检索结果-内蒙古大学图书馆

Development of an autonomous fog computing platform using control-theoretic approach for robot-vision applications

ROBOTICS AND AUTONOMOUS SYSTEMS 2022年 155卷

作者： Vinod, Dinsha SaiKrishna, P. S. Indian Inst Technol IIT Tirupati Dept Elect Engn Chindepalle Andhra Pradesh India

This paper presents the dynamic modelling and linear matrix inequality (LMI) based controller design of a distributed fog computing framework for real-time robot vision applications. A mobile robot vision system acquires the images from an application environment such as a warehouse, where articles are stacked in numerous racks. We characterise the mobile robot vision data (MRVD) using frames per second (FPS) and the image resolution. From the MRVD, object detection is performed by an open-source deep learning (DL) platform for detecting and localising various objects. However, with higher FPS together with high-resolution images, the processing time by the DL algorithm increases significantly. This necessitates the deployment of a distributed computing platform with several computing nodes. In this work, we deploy a distributed fog computing environment (DFCE) for the real-time object detection in an application environment. The processing time required to handle the MRVD is called the service time. However, for efficient auto-scaling performance, the mathematical model of the DFCE, taking into consideration the characteristics of the MRVD is necessary. In this context, we envisage the application of control theory to build the dynamic model of the DFCE. A Linear Parameter Varying (LPV) model is proposed for the DFCE with the service time as the output, the number of fog nodes as the input, and the characteristics of MRVD as the time-varying parameters. At first, an LPV model for the DFCE is derived using system identification, and the model is validated using the real-time test data. The LPV model is converted to a Polytopic LPV (PLPV) model for LMI based controller design. Finally, we develop and validate a Linear Matrix Inequality (LMI) based LPV controller to meet the service time constraints for a given application environment. For localisation and trajectory tracking with obstacle avoidance in the application environment, the mobile robot implements an Extend

关键词： Fog computing LPV modelling LMI based control deep learning for object detection Mobile robot SLAM

来源：评论

学校读者我要写书评

暂无评论

Multi-modal Conditional Bounding Box Regression for Music Score Following 29

Multi-modal Conditional Bounding Box Regression for Music Sc...

引用

29th European Signal processing Conference (EUSIPCO)

作者： Henkel, Florian Widmer, Gerhard Johannes Kepler Univ Linz Inst Computat Percept Linz Austria Johannes Kepler Univ Linz LIT Artificial Intelligence Lab Linz Austria

ISBN: (纸本)9789082797060

This paper addresses the problem of sheet-image-based on-line audio-to-score alignment also known as score following. Drawing inspiration from object detection, a conditional neural network architecture is proposed that directly predicts x,y coordinates of the matching positions in a complete score sheet image at each point in time for a given musical performance. Experiments are conducted on a synthetic polyphonic piano benchmark dataset and the new method is compared to several existing approaches from the literature for sheet-image-based score following as well as an Optical Music Recognition baseline. The proposed approach achieves new state-of-the-art results and furthermore significantly improves the alignment performance on a set of real-world piano recordings by applying Impulse Responses as a data augmentation technique.

关键词： audio-to-score alignment score following conditional object detection multi-modal deep learning

来源：评论

学校读者我要写书评

暂无评论

Combining deep learning with Single-Spectrum UV Imaging for Rapid Detection of HNSs Spills

引用

REMOTE SENSING 2022年第3期14卷 576-576页

作者： Mehdi, Syed Raza Raza, Kazim Huang, Hui Naqvi, Rizwan Ali Ali, Amjad Song, Hong Zhejiang Univ Dept Marine Engn & Technol Ocean Coll Zhoushan 316021 Peoples R China Zhejiang Univ Coll Opt Sci & Engn Hangzhou 310058 Peoples R China Zhejiang Univ Hainan Inst Sanya 572025 Peoples R China Sejong Univ Dept Unmanned Vehicle Engn 209 Neungdong Ro Seoul 05006 South Korea Peking Univ Sch Elect & Comp Engn Shenzhen 518055 Peoples R China

Vital transportation of hazardous and noxious substances (HNSs) by sea occasionally suffers spill incidents causing perilous mutilations to off-shore and on-shore ecology. Consequently, it is essential to monitor the spilled HNSs rapidly and mitigate the damages in time. Focusing on on-site and early processing, this paper explores the potential of deep learning and single-spectrum ultraviolet imaging (UV) for detecting HNSs spills. images of three floating HNSs, including benzene, xylene, and palm oil, captured in different natural and artificial aquatic sites were collected. The image dataset involved UV (at 365 nm) and RGB images for training and comparative analysis of the detection system. The You Only Look Once (YOLOv3) deep learning model is modified to balance the higher accuracy and swift detection. With the MobileNetv2 backbone architecture and generalized intersection over union (GIoU) loss function, the model achieved mean IoU values of 86.57% for UV and 82.43% for RGB images. The model yielded a mean average precision (mAP) of 86.89% and 72.40% for UV and RGB images, respectively. The average speed of 57 frames per second (fps) and average detection time of 0.0119 s per image validated the swift performance of the proposed model. The modified deep learning model combined with UV imaging is considered computationally cost-effective resulting in precise detection accuracy and significantly faster detection speed.

