检索结果-内蒙古大学图书馆

Uncertainty-Aware real-time Visual Anomaly Detection With Conformal Prediction in Dynamic Indoor Environments

IEEE ROBOTICS AND AUTOMATION LETTERS 2025年第5期10卷 4468-4475页

作者： Saboury, Arya Uyguroglu, Mustafa Kemal Eastern Mediterranean Univ Dept Elect & Elect Engn TR-99628 Mersin Turkiye

This letter presents an efficient visual anomaly detection framework designed for safe autonomous navigation in dynamic indoor environments, such as university hallways. The approach employs an unsupervised autoencoder method within deep learning to model regular environmental patterns and detect anomalies as deviations in the embedding space. To enhance reliability and safety, the system integrates a statistical framework, conformal prediction, that provides uncertainty quantification with probabilistic guarantees. The proposed solution has been deployed on a real-time robotic platform, demonstrating efficient performance under resource-constrained conditions. Extensive hyperparameter optimization ensures the model remains dynamic and adaptable to changes, while rigorous evaluations confirm its effectiveness in anomaly detection. By addressing challenges related to real-time processing and hardware limitations, this work advances the state-of-the-art in autonomous anomaly detection. The probabilistic insights offered by this framework strengthen operational safety and pave the way for future developments, such as richer sensor fusion and advanced learning paradigms. This research highlights the potential of uncertainty-aware deep learning to enhance safety monitoring frameworks, thereby enabling the development of more reliable and intelligent autonomous systems for real-world applications.

关键词： Anomaly detection Autoencoders image reconstruction Robots Training Safety Uncertainty Reliability real-time systems Probabilistic logic deep learning for visual perception probability and statistical methods anomaly detection conformal prediction

来源：评论

学校读者我要写书评

暂无评论

Scientific preparation for CSST: classification of galaxy and nebula/star cluster based on deep learning

引用

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY 2024年第4期527卷 11935-11944页

作者： Zhang, Yuquan Cao, Zhong Wang, Feng Lam, Man, I Deng, Hui Mei, Ying Tan, Lei Guangzhou Univ Sch Elect & Commun Engn Guangzhou 510006 Peoples R China Guangzhou Univ Ctr Astrophys Guangzhou 510006 Peoples R China Natl Astron Data Ctr Great Bay Ctr Guangzhou 510006 Guangdong Peoples R China Peng Cheng Lab Shenzhen 518000 Peoples R China Chinese Acad Sci Natl Astron Observ Beijing 100101 Peoples R China

The Chinese Space Station Telescope (abbreviated as CSST) is a future advanced space telescope. real-time identification of galaxy and nebula/star cluster (abbreviated as NSC) images is of great value during CSST survey. While recent research on celestial object recognition has progressed, the rapid and efficient identification of high-resolution local celestial images remains challenging. In this study, we conducted galaxy and NSC image classification research using deep learning methods based on data from the Hubble Space Telescope. We built a local celestial image data set and designed a deep learning model named HR-CelestialNet for classifying images of the galaxy and NSC. HR-CelestialNet achieved an accuracy of 89.09 per cent on the testing set, outperforming models such as AlexNet, VGGNet, and ResNet, while demonstrating faster recognition speeds. Furthermore, we investigated the factors influencing CSST image quality and evaluated the generalization ability of HR-CelestialNet on the blurry image data set, demonstrating its robustness to low image quality. The proposed method can enable real-time identification of celestial images during CSST survey mission.

关键词： methods: data analysis techniques: image processing

来源：评论

学校读者我要写书评

暂无评论

real-time particle concentration measurement from a hologram by deep learning

引用

PHYSICA SCRIPTA 2024年第9期99卷 095512-095512页

作者： Ou, Hongjie Lin, Wendi Li, Wei-Na Xie, Xiangsheng Shantou Univ Coll Sci Phys Dept Shantou Guangdong Peoples R China

Although the existing digital holographic technologies are effective in measuring particle concentration, the processes are cumbersome and time-consuming. The purpose of this study is to quickly and accurately measure the particle number from a single hologram through deep learning. The simulation and experimental results show that the prediction number are close to the ground truth without the complicated reconstructions and denoising processes, and the average relative error remains less than 10%. The prediction time of a hologram is at the millisecond level, which offers a new possibility for real-time processing.

