检索结果-内蒙古大学图书馆

Pavement Distress Detection Using image processing from Unmanned Aerial vehicle Data

Pavement Distress Detection Using Image Processing from Unma...

International Conference on Innovative Methods and Practical Applications for Cognizant Transportation systems, IMPACTS 2023

作者： Manjusha, M. Rudhra, A. Sunitha, v. Department of Civil Engineering National Institute of Technology Tiruchirappalli India

ISBN: (纸本)9789819772995

The scale of public roads, particularly highways, has rapidly increased in many nations over the last few decades. To increase the road’s usability and thus its social and economic benefits, road maintenance has received more attention lately. Road inspections were done manually, the old-fashioned way takes a lot of time, and work, and is subjective. For proper road maintenance, deteriorated roads must be repaired as quickly as possible. Therefore, there is an urgent need for high-performance, low-cost technology to identify road surface distress. Unmanned aerial vehicles (UAvs), on the other hand, are an exciting option for monitoring the status of roads. They have the benefits of great flexibility, cheap cost, and simple agility. The data was collected in a 5 km road stretch of NH-336, Tamil Nadu. In this study, some of the computer vision tools including OpenCv, CUDA, etc. are tried to detect and localize the distress. It includes the detection and classification of pavement distress by using Object detection algorithms like Faster RCNN, Yolov3, and Yolov4 were used for detection and classification of road distresses. The main focus is on the detection and classification of potholes and cracks. Local road authorities and communities can benefit from this system to evaluate the state of their road network pavement in real-time. The application of deep learning techniques in transportation engineering problems is very rare. This study makes an effort to use deep learning techniques in the classification of the distresses and localizing them. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Unmanned aerial vehicles (UAv)

来源：评论

学校读者我要写书评

暂无评论

Sign Language Translation Using image processing to Audio Conversion

Sign Language Translation Using Image Processing to Audio Co...

引用

IEEE International Conference on Intelligent Techniques in Control, Optimization and Signal processing (INCOS)

作者： v Subashini B Someshwaran S Sowmya S Ashwin Kumar Department of Electronics and Communication Engineering Rajalakshmi Institute of Technology Chennai India

ISBN: (数字)9798350361186

ISBN: (纸本)9798350361193

Sign language has long been a fundamental mode of communication for deaf and mute individuals, serving as a crucial tool for inclusivity and interaction. Nonetheless, communication barriers persist as many individuals outside of these communities struggle to comprehend and utilize sign language effectively. A ground-breaking system known as hand gesture recognition using image processing to audio conversion has emerged to address this issue. This innovative system aims to develop an application capable of translating sign language and hand gestures into text and audio, thereby facilitating communication between deaf and mute individuals and the wider society. This system enables the detection and classification of hand gestures by employing computer vision techniques, such as CNN algorithms for image processing and the MediaPipe framework for hand gesture identification in real-time video streams. Subsequently, the system utilizes audio signals to provide immediate feedback by converting the detected gestures into corresponding sounds. The feature extraction CNN algorithm is implemented in Python, while the execution takes place on a Raspberry Pi connected to an external camera utilizing OpenCv libraries. Through this comprehensive approach, the system endeavours to bridge the communication gap and enhance the inclusion of deaf and mute individuals in various social settings.

关键词： Sign language image recognition Signal processing algorithms Streaming media Signal processing Libraries Real-time systems

来源：评论

学校读者我要写书评

暂无评论

CNN Ensembles for Nuclei Segmentation on Histological images of OED 36

CNN Ensembles for Nuclei Segmentation on Histological Images...