关键词： hazardous and noxious substances marine pollution spectral imaging deep learning YOLO image processing object detection

来源：评论

学校读者我要写书评

暂无评论

deep Spatiotemporal Clutter Filtering of Transthoracic Echocardiographic images: Leveraging Contextual Attention and Residual learning

arXiv

引用

arXiv 2024年

作者： Tabassian, Mahdi Akbari, Somayeh Queirós, Sandro D’hooge, Jan Cardiovascular Imaging and Dynamics Department of Cardiovascular Sciences KU Leuven Leuven Belgium School of Medicine University of Minho Braga Portugal ICVS/3B’s - PT Government Associate Laboratory Braga Guimarães Portugal

This study presents a deep convolutional autoencoder network for filtering reverberation clutter from transthoracic echocardiographic (TTE) image sequences. Given the spatiotemporal nature of this type of clutter, the filtering network employs 3D convolutional layers to suppress it throughout the cardiac cycle. The design of the network incorporates two key features that contribute to the effectiveness of the filter: 1) an attention mechanism for focusing on cluttered regions and leveraging contextual information, and 2) residual learning for preserving fine image structures. To train the network, a diverse set of artifact patterns was simulated and superimposed onto ultra-realistic synthetic TTE sequences from six ultrasound vendors, generating input for the filtering network. The artifact-free sequences served as ground-truth. Performance of the filtering network was evaluated using unseen synthetic and in vivo artifactual sequences. Results from the in vivo dataset confirmed the network’s strong generalization capabilities, despite being trained solely on synthetic data and simulated artifacts. The suitability of the filtered sequences for downstream processing was assessed by computing segmental strain curves. A significant reduction in the discrepancy between strain profiles computed from cluttered and clutter-free segments was observed after filtering the cluttered sequences with the proposed network. The trained network processes a TTE sequence in a fraction of a second, enabling real-time clutter filtering and potentially improving the precision of clinically relevant indices derived from TTE sequences. The source code of the proposed method and example video files of the filtering results are available at: https://***/MahdiTabassian/deep-ClutterFiltering/tree/main. Copyright © 2024, The Authors. All rights reserved.

关键词： Radar clutter

来源：评论

学校读者我要写书评

暂无评论

Malaria Detection Using image processing and Machine learning 3

Malaria Detection Using Image Processing and Machine Learnin...

引用

3rd International Conference on Advances in Computing, Communication Control and Networking, ICAC3N 2021

作者： Maduri, Praveen Kumar Shalu Agrawal, Shobhit Rai, Alok Chaubey, Shubham Department of Electronics and Instrumentation Engineering Knowledge Park 2 Greater Noida India

ISBN: (纸本)9781665438117

Malaria which has now become a common human disease is diagnosed in the present scenario starting with a clinical screening and then by medical treatment. Automated classification of malaria parasites using images is a bit challenging task due to the large amount of variability found in the display of skin abrasion. Many deep convolution neural networks show possibility for general highly variable tasks across many fine-grained object categories. Here we are working by using CNN network and datasets. CNN which is known as convolutional neural network is used to differentiate images on the basis of image pixel patterns. Our model mostly focusses on image processing using keras image generator for creating real time images. We basically train our model to easily differentiate between positive and negative images from the given datasets. Detecting malaria by image processing is very fast and reliable method as it does not require any experience. The main aim of using image processing is that our model can detect cells from multiple images taken from microscope via thin blood smear and detect them as positive and negative human blood cell and also it performs classification on human blood cell by using deep learning. © 2021 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Fault detection of railway freight cars mechanical components based on multi-feature fusion convolutional neural network

引用

INTERNATIONAL JOURNAL OF MACHINE learning AND CYBERNETICS 2021年第6期12卷 1789-1801页

作者： Ye, Tao Zhang, Zhihao Zhang, Xi Chen, Yongran Zhou, Fuqiang China Univ Min & Technol Sch Energy & Min Engn Ding 11 Xueyuan Rd Beijing 100083 Peoples R China Min Prod Safety Approval & Certificat Ctr Co Ltd Beijing 100013 Peoples R China Beihang Univ Sch Instrumentat Sci & Optoelect Engn 37 Xueyuan Rd Beijing 100191 Peoples R China

