检索结果-内蒙古大学图书馆

2023 China Automation Congress, CAC 2023

作者： Tian, LiHua Wang, AoZe Sun, ZhiGang Xiao, Li Huazhong University of Science and Technology Key Laboratory of Image Information Processing and Intelligent Control Ministry of Education of China School of Artificial Intelligence and Automation Wuhan China

ISBN: (纸本)9798350303759

In order to address the issues of real-time performance and the low dependency between feature channels in fabric defect detection networks, this paper proposes the ESE-YOLOv5 network based on YOLOv5. Firstly, to address the relative redundancy of the neck detection network feature channels, a relatively lightweight and efficient convolution module is adopted to ensure accuracy while reducing computation and parameter volume. Furthermore, the Efficient Squeeze-Excitation (ESE) module is introduced into the backbone to optimize the dependency of feature channels, which enhances the model's feature extraction capacity and improves detection accuracy. Experimental results show that compared to YOLOv5, the proposed ESE-YOLOv5 model reduces computation and parameter volume while improving accuracy, meeting the needs of fabric defect detection for recognizing fabric defects that have similar characteristics to the background while maintaining real-time performance. © 2023 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Transformer-based Lossless Compression of Aurora Spectral images: A Spatial-Temporal-Spectral Joint Approach 17

Transformer-based Lossless Compression of Aurora Spectral Im...

引用

17th IEEE International Conference on Signal processing, ICSP 2024

作者： Cao, Xinlong Li, Jiaojiao Li, Yuanqing Yan, Jiapeng Zheng, Zhenxing Xi'an University of Posts & Telecommunications School of Communications and Information Engineering School of Artificial Intelligence Xi'an710121 China Xi'an Key Laboratory of Image Processing Technology and Applications for Public Security Xi'an710121 China International Joint Research Center for Wireless Communication and Information Processing Technology of Shaanxi Province Xi'an710121 China

ISBN: (纸本)9798350387384

Aurora spectral image lossless compression has seen significant advancements in recent years. However, most compression algorithms are based on traditional image compression techniques, focusing solely on spectral and spatial correlations without considering temporal correlations. To further enhance compression performance, this paper proposes a Transformer-based point-by-point prediction algorithm for auroral spectral images, which simultaneously uses spatial, spectral and temporal contexts for prediction. Our prediction network consists of two parts: an encoder and a decoder. The encoder is composed of the encoding unit of the original Transformer and is used to extract features from spatial, spectral and temporal contexts. The decoder consists of fully connected layers and is used for prediction. Experimental results show that the average bitrate of this method is reduced by 0.179 bpp compared with the JPEG2000 algorithm, and the average bitrate is reduced by 0.054 bpp compared with the online DPCM algorithm. © 2024 IEEE.

关键词： image compression

来源：评论

学校读者我要写书评

暂无评论

Non-intrusive load monitoring based on a combination of Transformer and CNN 4

Non-intrusive load monitoring based on a combination of Tran...

引用

4th International Conference on Energy, Power and Electrical Engineering, EPEE 2024

作者： Cheng, Yiqi Zhong, Yanru Guilin University of Electronic Technology College of Computer and Information Security Guangxi Guilin China Guilin University of Electronic Technology Guangxi Key Laboratory of Image And Graphic Intelligent Processing Guangxi Guilin China

