling matrix for flexible sampling during SPI and divides the measurements into blocks, which are processed by a transformer network. Each block is treated as a sequence element, allowing the transformer to capture spatial and contextual relationships. Experiments show strong robustness to atmospheric turbulence, achieving 87% classification accuracy even at a 1% sampling rate, making this method suitable for challenging environments. © 2025 SPIE.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Intelligent tailoring of a broadband orbital angular momentum comb towards efficient optical convolution

引用

Photonics Research 2025年第5期13卷 1148-1157页

作者： Zhou, Shiyun Li, Lang Wang, Yishu Gao, Liliang Zhang, Zhichao Gao, Chunqing Fu, Shiyao School of Optics and Photonics Beijing Institute of Technology Beijing100081 China Key Laboratory of Photoelectronic Imaging Technology and System Ministry of Education Beijing100081 China Key Laboratory of Information Photonics Technology Ministry of Industry and Information Technology Beijing100081 China National Key Laboratory on Near-surface Detection Beijing100072 China

Due to the high-dimensional characteristics of photon orbital angular momentum (OAM), a beam can carry multiple OAMs simultaneously thus forming an OAM comb, which has been proved to show significant potential in both classical and quantum photonics. Tailoring broadband OAM combs on demand in a fast and accurate manner is a crucial basis for their application in advanced scenarios. However, obtaining phase-only gratings for the generation of arbitrary desired OAM combs still poses challenges. In this paper, we propose a multi-scale fusion learning U-shaped neural network that encodes a phase-only hologram for tailoring broadband OAM combs on-demand. Proof-of-principle experiments demonstrate that our scheme achieves fast computational speed, high modulation precision, and high manipulation dimensionality, with a mode range of −75 to +75, an average root mean square error of 0.0037, and a fidelity of 85.01%, all achieved in about 30 ms. Furthermore, we utilize the tailored broadband OAM combs in conducting optical convolution calculation, enabling vector convolution for arbitrary discrete functions, showcasing the extended capability of our proposal. This work opens, to our knowledge, new insight for on-demand tailoring of broadband OAM combs, paving the way for further advancements in high-dimensional OAM-based applications. © 2025 Chinese Laser Press.

关键词： Angular momentum

来源：评论

学校读者我要写书评

暂无评论

Target detection enhancement method through multi-dimensional information differential projection and fusion

引用

Optics Express 2025年第10期33卷 21116-21131页

作者： Xue Dong Yubo Lan Zongmin Zhao Chang Cai Zhiming Zhou Tong Zhang Pingli Han Meng Xiang Jinpeng Liu Peiyue Xie Fei Liu School of Optoelectronic Engineering Xidian University Xi’an 710071 China Xi’an Key Laboratory of Computational Imaging Xi’an 710071 China National Key Laboratory of Infrared Detection Technologies Shanghai 200083 China Beijing Key Laboratory of Advanced Optical Remote Sensing Technology Beijing 100094 China

As a powerful detection tool, spectral polarization imaging (SPI) reveals spatial, spectral, and polarization characteristics. When combined with deep learning, its detection capabilities can be further improved. However, SPI requires the acquisition and processing of large-scale data, and it is still facing significant challenges in detecting targets in complex scenes with reduced contrast, loss of spatial structures, and cluttered backgrounds. Hence, an innovative target detection enhancement method via multi-dimensional information differential projection and fusion is presented based on our self-developed SPI systems. It primarily comprises a target retrieval algorithm based on angle of polarization purification and a novel projection and fusion strategy, which can effectively exploit, enhance, and utilize the multi-dimensional distinctions between the target and background. The resulting fused image visualizes these distinctions, thereby highlighting the target from its background. Experiment results demonstrate the efficacy of our method in detecting targets with shielding, camouflage and shape loss in complex natural environments, i.e., grasslands, woodlands, and sky. This significantly enhances scenario comprehension and detection efficiency without extensive computation or model training, making it especially advantageous for military reconnaissance applications.

关键词： Color spaces Deep learning imaging techniques Machine learning Polarimetric imaging Underwater imaging

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：