检索结果-内蒙古大学图书馆

8th IEEE Asia-Pacific Conference on Computer Science and Data Engineering (IEEE CSDE)

作者： Apon, Tasnim Sakib Hasan, Mohammad Mahmudul Islam, Abrar Alam, Md Golam Rabiul BRAC Univ Dept Comp Sci & Engn Dhaka Bangladesh Islamic Univ Technol Elect & Elect Engn Dhaka Bangladesh

ISBN: (纸本)9781665495523

In the world of medical diagnostics, the adoption of various deep learning techniques is quite common as well as effective, and its statement is equally true when it comes to implementing it into the retina Optical Coherence Tomography (OCT) sector. However, firstly, these techniques have the black box characteristics that prevent the medical professionals from completely trusting the results generated from them. Secondly, the lack of precision of these methods restricts their implementation in clinical and complex cases, and finally, the existing works and models on the OCT classification are substantially large and complicated and they require a considerable amount of memory and computational power, reducing the quality of classifiers in real-time applications. To meet these problems, in this paper a self-developed CNN model has been proposed which is comparatively smaller and simpler along with the use of Lime that introduces Explainable AI to the study and helps to increase the interpretability of the model. This addition will be an asset to the medical experts for getting major and detailed information and will help them in making final decisions and will also reduce the opacity and vulnerability of the conventional deep learning models.

关键词： Medical image processing Explainable AI Retinal OCT Lime image Classification deep Neural Network AI in Healthcare

来源：评论

学校读者我要写书评

暂无评论

Low-Budget real-time Pose Estimation Method for Personal Physical Exercise Assistant 12

Low-Budget Real-time Pose Estimation Method for Personal Phy...

引用

12th International Conference on Graphics and image processing (ICGIP)

作者： Bing, Zhaodong Wang, Han Su, Yixing Wang, Shengjin Tsinghua Univ Dept Elect Engn Beijing Peoples R China

ISBN: (纸本)9781510642782;9781510642775

Pose estimation is a fundamental task in the field of computer vision. It contains a huge variety of sub-tasks, including 3D pose estimation, pose tracking, etc. In this paper, we propose a novel algorithm of pose estimation to determine whether it is correct of doing certain physical exercises by single-person pose-tracking and key frame extraction method. First, we use the proposed tracking compensation method to refine the output of pose estimation network. Second, we define different angles composed of human key joints as action angles to determine the standards of physical exercises. Therefore, we can have a personal physical exercise assistant and do physical exercises even without professional personal trainer around. Experiments show that our real-time method can achieve 92.0% accuracy on two kinds of physical exercise actions. It can be adapted to different applications with important significance in theory and practice.

关键词： deep learning low-budget pose estimation lightweight exercise guidance

来源：评论

学校读者我要写书评

暂无评论

Metrically Scaled Monocular Depth Estimation through Sparse Priors for Underwater Robots

Metrically Scaled Monocular Depth Estimation through Sparse ...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Luca Ebner Gideon Billings Stefan Williams Robotic Systems Lab ETH Zurich Australian Centre for Field Robotics University of Sydney

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

In this work, we address the problem of real-time dense depth estimation from monocular images for mobile underwater vehicles. We formulate a deep learning model that fuses sparse depth measurements from triangulated features to improve the depth predictions and solve the problem of scale ambiguity. To allow prior inputs of arbitrary sparsity, we apply a dense parameterization method. Our model extends recent state-of-the-art approaches to monocular image based depth estimation, using an efficient encoder-decoder backbone and modern lightweight transformer optimization stage to encode global context. The network is trained in a supervised fashion on the forward-looking underwater dataset, FLSea. Evaluation results on this dataset demonstrate significant improvement in depth prediction accuracy by the fusion of the sparse feature priors. In addition, without any retraining, our method achieves similar depth prediction accuracy on a downward looking dataset we collected with a diver operated camera rig, conducting a survey of a coral reef. The method achieves real-time performance, running at 24 FPS on a NVIDIA Jetson Xavier NX, 160 FPS on a NVIDIA RTX 2080 GPU and 7 FPS on a single Intel i9-9900K CPU core, making it suitable for direct deployment on embedded GPU systems. The implementation of this work is made publicly available at https://***/ebnerluca/uw_depth.

关键词： Surveys deep learning Accuracy Fuses Graphics processing units Estimation Predictive models

来源：评论

学校读者我要写书评

暂无评论

real-time crowd behavior recognition in surveillance videos based on deep learning methods

Real-time crowd behavior recognition in surveillance videos ...

