检索结果-内蒙古大学图书馆

智能系统学报 2024年第6期19卷 1428-1437页

作者：李想张婷刘兆英刘波李玉鑑北京工业大学信息学部北京100124 桂林电子科技大学人工智能学院广西桂林541004

由于红外图像特征判别力低,现有方法很难从背景中分割目标。而受到红外成像机制的影响,红外目标通常具有较高的局部显著性,因此本文提出一种基于显著性导引孪生网络的跟踪方法,以目标的显著性信息为先验知识,引导跟踪模型准确地定位目... 详细信息

由于红外图像特征判别力低,现有方法很难从背景中分割目标。而受到红外成像机制的影响,红外目标通常具有较高的局部显著性,因此本文提出一种基于显著性导引孪生网络的跟踪方法,以目标的显著性信息为先验知识,引导跟踪模型准确地定位目标。本文提出显著性预测网络和显著性增强网络。显著性预测网络用于获得搜索区域的全局显著性图,并将其输入到显著性增强网络以增强目标,提高模型的判别能力;设计了一个共享互相关结构来计算模板图像特征与显著性增强后的搜索区域特征之间的相似度,通过分类和回归两个任务共享互相关特征图,同时提升模型的效率和性能;由于目前缺少公开的红外船跟踪数据集,本文构建了一个新的红外船目标跟踪数据集(infrared ship dataset,ISD),共包括16种不同类型的船,7800幅带有标签的视频帧。在ISD上的实验结果显示,与其他18个常用跟踪模型相比,本模型达到了最高的准确率和最高的期望平均交并比。

关键词：红外船跟踪孪生网络显著性目标检测特征融合共享互相关多任务学习卷积神经网络深度学习

来源：评论

学校读者我要写书评

暂无评论

A GA-Based Learning Strategy Applied to YOLOv5 for Human Object detection in UAV Surveillance System 17

A GA-Based Learning Strategy Applied to YOLOv5 for Human Obj...

引用

IEEE 17th International Conference on Control and Automation (ICCA)

作者： Mantau, Aprinaldi Jasa Widayat, Irawan Widi Adhitya, Yudhi Prakosa, Setya Widyawan Leu, Jenq-Shiou Koppen, Mario Kyushu Inst Technol Grad Sch Comp Sci & Syst Engn 680-4 Kawazu Iizuka Fukuoka 8208502 Japan Natl Taiwan Univ Sci & Technol Taipei 10607 Taiwan

ISBN: (纸本)9781665495721

YOLO (You-Only-Look-Once) is a deep learning-based one-stage detection method that has been widely used and achieved great success in image classification and localization. As the state-of-the-art method, YOLO has been upgraded to version 5. This paper proposes a new approach to using a Genetic Algorithm (GA) within a YOLOv5 framework for human object detection applied in the Unmanned Aerial Vehicle (UAV) perspective image dataset. The dataset has challenges, such as a small target, the view of the object is from above, and there is an illumination and light effect. To comply with this challenge, we will utilize the dataset of visual images taken from a UAV (RGB-image) along with Thermal infrared (TIR) information. GA is used for optimizing the Hyperparameter, which is one of the critical factors in determining the model's performance. Based on our numerical experiments, we found that this YOLOv5-based transfer learning method using RGB-TIR dataset and optimized by GA can achieve higher accuracy compared with the original YOLOv5 for Human detection on Unmanned Aerial Vehicle Perspective. The objective of this research is to create a surveillance system that will be used to monitor a wide area using autonomous UAVs that can exchange information with each other. In the end, the solution from this research can help related parties in tackling the problem of illegal activities with limited human resources.

