检索结果-内蒙古大学图书馆

2nd International Conference on Computer Vision, image, and deep learning

作者： Su, Gewei Zhao, Hongbo He, Zhijun Sun, Zebin Beihang University 37 XueYuan Road Haidian District Beijing100083 China Hefei Innovation Research Institute Beihang University QianJiang Road Anhui Hefei230012 China

ISBN: (数字)9781510646827

ISBN: (纸本)9781510646810

In recent years, there has been a great progress on object-tracking task. Most of them are based on Joint Detection and Embedding (JDE) benchmark, which accomplish detection and Re-ID task in a single module and thus could reduce the time cost and help to gain a higher processing FPS. However, large computation requirement of existing JDE-based method, which usually demand several expensive GPU devices, is still an obstacle to wide application for industry. In this paper, we propose a new lightweight structure named ShuffleXnet, and further build a simple module named Pyramid-ShuffleXnet (PSXnet) for Multiple-Object Tracking (MOT) task. The motivation of this work is to reduce the amount of calculation and make the network easier to be employed for online and real-time applications. Experimental results show that our method could achieve nearly 28% higher FPS than FairMOT with just 6.7% less by Multi-Object Tracking Accuracy (MOTA) score on MOT17 dataset. © 2021 SPIE.

关键词： deep learning

来源：评论

学校读者我要写书评

暂无评论

A hybrid mask RCNN-based tool to localize dental cavities from real-time mixed photographic images

引用

PEERJ COMPUTER SCIENCE 2022年 8卷 e888页

作者： Rashid, Umer Javid, Aiman Khan, Abdur Rehman Liu, Leo Ahmed, Adeel Khalid, Osman Saleem, Khalid Meraj, Shaista Iqbal, Uzair Nawaz, Raheel Quaid i Azam Univ Dept Comp Sci Islamabad Pakistan Manchester Metropolitan Univ Sch Business & Law Manchester Lancs England COMSATS Univ Dept Comp Sci Islamabad Pakistan Bolton NHS Fdn Trust Dept Radiol Bolton England Natl Univ Comp & Emerging Sci Dept Comp Sci Islamabad Pakistan

Nearly 3.5 billion humans have oral health issues, including dental caries, which requires dentist-patient exposure in oral examinations. The automated approaches identify and locate carious regions from dental images by localizing and processing either colored photographs or X-ray images taken via specialized dental photography cameras. The dentists' interpretation of carious regions is difficult since the detected regions are masked using solid coloring and limited to a particular dental image type. The software-based automated tools to localize caries from dental images taken via ordinary cameras requires further investigation. This research provided a mixed dataset of dental photographic (colored or X-ray) images, instantiated a deep learning approach to enhance the existing dental image carious regions' localization procedure, and implemented a full-fledged tool to present carious regions via simple dental images automatically. The instantiation mainly exploits the mixed dataset of dental images (colored photographs or X-rays) collected from multiple sources and pre-trained hybrid Mask RCNN to localize dental carious regions. The evaluations performed by the dentists showed that the correctness of annotated datasets is up to 96%, and the accuracy of the proposed system is between 78% and 92%. Moreover, the system achieved the overall satisfaction level of dentists above 80%.

关键词： Dental cavities deep learning Dental image processing Mask RCNN

来源：评论

学校读者我要写书评

暂无评论

real-time and efficient eyes and mouth state detection: an artificial intelligence application based on embedded systems

引用

JOURNAL OF OPTICAL TECHNOLOGY 2020年第12期87卷 742-749页

作者： Liu, Fei Qin, Changcheng Yu, Hongliu Univ Shanghai Sci & Technol Rehabil Engn & Technol Inst Shanghai 200093 Peoples R China Shanghai Engn Res Ctr Assist Devices Shanghai 200093 Peoples R China Minist Civil Affairs Key Lab Neural Funct Informat & Rehabil Engn Shanghai 200093 Peoples R China