关键词： digital holography fresnel diffraction deep learning concentration measurement particles

来源：评论

学校读者我要写书评

暂无评论

Enhanced synthetic aperture radar image autofocus and classification using 2D SARNet framework

引用

JOURNAL OF APPLIED REMOTE SENSING 2024年第2期18卷

作者： Sakr, Mohamed Saleh, Ahmed AbdElkader, Fathy Amer, Ghada AboElenean, Mohamed Mil Tech Coll Elect Engn Cairo Egypt October 6 Univ Fac Informat & Comp Sci Giza Egypt MUST Univ Fac Engn Dept Elect Engn Giza Egypt

A synthetic aperture radar (SAR) system is a notable source of information, recognized for its capability to operate day and night and in all weather conditions, making it essential for various applications. SAR image formation is a pivotal step in radar imaging, essential for transforming complex raw radar data into interpretable and utilizable imagery. Nowadays, advancements in SAR sensor design, resulting in very wide swaths, generate a massive volume of data, necessitating extensive processing. Traditional methods of SAR image formation often involve resource-intensive and time-consuming postprocessing. There is a vital need to automate this process in near-real-time, enabling fast responses for various applications, including image classification and object detection. We present an SAR processing pipeline comprising a complex 2D autofocus SARNet, followed by a CNN-based classification model. The complex 2D autofocus SARNet is employed for image formation, utilizing an encoder-decoder architecture, such as U-Net and a modified version of ResU-Net. Meanwhile, the image classification task is accomplished using a CNN-based classification model. This framework allows us to obtain near real-time results, specifically for quick image viewing and scene classification. Several experiments were conducted using real-SAR raw data collected by the European remote sensing satellite to validate the proposed pipeline. The performance evaluation of the processing pipeline is conducted through visual assessment as well as quantitative assessment using standard metrics, such as the structural similarity index and the peak-signal-to-noise ratio. The experimental results demonstrate the processing pipeline's robustness, efficiency, reliability, and responsivity in providing an integrated neural network-based SAR processing pipeline.

关键词： synthetic aperture radar (SAR) deep learning CNN-based model ResU-Net SAR autofocus

来源：评论

学校读者我要写书评

暂无评论

real-time Pantograph Anomaly Detection Using Unsupervised deep learning and K-Nearest Neighbor Classification

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2024年 73卷 1页

作者： Guo, Ningning Lin, Chuan Yan, Hao Zang, Jiefeng Xiong, Minjun Southwest Jiaotong Univ Sch Elect Engn Chengdu 611756 Peoples R China Southwest Jiaotong Univ Sch Phys Sci & Technol Chengdu 611756 Peoples R China Zhuzhou CRRC Times Elect Co Ltd Zhuzhou 412000 Peoples R China

An image-based real-time pantograph anomaly detection method is presented by combining unsupervised deep learning and nearest neighbor classification. The proposed method includes the following key steps. First, an improved DeblurGAN-v2 deblurring algorithm is applied to the input pantograph image if there exists motion blur. Next, deep learning semantic segmentation with hybrid coding that combines lightweight convolutional neural network (CNN) and vision transformer (VIT) is employed to accurately segment the pantograph structure within the image. And multiscale feature-dense aggregation network based on an attentional feature fusion (AFF) module has been designed to efficiently integrate information from different feature layers. Finally, a K -nearest neighbor (KNN) classification algorithm with deep pretrained features from the segmented pantograph mask image has been utilized to detect anomalies in the pantograph. Experimental results demonstrate that the proposed pantograph segmentation network outperforms several general segmentation algorithms, achieving a high mean intersection over union (MIoU) of 95.86% with a parameter size of 7 M and FPS of 81.7. And nearest neighbor classification with deep pretrained features achieves excellent pantograph anomaly detection performance with area under the receiver operating characteristic (ROC) curve of 0.987 and area under a precision-recall (PR) curve of 0.998. It is verified that the proposed pantograph anomaly detection method does not rely on abnormal data, and can achieve a high anomaly detection accuracy of 98.75%.