ISBN: (纸本)9798331518066

Non-intrusive load monitoring (NILM) estimates the energy usage of individual devices by analyzing the total power meter data from a household. To address the issue of decreased monitoring accuracy with an increasing number of electricity meters, this paper proposes a solution for single appliance load monitoring (Tra-CNN). The solution uses the UK-DALE dataset, which contains high and low frequencies electricity consumption data of multiple households in the UK and the electricity consumption data of each household appliance, and uses the active power of the appliance as the input of the algorithm. The first part of the model consists of a convolutional layer, a normalization layer, and a dropout layer, with the primary task of capturing local dependencies in the data. The second part consists of a Transformer, whose self-attention mechanism associates features at different positions in the sequence to achieve modeling of long-term dependencies. The third part introduces a convolutional neural network, which uses a sliding window for convolution operations to extract local features from different positions and further extract features from sequence data. The final decoder consists of a transposed convolutional layer and a normalization layer, designed to revert the learned features to their original dimensions. Through experimental verification, the effectiveness and superiority of Tra-CNN are shown, which provides important ideas and methods for the further development of NILM technology. © 2024 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Low-light few-shot object detection via curve contrast enhancement and flow-encoder-based variational autoencoder

引用

Neural Computing and Applications 2025年第10期37卷 7261-7278页

作者： Jiang, Zetao Jin, Xin Kang, Junjie The Key Laboratory of image and graphic intelligent processing Guilin University of Electronic Technology Guangxi Guilin541004 China Wuhan Service Department Sinopec Shared Services.LTD.Nanjing Branch Jiangsu Nanjing210018 China Co. LTD Geely Group Zhejiang Ningbo315336 China

Aiming at the problem of insufficient samples in low-light object detection in some environments, a low-light few-shot object detection method based on curve contrast enhancement and flow-encoder-based variational autoencoder (CCEFVAE) is proposed. Our approach involves designing a CCE module to enhance the detailed features and contrast of low-light images by deriving a relationship expression between the enhanced image and the low-light image through the recursive relationship of high-order curves. The lumination estimation module in the CCE module estimates the parameters of the expression to calculate the pixel values of the enhanced image. Moreover, we propose an FVAE module to improve the decoupling of support features by combining the flow model encoder with the variational autoencoder, facilitating subsequent feature aggregation and classification. To ensure the consistency of the loss function of the flow model with the few-shot object detection loss, we design a negative Jacobian determinant transformation function. This enables direct addition of the two losses, allowing for unified optimization. Experimental results demonstrate that our proposed algorithm outperforms mainstream few-shot object detection models by an average of 13.1–23% in average after training on the low-light dataset (ExDark), and shows an average improvement of 5.8% compared to the state-of-the-art (SOTA) few-shot object detection model VFA. When trained on the normal lighting dataset (PASCAL VOC), the proposed algorithm exhibits a 1.7% improvement in average compared to VFA. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Curve contrast enhancement Few-shot object detection Flow-encoder-based variational autoencoder Low-light environment

来源：评论

学校读者我要写书评

暂无评论

Smart Power Safety Hazard Inspection System Based on YOLOv7 1st

Smart Power Safety Hazard Inspection System Based on YOLOv7

引用

1st International Conference on Applied Intelligence, ICAI 2023

作者： Liang, Yiheng Li, Xiaoming Deng, Zhenrong School of Computer and Information Security Guilin University of Electronic Technology Guilin541004 China Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin541004 China

ISBN: (纸本)9789819708260

Power safety is closely related to people’s well-being. Electric power sectors regularly inspect and maintain power lines to guarantee people’s safe and stable use of electricity, and the current mainstream inspection method is to use UAVs for power inspection. Traditional inspection and detection methods have many shortcomings, such as high labor costs, slow inspection speed, low detection efficiency, and single detection targets. In this paper, a set of smart power inspection systems based on YOLOv7 was designed to check the common potential security risks of power lines such as bird nests, insulators, garbage, and hardware. After the detection, the detection report could be generated. The system adopted the YOLOv7 target detection algorithm. The accuracy rate of all detection targets was up to 93.9%, and the mAP @.5% reached 95.9%. Therefore, the algorithm could greatly improve the detection efficiency and greatly facilitate the electric power sectors to check power lines, so it has a high use value. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Inspection

来源：评论

学校读者我要写书评

暂无评论

Learning to Reconnect Interrupted Trajectories for Weakly Supervised Multi-Object Tracking 48

Learning to Reconnect Interrupted Trajectories for Weakly Su...

