检索结果-内蒙古大学图书馆

IEEE OPEN JOURNAL OF SIGNAL processing 2024年 5卷 858-866页

作者： Coda, Elizabeth Clymer, Brad Desmet, Chance Watkins, Yijing Girard, Michael Pacific Northwest Natl Lab Richland WA 99354 USA

A wide variety of adversarial attacks have been proposed and explored using image and audio data. These attacks are notoriously easy to generate digitally when the attacker can directly manipulate the input to a model, but are much more difficult to implement in the real world. In this paper we present a universal, time invariant attack for general time series data such that the attack has a frequency spectrum primarily composed of the frequencies present in the original data. The universality of the attack makes it fast and easy to implement as no computation is required to add it to an input, while time invariance is useful for real world deployment. Additionally, the frequency constraint ensures the attack can withstand filtering defenses. We demonstrate the effectiveness of the attack on two different classification tasks through both digital and real world experiments, and show that the attack is robust against common transform-and-compare defense pipelines.

关键词： Training time-frequency analysis Predictive models time series analysis Recording Data models Wireless networks Adversarial machine learning deep learning time series automatic speech recognition artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

An automatic fine-grained violence detection system for animation based on modified faster R-CNN

引用

EXPERT SYSTEMS WITH APPLICATIONS 2024年 237卷

作者： Tang, Yixin Chen, Yu Sharifuzzaman, Sagar A. S. M. Li, Tie Sejong Univ Dept Cooperat Course Performance Film & Animat Seoul 05006 South Korea Sejong Univ Dept Comp Sci & Engn Seoul 05006 South Korea Sejong Univ Dept Intelligent Mechatron Engn Seoul 05006 South Korea Tiangong Univ Dept Comp Sci & Technol Tianjin Peoples R China

Animation drama and movies are important entertainment sources for children and young people. However, many of these entertainment videos introduce ideas such as violence, fighting, abuse, and car accidents, which are not suitable for children and young people. In order to prevent children from viewing these videos, different countries' government bodies put restrictions on age on these videos. Violence detection is mostly done using manual inspection, which is time and resource consuming and cannot achieve a very good result. Therefore, artificial technologies such as deep learning and machine learning can detect violence in a video. Bleeding is one of the distinct characteristics of violent actions presented in such videos. This paper aims to propose a system that can detect a given video's blood in real-time. Researchers have proposed different image processing-based techniques to detect violence, but their proposed systems lack precision and real-time detection. To this end, a deep learning-based approach is proposed to detect violence in a given video and images. A Faster R-CNN model is modified due to the sophisticated characteristics of the violence in the cartoon and animation images to achieve the highest performance. The backbone of the proposed violence detection model is changed to a modified RegNet model to extract the features from the frame. The standard inner lateral connection is replaced with the modulated deformable convolutional (MDC) layer to extract deformable feature maps. A novel distributed attention module (DAM) is proposed on the feature pyramid network to improve the performance of the feature extraction. The multiscale Region of interest (ROI) Align is adapted to improve the detection performance of violence in a different scenario. Moreover, the classification approach is integrated with the detection model to classify the different levels of violence in a given frame. We have explored state-of-the-art object detection methods such as F

关键词： Violence Fine-grained Animation deep learning CNN Faster R -CNN

来源：评论

学校读者我要写书评

暂无评论

TLEAR-Net: A Network for Defect Detection in Train Wheelset Treads Based on Transfer learning and Edge Adaptive Reinforcement Attention

引用

IET image processing 2025年第1期19卷

作者： Hu, Xinliang He, Jing Zhang, Changfan Cheng, Xiang Chenzhou Vocat Tech Coll Sch Modern Equipment Mfg Chenzhou Hunan Peoples R China Hunan Univ Technol Sch Elect & Informat Engn Zhuzhou Hunan Peoples R China Hunan Railway Profess Technol Coll Dept Intelligent Control Zhuzhou Hunan Peoples R China

