检索结果-内蒙古大学图书馆

16th International Conference on Digital image processing, ICDIP 2024

作者： Bouraya, Sara Belangour, Abdessamad Laboratory of Information Technology and Modeling Hassan II University Faculty of sciences Ben M'sik Casablanca Morocco

ISBN: (数字)9781510682917

ISBN: (纸本)9781510682900

Various applications such as urban monitoring, security, and autonomous systems rely heavily on object classification in video imagery. In this paper we present a backbone for an object detection model that uses ConvNeXt architectures with transfer learning to focus specifically on vehicle classification. By adapting the ConvNeXtBase and ConvNeXtXLarge models, and utilizing "Car Object Detection" dataset which consists of numerous videos captured in different environmental settings including varying traffic densities, weather changes and light intensities. To improve the classification capabilities to match vehicles, specialists are incorporated into these adaptations who have developed special convolutional and fully connected layers. This is accomplished through our transfer learning approach that helps the model produce distinctive features needed for accurate detection. Our models are systematically evaluated using standard performance metrics. For instance, ConvNeXtBase achieves 97.91% accuracy with validation accuracy being 97.82%, while ConvNeXtXLarge has an accuracy of 98.34% with validation accuracy at 98.11%. These results not only outperform numerous baseline models but also demonstrate that our models are effective in real world scenarios. The results obtained from this study constitute a significant contribution towards the development of intelligent transport systems as well as provide a solid foundation for future improvements in object classification via transfer learning methods. That’s why you should highly value methodologies provided in this article because they will be useful for any further findings in enhancing intelligent transportation systems by means of deep learning techniques applied to video surveillance tasks one of many applications where transfer learning can be employed successfully for more efficient outcomes. © 2024 SPIE.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

SIFDriveNet: Speed and image Fusion for Driving Behavior Classification Network

引用

IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS 2024年第1期11卷 1244-1259页

作者： Gong, Yan Lu, Jianli Liu, Wenzhuo Li, Zhiwei Jiang, Xinmin Gao, Xin Wu, Xingang Beijing Univ Chem Technol Coll Informat Sci & Technol Beijing 100029 Peoples R China China Univ Min & Technol Sch Mech Elect & Informat Engn Beijing 100083 Peoples R China AVIC CHANGCHENG Inst Metrol & Measurement Beijing 100095 Peoples R China Northeastern Univ Sch Comp Sci & Engn Shenyang 110169 Peoples R China Tsinghua Univ Sch Vehicle & Mobil Beijing 100084 Peoples R China Beijing Jiaotong Univ Sch Mech Elect & Control Engn Beijing 100044 Peoples R China

Driving behavior classification is an important direction in the field of social transportation systems and advanced driving assistance system (ADAS), which has attracted more and more attention in recent years. An accurate driving behavior classification algorithm plays a great role in traffic safety, energy saving, and other fields. In this article, we propose a novel vehicle speed and image fusion for driving behavior classification network (SIFDriveNet), which classifies driver behaviors into normal driving, aggressive driving, and drowsy driving. Our method has the following key advantages. First, in the research of driving behavior classification, we are the first to introduce a 2-D image with rich roadside information and convert speeds into a 2-D spectrogram expressing the time-frequency characteristics of speeds through short-time Fourier transform (STFT) while unifying the data space of image information and speed information. Second, we propose a tensor fusion method based on weight decomposition to fully fuse the vectors of the two modalities. This method maps the tensor outer product results to the low-dimensional space through weight decomposition and has a low computational cost while maintaining the fusion effect of the tensor outer product. In addition, we evaluated our model on the public UAH-DriveSet and compared it with the most advanced model. Experimental results show that our model has a better performance, and F1-score is 97.9% on all roads. Especially on the secondary road, our F1-score is 99.4%. Also, our model has strong generalization, and we have reached 99.3% F1 in distracted driving multimodal dataset. In addition, the inference speed reaches 411 FPS, enabling real-time needs. The code is available on https://***/alu222/SIFDriveNet.