引用

36th IEEE International Symposium on Computer-Based Medical systems (CBMS)

作者： Silva, Adriano B. Rozendo, Guilherme B. Tosta, Thaina A. A. Martins, Alessandro S. Loyola, Adriano M. Cardoso, Sergio v. Lumini, Alessandra Neves, Leandro A. de Faria, Paulo R. do Nascimemo, Marcelo Z. Univ Fed Uberlandia Fac Comp Sci Uberlandia Brazil Sao Paulo State Univ Dept Comp Sci & Stat DCCE Sao Paulo Brazil Univ Fed Sao Paulo Inst Sci & Technol Sao Paulo Brazil Fed Inst Triangulo Mineiro Uberaba Brazil Univ Fed Uberlandia Sch Dent Area Oral Pathol Uberlandia Brazil Univ Bologna Dept Comp Sci & Engn DISH Bologna Italy Univ Fed Uberlandia Inst Biomed Sci Dept Histol & Morphol Uberlandia Brazil

ISBN: (纸本)9798350312249

Early diagnosis of potentially malignant disorders, such as oral epithelial dysplasia (OED), is the most reliable way to prevent oral cancer. Computational algorithms have been used as a tool to aid specialists in this process. In recent years, CNN-based methods have gained more attention due to their improved results in nuclei segmentation tasks. Despite these relevant results, achieving high segmentation accuracy remains a challenging task. In this paper, we propose an ensemble of segmentation models to improve the performance of nuclei segmentation in OED histopathology images. The proposed ensemble consists of four CNN segmentation models, which were combined using three ensemble strategies: simple averaging, weighted averaging and majority voting, achieved accuracy of 90.69%, 90.70% and 88.49%, respectively, when applied to OED images. The model's performance was also evaluated on three publicly available datasets and achieved comparable performance to state-of-the-art segmentation methods. These values indicate that the proposed ensemble methods can be used in medical image analysis applications.

关键词： Oral Epihtelial Dysplasia Nuclei Segmentation Histological image processing CNN Ensemble

来源：评论

学校读者我要写书评

暂无评论

Advanced E-Commerce Trend Prediction Software

Advanced E-Commerce Trend Prediction Software

引用

image processing and Capsule Networks (ICIPCN), International Conference on

作者： P. Megaladevi D Rojaramani S. Kaliappan B v Santhosh Krishna S. Muthumanickam D Rajababu Management Studies Jai Shriram Engineering College Tirupur Tamilnadu India Computer Science and Engineering New Horizon College of Engineering Bangalore Karnataka India Department of Mechanical Engineering AMITY University Dubai United Aram Emirates Electronics and Communication Engineering RMK College of Engineering and Technology Chennai Tamilnadu India Department of Electrical and Electronics Engineering SR University Warangale Telangana India

ISBN: (数字)9798350367171

ISBN: (纸本)9798350367188

In the modern-era of technology, there is an immense boom of e-commerce business and e-commerce powered SAAS. It includes building robust services and good exchange with the internet. Therefore, the Recommendation systems can reorganize and restructure the overload of information based on the filtering and bifurcation methods. This research study will illustrate a comprehensive Literature Survey regarding the published articles in the field of e-commerce recommendation systems, which will help the researchers and Software Engineers to do future work. This study has provided varieties of traditional techniques to build such recommendation systems and the challenges faced during creating such recommendation systems. This study has analyzed different recommendation algorithms and a potentially improved model is proposed. Building the Recommendation system is a challenging task, as it involves the problems of data sparsity and scalability requirements. Recommendation systems are crucial for E-commerce business, it provides personalized recommendations to the customer. Software Engineers and researchers can play a vital role in building and improving such recommendation systems by understanding its traditional techniques, challenges and future directions.

关键词： Machine learning algorithms Buildings Predictive models Prediction algorithms Electronic commerce Forecasting Recommender systems

来源：评论

学校读者我要写书评

暂无评论

An Intelligent video Surveillance System for Human Behavior

引用

SCIENTIFIC AND TECHNICAL INFORMATION processing 2021年第5期48卷 388-397页

作者： Ulyev, A. D. Rozaliev, v. L. Zaboleeva-Zotova, A., v Orlova, Y. A. Volgograd State Tech Univ Volgograd Russia

This paper describes an intelligent video surveillance system for human behavior and provides a brief overview of systems with similar functional characteristics. We present a collection of methods and algorithms for automatic recognition of human images, their identification, and analysis of behavior based on motor activity using a cascade of neural networks. A technology for capturing a person's image and tracking their movements between video cameras is proposed.