关键词： Location awareness Visualization Surveillance Transfer learning Lighting Object detection Autonomous aerial vehicles

来源：评论

学校读者我要写书评

暂无评论

DCMF-AFNet: An anchor-free photovoltaic hot-spot fault detection network based on deformable context transformer and bi-branch multi-level feature fusion

引用

SOLAR ENERGY 2023年第1期263卷

作者： He, Tian Hao, Shuai Ma, Xu Sun, Xizi Zhao, Qiulin Sun, Haobo Xian Univ Sci & Technol Coll Elect & Control Engn Xian 710054 Peoples R China

In the process of photovoltaic hot-spot detection by thermal infrared sensors, the fault features cannot be effectively represented due to low pixel ratios and complex environmental interference, which makes it difficult for the detection network to accurately detect hot-spot faults. Therefore, an anchor-free photovoltaic hot-spot fault detection algorithm based on deformable context Transformer and bi-branch multi-level feature fusion is proposed. First, to improve the feature extraction ability of the backbone network for small-scale hot-spot faults, a deformable context Transformer module is constructed. By building an offset network in a multi-headed self-attention mechanism, dynamic and static context information with small-scale fault features can be explored from shallow feature maps. Second, to solve the problem of low target saliency due to the complex background interference, a bi-branch multi-level feature fusion module is designed to aggregate global and local multi-level features in a parallel fusion manner, enabling the detection network to rapidly focus on the fault target region in complex environments. Then, an anchor-free mechanism is introduced, and a dynamic task alignment prediction module is proposed to avoid feature misalignment in the classification and localization tasks and further improve the algorithm detection accuracy. Finally, to verify the superiority of the proposed network, seven detection algorithms are selected for comparison experiments. The experimental results show that the DCMF-AFNet network can accurately detect multi-scale hot-spot targets under various harsh conditions, and the detection accuracy can reach 87.3%.

关键词： Hot-spot fault detection Thermal infrared sensors Deformable context transformer Bi-branch multi-level feature fusion Dynamic task alignment prediction

来源：评论

学校读者我要写书评

暂无评论

PCBA板载DDR芯片焊点缺陷检测研究

引用

仪器仪表学报 2023年第2期44卷 129-137页

作者：姜也黄一凡熊美明刘智勇廖广兰华中科技大学机械科学与工程学院武汉430074

板载芯片朝着小尺寸高密度方向发展,隐藏于芯片封装内部的微焊球缺陷检测愈发困难。针对工业高密度集成印刷电路板组件(PCBA)板载集成电路(IC)内部故障定位难、效率低的问题,提出一种芯片功能测试过程中采用红外热成像检测结合深度学习... 详细信息

板载芯片朝着小尺寸高密度方向发展,隐藏于芯片封装内部的微焊球缺陷检测愈发困难。针对工业高密度集成印刷电路板组件(PCBA)板载集成电路(IC)内部故障定位难、效率低的问题,提出一种芯片功能测试过程中采用红外热成像检测结合深度学习的多类型缺陷识别方法。以现场可编程门阵列(FPGA)单板双倍数据速率(DDR)存储芯片为对象,建立了芯片缺陷检测模型,搭建检测平台开展芯片内部焊点故障检测试验研究。设计程序实现芯片的数据存储与读出,同步采集红外图像序列,分析存储芯片读写过程中温度变化,并提取不同敏感测量区域热信号。构建卷积神经网络(CNN)分类模型,并进行超参数调优,实现了内部隐藏缺陷包括不同地址、数据、地址空间焊点故障的高效准确识别。引入迁移学习拓展应用于芯片其他9种不同焊点缺陷的检测,在10、20 dB高斯白噪声条件下分别达到95%、92%以上的准确率,从而为实际工业高密度集成PCBA板载微电子封装及可靠性分析提供了一种快速、有效的方法。

关键词：焊球红外板载芯片缺陷检测

来源：评论

学校读者我要写书评

暂无评论

基于遥感影像水下目标尾迹探测综述

引用

现代防御技术 2024年第1期52卷 83-91页

作者：师俞晨核工业北京地质研究院遥感信息与图像分析技术国家级重点实验室北京100029

水下目标识别技术在现代战争中发挥着重要的作用。随着遥感技术的发展,通过遥感手段检测尾迹识别水下目标是重点研究方向之一。简要介绍了水动力学尾迹和热尾迹,并且根据遥感影像分类讨论,分析了光学影像、合成孔径雷达(SAR)影像、热红... 详细信息

水下目标识别技术在现代战争中发挥着重要的作用。随着遥感技术的发展,通过遥感手段检测尾迹识别水下目标是重点研究方向之一。简要介绍了水动力学尾迹和热尾迹,并且根据遥感影像分类讨论,分析了光学影像、合成孔径雷达(SAR)影像、热红外影像尾迹识别技术的特点和算法,提出未来发展初步构想,梳理总结了应关注的重点技术方向,为水下目标探测发展提供参考。

关键词：尾迹水下目标目标检测目标识别遥感影像

来源：评论

学校读者我要写书评

暂无评论

YOLOv8-CVIFB: A Fast Object detection Algorithm for UAV Power Patrol Based on YOLOv8 Heterogeneous Image Fusion

YOLOv8-CVIFB: A Fast Object Detection Algorithm for UAV Powe...