关键词： Feature extraction Anomaly detection image restoration image reconstruction Classification algorithms Vectors Semantic segmentation K-nearest neighbor (KNN) motion blur detection pantograph anomaly detection semantic segmentation unsupervised deep learning

来源：评论

学校读者我要写书评

暂无评论

Nonlinear ultrasonic concrete crack identification with deep learning based on time-frequency image

引用

NONDESTRUCTIVE TESTING AND EVALUATION 2024年第5期39卷 1225-1249页

作者： Liu, Jianfeng Wang, Kui Zhao, Mingjie Chen, Yongjiang Chongqing Jiaotong Univ Engn Res Ctr Diag Technol Hydroconstruct Chongqing Peoples R China Chongqing Univ Sci & Technol Sch Civil Engn & Architecture Chongqing Peoples R China

By combining time-frequency images and deep learning models, the nonlinear ultrasound signals can be classified, detected, and predicted, using the nonlinear coefficient as a fundamental label for training deep learning models. This integrated approach enables quantitative identification and real-time monitoring of concrete damage, promoting the widespread adoption of nonlinear ultrasonic techniques in engineering applications. As a basis, the relationship between damage variations and nonlinear coefficients is discussed by performing nonlinear ultrasonic damage testing on concrete specimens with different crack lengths and angles. The testing signals are converted into time-frequency images using the short-time Fourier transform and the continuous wavelet transform, and both types of images are combined for data augmentation and input into the deep learning model for training, with nonlinear coefficients serving as labels for the time-frequency images. The MobileNetV2, VGG16, and ResNet18 deep learning models are trained separately on time-frequency image datasets for the length specimens, the angle specimens, and the length-angle specimens, and the performance of the different models is evaluated and compared. The results show that all three models have accuracy rates above 94%, indicating good identification performance. Finally, with the example, the nonlinear coefficients of the testing signals are compared with the labels of the nonlinear coefficients in the time-frequency images identified by the deep learning model, which confirms the high accuracy of damage identification by the deep learning model.

关键词： time-frequency image deep learning nonlinear ultrasound nonlinear coefficient concrete

来源：评论

学校读者我要写书评

暂无评论

A deep learning Approach for Fear Recognition on the Edge Based on Two-Dimensional Feature Maps

引用

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS 2024年第7期28卷 3973-3984页

作者： Sun, Junjiao Portilla, Jorge Otero, Andres Univ Politecn Madrid Ctr Elect Ind Madrid 28006 Spain

Applying affective computing techniques to recognize fear and combining them with portable signal monitors makes it possible to create real-time detection systems that could act as bodyguards when users are in danger. With this aim, this paper presents a fear recognition method based on physiological signals obtained from wearable devices. The procedure involves creating two-dimensional feature maps from the raw signals, using data augmentation and feature selection algorithms, followed by deep learning-based classification models, taking inspiration from those used in image processing. This proposal has been validated with two different datasets, achieving, in WEMAC, WESAD 3-classes, and WESAD 2-classes, F1-score results of 78.13%, 88.07%, and 99.60%, respectively, and 79.90%, 89.12%, and 99.60% in accuracy. Furthermore, the paper demonstrates the feasibility of implementing the proposed method on the Coral Edge TPU device, prepared to make inferences on the edge.

关键词： real-time systems Affective computing fear recognition deep learning feature selection physiological signals edge computing

来源：评论

学校读者我要写书评

暂无评论

A real-time foreign object detection method based on deep learning in complex open railway environments

引用

JOURNAL OF real-time image processing 2024年第5期21卷 166页

作者： Zhang, Binlin Yang, Qing Chen, Fengkui Gao, Dexin Qingdao Univ Sci & Technol Sch Informat Sci & Technol Qingdao 266061 Peoples R China Qingdao Univ Sci & Technol Sch Automat & Elect Engn Qingdao 266061 Peoples R China