引用

作者： Rezaei, Fariba Yazdi, Mehran School of Electrical and Computer Engineering Shiraz University Shiraz Iran

Automatic video surveillance in public crowded places has been an active research area for security purposes. Traditional approaches try to solve the crowd behavior recognition task using a sequential two-stage pipeline as low-level feature extraction and classification. Lately, deep learning has shown promising results in comparison to traditional methods by extracting high-level representation and solving the problem in an end-to-end pipeline. In this paper, we investigate a deep architecture for crowd event recognition to detect seven behavior categories in PETS2009 event recognition dataset. More especially, we apply an integrated handcrafted and Conv-LSTM-AE method with optical flow images as input to extract a high-level representation of data and conduct classification. After achieving a latent representation of input optical flow image sequences in the bottleneck of autoencoder(AE), the architecture is split into two separate branches, one as AE decoder and the other as the classifier. The proposed architecture is jointly trained for representation and classification by defining two different losses. The experimental results in comparison to the state-of-the-art methods demonstrate that our algorithm can be promising for real-time event recognition and achieves a better performance in calculated metrics. © 2021, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

RTX on-The NVIDIA Turing GPU

引用

IEEE MICRO 2020年第2期40卷 36-44页

作者： Burgess, John NVIDIA GPU Architecture Santa Clara CA 95051 USA

NVIDIA's latest processor family, the Turing GPU, was designed to realize a vision for next-generation graphics combining rasterization, ray tracing, and deep learning. It includes fundamental advancements in several key areas: streaming multiprocessor efficiency, a Tensor Core for accelerated AI inferencing, and an RTCore for accelerated ray tracing. With these innovations, Turing unlocks both real-time ray-tracing performance and deep-learning inference in consumer, professional, and datacenter solutions.

关键词： Graphics processing Units Inference Mechanisms learning Artificial Intelligence Neural Nets Ray Tracing real time Systems Tensor Core Multiprocessor Efficiency Next Generation Graphics Combining Rasterization NVIDIA Turing GPU RTX deep learning Inference real time Ray Tracing Performance Accelerated Ray Tracing Accelerated AI Inferencing Graphics processing Units Ray Tracing Tensors Multiprocessors Random Access Memory deep learning Instruction Sets I 3 1 A Graphics Processors Lt I 3 1 Hardware Architecture Lt I 3 Computer Graphics Lt I Computing Methodologies C 1 2 I TC Scheduling And Synchronization Lt C 1 2 Multiple Data Stream Architectures Multiprocessors Lt C 1 Processor Architect C 1 4 E Multi Core Single Chip Multiprocessors Lt C 1 4 Parallel Architectures Lt C 1 Processor Architectures Lt C Computer Systems deep learning Ray Tracing GPU Turing Tensor Core RT Core SIMT

来源：评论

学校读者我要写书评

暂无评论

Radar image Prediction Using Generative Adversarial Networks 12

Radar Image Prediction Using Generative Adversarial Networks

引用

12th International Conference on Graphics and image processing (ICGIP)

作者： Han, Lei Fang, Liyuan Zhang, Wei Ge, Yorong Ocean Univ China Coll Informat Sci & Engn Qingdao Peoples R China

ISBN: (纸本)9781510642782;9781510642775

Doppler radar is the main remote sensing equipment to monitor severe convective weather which has significant threats to social and economic activities. It is important to accurately predict the time and location of severe weather events. In this study, we use a deep learning technique to predict severe weather events based on radar images. Firstly, we transform the prediction problem into a binary classification problem and use Generative Adversarial Networks (GANs) to construct a classifier. Then Doppler radar images are used to train the model. The critical success index, probability of detection, and false alarm ratio are used to evaluate the prediction results. The experimental results show that the GANs model provides satisfactory results.

关键词： Radar image Generative Adversarial Networks deep learning

来源：评论

学校读者我要写书评

暂无评论

deep-learning-based single-photon-counting compressive imaging via jointly trained subpixel convolution sampling

引用

APPLIED OPTICS 2020年第23期59卷 6828-6837页

作者： Li, Wen-Cheng Yan, Qiu-Rong Guan, Yan-Qiu Yang, Sheng-Tao Peng, Cong Fang, Zhe-Yu Nanchang Univ Sch Informat Engn Nanchang 330031 Jiangxi Peoples R China

The combination of single-pixel-imaging and single-photon-counting technology can achieve ultrahigh-sensitivity photon-counting imaging. However, its applications in high-resolution and real-time scenarios are limited by the long sampling and reconstruction time. deep-learning-based compressive sensing provides an effective solution due to its ability to achieve fast and high-quality reconstruction. This paper proposes a sampling and reconstruction integrated neural network for single-photon-counting compressive imaging. To effectively remove the blocking artefact, a subpixel convolutional layer is jointly trained with a deep reconstruction network to imitate compressed sampling. By modifying the forward and backward propagation of the network, the first layer is trained into a binary matrix, which can be applied to the imaging system. An improved deep-reconstruction network based on the traditional Inception network is proposed, and the experimental results show that its reconstruction quality is better than existing deep-learning-based compressive sensing reconstruction algorithms. (C) 2020 Optical Society of America

关键词： Compressive imaging Computational imaging Digital micromirror devices image processing Imaging systems Imaging techniques

来源：评论

学校读者我要写书评

暂无评论

Maritime Human Drone Teaming For Search and Rescue Operations

Maritime Human Drone Teaming For Search and Rescue Operation...