It is reported that many traffic accidents are caused by fatigued driving. Detection of the state of the eyes and mouth is usually employed to judge whether the driver is fatigued. However, the traditional image processing methods cannot achieve satisfactory detection accuracy due to the changes of illumination, head posture, and other factors in the actual environment. To date, although the methods based on deep learning have reached adequate accuracy in the tasks of object detection, they are obliged to rely on high hardware configuration to meet the real-time requirements. To achieve satisfactory accuracy in the task of eyes and mouth detection and obtain good real-time performance on embedded platforms such as NVIDIA Jetson TX2, we improve the object detection algorithm based on deep learning. In this paper, based on the original YOLOv3-Tiny structure, we not only added the structure of deep residual learning, but also calculated six new anchor boxes according to the training set using the K-means algorithm. We also used six data augmentation methods in the training set to improve the detection accuracy. The improved algorithm proposed in this paper can achieve satisfactory detection speed and accuracy on the TX2 embedded hardware configuration platform, validating that the ameliorated scheme is effective. (c) 2021 Optical Society of America

关键词： Algorithms Eyes image recognition Machine vision Neural networks Object detection

来源：评论

学校读者我要写书评

暂无评论

Efficient real-time Okra Stage Identification using YOLOV8

Efficient Real-Time Okra Stage Identification using YOLOV8

引用

IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT)

作者： Nikhilesh Kumar B Ferbin FJ Shoba Sivapatham Asutosh Kar Krithiga R School of Mechanical Engineering Vellore Institute of Technology Chennai India Center for Advanced Data Science Vellore Institute of Technology Chennai India Electronics and Communication Engineering National Institute of Technology Jalandhar Punjab School of Computer Science Vellore Institute of Technology Chennai India

ISBN: (数字)9798350385922

ISBN: (纸本)9798350385939

In modern agriculture, crop growth monitoring is a crucial component, as it offers intuitive information about the health and growth of the plant, assisting farmers and other agricultural specialists. This systematic growth monitoring is necessary for crop health and agricultural productivity. We preferred the YOLOv8, which utilizes machine learning and offers efficient plant analysis in agriculture. This preferred method predicts bounding boxes and the probability of each possible class, allowing it to achieve exceptional detection speed without trading off accuracy. Pre-processing was done on the created, "Okra-dataset" to standardize the image to a fixed resolution and enhance our dataset’s strength. We tested our work using different models: YOLOv8s, YOLOv8m, YOLOv8l, and YOLOv8x. Our test revealed that YOLOv8x achieved the highest mean average precision (mAP) of 82.9%. The implementation of research indicates that YOLOv8x is a good tool for agricultural applications, which can be very helpful to farmers.

关键词： deep learning Agricultural robots Computational modeling Plants (biology) Crops Prediction algorithms real-time systems

来源：评论

学校读者我要写书评

暂无评论

Intelligent marine detection based on spectral imaging and neural network modeling

引用

OCEAN ENGINEERING 2024年第Part1期310卷

作者： Lu, Fengqin Gao, Xinyu Ma, Jun Xu, Jinfeng Xue, Qingsheng Cao, Diansheng Quan, Xiangqian Ocean Univ China Coll Phys & Optoelect Engn Dept Informat Sci & Engn Qingdao 266100 Shandong Peoples R China Ocean Univ China Basic Teaching Ctr Qingdao 266100 Peoples R China Minist Educ Engn Res Ctr Adv Marine Phys Instruments & Equipme Qingdao 266100 Peoples R China Chinese Acad Sci Inst Deep Sea Sci & Engn Sanya 572000 Peoples R China Univ Calif San Diego Dept Mech & Aerosp Engn La Jolla CA 92093 USA Univ Calif San Diego Scripps Inst Oceanog La Jolla CA 92093 USA

Underwater spectral imaging combined with neural networks provides a practical means for intelligent detection and maintenance of offshore engineering. As an underwater detection technology, the data obtained from underwater hyperspectral imaging can be used for both qualitative analysis and quantitative detection of underwater targets, which is an efficient means of underwater target detection in offshore engineering. In this paper, An underwater hyperspectral imaging system based on PGP spectral structure line scanning imaging has been designed and developed for shallow water detection. It has a spectral range of 400-1000 nm, over 200 channels, a spectral resolution of 2.5 nm, a field of view angle of 35.2 degrees, and a focal length of 25 mm. According to the design results, the system was assembled, calibrated and tested. Aiming at solving the shortcomings of the current underwater hyperspectral system, such as the inability of real-time observation of the scanned image, large data volume and complicated processing, the upper computer software was designed and developed to realize the functions of controlling and adjusting the parameter, real-time displaying the scanned image, reconstructing the image and outputting the data in ENVI standard format to the underwater hyperspectral system. The prototype of the system was used to conduct coral detection experiments in Weizhou Island, and the neural network model was used to classify the experimental data, and the overall classification accuracy was above 98%. The experimental results show that the whole system has good imaging quality and good underwater detection capability, and the developed host computer software greatly reduces the workload of raw data processing, improves the experimental detection efficiency, and provides a feasible technical solution for underwater intelligent detection and analysis.