引用

Power and Electrical Engineering (ACPEE), 5th Asia Conference on

作者： Ze Wei Chaoyi Dong Zhiming Zhang Xiaoyan Chen Dongyang Lei Yao Xue Inner Mongolia University of Technology Intelligent Energy Technology and Equipment Engineering Research Centre of Colleges and Universities in Inner Mongolia Autonomous Region Hohhot China Engineering Research Center of Large Energy Storage Technology Ministry of Education Inner Mongolia University of Technology Intelligent Energy Technology and Equipment Engineering Research Centre of Colleges and Universities in Inner Mongolia Autonomous Region Hohhot China College of Electric Power Inner Mongolia University of Technology Intelligent Energy Technology and Equipment Engineering Research Centre of Colleges and Universities in Inner Mongolia Autonomous Region Hohhot China Engineering Research Center of Large Energy Storage Technology Ministry of Education College of Electric Power Inner Mongolia University of Technology Intelligent Energy Technology and Equipment Engineering Research Centre of Colleges and Universities in Inner Mongolia Autonomous Region Hohhot China

ISBN: (数字)9798350309638

ISBN: (纸本)9798350309645

Visual inspection of power equipment has been a hot topic in recent years. In this field, people either focus on object detection, image fusion, or image registration, lacking overall coordination considerations. To solve this problem, this article proposes a fast target detection algorithm for unmanned aerial vehicle power inspection based on YOLOv8 heterogeneous image fusion (YOLOv8-CVIFB), which can detect power devices fused with infrared and visible. The proposed algorithm mainly consists of three steps. Firstly, the CAO-C2F method is used to register the infrared and visible images collected by unmanned aerial vehicles. Secondly, the registered infrared and visible images are fused using the RFN-Nest method. Finally, the fused images were detected using YOLOv8s with Bi-Level Routing Attention added, generating images with detection results. The experimental results show that the algorithm proposed in this paper can reach 79.6% mAP and process 80 frames per second, at the same time the method can achieve higher accuracy and processing speed with a small computational improvement, which outperformed than some other algorithms.

关键词： Image registration Visualization Object detection Inspection Autonomous aerial vehicles Routing classification algorithms

来源：评论

学校读者我要写书评

暂无评论

An infrared Array Sensor-Based Approach for Activity detection, Combining Low-Cost technology with Advanced Deep Learning Techniques

引用

SENSORS 2022年第10期22卷 3898-3898页

作者： Krishnan, Arumugasamy Muthukumar Bouazizi, Mondher Ohtsuki, Tomoaki Keio Univ Grad Sch Sci & Technol Yokohama Kanagawa 2238522 Japan Keio Univ Fac Sci & Technol Yokohama Kanagawa 2238522 Japan

In this paper, we propose an activity detection system using a 24 x 32 resolution infrared array sensor placed on the ceiling. We first collect the data at different resolutions (i.e., 24 x 32, 12 x 16, and 6 x 8) and apply the advanced deep learning (DL) techniques of Super-Resolution (SR) and denoising to enhance the quality of the images. We then classify the images/sequences of images depending on the activities the subject is performing using a hybrid deep learning model combining a Convolutional Neural Network (CNN) and a Long Short-Term Memory (LSTM). We use data augmentation to improve the training of the neural networks by incorporating a wider variety of samples. The process of data augmentation is performed by a Conditional Generative Adversarial Network (CGAN). By enhancing the images using SR, removing the noise, and adding more training samples via data augmentation, our target is to improve the classification accuracy of the neural network. Through experiments, we show that employing these deep learning techniques to low-resolution noisy infrared images leads to a noticeable improvement in performance. The classification accuracy improved from 78.32% to 84.43% (for images with 6 x 8 resolution), and from 90.11% to 94.54% (for images with 12 x 16 resolution) when we used the CNN and CNN + LSTM networks, respectively.