关键词： deep learning driving behavior classification multimodal fusion spectrogram

来源：评论

学校读者我要写书评

暂无评论

RepDNet:A re-parameterization despeckling network for autonomous underwater side-scan sonar imaging with prior-knowledge customized convolution

引用

Defence Technology（防务技术） 2024年第5期35卷 259-274页

作者： Zhuoyi Li Zhisen Wang Deshan Chen Tsz Leung Yip Angelo P.Teixeira Department of Logistics and Maritime Studies The Hong Kong Polytechnic UniversityChina State Key Laboratory of Maritime Technology and Safety Wuhan University of TechnologyChina School of Transportation and Logistics Engineering Wuhan University of TechnologyChina National Engineering Research Center for Water Transport Safety Wuhan University of TechnologyChina Centre for Marine Technology and Ocean Engineering(CENTEC) Instituto Superior TecnicoUniversidade de LisboaPortugal

Side-scan sonar(SSS)is now a prevalent instrument for large-scale seafloor topography measurements,deployable on an autonomous underwater vehicle(AUV)to execute fully automated underwater acoustic scanning imaging along a predetermined ***,SSS images often suffer from speckle noise caused by mutual interference between echoes,and limited AUV computational resources further hinder noise *** approaches for SSS image processing and speckle noise reduction rely heavily on complex network structures and fail to combine the benefits of deep learning and domain *** address the problem,Rep DNet,a novel and effective despeckling convolutional neural network is *** DNet introduces two re-parameterized blocks:the Pixel Smoothing Block(PSB)and Edge Enhancement Block(EEB),preserving edge information while attenuating speckle *** training,PSB and EEB manifest as double-layered multi-branch structures,integrating first-order and secondorder derivatives and smoothing *** inference,the branches are re-parameterized into a 3×3 convolution,enabling efficient inference without sacrificing *** DNet comprises three computational operations:3×3 convolution,element-wise summation and Rectified Linear Unit *** on benchmark datasets,a real SSS dataset and Data collected at Lake Mulan aestablish Rep DNet as a well-balanced network,meeting the AUV computational constraints in terms of performance and latency.

关键词： Side-scan sonar Sonar image despeckling Domain knowledge Re-parameterization

来源：评论

学校读者我要写书评

暂无评论

5th International Conference on deep learning Theory and Applications, DeLTA 2024

5th International Conference on Deep Learning Theory and App...

引用

5th International Conference on deep learning Theory and Applications, DeLTA 2024

ISBN: (纸本)9783031667046

The proceedings contain 45 papers. The special focus in this conference is on deep learning Theory and Applications. The topics include: CNN-N-BEATS: Novel Hybrid Model for time-Series Forecasting;development and Applications of Gesture-Controlled Drones: Advances in Hand Gesture Recognition for Aerial Navigation;towards Natural-Sounding Speech to Text in English;scoping Review of Active learning Strategies and Their Evaluation Environments for Entity Recognition Tasks;solar Activity Impact on Firefighter Interventions: Factors Analysis;Detecting Flow via a Machine learning Model in a MOOC Context;Online Job Posting Authenticity Prediction with Machine and deep learning: Performance Comparison Between N-Gram and TF-IDF;Evolving deep Architectures: A New Blend of CNNs and Transformers Without Pre-training Dependencies;Closing the Sim-to-real Gap: Enhancing Autonomous Precision Landing of UAVs with Detection-Informed deep Reinforcement learning;Mitigating Class Imbalance in Healthcare AI image Classification: Evaluating the Efficacy of Existing Generative Adversarial Networks;more Than Noise: Assessing the Viscosity of Food Products Based on Sound Emission;vector Analysis of deep Neural Network Training Process;secure Coalition Formation for Federated Machine learning;action Conditioned Attention Encoder-Decoder and Discriminator for Human Motion Generation;citation Polarity Identification in Scientific Research Articles Using deep learning Methods;exploring Physiology-Based Classification of Flow During Musical Improvisation in Mixed reality;refining Weights for Enhanced Object Similarity in Multi-perspective 6Dof Pose Estimation and 3D Object Detection;end-to-End Video Surveillance Framework for Anomaly Detection and Person Re-identification;few-Shot learning with Novelty Detection.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improving Local Latent Fingerprint Representations under Data Constraints 37

Improving Local Latent Fingerprint Representations under Dat...