关键词： Machine intelligence Hyperspectral imaging Neural networks Hyperspectral data classification Offshore structures maintenance

来源：评论

学校读者我要写书评

暂无评论

A Power-efficient image Classifier using Neural Network with Pipelined FFT Architecture

TechRxiv

引用

TechRxiv 2023年

作者： Hai, Shafiqul Reddy, Tella Rajashekhar Department of Electrical and Computer Engineering Lakehead University BarrieON Canada

deep Neural Network (DNN) belongs to an important class of machine learning algorithms generally used to classify digital data in the form of image and speech recognition. The computational complexity of a DNN-based image classifier is higher than traditional fully connected (FC) feed-forward NNs. Therefore, dedicated cloud servers and Graphical Processor Units (GPU) are utilized to achieve high-speed and large-capacity computation tasks in machine vision systems. However, a growing demand exists for real-time processing of complex machine-learning tasks on embedded systems. As FC layers consume the highest fraction of computational power and memory footprint, innovating novel power-efficient and low-footprint NN architecture for embedded systems is crucial. A novel design strategy and algorithms are proposed in this article, where a power-efficient FC DNN is implemented using a pipelined and parallel Fast Fourier Transform (FFT) on a circular projection-based architecture. The footprint of the DNN is further reduced using a folded FFT network. The proposed algorithm is tested using two benchmark training set examples, the "MNIST database of handwritten digits" and the "CIFAR-10 database". In both cases, we achieved > 90% accuracy, while the power consumption of the network is 37% less than the traditional FFT architecture-based DNNs. © 2023, CC BY.

关键词： deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Vision Transformers for Brain Tumor Classification

Vision Transformers for Brain Tumor Classification

引用

15th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC) / 9th International Conference on Bioimaging (BIOIMAGING)

作者： Simon, Eliott Briassouli, Alexia Maastricht Univ Dept Data Sci & Knowledge Engn Maastricht Netherlands

ISBN: (纸本)9789897585524

With the increasing amount of data gathered by healthcare providers, interest has been growing in Machine learning, and more specifically in deep learning. Medical applications of machine learning range from the prediction of medical events, to computer-aided detection, diagnosis, and classification. This paper will investigate the application of State-of-the-Art (SoA) deep Neural Networks in classifying brain tumors. We distinguish between several types of brain tumors, which are typically diagnosed and classified by experts using Magnetic Resonance Imaging (MRI). The most common benign tumors are gliomas and meningiomas, however there exist many more which vary in size and location. Convolutional Neural Networks (CNN) are the SoA deep learning technique for image processing tasks such as image segmentation and classification. However, a recently developed architecture for image classification, namely Vision Transformers, have been shown to outperform classical CNNs in efficiency. while requiring fewer computational resources. This work introduces using only Transformer networks in brain tumor classification for the first time, and compares their performance with CNNs. A significant difference between the two models, tested in this manner, is the lack of translational equivariance in Transformers, which the CNNs already have. Experiments for brain tumor classification on benchmark real-world datasets show they can achieve comparable or better performance, despite using limited training data.

关键词： Brain Tumor Classification deep learning Vision Transformer Convolutional Neural Network

来源：评论

学校读者我要写书评

暂无评论

SMA: A Suitable-Matching Area Selection Dataset

SMA: A Suitable-Matching Area Selection Dataset

引用

Advanced Algorithms and Control Engineering (ICAACE), International Conference on

作者： Supeng Jiang Yunpeng Liu Depeng Zou Hengjia Qin Haibo Luo Key Laboratory of Opto-Electronic Information Processing Chinese Academy of Sciences Shenyang China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China Uuiversity of Chinese Academy of Sciences Beijing China The Third Military Representative Office of the Air Force Equipment Department in Shenyang Shenyang China

ISBN: (数字)9798350361445

ISBN: (纸本)9798350361452

Scene matching is a commonly used guidance technology in the final guidance stage of missiles. Suitable-matching area selection is the core technology of reference map preparation and one of the critical factors affecting the performance of the scene-matching system. Since there is no public dataset for scene-matching suitable area selection, it is difficult to compare related selection algorithms uniformly. In this paper, we analyze the scene categories that may be encountered in the scene-matching process and create a dataset SMA, which contains six scene types and various scene contents. This dataset can be used for matching performance analysis and evaluation of scene areas. We analyze the information content, stability, uniqueness, and significance of the images and conduct matching experiments by simulating real-time images to prove the matching performance of the calibration area.