引用

48th IEEE International Conference on Acoustics, Speech and Signal processing, ICASSP 2023

作者： Li, Yu-Lei Lu, Yang Li, Jie Wang, Hanzi Xiamen University Fujian Key Laboratory of Sensing and Computing for Smart City School of Informatics China Xidian University Video and Image Processing System Laboratory School of Electronic Engineering China

ISBN: (纸本)9781728163277

Recently, some weakly supervised multi-object tracking (MOT) methods learn identity embedding features with pseudo identity labels rather than the high-cost manual ones. However, these pseudo identity labels may contain many false or missing identities, which adversely affect the optimization of tracking networks, resulting in interrupted trajectories of occluded targets. To effectively reconnect the interrupted trajectories caused by noisy pseudo labels, we propose a novel weakly supervised MOT method based on a Trajectory-Reconnecting Transformer (TRTMOT). TRT-MOT performs feature decoupling to extract discriminative embedding features for reconnecting trajectories of occluded targets. Experimental results show that TRTMOT outperforms previous weakly supervised MOT methods by at least +3.6 and +5.6 on MOTA for the MOT17 and MOT20 datasets, respectively. © 2023 IEEE.

关键词： Feature Decoupling Pseudo Identity Labels Trajectory-Reconnecting Transformer Weakly Supervised Multi-Object Tracking

来源：评论

学校读者我要写书评

暂无评论

Research summary of "Camellia oleifera fruit picking robot" technical analysis

Research summary of "Camellia oleifera fruit picking robot" ...

引用

2021 International Conference on Signal processing and communication Technology, SPCT 2021

作者： Wang, Liang Hou, Yifeng Wang, Kuikui Wei, Chunming Guangxi Key Laboratory of Image Processing and Intelligent Information System Wuzhou University Wuzhou Guangxi543003 China

ISBN: (数字)9781510653344

ISBN: (纸本)9781510653337

Aiming at the problems of my country's current camellia fruit picking mainly relying on manual picking, large labor and low efficiency, the development and promotion of camellia fruit picking equipment and technology are discussed, and technical analysis is carried out for the design of camellia fruit picking robots. This article analyzes the characteristics and existing problems of camellia fruit picking, and analyzes the four major components of the picking robot: "end effector", "manipulator motion control system", "visual recognition positioning system"and "driving walking device". In summary, summarize the problems that have been solved, the results achieved, and the difficulties that still exist, so as to provide enlightenment for the subsequent exploration of the subject research of "camellia fruit picking robot". © 2022 SPIE.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

GFENet: Enabling Attention and Adaptive Feature Fusion in Real-time Object Detection 2

GFENet: Enabling Attention and Adaptive Feature Fusion in Re...

引用

2nd International Symposium on Electrical, Electronics and Information Engineering, ISEEIE 2022

作者： Pan, Chaolin Zhu, Xiaoyang Chu, Jun Nanchang Hangkong University Department of Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition Nanchang China

ISBN: (数字)9781665468749

ISBN: (纸本)9781665468749

Real-time object detection has been a critical component of onboard instrumentation for next-generation autonomous driving. To enable safety and reliability in autonomous driving systems, we must continue advancing its real-time object detection accuracy for future autonomous driving systems in complex environments. Existing works in real-time object detection cannot accurately detect objects with similar appearances and in complex environments. In particular, existing approaches missed many essential features because of the loss of multi-scale contextual features. Therefore, they cannot differentiate objects that have a similar appearance, a low-resolution, and a small size. To solve these issues, and to advance real-time object detection accuracy, we develop GFENet (Global Feature Enhancement Network), an end-to-end real-time object detection framework. First, we introduce a convolutional attention module that integrates spatial and channel-wise features and eliminates ineffective features to enable a strong feature representation of the network, followed by a lightweight residual module that further advances the feature representation by highlighting salient changes in features. Second, we build an adaptive feature fusion module to adaptively learn weights of multi-scale contextual features across layers, aiming to strengthen weights for small-size objects. We comprehensively evaluate GFENet on two leading object detection datasets-PASCAL VOC and MS COCO. The evaluation results (mAP of 82.9 and FPS of 31 on PASCAL VOC;mAP of 39.0 and FPS of 23 on MS COCO) show the outperformance of GFENet compared to competing baseline methods. © 2022 IEEE.