As a critical load-bearing and running component of railway systems, the wheelset's operational safety fundamentally depends on precise detection and localisation of tread defects. Current deep learning-based detection methods face significant challenges in extracting discriminative edge features under small-sample conditions, leading to suboptimal defect localisation accuracy. To address these limitations, this study proposes TLEAR-Net, a novel defect detection framework integrating transfer learning with an edge-adaptive reinforcement attention mechanism. The methodology employs RetinaNet as the baseline architecture, enhanced through multi-stage domain adaptation using COCO 2017 pretraining and parameter-shared ResNet-50 backbone optimisation to bridge cross-domain feature discrepancies. An innovative edge-adaptive reinforcement (EAR) attention module is developed to selectively amplify defect boundary features through learnable gradient operators and hybrid spatial-channel attention mechanisms. Comprehensive evaluations on a proprietary data set annotated defect samples demonstrate the framework's superior performance, achieving state-of-the-art detection accuracy (89.22% mAP) while maintaining real-time processing capability (42.45 FPS).

关键词： big data CCD image sensors convolutional neural nets crack detection decision making edge detection learning (artificial intelligence) neural net architecture non-destructive testing object detection

来源：评论

学校读者我要写书评

暂无评论

Development of deep learning Color Recognition Model for Color Measurement Processes

引用

JOURNAL OF ELECTRICAL ENGINEERING & TECHNOLOGY 2024年第4期19卷 2779-2785页

作者： Lee, Sanghun Kim, Ki-Sub Kang, Jeong Won KCC Cent Res Inst Yongin 16891 South Korea Univ Southern Calif Daniel J Epstein Dept Ind & Syst Engn Los Angeles CA 90007 USA Korea Natl Univ Transportat Dept Chem & Biol Engn Chungju South Korea Korea Natl Univ Transportat Dept IT Energy Convergence Chungju South Korea Korea Natl Univ Transportat Dept Transportat Syst Engn Uiwang South Korea

We present a deep learning color recognition model for the color measurement process in the paint industry. Currently, spectrophotometers are primarily used for color measurements owing to their accuracy. The measurement method involves manually injecting the sample into a spectrophotometer. Our proposed method uses a webcam with a deep learning model on the stand of a spectrophotometer. deep learning models are widely used for image and color detection. In this study, the "you only look once (YOLO)" algorithm is applied for real-time detection of color samples. Upon training various sample images using YOLO, the model could detect the sample area in real time using a webcam. An open source computer vision (OpenCV) library was used for the color recognition model, and the detected RGB color value was converted to the international commission on illumination color space (CIELAB) value, which is primarily used in the color measuring process. However, because of the mirror-like reflection of light from a surface with specular reflection, it is difficult to implement the color value using a camera. To address this problem, we compare several specular removal methods and propose the most suitable model for the color recognition model of color samples. The accuracy of the proposed model was verified by comparing the colors of various samples. Our proposed approach can easily detect samples and color values, which can contribute significantly to automatically calculating the exact amount of coloring required for the target color.

关键词： deep learning Object detection Color recognition Open source computer vision You only look once algorithm (YOLO)

来源：评论

学校读者我要写书评

暂无评论

A real-time deep learning network for ship detection in SAR images

引用

SIGNAL image AND VIDEO processing 2024年第2期18卷 1893-1899页

作者： Zhou, Wenxue Zhang, Huachun Chinese Acad Sci Aerosp Informat Res Inst Beijing 100094 Peoples R China Univ Chinese Acad Sci Sch Elect Elect & Commun Engn Beijing 100049 Peoples R China

In the field of ship detection in synthetic aperture radar (SAR) images using deep learning, traditional models often face challenges related to their complex structure and high computational demands. To address these problems, this paper proposes a lightweight end-to-end convolutional neural network called BGD-Net, which is based on anchor-free methods. This network incorporates a novel feature pyramid called Ghost, Cross-Stage-Partial, and Path Aggregation Network (G-CSP-PAN) to enhance the detection performance across targets of varying scales. Additionally, it introduces an efficient decoupled detection head, termed the efficient decoupled head (ED-Head), to enhance the interaction between regression and classification. Furthermore, an optimized loss function named optimized efficient intersection over union (OEIoU) loss is proposed for edge regression. The proposed method is evaluated on public datasets, SSDD and SAR-Ship-Dataset, demonstrating a balance between detection accuracy and efficiency.