引用

37th SIBGRAPI Conference on Graphics, Patterns and images (SIBGRAPI)

作者： Nobrega, Andre Theodoro, Ilan Figueroa, Pascual Falcao, Alexandre Univ Estadual Campinas Inst Comp Campinas SP Brazil Griaule Res & Dev Campinas SP Brazil

ISBN: (纸本)9798350376043;9798350376036

Latent fingerprint identification is one of the most challenging tasks in fingerprint recognition due to poor image quality, small fingerprint areas, and significant deformations. State-of-the-art approaches typically treat the problem as a minutia classification task, requiring the establishment of weak minutiae correspondence labels and relying on deep minutiae descriptors trained on large private datasets. This paper proposes a novel method to develop efficient minutiae descriptors for latent fingerprint identification without using private datasets. Our approach utilizes self-supervised (contrastive) learning to design a similarity function using a Siamese network between pairs of aligned minutiae patches. We generate synthetic latent fingerprints from high-quality rolled and plain images in the public NIST SD 302 database to address the scarcity of real latent fingerprint databases. During the training, we employ the NTXent loss function to maximize the cosine similarity between the embeddings from a minutia patch and those from its synthetic augmented version. This removes the necessity for establishing weak minutiae correspondence labels. Experiments on the NIST SD27 database demonstrate that our method significantly improves identification performance, achieving a 6.59% increase in the hit rate compared to commercial software. This work highlights the potential of self-supervised learning and data augmentation techniques in advancing latent fingerprint identification systems.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Fluorescence Feature image: Fluorescence Enhancement Method Based on Illumination Adaptation

Fluorescence Feature Image: Fluorescence Enhancement Method ...

引用

2024 IEEE International Conference on Manipulation, Manufacturing and Measurement on the Nanoscale, 3M-NANO 2024

作者： Shi, Lemin Feng, Xin Song, Dianxin Gong, Ping Yue, Ming Si, Yuan Changchun University of Science and Technology School of Computer Science and Technology Changchun China Changchun University of Science and Technology School of Life Science and Technology Changchun China Changchun University of Science and Technology College of Physics Changchun China

ISBN: (纸本)9798350362107

In recent years, with the continuous development of computer technology in the field of molecular diagnosis, deep learning has shown great potential in enhancing fluorescence features in fluorescence in situ hybridization (FISH) images, allowing researchers to observe fluorescence distribution and abnormalities more clearly. Condition. of genetic material. Health status. Improves observation clarity and overall image quality of genetic material. However, due to problems such as uneven dyeing and lighting differences, the model training and generalization capabilities of deep learning are limited, thus affecting the feature recognition and accuracy of the algorithm. This method is approached from the perspective of image enhancement and feature recognition. By dynamically adjusting the lighting factors of the image to match the actual lighting distribution, this adjustment helps reduce the impact of lighting changes and makes the brightness of the image more uniform. At the same time, this method uses heat maps to quickly locate high-intensity signal areas in the image, that is, the parts with the most obvious fluorescence signals. By calculating 16 environments around these areas. Combined with the linear segmentation strategy and dynamically adjusting processing parameters, it not only highlights and enhances the clarity of image details, but also obtains accurate enhanced images. To avoid excessive enhancement of fluorescence characteristics, the fluorescence characteristics are compensated through the Cycle-Gan network to obtain the final compensation result. Finally, the effect of this method in image enhancement was verified through experimental analysis. © 2024 IEEE.

