检索结果-内蒙古大学图书馆

deepVision: Enhanced Drone Detection and Recognition in Visible imagery through deep learning Networks

SENSORS 2023年第21期23卷 8711-8711页

作者： Al Dawasari, Hassan J. Bilal, Muhammad Moinuddin, Muhammad Arshad, Kamran Assaleh, Khaled King Abdulaziz Univ Elect & Comp Engn Dept Jeddah 21589 Saudi Arabia King Abdulaziz Univ Ctr Excellence Intelligent Engn Syst Jeddah 21589 Saudi Arabia Ajman Univ Coll Engn & Informat Technol Dept Elect & Comp Engn Ajman 346 U Arab Emirates Ajman Univ Artificial Intelligence Res Ctr Ajman 346 U Arab Emirates

Drones are increasingly capturing the world's attention, transcending mere hobbies to revolutionize areas such as engineering, disaster aid, logistics, and airport protection, among myriad other fascinating applications. However, there is growing concern about the risks that they pose to physical infrastructure, particularly at airports, due to potential misuse. In recent times, numerous incidents involving unauthorized drones at airports disrupting flights have been reported. To solve this issue, this article introduces an innovative deep learning method proposed to effectively distinguish between drones and birds. Evaluating the suggested approach with a carefully assembled image dataset demonstrates exceptional performance, surpassing established detection systems previously proposed in the literature. Since drones can appear extremely small compared to other aerial objects, we developed a robust image-tiling technique with overlaps, which showed improved performance in the presence of very small drones. Moreover, drones are frequently mistaken for birds due to their resemblances in appearance and movement patterns. Among the various models tested, including SqueezeNet, MobileNetV2, ResNet18, and ResNet50, the SqueezeNet model exhibited superior performance for medium area ratios, achieving higher average precision (AP) of 0.770. In addition, SqueezeNet's superior AP scores, faster detection times, and more stable precision-recall dynamics make it more suitable for real-time, accurate drone detection than the other existing CNN methods. The proposed approach has the ability to not only detect the presence or absence of drones in a particular area but also to accurately identify and differentiate between drones and birds. The dataset utilized in this research was obtained from a real-world dataset made available by a group of universities and research institutions as part of the 2020 Drone vs. Bird Detection Challenge. We have also tested the performance of the pr

关键词： artificial intelligence classification drones detection transfer learning deep learning

来源：评论

学校读者我要写书评

暂无评论

Road Condition Detection using Adaptively Chosen deep learning Model and Precautionary Special-Guidance for Driver-Safety 5

Road Condition Detection using Adaptively Chosen Deep Learni...

引用

5th International Conference on Electronics, Materials Engineering and Nano-Technology, IEMENTech 2021

作者： Billah, Md Masum Chattaraj, Nilanjan National Institute of Technology Durgapur Department of Electronics And Communication Engineering Durgapur India

ISBN: (纸本)9781665418034

An integrated pattern recognition model is proposed through a comparative study of image processing and various deep learning algorithms to surmount the fatal accidents due to potholes, broken roads, speed breakers. By processing images of the road in real-time and considering the values in the speedometer the system aims to choose the appropriate model among ResNet50, EfficientNet B7, VGG16 and AlexNet assessing the trade-off between the model-efficiency and prediction-time complexity. This adaptive selection process of DL algorithms with the vehicle's speed is adopted to emphasize the human-safety. The classified bad roads will also be flagged with a dynamic time-dependent variable associated to the number of vehicles passing through that road and the GPS locations of the road map. This integrated model not only can suggest precautionary warning in real time in the day time, but also during the night, foggy or hazy weather when visual limitation takes place. © 2021 IEEE.

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

image processing Technique for Tracking and Counting of Vehicles Using ROI

Image Processing Technique for Tracking and Counting of Vehi...

