检索结果-内蒙古大学图书馆

MAGPNet: Multi-Domain Attention-Guided Pyramid Network for infrared Small Object detection

Journal of Shanghai Jiaotong University (Science) 2024年 1-18页

作者： Ding, Leqi Wang, Biyun Yao, Lixiu 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

To overcome the obstacles of poor feature extraction and little prior information on the appearance of infrared dim small targets, we propose a multi-domain attention-guided pyramid network (MAGPNet). Specifically, we design three modules to ensure that salient features of small targets can be acquired and retained in the multi-scale feature maps. To improve the adaptability of the network for targets of different sizes, we design a kernel aggregation attention block with a receptive field attention branch and weight the feature maps under different perceptual fields with attention mechanism. Based on the research on human vision system, we further propose an adaptive local contrast measure module to enhance the local features of infrared small targets. With this parameterized component, we can implement the information aggregation of multi-scale contrast saliency maps. Finally, to fully utilize the information within spatial and channel domains in feature maps of different scales, we propose the mixed spatial-channel attention-guided fusion module to achieve high-quality fusion effects while ensuring that the small target features can be preserved at deep layers. Experiments on public datasets demonstrate that our MAGPNet can achieve a better performance over other state-of-the-art methods in terms of the intersection of union, Precision, Recall, and F-measure. In addition, we conduct detailed ablation studies to verify the effectiveness of each component in our network. © 2024, Shanghai Jiao Tong University.

关键词： Software engineering

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

Prediction of Pediatric Sepsis Using a Deep Encoding Network with Cross Features

引用

Journal of Shanghai Jiaotong university(Science) 2024年第1期29卷 131-140页

作者：陈潇张瑞汤心溢钱娟 University of Chinese Academy of Sciences Beijing 100084China Shanghai Institute of Technical Physics of the Chinese Academy of Sciences Key Laboratory of Infrared Detection and Imaging TechnologyShanghai 200083China Shanghai Children's Medical Center Shanghai Jiao Tong University School of MedicineShanghai 200127China

Sepsis poses a serious threat to health of children in pediatric intensive care *** mortality from pediatric sepsis can be effectively reduced through in-time diagnosis and therapeutic *** bacilliculture detection method is too time-consuming to receive timely *** this research,we propose a new framework:a deep encoding network with cross features(CF-DEN)that enables accurate early detection of *** features are automatically constructed via the gradient boosting decision tree and distilled into the deep encoding network(DEN)we *** DEN is aimed at learning sufficiently effective representation from clinical test *** layer of the DEN fltrates the features involved in computation at current layer via attention mechanism and outputs the current prediction which is additive layer by layer to obtain the embedding feature at last *** framework takes the advantage of tree-based method and neural network method to extract effective representation from small clinical dataset and obtain accurate prediction in order to prompt patient to get timely *** evaluate the performance of the framework on the dataset collected from Shanghai Children's Medical *** with common machine learning methods,our method achieves the increase on F1-score by 16.06%on the test set.

关键词： pediatric sepsis gradient boosting decision tree cross feature neural network deep encoding network with cross features(CF-DEN)

来源：评论

学校读者我要写书评

暂无评论

Research on an automatic light field refocusing method for a camera array

引用

Optics Express 2025年第10期33卷 20964-20980页

作者： Pan, Yihua Zhao, Yushan Li, Yuyang Liu, Bin Chen, Ping Shanxi Key Laboratory of Intelligent Detection Technology & Equipment School of Information and Communication Engineering North University of China Shanxi Taiyuan030051 China Key Laboratory of Photoelectronic Imaging Technology System of Ministry of Education of China School of Optics and Photonics Beijing Institute of Technology Beijing100081 China State Key Laboratory of Extreme Environment Optoelectronic Dynamic Testing Technology and Instruments North University of China Shanxi Taiyuan030051 China