关键词： III-V semiconductors

来源：评论

学校读者我要写书评

暂无评论

Rethinking Building Change Detection: Dual-Frequency Learnable Visual Encoder With Multiscale Integration Network

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2024年 17卷 6174-6188页

作者： Xu, Chuan Yu, Haonan Mei, Liye Wang, Ying Huang, Jian Du, Wenying Jin, Shuangtong Li, Xinliu Yu, Minglin Yang, Wei Li, Xinghua Hubei Univ Technol Sch Comp Sci Wuhan 430068 Peoples R China Wuhan Univ Inst Technol Sci Wuhan 430072 Peoples R China Wuchang Shouyi Univ Sch Informat Sci & Engn Wuhan 430032 Peoples R China China Univ Geosci Natl Engn Res Ctr Geog Informat Syst Wuhan 430074 Peoples R China Wuhan Univ Sch Remote Sensing Informat Engn Wuhan 430072 Peoples R China

Remote sensing (RS) image change detection (CD) methods based on deep learning, such as convolutional neural networks (CNNs) and transformers, are still spatial domain-based image processing methods by nature, and their detection accuracy is strongly affected by chromatic aberration due to imaging time, shadows caused by lighting conditions, and object confusion and other disturbances. In this study, we revisit CD from a signal processing perspective, framing it as the task of consistency detection of the distributional features of two 2-D signals. We aim to extract the primary components of the two signals while suppressing interfering noises. To address this, we propose a novel CD method called DFNet, which leverages a dual-frequency learnable encoder. First, we construct a dual-frequency feature encoder Siamese framework to capture local high-frequency signals and global low-frequency signals using CNN and attention mechanisms after dividing the input RS image signals into two channels. Second, we introduce the frequency explicit visual center module as a part of the multifrequency-domain dense interaction (MFDDI) module at the decoder stage, allowing long-distance dependency to be established between high-low frequency components in the same layer as well as signal aggregation in regions of small edge variations. In addition, the MFDDI module adopts a layer-by-layer interactive fusion approach to synthesize discriminative information in a wide frequency-domain range, enhancing the characterization capability of frequency-domain signals. We conduct comparison experiments with the current mainstream methods on the land cover dataset SYSU-CD and two building datasets, LEVIR-CD and WHU-CD, and the results show that our method is not only resistant to interference but also outperforms all the comparison methods.

关键词： Frequency-domain analysis Feature extraction Convolutional neural networks Noise Convolution Transformers image segmentation Building change detection (BCD) dual-frequency feature encoder (DFFE) frequency domain high-low frequency information remote sensing (RS) image processing

来源：评论

学校读者我要写书评

暂无评论

An improved image processing based welding automation in Industry 4.0 2

An improved image processing based welding automation in Ind...

引用

2nd International Conference on Artificial Intelligence and Machine learning Applications, AIMLA 2024

作者： Dheer, Meenakshi Raghotham, Saritha Srinivasmurthy Tripathy, Padmaja Vivekananda Global University Department of Agriculture Jaipur India School of Mangement - UG Department of Management Karnataka Bangalore India ARKA JAIN University Department of Mechnical Engineering Jharkhand Jamshedpur India

ISBN: (纸本)9798350349221

An unique method to improve the overall performance of welding operations via photo processing. via using picture processing strategies along with segmentation, characteristic extraction, and class, we can discover shapes and features that constitute the welds and analyze their properties. moreover, the detection of defects in the welds is important for stopping lack of product exceptional. We suggest to make use of the obtained pics of the welds and stumble on welding defects based on described criteria, inclusive of porosity and incomplete fusion. through acting real-time evaluation, our technique helps to markedly growth the fine and efficiency in welding operations. additionally, our technique enables to lessen the desired analysis time, thereby minimizing downtime and improving productiveness. We applied our device on a set of welding data and reveal first-class consequences. The technique has been successfully implemented and advanced the overall performance of welding operations. © 2024 IEEE.