关键词： video image human posture recognition motor activity behavior monitoring intelligent system artificial neural networks

来源：评论

学校读者我要写书评

暂无评论

RISC-v Architecture based Hardware Accelerator for kNN

RISC-V Architecture based Hardware Accelerator for kNN

引用

International Conference on Circuits, Communication, Control and Computing

作者： Shreya P Manchala Shreeya Ranganath v. Anandi Shreesha T P Satwik Kamath Soham Bhattacharya Ramaiah Institute of Technology Rowan University USA

ISBN: (数字)9798331528539

ISBN: (纸本)9798331528546

The demand for smarter devices has pushed embedded systems to their limits, particularly in computationally intensive tasks like image recognition and natural language processing. Hardware accelerators have emerged as a solution, offering significant performance and energy efficiency gains. However, traditional accelerators tied to specific processor architectures suffer from limitations like reduced flexibility and vendor lock-in. This project proposes a hardware accelerator for the K-Nearest Neighbor (kNN) algorithm, leveraging the open-source RISC-v architecture. RISC-v addresses the computational complexity, performance bottlenecks, and energy efficiency challenges of existing kNN implementations. The accelerator is designed with key features such as a customized instruction set, parallelism, pipelining, reduced power consumption, and optimized area utilization. The project aims for efficient use of flip-flops (FFs) and look-up tables (LUTs), ensuring optimal resource *** utilizing RISC-v's flexibility, this project aims to create an efficient hardware accelerator for kNN, enabling real-time processing of large datasets, minimizing energy use, and ensuring scalability across different applications.

关键词： Performance evaluation Machine learning algorithms Power demand Embedded systems Heuristic algorithms Computer architecture Real-time systems Energy efficiency Table lookup Hardware acceleration

来源：评论

学校读者我要写书评

暂无评论

A DEEP LEARNING APPROACH LUNG SEGMENTATION AND PNEUMONIA DETECTION FROM X-RAYS 1

A DEEP LEARNING APPROACH LUNG SEGMENTATION AND PNEUMONIA DET...

引用

1st International Conference on Recent Trends in Microelectronics, Automation, Computing and Communications systems, ICMACC 2022

作者： Rao, Y. Chalapathi Lavanya, P. Reddy, v. Sagar Kumar, v. Naveen Department of Ece Vnr Vjiet Telangana Hyderabad India Department of Ece Mlritm Telangana Hyderabad India

ISBN: (纸本)9781665496049

Lung segmentation is a process of detection and identification of lung cancer and pneumonia with the help of image processing techniques. Deep learning algorithms can be incorporated to build the computer-aided diagnosis (CAD) system for detecting or recognizing broad objects like acute respiratory distress syndrome (ARDS), Tuberculosis, Pneumonia, Lung cancer, Covid, and several other respiratory diseases. This paper presents pneumonia detection from lung segmentation using deep learning methods on chest radiography. Chest X-ray is the most useful technique among other existing techniques, due to its lesser cost. The main drawback of a chest x-ray is that it cannot detect all problems in the chest. Thus, implementing convolutional neural networks (CNN) to perform lung segmentation and to obtain correct results. The 'lost' regions of the lungs are reconstructed by an automatic segmentation method from raw images of chest X-ray. © 2022 IEEE.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Automatic Detection and Counting System for Pavement Cracks Based on PCGAN and YOLO-MF

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION systems 2022年第11期23卷 22166-22178页

作者： Ma, Duo Fang, Hongyuan Wang, Niannian Zhang, Chao Dong, Jiaxiu Hu, Haobang Zhengzhou Univ Coll Water Conservancy & Engn Zhengzhou 450001 Peoples R China Natl Local Joint Engn Lab Major Infrastruct Testi Zhengzhou 450001 Peoples R China Collaborat Innovat Ctr Water Conservancy & Transp Zhengzhou 450001 Henan Peoples R China

