检索结果-内蒙古大学图书馆

Sparsity Regularized Deep Subspace Clustering for Multicriterion-Based Hyperspectral Band Selection

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2022年 15卷 4264-4278页

作者： Das, Samiran Pratiher, Sawon Kyal, Chirag Ghamisi, Pedram JIS Univ JIS Inst Adv Studies & Res Kolkata 700109 India Indian Inst Technol Kharagpur Kharagpur 721302 W Bengal India Tata Consultancy Serv Bangalore 560067 Karnataka India Inst Adv Res Artificial Intelligence IARAI A-1030 Vienna Austria Helmholtz Inst Freiberg Resource Technol Machine Learning Grp Helmholtz Zentrum Dresden Rossendorf D-09599 Freiberg Germany

Hyperspectral images provide rich spectral information corresponding to visible and near-infrared imaging regions, facilitating accurate classification, object identification, and target detection. However, the high volume of data creates a computational challenge in processing. The band selection process identifies specific informative and discriminative spectral bands from the data to speed up the processing without impeding the performance. This article presents an application-independent band selection framework that utilizes improved sparse deep subspace clustering and introduces an efficient multicriteria-based representative band selection (BS). The proposed sparse deep subspace clustering approach efficiently identifies the underlying nonlinear subspace structure of the data and organizes the data accordingly. The work introduces a novel, robust sparsity measure to obtain a powerful self-representation and ameliorated performance compared to the prevalent subspace clustering methods. The work subsequently selects the representative bands from each cluster by combining structural information of the band images with the statistical similarity measure. We evaluate the BS performance on standard real images using information-theoretic criterion, classification, and unmixing performance. The comparative performance assessment demonstrates that our proposed method identifies the informative bands and outperforms the other approaches in terms of the subsequent tasks.

关键词： Task analysis Manifolds Hyperspectral imaging Optimization Object detection Sun Redundancy Deep subspace clustering hyperspectral band selection representative band selection sparsity regularization

来源：评论

学校读者我要写书评

暂无评论

infrared Ship detection Based on Improved YOLO-11

Infrared Ship Detection Based on Improved YOLO-11

引用

International Conference on Computational Intelligence and Communication Networks (CICN)

作者： Yayuan Hu School of Computing Northeast Electric Power University Jilin China

ISBN: (数字)9798331505264

ISBN: (纸本)9798331505271

In the marine field, infrared detection technology is of great significance for timely localization and detection of ships in security missions. However, since infrared ship targets are often in the environmental conditions of small pixel occupancy, low contrast and complex background, it poses a great challenge for multiship detection, classification, and localization tasks. Therefore, to solve these problems, we propose a lightweight enhanced small target infrared ship target detection (YOLO-FFE) network, Designed lightweight and efficient C2FFA module to increase the feature extraction capability of the backbone network. A lightweight attention mechanism, ELA, is added to the small-target detection header to better learn and predict the locations and bounding boxes of small targets in ship images. Experiments demonstrate that the proposed YOLO-FFE has better detection performance for infrared ship targets.

关键词： Location awareness Sea surface Attention mechanisms Surface waves Object detection Network architecture Feature extraction Reflection Security Marine vehicles

来源：评论

学校读者我要写书评

暂无评论

High-Performance Embedded System for Onboard Object detection in Hyperspectral Images 30

High-Performance Embedded System for Onboard Object Detectio...

引用

Artificial Intelligence and Image and Signal Processing for Remote Sensing XXX 2024

作者： Véstias, Mário Nascimento, José INOV/INOV-Lab/ISEL Lisbon Portugal Lisbon School of Engineering NOVA LINCS/ISEL Lisbon Portugal

ISBN: (纸本)9781510681002

Hyperspectral imaging instruments can collect hundreds of spectral bands for the same area on the Earth surface which enables extracting extended fine information of the area of interest. Due to limited bandwidth from the satellite to Earth ground station, hyperspectral image classification and object detection on-board have gained significant interest due to their importance in the analysis and interpretation of the content of the image opening new applications based on hyperspectral images. The processing and analysis of images onboard reduces the data volume to be transmitted to the ground station and allows real-time decisions to be made onboard. In this paper, a high-performance embedded system is considered to run target detection in hyperspectral images. The work considers several deep-learning models and their deployment in a Jetson Orin Nano to run object detection. It takes into account the tradeoff between throughput, model complexity, and accuracy. The model is quantized to 8-bits to explore the utilization of INT8 operations of the Jetson Orin GPU, to achieve real-time performance. © 2024 SPIE.

关键词： Image analysis

来源：评论

学校读者我要写书评

暂无评论

GAANet: Ghost Auto Anchor Network for Detecting Varying Size Drones in Dark 97

GAANet: Ghost Auto Anchor Network for Detecting Varying Size...