In response to the current challenges of numerous background influencing factors and low detection accuracy in the open railway foreign object detection, a real-time foreign object detection method based on deep learning for open railways in complex environments is proposed. Firstly, the images of foreign objects invading the clearance collected by locomotives during long-term operation are used to create a railway foreign object dataset that fits the current situation. Then, to improve the performance of the target detection algorithm, certain improvements are made to the YOLOv7-tiny network structure. The improved algorithm enhances feature extraction capability and strengthens detection performance. By introducing a Simple, parameter-free Attention Module for convolutional neural network (SimAM) attention mechanism, the representation ability of ConvNets is improved without adding extra parameters. Additionally, drawing on the network structure of the weighted Bi-directional Feature Pyramid Network (BiFPN), the backbone network achieves cross-level feature fusion by adding edges and neck fusion. Subsequently, the feature fusion layer is improved by introducing the GhostNetV2 module, which enhances the fusion capability of different scale features and greatly reduces computational load. Furthermore, the original loss function is replaced with the Normalized Wasserstein Distance (NWD) loss function to enhance the recognition capability of small distant targets. Finally, the proposed algorithm is trained and validated, and compared with other mainstream detection algorithms based on the established railway foreign object dataset. Experimental results show that the proposed algorithm achieves applicability and real-time performance on embedded devices, with high accuracy, improved model performance, and provides precise data support for railway safety assurance.

关键词： YOLOv7-tiny Object detection deep learning Complex environment

来源：评论

学校读者我要写书评

暂无评论

A DRL-Based real-time Video processing Framework in Cloud-Edge Systems

引用

IEEE INTERNET OF THINGS JOURNAL 2024年第24期11卷 40547-40558页

作者： Fu, Xiankun Pan, Li Liu, Shijun Shandong Univ Sch Software Jinan 250101 Peoples R China

Nowadays, the Internet is rapidly evolving toward the future of the Internet of Things (IoT), where billions or even trillions of edge devices may be interconnected. The proliferation of network cameras and the advancement of IoT technologies have provided broader opportunities for data collection and utilization. In the past, the massive real-time videos generated by network cameras were mostly transmitted over the network to the cloud for analysis. However, due to network speed limitations, the latency incurred by uploading all videos to the cloud makes it difficult to meet the real-time requirements of video analysis. While edge computing significantly reduces latency, the computational capabilities of edge devices are limited, making it difficult to handle large amounts of real-time video data. In this article, we introduce a real-time video processing framework called deepVA, which utilizes cloud-edge collaboration technology to reduce latency in real-time video processing and enhance the accuracy of analysis. The deepVA framework incorporates the DRLVA video frame distribution algorithm based on deep reinforcement learning (DRL), which dynamically determines whether to distribute video frames for processing at the cloud or edge. To evaluate the performance of the proposed DRLVA algorithm, we first verify that it is superior to several other DRL-based distribution algorithms on the Gym environment. We also evaluate the performance of deepVA on the MOT2015 data set, MOTSynth data set, and real campus surveillance videos. The experiments show that our deepVA outperforms both cloud-only and edge-only solutions in terms of reducing latency and improving accuracy.

关键词： Cloud-edge collaboration deep reinforcement learning (DRL) edge computing real-time video analysis the Internet of Things (IoT) Cloud-edge collaboration deep reinforcement learning (DRL) edge computing real-time video analysis the Internet of Things (IoT)

来源：评论

学校读者我要写书评

暂无评论

Regularization by deep learning in signal processing

引用

SIGNAL image AND VIDEO processing 2024年第5期18卷 4425-4433页

作者： Villamarin, Carlos Ramirez Suazo, Erwin Oraby, Tamer Univ Texas Rio Grande Valley Dept Math & Stat Sci 1201 Univ Dr Edinburg TX 78539 USA

In this paper, we explore a new idea of using deep learning representations as a principle for regularization in inverse problems for digital signal processing. Specifically, we consider the standard variational formulation, where a composite function encodes a fidelity term that quantifies the proximity of the candidate solution to the observations (under a physical process), and a second regularization term that constrains the space of solutions according to some prior knowledge. In this work, we investigate deep learning representations as a means of fulfilling the role of this second (regularization) term. Several numerical examples are presented for signal restoration under different degradation processes, showing successful recovery under the proposed methodology. Moreover, one of these examples uses real data on energy usage by households in London from 2012 to 2014.

关键词： Inverse problems Denoising Deconvolution Regularization deep learning

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：