检索结果-内蒙古大学图书馆

2nd International conference on Electronics, communications and Information Technology, CECIT 2021

作者： Yang, Xiaokang Li, Hengyu Liu, Jingyi Song, Tao Cui, Guohua Xie, Shaorong School of Mechatronic Engineering and Automation Shanghai University Shanghai200444 China School of Mechanical and Automotive Engineering Shanghai University of Engineering Science Shanghai201620 China

ISBN: (纸本)9781665437578

The binocular vision systems provide a wealth of visual information for UGVs. However, the dust, soil and water droplets in the environment can easily contaminate the camera lens, which will cause errors in the robot's visual perception system. However, the current GAN-based image inapinting methods usually generate wrong textures, which are quite different from the real scenes. To address this problem, we propose an inpainting method that uses stereo image information as prior knowledge. In this work, we first use a multistage feature alignment module to align the left and right feature maps, and use the dynamic fusion module to fuse the two features after each alignment stage. After that, we use the feature refinement module to refine the texture information of the feature maps to generate more refined details. Experiments show that our method surpasses previous work, and achieves a higher PSNR and SSIM evaluation metrics while running over 25 fps on single NVIDIA GeForce RTX 2080 Ti, which provides effective self-inpainting capabilities for the binocular vision system of UGVs to keep driving safety. © 2021 IEEE.

关键词： Stereo image processing

来源：评论

学校读者我要写书评

暂无评论

Wavelet-Based CNN for Robust and High-Capacity image Watermarking

Wavelet-Based CNN for Robust and High-Capacity Image Waterma...

引用

2022 IEEE International conference on Multimedia and Expo, ICME 2022

作者： Lu, Junxiong Ni, Jiangqun Su, Wenkang Xie, Hao School of Computer Science and Engineering Sun Yat-sen University China Cyberspace Security Research Center Peng Cheng Laboratory Shenzhen China School of Electronics and Information Technology Sun Yat-sen University China

ISBN: (数字)9781665485630

ISBN: (纸本)9781665485630

'Physical' watermarking, i.e., print-scanning, print-camera, and screen-shooting resilient watermarking, has drawn great attention these years. Recent studies show that watermarking with deep networks, e.g., StegaStamp, is particularly suitable for these tasks with strong robustness against the attacks from 'physical transmissions' in the wild, although it usually has a relatively small amount of embedding capacity. Recognizing the conventional CNNs are vulnerable to input noise inter-ruptions, the wavelet-based CNNs are adopted in our work by replacing their down-sampling (pooling) and up-sampling layers with Discrete Wavelet Transform (DWT) and Inverse Discrete Wavelet Transform (IDWT), respectively, to learn the stable feature representation from noise-corrupted sam-ples. A new residual regularization loss function incorporating the texture complexity is also proposed to significantly improve the visual quality of watermarked images. Exper-imental results show that the proposed wavelet-based CNN model significantly outperforms the state-of-the-art StegaS-tamp in terms of embedding capacity, imperceptibility, and robustness. © 2022 IEEE.

关键词： Discrete wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

MixConvSAM: Improving Segment Anything Model for Smart Construction Site Segmentation

MixConvSAM: Improving Segment Anything Model for Smart Const...

引用

Artificial Intelligence Technology (ACAIT), Asian conference on

作者： Yao He Yang Fang Qilie Liu Weihua Ouyang School of Communications and Information Engineering Chongqing University of Posts and Telecommunications Chongqing China School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing China