引用

97th IEEE Vehicular technology Conference (VTC-Spring)

作者： Khan, Misha Urooj Misbah, Maham Kaleem, Zeeshan Deng, Yansha Jamalipour, Abbas COMSATS Univ Islamabad Elect & Comp Engn Wah Campus Islamabad Pakistan Kings Coll London Dept Engn London England Univ Sydney Sch Elect & Informat Engn Sydney NSW 2006 Australia

ISBN: (纸本)9798350311143

The usage of drones has tremendously increased in different sectors spanning from military to industrial applications. Despite all the benefits they offer, their misuse can lead to mishaps, and tackling them becomes more challenging particularly at night due to their small size and low visibility conditions. To overcome those limitations and improve the detection accuracy at night, we propose an object detector called Ghost Auto Anchor Network (GAANet) for infrared (IR) images. The detector uses a YOLOv5 core to address challenges in object detection for IR images, such as poor accuracy and a high false alarm rate caused by extended altitudes, poor lighting, and low image resolution. To improve performance, we implemented auto anchor calculation, modified the conventional convolution block to ghost-convolution, adjusted the input channel size, and used the AdamW optimizer. To enhance the precision of multiscale tiny object recognition, we also introduced an additional extra-small object feature extractor and detector. Experimental results in a custom IR dataset with multiple classes (birds, drones, planes, and helicopters) demonstrate that GAANet shows improvement compared to state-ofthe-art detectors. In comparison to GhostNet-YOLOv5, GAANet has higher overall mean average precision (mAP@50), recall, and precision around 2.5%, 2.3%, and 1.4%, respectively. The dataset and code for this paper are available as open source at https://***/ZeeshanKaleem/GhostAutoAnchorNet.

关键词： Drones YOLOv5 Multi-class classification Night-Vision target detection

来源：评论

学校读者我要写书评

暂无评论

基于并行注意力机制的地面红外目标检测方法(特邀)

引用

红外与激光工程 2022年第4期51卷 90-97页

作者：赵晓枫徐叶斌吴飞牛家辉蔡伟张志利火箭军工程大学兵器发射理论与技术国家重点学科实验室陕西西安710025

地面背景下的红外目标检测是伪装防护、精确制导等领域的关键技术。针对现有基于深度学习的目标检测模型对地面背景下红外目标进行检测时容易受到复杂背景干扰、对目标关注不足,从而导致检测准确率不高的问题,文中提出了一种基于并行注... 详细信息

地面背景下的红外目标检测是伪装防护、精确制导等领域的关键技术。针对现有基于深度学习的目标检测模型对地面背景下红外目标进行检测时容易受到复杂背景干扰、对目标关注不足,从而导致检测准确率不高的问题,文中提出了一种基于并行注意力机制的地面红外目标检测方法。首先,利用卷积和注意力并行的下采样方式,在降低模型的空间复杂度和提升训练速度的同时,对目标特征进行聚焦和关注;其次,对主干网络提取的多尺度特征进行融合,通过不同尺度信息的复用与互补抑制背景信息的干扰,提升目标检测的准确率;最后,利用焦点损失函数和CIOU损失函数提高模型的分类与回归精度。实验结果表明,在infrared-VOC数据集上该模型的平均检测精度为82.2%,比YOLOv3提高了6.9%,同时模型的空间复杂度仅为YOLOv3的32.6%,训练时间为YOLOv3的43.7%,实现了模型训练效率和检测精度的提升。

关键词：红外目标检测并行注意力机制深度学习 YOLOv3 训练效率

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

Accurate detection and intelligent classification of solar cells defects based on photoluminescence images: A novel study on the optimized YOLOv5 model

引用

infrared Physics and technology 2024年 138卷

作者： Wang, Xinjian Gao, Mingyu Xie, Yunji Song, Yinghao Liang, Zhipeng Song, Peng Liu, Junyan Du, Qihou Zhou, Yulong Chen, Jiaye Zhou, Yihao Fang, Zebang Qian, Jiahong Sichuan Institute of Aerospace Systems Engineering Chengdu610100 China School of Mechatronics Engineering Harbin Institute of Technology Harbin150001 China

In the production process of solar cells, inevitable faults such as cracks, dirt, dark spots, and scratches may occur, which could potentially impact the lifespan and power generation efficiency of solar cells. Addressing this issue, this paper combines neural networks with photoluminescence detection technology and proposes a novel neural network model for the classification and grading of defects in solar cells. Firstly, the YOLOv5 model is optimized and adjusted for algorithm and network structure. The optimization process is divided into three parts: global optimization of the network structure, optimization of the neck network structure, and optimization of the head structure, each addressing specific issues in recognition, detection, and classification. The impact of the optimized network model on recognition and detection speed is analyzed, and solutions are proposed to address any observed effects. Additionally, an iterative update of neural network hyperparameter combinations is performed for solar cell defect identification. Finally, using the ultimately optimized model structure in conjunction with the optimal hyperparameter combination, comparative experiments are conducted on neural networks for different target identification using the photoluminescence characteristics dataset of solar cells. The recognition improvement of the optimized model and its differences from other models are analyzed. © 2024

关键词： Solar cells

来源：评论

学校读者我要写书评

暂无评论

infrared and small target detection based on convolution neural network under the ground-air background 7

Infrared and small target detection based on convolution neu...