关键词： deep learning Missiles image edge detection Stability analysis real-time systems Calibration Performance analysis

来源：评论

学校读者我要写书评

暂无评论

deep learning based CNN Model for Classification and Detection of Individuals Wearing Face Mask

arXiv

引用

arXiv 2023年

作者： Chinnaiyan, R. Iyyappan, M. Shariff, Al Raiyan A. Sai, Kondaveeti Mallikarjunaiah, B.M. Bharath, P. Department of Computer Science and Engineering Alliance University Bengaluru562106 India

In response to the global COVID-19 pandemic, there has been a critical demand for protective measures, with face masks emerging as a primary safeguard. The approach involves a two-fold strategy: first, recognizing the presence of a face by detecting faces, and second, identifying masks on those faces. This project utilizes deep learning to create a model that can detect face masks in real-time streaming video as well as images. Face detection, a facet of object detection, finds applications in diverse fields such as security, biometrics, and law enforcement. Various detector systems worldwide have been developed and implemented, with convolutional neural networks chosen for t heir superior performance accuracy and speed in object detection. Experimental results attest to the model's excellent accuracy on test data. The primary focus of this research is to enhance security, particularly in sensitive areas. The research paper proposes a rapid image preprocessing method with masks centred on faces. Employing feature extraction and Convolutional Neural Network, the system classifies and detects individuals wearing masks. The research unfolds in three stages: image pre-processing, image cropping, and image classification, collectively contributing to the identification of masked faces. Continuous surveillance through webcams or CCTV cameras ensures constant monitoring, triggering a security alert if a person is detected without a mask. © 2023, CC BY.

关键词： deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Adversarial Multi-Path Residual Network for image Super-Resolution

引用

IEEE TRANSACTIONS ON image processing 2021年 30卷 6648-6658页

作者： Wang, Qianqian Gao, Quanxue Wu, Linlu Sun, Gan Jiao, Licheng Xidian Univ State Key Lab Integrated Serv Networks Xian 710071 Peoples R China Xidian Univ Sch Telecommun Engn Key Lab Minist Educ Intellisense & Image Understanding Xian 710071 Peoples R China Xidian Univ State Key Lab ISN Xian 710071 Shaanxi Peoples R China Xidian Ningbo Informat Technol Inst Ningbo 315000 Peoples R China Huawei Consumer Business Grp Xian Peoples R China Chinese Acad Sci Shenyang Inst Automat State Key Lab Robot Shenyang 110016 Peoples R China Chinese Acad Sci Inst Robot & Intelligent Mfg Shenyang 110016 Peoples R China Xidian Univ Sch Artificial Intelligence Minist Educ Intellisense & Image Understanding Key Lab Xian 710071 Peoples R China

Recently, deep convolutional neural networks have demonstrated remarkable progresses on single image super-resolution (SR) problem. However, most of them use more deeper and wider networks to improve SR performance, which is not practical in real-world applications due to large complexity, high computation cost, and low efficiency. In addition, they cannot provide high perception quality and guarantee objective quality simultaneously. To address these limitations, we in this paper propose a novel Adversarial Multi-path Residual Network (AMPRN), which can largely suppress the number of network parameters and achieve a higher SR performance compared with the state-of-the-art methods. More specifically, we propose a multi-path residual block (MPRB) for multi-path residual network (MPRN) with fewer network parameters, which can extract abundant local features by fully using features from different paths generated by channel slices. These hierarchical features from all the MPRBs are then jointly aggregated by global gradual feature fusion. Following MPRN, we construct an adversarial gradient network with a gradient loss to make the gradient distribution of the generated SR images and ground truth image closer. In this way, the generated SR images of our model can provide high perception quality and objective quality. Finally, several experimental results demonstrate that our AMPRN achieves better performance in comparison with fewer parameters than the state-of-the-art methods.

关键词： Feature extraction Residual neural networks Superresolution Generative adversarial networks image reconstruction Generators Training Single image super-resolution (SISR) residual learning deep convolutional neural network

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：