引用

International Conference on Power Energy, Environment and Intelligent Control (PEEIC)

作者： Ankit Kumar Ritika Chandel Monika Singh Apex Institute of Technology Chandigarh University Mohali India

This research paper presents a novel approach for vehicle tracking and counting utilizing the advanced object detection model YOLOv8 in the field of image processing. The accurate monitoring of vehicular traffic is crucial for various applications, including traffic management, urban planning, and safety analysis. Existing methods often struggle with real-time tracking and counting of vehicles due to challenges such as occlusions, varying lighting conditions, and complex traffic scenarios. In our proposed methodology, we leverage the power of YOLOv8, a deep learning-based object detection model, uses real-time detection to identify and monitor vehicles, ensuring high accuracy and robustness in various traffic environments. The proposed approach provides a valuable tool for traffic management authorities and urban planners, offering precise data for traffic flow analysis and infrastructure development.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A deep learning method for kidney segmentation in 2D ultrasound images 44

A deep learning method for kidney segmentation in 2D ultraso...

引用

44th Annual International Conference of the IEEE-Engineering-in-Medicine-and-Biology-Society (EMBC)

作者： Valente, Simao Morais, Pedro Torres, Helena R. Oliveira, Bruno Gomes-Fonseca, Joao Buschle, L. R. Fritz, A. Correia-Pinto, Jorge Lima, Estevao Vilaca, Joao L. IPCA 2Ai Sch Technol Barcelos Portugal Univ Minho Sch Med Life & Hlth Sci Res Inst ICVS Braga Portugal ICVS 3Bs PT Govt Associate Lab Braga Portugal Univ Minho Algoritmi Ctr Sch Engn Guimaraes Portugal Karl Storz SE & Co KG Tuttlingen Germany

ISBN: (数字)9781728127828

ISBN: (纸本)9781728127828

Ultrasound (US) is a medical imaging modality widely used for diagnosis, monitoring, and guidance of surgical procedures. However, the accurate interpretation of US images is a challenging task. Recently, portable 2D US devices enhanced with Artificial intelligence (AI) methods to identify, in real-time, specific organs are widely spreading worldwide. Nevertheless, the number of available methods that effectively work in such devices is still limited. In this work, we evaluate the performance of the U-NET architecture to segment the kidney in 2D US images. To accomplish this task, we studied the possibility of using multiple sliced images extracted from 3D US volumes to achieve a large, variable, and multi-view dataset of 2D images. The proposed methodology was tested with a dataset of 66 3D US volumes, divided in 51 for training, 5 for validation, and 10 for testing. From the volumes, 3792 2D sliced images were extracted. Two experiments were conducted, namely: (i) using the entire database (WWKD);and (ii) using images where the kidney area is > 500 mm2 (500KD). As a proof-of-concept, the potential of our strategy was tested in real 2D images (acquired with 2D probes). An average error of 2.88 +/- 2.63 mm in the testing dataset was registered. Moreover, satisfactory results were obtained in our initial proof-of-concept using pure 2D images. In short, the proposed method proved, in this preliminary study, its potential interest for clinical practice. Further studies are required to evaluate the real performance of the proposed methodology.

关键词： deep learning Training image segmentation Three-dimensional displays Ultrasonic imaging Task analysis Probes

来源：评论

学校读者我要写书评

暂无评论

deep neural network: Trains to pinpoint microseismic events in real time

引用

JPT, Journal of Petroleum Technology 2021年第3期73卷 31-33页

作者： Szymczak, Pat Davis JPT Contributing Editor

real-time analysis of microseismic events using data gathered during hydraulic fracturing can give engineers critical feedback on whether a particular fracturing job has achieved its goal of increasing porosity and permeability and boosting stimulated reservoir volume (SRV). Currently, no perfect way exists to understand clearly if a fracturing operation has had the intended effect. Engineers collect data, but the methods used to gather it, manually sort it, and analyze it provide an inconclusive picture of what really is happening underground. Daniel Stephen Wamriew, a PhD candidate at the Skolkovo Institute of Science and Technology (Skoltech) in Moscow, said he believes this can change with advances in artificial intelligence and machine learning that can enhance accuracy in determining the location of a microseismic event while obtaining stable source mechanism solutions, all in real time. Wamriew presented his research at the 2020 SPE Russian Petroleum Technology Conference in Moscow in October in paper SPE 201925, “deep Neural Network for real-time Location and Moment Tensor Inversion of Borehole Microseismic Events Induced by Hydraulic Fracturing.”The paper’s coauthors included Marwan Charara, Aramco Research Center, and Evgenii Maltsev, Skolkovo Institute of Science and Technology. Skoltech is a private institute established in 2011 as part of a multiyear partnership with the Massachusetts Institute of Technology.“People in the field mainly want to know if they created more fractures and if the fractures are connected,” Wamriew explained in a recent interview with JPT. “So, we need to know where exactly the fractures are, and we need to know the orientation (the source mechanism).”It Starts With Data “Usually, when you do hydraulic fracturing, a lot of data comes in,” Wamriew said. “It is not easy to analyze this data manually because you have to choose what part of the data you deal with, and, in doing that, you might leave out some necessary data that the