The regular detection of pavement cracks is critical for life and property security. However, existing deep learning-based methods of crack detection face difficulties in terms of data acquisition and defect counting. An automatic intelligent detection and tracking system for pavement cracks is proposed. Our system is formed of a pavement crack generative adversarial network (PCGAN) and a crack detection and tracking network called YOLO-MF. First, PCGAN is used to generate realistic crack images, to address the problem of the small number of available images. Next, YOLO-MF is developed based on an improved YOLO v3 modified by an acceleration algorithm and median flow (MF) algorithm to count the number of cracks. In a counting loop, our improved YOLO v3 detects cracks and the MF algorithm tracks the cracks detected in a video. This improved algorithm achieves the best accuracy of 98.47% and F1 score of 0.958 among other algorithms, and the precision-recall curve was close to the top right. A tiny model was developed and an acceleration algorithm was applied, which improved the detection speed by factors of five and six, respectively. In on-site measurement, three cracks were detected and tracked, and the total count was correct. Finally, the system was embedded in an intelligent device consisting of a calculating module, an automated unmanned aerial vehicle, and other components.

关键词： Autonomous aerial vehicles Graphics processing units Generative adversarial networks Roads Real-time systems Deep learning image edge detection Portable detection system unmanned aerial vehicle (UAv) pavement cracks generative adversarial network (GAN) crack tracking and counting

来源：评论

学校读者我要写书评

暂无评论

Implementation of Automated Forest Fire Detection System using IoT

Implementation of Automated Forest Fire Detection System usi...

引用

Applied Artificial Intelligence and Computing (ICAAIC), International Conference on

作者： S Sujitha Harshika M Disha Aamna Nafiza v Hemavathi Department of EEE New Horizon College of Engineering Bengaluru India

ISBN: (数字)9798350375190

ISBN: (纸本)9798350375206

Forest fires pose a significant threat to ecosystems and wildlife, exacerbating global warming and environmental degradation. The contemporary challenge lies in the difficulty of timely detection by modern organizations. In response, the development of an automated forest fire detection system becomes imperative. The system involves the integration of various technologies, including Arduino microcontrollers, cameras, smoke detectors, flame detectors, and image processing algorithms. When a fire is detected, the system promptly sends alert messages to nearby forest departments, facilitating rapid response and mitigation efforts. This research work explores the design, implementation, and functionality of such an automated forest fire detection system, emphasizing the role of each component in enhancing the overall efficacy of early fire detection. The integration of Arduino technology, coupled with advanced sensors and image processing, exemplifies a multidimensional approach to addressing the pressing issue of forest fires.

关键词： Wildfires image processing Wildlife Prototypes Forestry Cameras Climate change Smoke detectors Global warming Environmental monitoring Autonomous systems Microcontrollers image sensors Alarm systems Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Fast Generation of Custom Floating-Point Spatial Filters on FPGAs

引用

IEEE ACCESS 2024年 12卷 167059-167071页

作者： Campos, Nelson Edirisinghe, Eran Chesnokov, Slava Larkin, Daniel ARM Ltd Manchester M1 3HU England Keele Univ Sch Comp Sci & Math Keele ST5 5BG England Imaging CV Ltd London EC1V 9BD England

Convolutional Neural Networks (CNNs) have been utilised in many image and video processing applications. The convolution operator, also known as a spatial filter, is usually a linear operation, but this linearity compromises essential features and details inherent in the non-linearity present in many applications. However, due to its slow processing, the use of a nonlinear spatial filter is a significant bottleneck in many software applications. Further, due to their complexity, they are difficult to accelerate in FPGA or vLSI architectures. This paper presents novel FPGA implementations of linear and nonlinear spatial filters. More specifically, the arithmetic computations are carried out in custom floating-point, enabling a tradeoff of precision and hardware compactness, reducing algorithm development time. Further, we show that it is possible to process video at a resolution of 1080p with a frame rate of 60 frames per second, using a low-cost FPGA board. Finally, we show that using a domain-specific language will allow the rapid prototyping of image processing algorithms in custom floating-point arithmetic, allowing non-experts to quickly develop real-time video processing applications.

关键词： Streaming media Field programmable gate arrays Hardware Convolution Spatial filters Mathematical models Kernel Real-time systems Fast Fourier transforms Domain-specific language embedded video processing floating-point arithmetic FPGA real-time real-time

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：