引用

Technology & Engineering Management Conference - Asia Pacific (TEMSCON-ASPAC), IEEE

作者： S Sneha P Surekha Department of Electrical and Electronics Engineering Amrita School of Engineering Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (数字)9798350384659

ISBN: (纸本)9798350384666

Drowning detection is a critical safety measure aimed at identifying and preventing drowning incidents in various environments, such as swimming pools, beaches, rivers, and other bodies of water. Drowning is a leading cause of accidental death worldwide, and early detection is essential for saving lives and ensuring water-related activities remain safe. The goal of drowning detection systems is to promptly identify when a person is in distress or submerged in the water, triggering an immediate response to prevent potential drowning incidents. In this proposed work, a monitoring system using UAV (drones) to detect a drowning person is proposed. The system includes an operator, camera gear, Raspberry Pi3, and rescue UAV. The real-time image is assisted by the drowning detection algorithm, and judges whether there are targets to be rescued, so the performance of detection algorithm used in this process is very important. The drowning activity detection is identified using deep learning algorithm. After comparison with other models/methods, the deep learning model chosen for drowning detection is Convolutional Neural Networks (CNN). Conv2dLstm is the convolution layer used for developing the model, since the proposed work deals with 3D input data instead of 1D vector. deep learning model is successfully built using CNN architecture which has an accuracy of 0.9341. The processing time taken for the model to detect the drowning activity is 5 seconds where the rescue operation can be done immediately to save the person. real time implementation of the proposed system has been achieved using Raspberry Pi 3. For the rescue operation, human-drone communication is established. The controller is mounted on a carrier device and is tested in real time environment. The drowning detection system has successfully identified a person drowning in a swimming pool.

关键词： deep learning Solid modeling Three-dimensional displays Autonomous aerial vehicles real-time systems Vectors Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

deep learning assisted vision inspection of resistance spot welds

引用

JOURNAL OF MANUFACTURING PROCESSES 2021年 62卷 262-274页

作者： Dai, Wei Li, Dayong Tang, Ding Jiang, Qin Wang, Dong Wang, Huamiao Peng, Yinghong Shanghai Jiao Tong Univ State Key Lab Mech Syst & Vibrat Shanghai 200240 Peoples R China

Spot welds are extensively used on autobodies and also a key factor affecting the performance of automobiles. Automatic detection of spot welding based on machine vision provides an effective way for car body welding quality control. Considering the traditional image processing methods are greatly disturbed by the environment and have unsatisfying robustness, a network model for small object detection is proposed to detect the position and quality of the spot welding of the car body. Based on the existing You Only Look Once (YOLOv3) model, the proposed model has three novel improvements. Firstly, the lightweight network MobileNetV3 is introduced to replace the backbone network of YOLOv3 to ensure accuracy and real-time performance. Secondly, to improve the model's ability for small object detection, a new feature pyramid network (FPN) with efficient cross-scale connections is proposed, which allows easy and fast multiscale feature fusion. Finally, considering the shortcomings of intersection and union ratio (IoU) loss, complete IoU (CIoU) loss is used to improve convergence speed and regression accuracy. Moreover, novel data augmentation is used to enrich the dataset during the model training. Quantitative results on the spot welding dataset show that the proposed approach achieves successful results for resistance spot welding vision inspection.

关键词： Resistance spot welding Quality vision inspection deep learning model YOLOv3 Small object detection

来源：评论

学校读者我要写书评

暂无评论

Automated Pest Classification of Paddy Field using Drone imagery

Automated Pest Classification of Paddy Field using Drone Ima...

引用

International Conference on Trends in Electronics and Informatics (ICEI)

作者： Pamarthi Akhil Pennera Dinesh Kumar Lakshmi Priya S Department of Computer Science and Engineering Sathyabama Institute of Science and Technology

ISBN: (数字)9798331544607

ISBN: (纸本)9798331544614

Pests are a real problem to agriculture especially the paddy fields in that they contribute greatly to losses in agricultural productivity. The present research presents an innovative approach for unearthing the topology of pest-infected rice crops through a classification of a periodic series of images captured on a drone. The system consists of image processing procedures and deep learning algorithms to scan images of high spatial resolution obtained from drones. The method integration plan comprises pretreatment of images acquired from the drone, feature extraction by CNNs, and pest classification by a multi-class classification model. It is adept at distinguishing between general pest species that infest paddy fields to allow early, targeted pest control. They also bring the added value of scalability and accessibility, which make it possible to implement large scale pest monitoring. Performance evaluations prove that the system is very resistant and precise thus showing its ability to change the current pest control strategies used in farming. This minimizes the reliance on the inspection method and at the same time supports sustainable agriculture through development of constructive pest control strategies.

关键词： deep learning Productivity Precision agriculture Pest control Inspection Feature extraction Convolutional neural networks Monitoring Drones Farming

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：