Light field information includes the position and angle information of light in space. A camera array is one of the methods for obtaining light field information, which combines and arranges multiple cameras in space to achieve multi-angle imaging of the same target. Based on the light field information, a computational imaging method can be used to achieve refocusing technology for a camera array (also known as optical synthetic aperture imaging technology). In this technology, by setting the focusing coefficient, the light field information can be focused on different depths. This mode is called taking photos first and focusing later. However, in order to focus on a specific object surface, traditional refocusing methods require users to manually adjust the focusing coefficient multiple times, which is time-consuming and user-unfriendly. Therefore, in this paper, we propose an automatic focusing method based on the optimal focusing coefficient map (OFCM) to address the manual refocusing problem. This method transforms the refocusing problem into obtaining the optimal focus coefficient map. In the process of solving OFCM, the threshold filtering method and the neighborhood filling method are used to optimize the results and improve the robustness of the proposed method. The experimental results show that our proposed method has higher imaging quality and faster running efficiency compared to automatic refocusing methods based on disparity maps and gradient functions. © 2025 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement.

关键词： Computational imaging

来源：评论

学校读者我要写书评

暂无评论

High-accuracy source-independent radiometric calibration with low complexity for infrared photonic sensors

引用

Light(Science & Applications) 2021年第9期10卷 1714-1725页

作者： Qiang Guo Fuchun Chen Xiangyang Li Boyang Chen Xin Wang Guilin Chen Caiying Wei National Satellite Meteorological Center China Meteorological Administration100081BeijingChina Key Laboratory of Infrared System Detection&Imaging Technology Shanghai Institute of Technical PhysicsChinese Academy of Sciences200083ShanghaiChina Key Laboratory of Infrared Imaging Materials&Detectors Shanghai Institute of Technical PhysicsChinese Academy of Sciences200083ShanghaiChina

Radiometric calibration(RC)is an essential solution to guarantee measurements from infrared photonic sensors with certain accuracy,the main task of which is to determine the radiometric responsivity of sensor and usually be solved by comparing with some radiation source(i.e.,blackbody),called source-based RC(SBRC).In addition to the complexity in manufacture,the nonideal characteristics of an available source will inevitably introduce unexpected uncertainties to reduce the final calibration accuracy by around 0.2–0.5 K in ***,we propose an original source-independent RC(SIRC)principle based on modeling instead of comparing for SBRC,where the incident background radiation to detector,as a dominated factor influencing the responsivity characteristics of a photonic sensor,is modeled to implement RC for both two fundamental types(photoconductive and photovoltaic)of HgCdTe photonic *** SIRC merely requires the temperature information of main components of a sensor other than some complex source and its assembly,and provides a traceable way at lower uncertainty costs relative to the traditional *** SIRC is being implemented in Fengyun-2 satellites since 2019,which ensures a long-term stable service of Chinese geostationary meteorological satellites for the global observation system under the framework of World Meteorological ***,a 20-year-period traceable Fengyun-2 dataset to be recalibrated with SIRC will benefit the further climate applications.

关键词： source complexity calibration

来源：评论

学校读者我要写书评

暂无评论

Multi-Channel Based on Attention Network for infrared Small Target detection

引用

Journal of Shanghai Jiaotong university(Science) 2024年第3期29卷 414-427页

作者：张彦军王碧云蔡云泽 Department of Automation Shanghai Jiao Tong UniversityShanghai 200240China Shanghai Institute of Aerospace Control Technology Shanghai 201109China Infrared Detection Technology R&D Center of China Aerospace Science and Technology Corporation Shanghai 201109China Key Laboratory of System Control and Information Processing Ministry of Education of ChinaShanghai 200240China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai 200240China Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Jiao Tong UniversityShanghai 200240China Institute of Marine Equipment Shanghai Jiao Tong UniversityShanghai 200240China