The fault detection of the mechanical components in railway freight cars is important to the safety of railway transportation. Owing to the small size of the mechanical components, a manual detection method has a low detection efficiency. In addition, traditional computer vision technology has difficulty detecting multiple categories of objects simultaneously. Inspired by the use of one-stage deep-learning-based object detectors, in this paper, a multi-feature fusion network (MFF-net) for the simultaneous detection of three typical mechanical component faults is proposed. By embedding three modules in the network to improve the detection effect of small mechanical component faults, the feature fusion module is used to supplement the deep semantic information of the shallow feature maps. A multi-branch dilated convolution module uses dilated convolution and multi-branch networks to obtain the fusion features of multi-scale receptive fields, and the squeeze-and-excitation block is embedded in the network to enhance the channel features. All experiments used Nvidia 1080Ti GPUs for training on the PyTorch platform. The experimental results show that the three modules used in the network all contribute to the fault detection of railway freight car mechanical components, and that the detection performance of MFF-net is better than that of most other popular SSD-based one-stage object detectors. When the input image size is 300 pixels x 300 pixels, MFF-net can achieve 0.8872 mAP and 33 frames per second. It has good robustness to complex noise environment and can realize real-time fault detection of railway freight car mechanical components.

关键词： One-stage deep-learning-based object detectors Feature fusion Dilated convolution Multi-branch networks Squeeze-and-excitation block

来源：评论

学校读者我要写书评

暂无评论

Hybrid context enriched deep learning model for fine-grained sentiment analysis in textual and visual semiotic modality social data

引用

INFORMATION processing & MANAGEMENT 2020年第1期57卷 102141-000页

作者： Kumar, Akshi Srinivasan, Kathiravan Cheng Wen-Huang Zomaya, Albert Y. Delhi Technol Univ Dept Comp Sci & Engn Delhi India Vellore Inst Technol Sch Informat Technol & Engn Vellore Tamil Nadu India Natl Chiao Tung Univ Dept Elect Engn Hsinchu Taiwan Natl Chiao Tung Univ Inst Elect Hsinchu Taiwan Univ Sydney Sch Comp Sci Sydney NSW Australia

Detecting sentiments in natural language is tricky even for humans, making its automated detection more complicated. This research proffers a hybrid deep learning model for fine-grained sentiment prediction in real-time multimodal data. It reinforces the strengths of deep learning nets in combination to machine learning to deal with two specific semiotic systems, namely the textual (written text) and visual (still images) and their combination within the online content using decision level multimodal fusion. The proposed contextual ConvNet-SVMBovw model, has four modules, namely, the discretization, text analytics, image analytics, and decision module. The input to the model is multimodal text, m epsilon {text, image, info-graphic}. The discretization module uses Google Lens to separate the text from the image, which is then processed as discrete entities and sent to the respective text analytics and image analytics modules. Text analytics module determines the sentiment using a hybrid of a convolution neural network (ConvNet) enriched with the contextual semantics of SentiCircle. An aggregation scheme is introduced to compute the hybrid polarity. A support vector machine (SVM) classifier trained using bag-of-visual-words (BoVW) for predicting the visual content sentiment. A Boolean decision module with a logical OR operation is augmented to the architecture which validates and categorizes the output on the basis of five fine-grained sentiment categories (truth values), namely 'highly positive,' positive,"neutral,"negative' and 'highly negative.' The accuracy achieved by the proposed model is nearly 91% which is an improvement over the accuracy obtained by the text and image modules individually.

关键词： Multimodal Sentiment analysis deep learning Context BoVW

来源：评论

学校读者我要写书评

暂无评论

Residual learning for Salient Object Detection

引用

IEEE TRANSACTIONS ON image processing 2020年 29卷 4696-4708页

作者： Feng, Mengyang Lu, Huchuan Yu, Yizhou Dalian Univ Technol Sch Informat & Commun Engn Dalian 116024 Peoples R China Deepwise Healthcare AI Lab Beijing 100080 Peoples R China

Recent deep learning based salient object detection methods improve the performance by introducing multi-scale strategies into fully convolutional neural networks (FCNs). The final result is obtained by integrating all the predictions at each scale. However, the existing multi-scale based methods suffer from several problems: 1) it is difficult to directly learn discriminative features and filters to regress high-resolution saliency masks for each scale;2) rescaling the multi-scale features could pull in many redundant and inaccurate values, and this weakens the representational ability of the network. In this paper, we propose a residual learning strategy and introduce to gradually refine the coarse prediction scale-by-scale. Concretely, instead of directly predicting the finest-resolution result at each scale, we learn to predict residuals to remedy the errors between coarse saliency map and scale-matching ground truth masks. We employ a Dilated Convolutional Pyramid Pooling (DCPP) module to generate the coarse prediction and guide the the residual learning process through several novel Attentional Residual Modules (ARMs). We name our network as Residual Refinement Network (R(2)Net). We demonstrate the effectiveness of the proposed method against other state-of-the-art algorithms on five released benchmark datasets. Our R(2)Net is a fully convolutional network which does not need any post-processing and achieves a real-time speed of 33 FPS when it is run on one GPU.