ISBN: (数字)9798331517090

ISBN: (纸本)9798331517106

Recently, with the advancement in the field of smart construction site segmentation, there has been a growing interest in Segment Anything Model (SAM). As a foundational visual model, SAM is renowned for its excellent performance in natural image processing. However, it has encountered challenges when applied to smart construction site images, such as low contrast, blurry boundaries, complex shapes, and small-sized objects, resulting in decreased performance and limited generalization capabilities. To overcome these challenges, this paper proposes a novel unifying model called Mixed Convolution Segment Anything Model (MixConvSAM), which aims to apply SAM’s excellent segmentation performance and strong generalization capabilities to the field of smart construction site segmentation. MixConvSAM not only seeks better generalization capabilities, but also achieves cost reduction in deployment by shortening the sequence length of the Vision Transformer (ViT) ***, we have introduced a MixConvolution model on top of SAM, incorporating convolutional localization and window-based self-attention mechanisms to effectively complement local information to the ViT image encoder of SAM. Finally, the outputs of the two pathways are added together to produce local features, which are then injected into the ViT encoder. Additionally, we have collected a dataset of construction site images comprising three categories: bare soil, railing, and stairs, totaling approximately 6.5k images and 6.5k masks. Extensive comparative experiments have shown that the MixConvSAM model outperforms existing task-specific models and generic baseline models in both task-specific evaluation and generalization assessment.

关键词： image segmentation Computer vision Adaptation models Attention mechanisms Convolution Computational modeling Stairs Soil Transformers Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Clustering tendency assessment for datasets having inter-cluster density variations

Clustering tendency assessment for datasets having inter-clu...

引用

13th International conference on Signal processing and communications (SPCOM)

作者： Kumar, Dheeraj Bezdek, James C. Indian Inst Technol Roorkee Elect & Commun Engn Roorkee Uttar Pradesh India Univ Melbourne Comp & Informat Syst Melbourne Vic Australia

ISBN: (纸本)9781728188959

Clustering tendency assessment, i.e., determining if a dataset has any inherent clusters, and if so, how many clusters, k to seek is a crucial pre-clustering task. The visual assessment of tendency (VAT) and improved visual assessment of tendency (iVAT) algorithms provide a visual way to assess cluster tendency of a dataset by reordering the pairwise dissimilarity matrix so that potential clusters are displayed as dark blocks along the diagonal in the image of the reordered dissimilarity matrix. VAT and iVAT, being distance-based schemes, fail to perform well for datasets consisting of clusters characterized by different density levels. In this paper, we introduce two new members of the VAT family of algorithms: Locally Scaled VAT (LS-VAT) and Locally Scaled iVAT (LS-iVAT), which produces better iVAT images for data having inter-cluster density variations. Numerical experiments comparing the proposed novel approach with baseline VAT/iVAT as well as spectral clustering and density-based clustering algorithms establish that LS-VAT and LS-iVAT are superior to the comparable algorithms in terms of clustering quality.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

USTC-TD: A Test Dataset and Benchmark for image and Video Coding in 2020s

arXiv

引用

arXiv 2024年

作者： Li, Zhuoyuan Liao, Junqi Tang, Chuanbo Zhang, Haotian Li, Yuqi Bian, Yifan Sheng, Xihua Feng, Xinmin Li, Yao Gao, Changsheng Li, Li Liu, Dong Wu, Feng MOE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition University of Science and Technology of China Hefei230027 China

image/video coding has been a remarkable research area for both academia and industry for many years. Testing datasets, especially high-quality image/video datasets are desirable for the justified evaluation of coding-related research, practical applications, and standardization activities. We put forward a test dataset namely USTC-TD, which has been successfully adopted in the practical end-to-end image/video coding challenge of the IEEE International conference on visual communications and lmage processing (VCIP) in 2022 and 2023. USTC-TD contains 40 images at 4K spatial resolution and 10 video sequences at 1080p spatial resolution, featuring various content due to the diverse environmental factors (e.g. scene type, texture, motion, view) and the designed imaging factors (e.g. illumination, lens, shadow). We quantitatively evaluate USTC-TD on different image/video features (spatial, temporal, color, lightness), and compare it with the previous image/video test datasets, which verifies its excellent compensation for the shortcomings of existing datasets. We also evaluate both classic standardized and recently learned image/video coding schemes on USTC-TD using objective quality metrics (PSNR, MS-SSIM, VMAF) and subjective quality metric (MOS), providing an extensive benchmark for these evaluated schemes. Based on the characteristics and specific design of the proposed test dataset, we analyze the benchmark performance and shed light on the future research and development of image/video coding. All the data are released online: https://***/USTC-TD . Copyright © 2024, The Authors. All rights reserved.