infrared detection technology has the advantages of all-weather detection and good concealment,which is widely used in long-distance target detection and tracking ***,the complex background,the strong noise,and the characteristics of small scale and weak intensity of targets bring great difficulties to the detection of infrared small targets.A multi-channel based on attention network is proposed in this paper,aimed at the problem of high missed detection rate and false alarm rate of traditional algorithms and the problem of large model,high complexity and poor detection performance of deep learning ***,given the difficulty in extracting the features of infrared multiscale and small dim targets,the multiple channels are designed based on dilated convolution to capture multiscale target ***,the coordinate attention block is incorporated in each channel to suppress background clutters adaptively and enhance target *** addition,the fusion of shallow detail features and deep abstract semantic features is realized by synthesizing the contextual attention fusion ***,it is verified that,compared with other state-of-the-art methods based on the datasets SIRST and MDFA,the proposed algorithm further improves the detection effect,and the model size and computational complexity are smaller.

关键词： infrared image small target detection deep learning attention mechanism feature fusion

来源：评论

学校读者我要写书评

暂无评论

Acceleration of infrared Target detection via Efficient Channel Pruning

Acceleration of Infrared Target Detection via Efficient Chan...

引用

2021 International Conference on Robotics Automation and Intelligent Control, ICRAIC 2021

作者： Miao, Zhuang Zhang, Yong Li, Weihua Chen, Ruimin Key Laboratory of Infrared System Detection and Imaging Technology Shanghai Institute of Technical Physics Chinese Academy of Sciences Shanghai200083 China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing100049 China

Deployment of modern detection models is difficult for infrared target detection used in robot vision systems due to their heavy computational burden. To alleviate this situation, a simple but efficient channel pruning method is proposed for model acceleration. Specifically, a soft-gated module combined with batch normalization (SGBN) is designed as a standalone layer to substitute the standard batch normalization (BN) layer during training. The conversion between SGBN and BN is easy, and the training overhead introduced is almost negligible after replacement. By controlling the sparsity of the scaling factor in SGBN, unimportant channels with small output are blocked automatically and globally, which is simultaneous with model training. Removing these redundant channels no longer requires fine-tuning, thus significantly speeding up the pruning process. Experiments of pruning different detection models on the infrared dataset show the effectiveness of our method. For example, the parameters and FLOPs of pruned CetnerNet are reduced by 72.70% and 40.20%, respectively, without accuracy loss. The inference speed on the CPU is 12.01ms faster. Extended studies on the classification task also demonstrate its great potential when transferring to other applications. © 2022 Institute of Physics Publishing. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Atmospheric Pollution Monitoring Based on Fourier Transform infrared Spectrometer

Atmospheric Pollution Monitoring Based on Fourier Transform ...

引用

Optical imaging and Measurement (ICOIM), International Conference of

作者： Jun Sun Zhijing Xu Yinghui Lin Ren Chen Zhanhu Wang College of Information Engineering Shanghai Maritime University Shanghai China Chinese Academy of Sciences Shanghai Institute of Technical Physics State Key Laboratory of Infrared Physics Key Laboratory of Infrared System Detection and Imaging Technology Shanghai China

Air pollution has serious impacts on human health and the environment, thus accurate monitoring and analysis of air pollutants is of vital importance. As an efficient monitoring technology, the Fourier Transform infrared Spectrometer has played a wide role in the study of air pollution. This paper elaborates on the basic principles and working mechanisms of the Fourier Transform infrared Spectrometer and discusses the important role in air pollution monitoring, also analyzes the development trend of the Fourier Transform infrared Spectrometer in air monitoring.

关键词：

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： Dong, Xue Lan, Yubo Zhao, Zongmin Cai, Chang Zhou, Zhiming Zhang, Tong Han, Pingli Xiang, Meng Liu, Jinpeng Xie, Peiyue Liu, Fei School of Optoelectronic Engineering Xidian University Xi’an710071 China Xi’an Key Laboratory of Computational Imaging Xi’an710071 China National Key Laboratory of Infrared Detection Technologies Shanghai200083 China Beijing Key Laboratory of Advanced Optical Remote Sensing Technology Beijing100094 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. © 2025 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement.

关键词： Open access

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：