关键词： Welds

来源：评论

学校读者我要写书评

暂无评论

Cascaded detection method for surface defects of lead frame based on high-resolution detection images

引用

JOURNAL OF MANUFACTURING SYSTEMS 2024年 72卷 180-195页

作者： Sun, Tingrui Li, Zhiwei Xiao, Xinjie Guo, Zhihui Ning, Wenle Ding, Tingting Shanghai Univ Engn Sci Coll Elect & Elect Engn Shanghai 201620 Peoples R China Shanghai Technol & Innovat Vocat Coll Shanghai 201620 Peoples R China

In the field of semiconductor production and manufacturing, the detection of defects on lead frame surfaces is a vital process. This process plays a key role in ensuring the quality of the final product. Using high-resolution detection images to detect multi-scale tiny surface defects is necessary, but this amplifies the impact of environmental noise. Therefore, suppressing both the false negative rate and false positive rate in practical detection scenarios is a challenge that needs to be overcome. Current research on lead frame surface defect detection is mostly concentrated on the downloaded standard original images, which limits its application in actual production lines. This paper presents a cascaded detection method for surface defects of lead frame based on high-resolution detection images. Firstly, this study presents the unit cell extraction module to convert the detection object from high-resolution image to hundreds of unit cells. The proposed module can handle real-time detection images in the production pipeline, especially addressing situations such as lighting imbalances and tilted detection images. Subsequently, this study proposes a lead frame surface defect detection network (LDD-net), which takes unit cells as inputs and can effectively detect multi-scale defects. Compared to other models, LDD-net can effectively capture the features of subtle defects. Additionally, this paper introduces the deviation in the central width direction into the CIoU localization loss, enhancing the accuracy of defect localization in LDD-net. The data set is constructed using the machine vision detection system and conducts training and testing. Specifically, experiments of LDD-net on the data set obtained 85.01% mean average precision (mAP) and 37 ms of inference time, respectively. The detection accuracy exceeds 95%, and the false negative rate can be controlled below 6%. This approach will assist manual monitoring personnel in evaluating product quality.

关键词： Lead frame Surface defect detection deep learning High-resolution image Machine vision

来源：评论

学校读者我要写书评

暂无评论

Two-Stage Cascaded Speech Enhancement by Exploiting Magnitude and Phase Optimization

引用

CIRCUITS SYSTEMS AND SIGNAL processing 2025年 1-22页

作者： Qing, Chaojin He, Linsi Fu, Xiaowei Lin, Hui Xihua Univ Sch Elect Engn & Elect Informat Chengdu 610039 Peoples R China Chengdu Aerosp Kate Electromech Technol Co Ltd Chengdu 610039 Peoples R China

Most existing deep speech enhancement (SE) methods leverage a single-stage network to optimize the phase by predicting either the mask or the real and imaginary (R&I) components. However, these methods encounter significant performance limitations. Moreover, the simultaneous modeling of magnitude and phase remains a formidable challenge, particularly in the context of non-stationary noise environments characterized by low signal-to-noise ratios (SNRs). To effectively alleviate these issues, we propose a two-stage SE method to optimize both the magnitude and phase in the time-frequency (T-F) domain for monaural SE. Specifically, in the first stage, the magnitude optimization part (MOP) is employed to estimate the magnitude spectrum with the estimated mask. In the second stage, based on the estimated magnitude spectrum, we extract coarse R&I spectrum to shrink the solution space. Furthermore, by leveraging the information complementarity between magnitude and phase, the magnitude information obtained by the estimated mask network (EMNet) within the MOP is applied to the magnitude information interaction network (MIINet) in the phase optimization part (POP) to assist the phase optimization. Experimental results demonstrate that the proposed method outperforms baseline model-based methods, improving the speech quality and intelligibility.

关键词： deep learning Phase optimization Speech enhancement Two-stage processing

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：