关键词： Object detection Feature extraction image reconstruction Visualization Task analysis image segmentation Spatial resolution Salient object detection residual refinement deep learning

来源：评论

学校读者我要写书评

暂无评论

Chaotic deep Network for Mobile D2D Communication

引用

IEEE INTERNET OF THINGS JOURNAL 2021年第10期8卷 8078-8096页

作者： Li, Lixiang Chen, Yixin Peng, Haipeng Yang, Yixian Beijing Univ Posts & Telecommun Informat Secur Ctr State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China Beijing Univ Posts & Telecommun Natl Engn Lab Disaster Backup & Recovery Beijing 100876 Peoples R China

Device-to-Device (D2D) communication has now become one of the most promising technologies in wireless communications of the Internet of Things (IoT). In view of the requirements on data security, response speed, signal decryption quality and storage cost of mobile devices in D2D networks, we propose chaotic deep network (CDN) to achieve secure transmission which is swifter, higher quality and lower cost. The proposed scheme consists of a prepositive nonrepetitive training procedure, a well-designed parallel encryption process, and a set of pretrained chaotic deep neural decryption networks. Benefiting from the utilization of deep learning methods, CDN achieves the swift and accurate decryption at a much lower sampling rate, which brings huge dimension reduction of both measurement matrices and ciphertext signals. Also, chaotic initial values and parameters are applied to matrix generation and network training, leading to great time reduction, storage saving and security improvement. In addition, CDN incorporates the frameworks of semitensor product (STP) and block-based image processing (BIP), which not only breaks through the dimension matching limitation of matrix multiplication by using STP but also maintains the parallelizable block-cipher mode of BIP. Proved by experiments, CDN at the sampling ratio of 25% achieves almost the same or even better peak signal to noise ratio compared to other 8 most frequently used methods at that of 50% for the same test images, and obtains better visual effects. When using a large-sized image of 2(10) x2(10) pixels for the experiments, CDN is dozens and even hundreds of times faster than those methods, while reduces the size of measurement matrix from a 500-kB level to a 3-kB level, and the size of compressed data to be transmitted can be reduced by more than 50% as well. Besides, the total key space is approximately 1093. The adjacent pixel correlation is less than 0.01.

关键词： Chaotic system deep convolutional network device-to-device (D2D) Internet of Things (IoT) semitensor product (STP)

来源：评论

学校读者我要写书评

暂无评论

GeFuNet: A knowledge-guided deep network for the infrared and visible image fusion

引用

INFRARED PHYSICS & TECHNOLOGY 2022年 127卷

作者： Su, Weijian Huang, Yongdong Li, Qiufu Zuo, Fengyuan Dalian Minzu Univ Sch Informat & Commun Engn Dalian 116600 Peoples R China Dalian Minzu Univ Ctr Math & Informat Sci Dalian 116600 Peoples R China Shenzhen Univ Comp Vis Inst Coll Comp Sci & Software Engn Shenzhen 518060 Peoples R China

deep learning has achieved great success in computer vision and image processing applications. Several pioneering works also succeeded in image fusion. However, due to the lack of ground truth, deep networks for image fusion are challenging to be well trained, restricting their fusion performance. In this paper, we design a knowledge-guided deep network, Generative -Fusion Network (GeFuNet), which takes natural images as its training data and ground truth. GeFuNet consists of two sub-networks: data generation subnet and image fusion subnet. In training, guided by the knowledge that real infrared and visible images respectively mainly contain contour and texture information, the data generation subnet is trained to generate pseudo infrared and pseudo visible images. The image fusion subnet is then trained using these pseudo images and further supervised by the natural images. The image fusion subnet adopts a hierarchical block to effectively extract and fuse multi-level information from the source images, which is learned by detail enhancement training. During the inference, the trained image fusion subnet is used to fuse real infrared and visible images. The experimental results show that GeFuNet can extract a complete contour and more details from the infrared and visible images, which are fused into the final image. The results also prove the applicability of GeFuNet on multi-scale image fusion, multi-focus image fusion, medical image fusion, and multi-exposure image fusion.

关键词： image fusion Infrared image Visible image Contour and texture information deep network Supervised training

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：