关键词： activity detection deep learning healthcare computer vision low-resolution infrared array sensor denoising super-resolution CGAN

来源：评论

学校读者我要写书评

暂无评论

infrared small target detection method based on visual mechanism and clutter suppression model 21

Infrared small target detection method based on visual mecha...

引用

2nd International Conference on Computing, Networks and Internet of Things, CNIOT 2021

作者： Guo, Shiqian Zhang, Baohua Zhu, Jinhui Information Engineering College Inner Mongolia University of Science and Technoogy Baotou China

ISBN: (纸本)9781450389693

Aiming at the problem of high false alarm rate in the detection of dim infrared targets in complex backgrounds, an infrared dim target detection method based on visual mechanism and clutter suppression model is proposed. Firstly, a weighted template is used to roam the image to enhance dim targets and suppress the background, then the image is divided into sub-regions, the local characteristics are used to suppress strong edge clutter. Finally the dim targets are selected according to the classification criteria. Experimental results show that the proposed algorithm can effectively reduce the false alarm rate in complex scenes, and signal-to-clutter ratio and background suppression factor are better than comparison algorithms. © 2021 ACM.

关键词： Clutter (information theory)

来源：评论

学校读者我要写书评

暂无评论

基于CBAM改进YOLOv7的电力设备红外图像分类检测

引用

红外技术 2025年第1期47卷 72-80页

作者：陈佳余成波王士彬蒋启超何鑫张未重庆理工大学电气与电子工程学院重庆400054 重庆市能源互联网工程技术研究中心重庆400054 国网重庆市电力公司市南供电分公司重庆401336

针对复杂环境下电力设备红外图像的深度学习目标检测数据繁杂、检测精度较低等问题,本文提出一种基于卷积块注意模块(Convolutional Block Attention Module,CBAM)改进YOLOv7的电力设备红外图像分类算法。首先将已有数据集进行标注,并... 详细信息

针对复杂环境下电力设备红外图像的深度学习目标检测数据繁杂、检测精度较低等问题,本文提出一种基于卷积块注意模块(Convolutional Block Attention Module,CBAM)改进YOLOv7的电力设备红外图像分类算法。首先将已有数据集进行标注,并按一定比例划分成训练集、验证集以及测试集,然后在YOLOv7的主干网络中引入CBAM,使模型能对感兴趣的区域进行强调并抑制无用信息,其次将划分好的数据集放入改进后的YOLOv7进行模型训练,同时对比了6种改进的YOLOv5s模型。实验结果表明,在相同实验条件下改进YOLOv7模型优于YOLOv7模型、YOLOv5s模型和基于YOLOv5s的6种注意力模型。改进YOLOv7性能有明显提升,可实现快速、精准的红外图像分类。

关键词：电力设备 YOLOv7 红外图像 CBAM

来源：评论

学校读者我要写书评

暂无评论

infrared dim target detection via hand-crafted features and deep information combination

Infrared dim target detection via hand-crafted features and ...

引用

IEEE Conference on Industrial Electronics and Applications (ICIEA)

作者： Siying Cao Ruiyi Lian Yiwei Zhang Fengyi Wu Zhenming Peng School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu China

ISBN: (纸本)9781665409858

infrared target detection is the key technology of infrared search and tracking system. In the case of complex background, dim target detection face difficulties such as high algorithm complexity and low robustness. To solve these problems, an infrared dim target detection method via handcrafted features and deep information combination is proposed. Firstly, an adaptive Top-Hat segmentation is used to extract candidate target region, then 128-dimensional deep learning features and 106-dimensional hand-crafted features are calculated for candidate region respectively. Finally, features are concatenated and input into a 4-layer fully connected network for feature fusion and classification to exclude false alarm sources. Experiments show that the proposed method can detect infrared dim targets accurately and robustly in various scenes.

关键词： Industrial electronics Deep learning target tracking Object detection Feature extraction Robustness Complexity theory

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：