关键词： machine learning neural network microseismic event hydraulic fracturing information operation source mechanism fracture artificial intelligence upstream oil & gas Hydraulic Fracturing Information Management and Systems Neural networks Reservoir Characterization Seismic processing and interpretation

来源：评论

学校读者我要写书评

暂无评论

Optimized Methods for Online Monitoring of L-Glutamic Acid Crystallization

Optimized Methods for Online Monitoring of L-Glutamic Acid C...

引用

2021 International Conference on Signal processing and Machine learning, CONF-SPML 2021

作者： Yang, Timing Jiang, Chen Meng, Qi Dalian University of Technology School of Information and Communication Engineering Dalian China Dalian University of Technology School of Control Science and Engineering Dalian China

ISBN: (纸本)9781665417341

In order to monitor the crystallization process of L-glutamic acid online, a real-time detection method based on non-invasive image analysis has been proposed to obtain in-situ images, and a deep-learning based network Mask R-CNN is applied to detect target crystals in images. Considering deep-learning network requires an enormous amount of dataset with labelled region of interest (RoI) samples, this paper proposes semi-automatic labelling methods to reduce human work when generating the dataset. By applying another Mask R-CNN for labelling the dataset, human work can be reduced from labelling the whole dataset to filtering the detection results of the labeller Mask R-CNN. The final detection results prove the feasibility of this method. The proposed method is also proved to be more feasible and reliable than transfer learning. © 2021 IEEE.

关键词： deep learning

来源：评论

学校读者我要写书评

暂无评论

real time Protein Crystal Monitoring System 7

Real Time Protein Crystal Monitoring System

引用

7th IEEE International conference for Convergence in Technology, I2CT 2022

作者： Sengar, Ratnesh S Sharma, Rohit Madhusoodanan, K. Das, Amit Bhabha Atomic Research Centre Division of Remote Handling & Robotics Mumbai India Bhabha Atomic Research Centre Radiation Biology and Health Sceince Division Mumbai India

ISBN: (纸本)9781665421683

High-resolution crystal structures of the biological macromolecules (protein, DNA, RNA or their complexes) are essential for understanding their biological functions and causes of diseases at a molecular level. X-ray crystallographic technique gives the atomic positions of these biological macromolecules and decodes the intermolecular interactions between protein-drug, protein-protein, protein-nucleic acids which are crucial for rational drug design. To aid the macromolecular crystallization experiments, we have indigenously developed automated system, called real time Protein Crystal Monitoring System (RT-PCMS) for crystal imaging and to monitor the progress of protein crystal growth during crystallization. RT-PCMS images crystallization drops at frequent time intervals in 24- or 96-well crystallization plate formats. The system consists of precise robotics motion and a custom designed motorized microscopic imaging system, capturing multi-focus composite images of protein crystals in droplets in multiple wells. In a typical successful trial, the crystallization drop comprises protein crystals of size 20 to 300 microns located at the different regions of an elliptical droplet. We have implemented powerful image processing and deep learning algorithms in this system, fusing multi-depth crystal images within a crystallization drop and classification into different crystallization stages. The system is controlled through a personal computer that provides a custom developed graphical user interface software for visualization of all captured images at different crystallization stages and record the results of crystal formation. © 2022 IEEE.