关键词： Instruments Object detection Detectors Feature extraction Real-time systems Safety Reliability

来源：评论

学校读者我要写书评

暂无评论

AGAV-Rater: Adapting Large Multimodal Model for AI-Generated Audio-Visual Quality Assessment

arXiv

引用

arXiv 2025年

作者： Cao, Yuqin Min, Xiongkuo Gao, Yixuan Sun, Wei Zhai, Guangtao Institute of Image Communication and Network Engineering Shanghai Key Laboratory of Digital Media Processing and Transmissions Shanghai Jiao Tong University Shanghai China

Many video-to-audio (VTA) methods have been proposed for dubbing silent AI-generated videos. An efficient quality assessment method for AI-generated audio-visual content (AGAV) is crucial for ensuring audio-visual quality. Existing audio-visual quality assessment methods struggle with unique distortions in AGAVs, such as unrealistic and inconsistent elements. To address this, we introduce AGAVQA, the first large-scale AGAV quality assessment dataset, comprising 3, 382 AGAVs from 16 VTA methods. AGAVQA includes two subsets: AGAVQA-MOS, which provides multi-dimensional scores for audio quality, content consistency, and overall quality, and AGAVQA-Pair, designed for optimal AGAV pair selection. We further propose AGAV-Rater, a LMM-based model that can score AGAVs, as well as audio and music generated from text, across multiple dimensions, and selects the best AGAV generated by VTA methods to present to the user. AGAV-Rater achieves state-of-the-art performance on AGAVQA, Text-to-Audio, and Text-to-Music datasets. Subjective tests also confirm that AGAV-Rater enhances VTA performance and user experience. The project page is available at https://***. Copyright © 2025, The Authors. All rights reserved.

关键词： Subjective testing

来源：评论

学校读者我要写书评

暂无评论

First-Principles Study on Switching Performance and Spin Filtering Efficiency of Dimethyldihydropyrene/Cyclophanediene Single-Molecule Devices with Zigzag Graphene Nanoribbon Electrodes

引用

Chinese Journal of Chemical Physics 2024年第5期37卷 644-652,I0066-I0072,I0100页

作者： Chang-Feng Zheng Yan-Qi Mu Zong-Liang Li Guang-Ping Zhang Shandong Key Laboratory of Medical Physics and Image Processing&Shandong Provincial Engineering and Technical Center of Light Manipulations School of Physics and ElectronicsShandong Normal UniversityJinan 250358China

Moleculardeviceswith highswitchingperformance and/or the perfect spin filtering effect have always been the pursuit with the development of molecular ***,yusingthe 2001.0V ***'s function method in combination with the density functionaltheory,the switching performance and spin filtering properties of dimethyldihydropyrene(DHP)/cyclophanediene(CPD)photoswitchable molecule connected by carbon atomic chains(CACs)to two zigzag graphene nanoribbon electrodes have been theoretically *** results show that DHP is more conductive than CPD and therefore an evident switching effect is demonstrated,and the switching ratio(RON/OFF)can reach 4.5×*** is further revealed that the RoON/OF of DHP/CPD closely depends on the length of *** specifically,the RoN/OFF values of DHP/CPD with odd-numbered CACs are larger than those with even-numbered *** interestingly,a high or even perfect spin filtering effect can be obtained in these investigated DHP/CPD single-molecule *** study is helpful for future design of single-molecule switches and spin filters and provides a way to optimize their performance by means of varying the length of bridging CACs.

关键词： Single-molecule switch Spin filtering effect Odd-even effect Nonequilibrium Green's function method Density functional 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：