关键词： image coding

来源：评论

学校读者我要写书评

暂无评论

Light-weight Super-Resolution Network based on Classified Measurement-domain Features 23

Light-weight Super-Resolution Network based on Classified Me...

引用

Proceedings of the 2023 6th International conference on Artificial Intelligence and Pattern Recognition

作者： Shuo Li Yinghua Li Dan Xu Ying Zhang Jinglu He School of Communications and Information Engineering Xi'an University of Posts and Telecommunications China Sichuan Jiuzhou Electric Group Co. Ltd. China

ISBN: (纸本)9798400707674

In contemporary research, natural images are frequently reconstructed using methods that are computationally intensive but highly effective. To solve this issue, we propose a light-weight super-resolution(SR) network based on classified measurement-domain features, abbreviated as SRCMF. images of nature can be divided into multiple smaller images for processing purposes. On the basis of this line of reasoning, it is possible to conclude that various image regions present unique recovery challenges and can be processed by models with differing degrees of complexity. Textured regions make supersegmentation more difficult than flat regions. To take advantage of this property, we can manage the various subgraphs of the split using an appropriate SR model, i.e. a simple small model for smooth regions and a complex large model for textured regions. With this as our starting point, we propose the SRCMF, a classification and supersegmentation integrating framework. Specifically, it employs Class Modules to categorize subgraphs based on their recovery difficulty, followed by numerous SRModules to super-score the subgraphs in each category. The computational cost can be drastically reduced because the preponderance of sub-images will travel through fewer networks. ClassSR is founded on a compression-aware image block processing method on the measurement domain, while SRModule is comprised of SR models of varying proportions. When reconstructing natural images, experimental data indicate that our SRCMF can save FLOPs and reduce the computational complexity of reconstruction. This general structure is applicable to additional simple visual duties.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Classification of the Type of Brain Tumor in MRI Using Xception Model

Classification of the Type of Brain Tumor in MRI Using Xcept...

引用

International conference on Electronics, Information and communications (ICEIC)

作者： Ramil Cobilla Jhon Carlo Dichoso Alexandre Benedict Miñon April Kate Pascual Mideth Abisado Shekinah Lor Huyo-a Gabriel Avelino Sampedro College of Computer Science Technological University of the Philippines Manila Philippines College of Computing and Information Technologies National University Manila Philippines Research and Development Center Philippine Coding Camp Manila Philippines Faculty of Information and Communication Studies University of the Philippines Open University Laguna Philippines

A brain tumor is recognized as one of the most invasive things to operate on. Cancer develops inside the brain due to unregulated and aberrant cell partitioning. The recent breakthroughs in deep learning greatly aided the medical imaging sector in diagnosing numerous diseases. In MR images, visual learning and image recognition have been used to classify the type of brain tumor. The researchers utilized a Convolutional Neural Network (CNN) approach, Data Augmentation, and image processing to organize brain MRI scans as cancerous or non-cancerous. Using the transfer learning method, the researchers compared the performance of the primary CNN model to that of pre-trained CNN and Xception models. However, the experiment was conducted on a limited dataset. Later results reveal that the model’s accuracy result is very effective and has a meager complexity rate, attaining 96% accuracy on the Xception Model.

关键词： Deep learning visualization image recognition Magnetic resonance imaging Transfer learning Brain modeling Complexity theory

来源：评论

学校读者我要写书评

暂无评论

Multiresolution Point Cloud Compression for Real-Time visualization and Streaming of Large 3D Datasets

Multiresolution Point Cloud Compression for Real-Time Visual...