关键词： Anchor-free One-stage detection Synthetic aperture radar Ship detection Decoupled head

来源：评论

学校读者我要写书评

暂无评论

CT synthesis with deep learning for MR-only radiotherap planning: a review

引用

BIOMEDICAL ENGINEERING LETTERS 2024年第6期14卷 1259-1278页

作者： Roh, Junghyun Ryu, Dongmin Lee, Jimin Ulsan Natl Inst Sci & Technol Grad Sch Artificial Intelligence 50 Unist Gil Ulsan 44919 South Korea Seoul Natl Univ Program Biomed Radiat Sci 71 Ihwajang Gil Seoul 03087 South Korea Ulsan Natl Inst Sci & Technol Dept Nucl Engn 50 Unist Gil Ulsan 44919 South Korea Ulsan Natl Inst Sci & Technol Grad Sch Hlth Sci & Technol 50 Unist Gil Ulsan 44919 South Korea

MR-only radiotherapy planning is beneficial from the perspective of both time and safety since it uses synthetic CT for radiotherapy dose calculation instead of real CT scans. To elevate the accuracy of treatment planning and apply the results in practice, various methods have been adopted, among which deep learning models for image-to-image translation have shown good performance by retaining domain-invariant structures while changing domain-specific details. In this paper, we present an overview of diverse deep learning approaches to MR-to-CT synthesis, divided into four classes: convolutional neural networks, generative adversarial networks, transformer models, and diffusion models. By comparing each model and analyzing the general approaches applied to this task, the potential of these models and ways to improve the current methods can be can be evaluated.

关键词： MR-to-CT synthesis deep learning Computer vision MR-only radiotherapy planning

来源：评论

学校读者我要写书评

暂无评论

Design and optimization of an aerobics movement recognition system based on high-dimensional biotechnological data using neural networks

引用

JOURNAL OF VISUAL COMMUNICATION AND image REPRESENTATION 2024年 103卷

作者： Ma, Yihan Shanghai Polytech Univ Sports Dept Shang Hai 201209 Peoples R China

This study presents the design and optimization of an aerobics movement recognition system utilizing highdimensional biotechnological data. deep learning techniques are employed to achieve accurate classification and recognition of movement actions. Biosensing technology and wearable devices are used to collect real-time, multidimensional physiological signal data from key anatomical regions of athletes. The system is constructed using convolutional neural networks (CNNs) and Long Short-Term Memory. Model performance is optimized through parameter selection and strategies such as Xavier initialization, the cross-entropy loss function, and the Adam optimizer. The results indicate that Model C achieves an accuracy of 0.987, significantly outperforming the standalone CNNs (accuracy 0.975) and the recurrent neural network models (accuracy 0.965). Furthermore, it demonstrates notable efficiency in practical applications, with considerably reduced execution times of 10 s for data processing, 25 s for feature extraction, and 20 s for classification. This aerobics recognition system excels in performance and efficiency, supporting precise movement classification.

关键词： High-dimensional biotechnological data Aerobics movement recognition Convolutional neural networks Long Short-Term Memory networks deep learning

来源：评论

学校读者我要写书评

暂无评论

A dual attentional skip connection based Swin-UNet for real-time cloud segmentation

引用

IET image processing 2024年第12期18卷 3460-3479页

作者： Wei, Fuhao Wang, Shaofan Sun, Yanfeng Yin, Baocai Beijing Univ Technol Sch Informat Sci & Technol Beijing Key Lab Multimedia & Intelligent Software Beijing Peoples R China

Developing real-time cloud segmentation technology is urgent for many remote sensing based applications such as weather forecasting. Existing deep learning based cloud segmentation methods involve two shortcomings. (a): They tend to produce discontinuous boundaries and fail to capture less salient feature, which corresponds to thin cloud pixels;(b): they are unrobust towards different scenarios. Those issues are circumvented by integrating U-Net and the swin transformer together, with an efficiently designed dual attention mechanism based skip connection. Typically, a swin transformer based encoder-decoder network, by incorporating a dual attentional skip connection with Swin-UNet (DASUNet) is proposed. DASUNet captures the global relationship of image patches based on its window attention mechanism, which fits the real-time requirement. Moreover, DASUNet characterizes the less salient features by equipping with token dual attention modules among the skip connection, which compensates the ignorance of less salient features incurred from traditional attention mechanism during the stacking of transformer layers. Experiments on ground-based images (SWINySeg) and remote sensing images (HRC-WHU, 38-Cloud) show that, DASUNet achieves the state-of-the-art or competitive results for cloud segmentation (six top-1 positions of six metrics among 11 methods on SWINySeg, two top-1 positions of five metrics among 10 methods on HRC-WHU, two top-1 positions of four metrics among 12 methods with ParaNum <= 30M$\le 30{\rm M}$ on 38-Cloud), with 100FPS implementation speed averagely for each 224x224$224\times 224$ image. We propose a swin transformer based encoder-decoder network, by incorporating a dual attentional skip connection with Swin-UNet (DASUNet) for cloud segmentation. DASUNet characterizes the less salient features by equipping with token dual attention modules among the skip connection. The token dual attention module consists of token similarity attention and token impor