引用

7th Symposium on Novel Photoelectronic detection technology and Applications

作者： Wan, Yaohui Chen, Liangyu Liu, Yingchao Key Lab Opt Radiat Beijing 100039 Peoples R China

ISBN: (数字)9781510643628

ISBN: (纸本)9781510643628

In this paper, a detection method of infrared dim target under ground-sky background is proposed. In view of the situation that there are more edges under the ground-sky background, the top-hat and median filtering algorithm are used for preliminary processing, and a large number of boundaries are estimated by combining Laplacian operator and Canny operator, and then the difference is made to eliminate the influence of boundary on detection, leaving some suspected target points. Finally, a lightweight convolution neural network is used to determine the suspected target points, and the regression problem of the target position is simplified to a binary classification problem. The experimental results show that the proposed algorithm has higher detection probability and lower false alarm rate than the traditional infrared small target detection algorithm under the ground-sky background, and has good detection effect.

关键词： ground-sky background infrared small target convolution neural network Canny Laplacian top-hat

来源：评论

学校读者我要写书评

暂无评论

An underwater near-infrared spectral continuum robot as a tool for in situ detection and classification

引用

MEASUREMENT 2023年第1期216卷

作者： Li, Yunfei Shen, Fuzhou Lang, Ziyue Cai, Maojian Zeng, Qingyi Liu, Qian Cai, Fuhong Hainan Univ Sch Biomed Engn Haikou Peoples R China Hainan Univ Mech & Elect Engn Coll Haikou Peoples R China Hainan Univ Sch Food Sci & Engn Haikou Peoples R China

Near-infrared spectral data can be used as a critical indicator for the quantitative analysis of sample molecules. However, water can strongly absorb infrared radiation, and the infrared spectrum of underwater targets cannot be directly obtained. In this study, we propose an underwater in situ near-infrared spectroscopy (875 nm-2350 nm) detection system that utilizes the structure of an optical fiber probe housed in a manipulator to perform approaching observation for underwater samples and uses compressed air to blow away the water between the probe and the target. To demonstrate the system validity, we built a set of optical fiber spectrometers embedded in the robotic arm of the traction lines tendon that can provide an air-blowing function to detect the reflection spectra of 15 minerals underwater and constructed the corresponding spectral database. Based on the above spectral database, an automated spectral identification algorithm was used to classify substances, and the SVM classification accuracy could reach 97 %. The experimental results confirm that our system is stable and can be used for infrared spectral detection of underwater mineral reflection. The relevant spectral data can be used to realize high-precision automatic mineral identification. Due to the compact structure of the system, the system will be able to carry out marine mineral detection in the future.

关键词： Underwater near-infrared sensing Ocean spectral sensor Manipulator aided optical fiber approaching observation Underwater in-situ identification of minerals

来源：评论

学校读者我要写书评

暂无评论

classification of High-Altitude Flying Objects Based on Radiation Characteristics with Attention-Convolutional Neural Network and Gated Recurrent Unit Network

引用

REMOTE SENSING 2023年第20期15卷 4985-4985页

作者： Dai, Deen Cao, Lihua Liu, Yangfan Wang, Yao Wu, Zhaolong Chinese Acad Sci State Key Lab Laser Interact Matter Changchun Inst Opt Fine Mech & Phys Changchun 130033 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China

In the task of classifying high-altitude flying objects, due to the limitations of the target flight altitude, there are issues such as insufficient contour information, low contrast, and fewer pixels in the target objects obtained through infrared detection technology, making it challenging to accurately classify them. In order to improve the classification performance and achieve the effective classification of the targets, this study proposes a high-altitude flying object classification algorithm based on radiation characteristic data. The target images are obtained through an infrared camera, and the radiation characteristics of the targets are measured using radiation characteristic measurement techniques. The classification is performed using an attention-based convolutional neural network (CNN) and gated recurrent unit (GRU) (referred to as ACGRU). In ACGRU, CNN-GRU and GRU-CNN networks are used to extract vectorized radiation characteristic data. The raw data are processed using Highway Network, and SoftMax is used for high-altitude flying object classification. The classification accuracy of ACGRU reaches 94.8%, and the F1 score reaches 93.9%. To verify the generalization performance of the model, comparative experiments and significance analysis were conducted with other algorithms on radiation characteristic datasets and 17 multidimensional time series datasets from UEA. The results show that the proposed ACGRU algorithm performs excellently in the task of high-altitude flying object classification based on radiation characteristics.

关键词： radiation characteristic measurement technique flying object classification convolutional neural network gated recurrent unit attention mechanism

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：