引用

Asilomar conference on Signals, Systems & Computers

作者： Dat Thanh Nguyen Daniel Zieger Markus Gambietz Anne D. Koelewijn Marc Stamminger André Kaup Chair of Multimedia Communications and Signal Processing Erlangen Germany Chair of Visual Computing Erlangen Germany Chair of Autonomous Systems and Mechatronics Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) Erlangen Germany

ISBN: (数字)9798350354058

ISBN: (纸本)9798350354065

In recent years, the integration of point cloud data has been observed across diverse domains such as immersive media, autonomous driving, and healthcare. However, processing and visualizing 3D point cloud data requires more computational power and processing time than typical 2D images or videos. In this paper, we present a multiresolution point cloud visualization approach that enables the encoding and reconstruction of human body point clouds at multiple quality/bitrate levels for streaming or real-time visualization applications. Specifically, we partition the 3D model into cells and build an octree structure to store the point cloud at multiple levels of detail. The hierarchical structure is encoded efficiently for fast loading times. We optimize the resolution selection for each visible node based on the camera viewpoint and the geometric error perceived by the user. We validate the proposed method using a widely known point cloud dataset from the Moving Picture Experts Group. The experiments demonstrate that the method can dynamically adapt the resolution of point clouds and provide faster rendering times compared to well-known point cloud visualization software.

关键词： Point cloud compression Three-dimensional displays image resolution Data visualization Rendering (computer graphics) Cameras Real-time systems Signal resolution Iterative decoding Videos

来源：评论

学校读者我要写书评

暂无评论

Part-Boundary-Aware Networks for Surgical Instrument Parsing 27th

Part-Boundary-Aware Networks for Surgical Instrument Parsing

引用

27th International conference on Neural Information processing

作者： Liu, Jiaqi Qi, Yu Yang, Jie Gu, Yun Shanghai Jiao Tong Univ Inst Med Robot Shanghai Peoples R China Shanghai Jiao Tong Univ Inst Image Proc & Pattern Recognit Shanghai Peoples R China

ISBN: (纸本)9783030638221;9783030638238

Semantic parsing of surgical instruments provides essential information for further control. Due to the visual variations in surgery scenes, it challenging for automate segmentation task of instruments. In this paper, we proposed PBANet, which is short for Part-Boundary-Aware Networks, decomposing the instrument segmentation into two sub-tasks. An encoder-decoder architecture is adopted to predict the part-aware distance map that highlights the spatial structure of instruments. The segmentation mask is then obtained via the sigmoid function. We further propose to use a multi-scale dilation loss to reduce the boundary confusion. Empirical evaluations are performed on EndoVis2017 sub-challenge, demonstrating that the proposed method achieves superior performance compared to baseline methods.

关键词： Boundary-aware dice Surgical instrument parsing Signed distance map

来源：评论

学校读者我要写书评

暂无评论

3rd International conference on Electronic Governance with Emerging Technologies, EGETC 2024

3rd International Conference on Electronic Governance with E...

引用

3rd International conference on Electronic Governance with Emerging Technologies, EGETC 2024

ISBN: (纸本)9783031770289

The proceedings contain 17 papers. The special focus in this conference is on Electronic Governance with Emerging Technologies. The topics include: Ecological Development of a Novel Machine Learning Technique for Electricity Consumption and Cost Prediction in Cloud Computing;blockchain Based Decentralized Approach for Securing Fog Computing Environment;Enhancing Face Spoofing Detection Via CNN Model Integration with Normalized Features;Study of ZigBee-Based Communication to Share Operative Weather Information Between UASs in the Frame of Smart Cities Concept;automating Exam Assessment Through Digital Transformation and image processing;an Analysis of Ethical Dimension of Machine Learning Models in Software Defect Prediction in Healthcare Sector;leaf Diseases Detection in Peach Using EfficientNet;medInsight: A Personalized Prescription Recommendation Using Machine Learning;intelligent Machine Learning for Cybersecurity: Anomaly Detection in Network Intrusion Systems and Beyond;Enhancing Cyber Resilience: Implementing DFMCAI for Threat Detection and Analysis;forecasting Future Credit Card Delinquencies: Leveraging Data Tables and visual Analysis for Enhanced Accuracy;navigating the Strategic Landscape: An In-Depth Review of the Strategic Planning Process;exploring Text Vectorization on the Polarity Detection of Spanish Comments;Evolutionary Optimization Techniques for the Design of Three-Dimensional UAV’s Antenna Arrays;cooperative Multi-agent Pursuit-Evasion Using Convolutional Neural Networks.

关键词：

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：