关键词： feature selection image processing image segmentation

来源：评论

学校读者我要写书评

暂无评论

Mist-fog-assisted real-time emotion recognition using deep transfer learning framework for smart city 4.0

引用

INTERNET OF THINGS 2024年 27卷

作者： Dalabehera, Aditya Ranjan Bebortta, Sujit Kumar, Naveen Senapati, Dilip Ravenshaw Univ Dept Comp Sci Cuttack 753003 Orissa India Univ Delhi Dept Comp Sci New Delhi 110007 India

Face emotion recognition (FER) has found several applications across numerous industries. One such application area lies in the field of human-computer interaction, where it can improve user experiences by allowing systems to adjust based on users' emotional states by leveraging the capabilities of the Internet of Things (IoT) to facilitate more responsive interactions. The increasing demand for precise and immediate emotion analysis across various applications drives the need for FER utilizing deep transfer learning (DTL). In this study, a novel Mist-Fog framework for real -time FER is introduced, which employs a DTL algorithm called MobileNet for quick and easy image classification on mobile and embedded devices. It addresses the challenges of operating deep neural networks (DNN) under limits on power and processing resources. By utilizing depth-wise separable convolutions, the MobileNet algorithm reduces computational complexity while maintaining reasonable accuracy on the FER -2013 dataset. A Fog-based architecture, in which a mist layer comprising edge devices like Raspberry-Pi (RPi), an ARM-based single-board computer, was considered for a smart city scenario. Further, the M/M/1/K queuing system was considered, which follows the First -Come -First -Serve (FCFS) scheduling criteria and a Markov Modulated Poisson Process (MMPP) arrival rate to evaluate the system's performance. The effectiveness of this novel approach towards industrial computer vision paradigms is assessed pertaining to different performance criteria.

关键词： deep transfer learning Edge computing Edge intelligence Fog computing realtime face emotion recognition

来源：评论

学校读者我要写书评

暂无评论

Enhanced Face Identification Performance Using Online Mining Strategy in Multi-Task Cascaded Mask Convolutional Networks

引用

TRAITEMENT DU SIGNAL 2025年第1期42卷 143-152页

作者： Mony, Krishnaraj Raj, Jeberson Retna Sathyabama Inst Sci & Technol Sch Comp Dept Comp Sci & Engn Chennai 600119 Tamil Nadu India

Due to the variety of lighting, postures, and occlusions, symmetry of faces and identification in an unrestricted area are difficult. The latest study demonstrates that deep learning techniques can do remarkably well on these two challenges. The complex transmitted multitask structure the developers provide in this research takes advantage of the natural relationship between them to improve efficiency. The suggested Multi-task Cascaded Mask Convolutional Network (MTCMCN) has three layers of carefully planned deep convolution networks that work together to figure out where faces and landmarks are from a wide range of angles. Additionally, they provide a novel, continuous, difficult sample mining approach for learning procedures, which may automatically boost efficiency without the manual choice of samples. The use of a sizable cross-age image collection containing gender and age descriptors advances the creation of Age-Invariant Face Recognition (AIFR) and FAS. MTCMCN outperforms existing methods by achieving state-of-the-art accuracy on benchmarks like FDDB and WIDER FACE, exceeding 95% accuracy in some cases. It has a Central processing Unit (CPU) speed of 16 frames per second and a GPU speed of 99 frames per second, ensuring real-time performance. The proposed system achieves this by using a special identification conditional block and live hard sample mining, thereby improving face recognition regardless of age.

关键词： Age-Invariant Face Recognition (AIFR) cross-age image collection deep learning face detection hard sample mining task Cascaded Mask Convolutional Network (MTCMCN) real-time performance symmetry and occlusion handling

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：