关键词： image fusion

来源：评论

学校读者我要写书评

暂无评论

Review on computer vision-based crack detection and quantification methodologies for civil structures

引用

CONSTRUCTION AND BUILDING MATERIALS 2022年 356卷

作者： Deng, Jianghua Singh, Amardeep Zhou, Yiyi Lu, Ye Lee, Vincent Cheng-Siong Changzhou Inst Technol Sch Civil Engn & Architecture Dept Struct Engn Changzhou 213032 Peoples R China Tongji Univ Dept Struct Engn Shanghai 200092 Peoples R China Monash Univ Dept Civil Engn Melbourne Australia Monash Univ Fac Informat Technol Melbourne Australia

Computer vision-based crack analysis for civil infrastructure has become popular to automatically process in-spection imaging data for crack detection, localisation and quantification. Some literature reviews have been conducted, which mostly focus on qualitative damage evaluation or damage segmentation, missing the meth-odology categorisation for applicability-oriented quantitative crack assessment. To fill the gap, this review provides a comprehensive overview of state-of-the-art image-based crack analysis under various conditions in both qualitative and quantitative aspects, particularly focusing on image processing and deep learning-based methodologies from image-level detection to pixel-level segmentation and quantification. The key challenges and research gaps are also discussed as follows, which indicate the importance of future research: (1) developing data model methodologies to resolve the difficulties due to the image data deficiency;(2) building a learning -based model capable of processing data with complex backgrounds;(3) enhancing the scene generalisation on different detection tasks;(4) establishing a lightweight mechanism for real-time crack analysis;(5) constructing learning-based systems that comprehend the local and global contexts during crack evaluation;(6) developing a semi-supervised mechanism for more information capturing and (7) establishing attention-based models for enhanced segmentation performance.

关键词： image processing techniques Structural health monitoring Crack detection and quantification deep learning image segmentation

来源：评论

学校读者我要写书评

暂无评论

Embedded Hyperspectral Band Selection with Adaptive Optimization for image Semantic Segmentation

arXiv

引用

arXiv 2024年

作者： Zimmer, Yaniv Glickman, Oren Computer Science Department Bar-Ilan University

The selection of hyperspectral bands plays a pivotal role in remote sensing and image analysis, with the aim of identifying the most informative spectral bands while minimizing computational overhead. This paper introduces a pioneering approach for hyperspectral band selection that offers an embedded solution, making it well-suited for resource-constrained or real-time applications. Our proposed method, embedded hyperspectral band selection (EHBS), excels in selecting the best bands without needing prior processing, seamlessly integrating with the downstream task model. This is achieved through stochastic band gates along with an approximation of the l0 norm on the number of selected bands as the regularization term and the integration of a dynamic optimizer, DoG, which removes the need for the required tuning of the learning rate. We conduct experiments on two distinct semantic-segmentation hyperspectral benchmark datasets, demonstrating their superiority in terms of accuracy and ease of use compared to many common and state-of-the-art methods. Furthermore, our contributions extend beyond hyperspectral band selection. Our approach’s adaptability to other tasks, especially those involving grouped features, opens promising avenues for broader applications within the realm of deep learning, such as feature selection for feature groups. © 2024, CC BY.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Fusing multi-source quality statistical data for construction risk assessment and warning based on deep learning

引用

KNOWLEDGE-BASED SYSTEMS 2024年 284卷

作者： Gao, Binwei Ma, Zhehao Gu, Jianan Han, Xueqiao Xiang, Ping Lv, Xiaoyue Xiamen Univ Sch Architecture & Civil Engn Xiamen Peoples R China Cent South Univ Sch Civil Engn Natl Engn Lab High Speed Railway Construction Tech Changsha 410075 Peoples R China Karlsruhe Inst Technol KIT Dept Elect Engn & Informat Technol Karlsruhe Germany Wuhan Univ Sch Civil Engn Wuhan Peoples R China

In the context where accidents and fatalities in the construction industry remain persistently high, the assessment and early warning of construction risks become critically imperative. However, existing research has not fully leveraged the multi-source construction quality statistical data available, leading to a hindrance in formulating data-driven effective risk warning strategies. Considering the urgent need for optimized risk identification and assessment methods, this study introduced a novel risk assessment and warning strategy for comprehensive processing of multi-source construction practical quality monitoring statistical data based on cloud model-optimized Dempster-Shafer (D-S) evidence theory. This method employed 4M1E for monitoring data categori-zation and integrated a deep learning prediction model based on Long Short-Term Memory (LSTM) for fore-casting potential quality monitoring data. Subsequently, the combination of the cloud model and D-S evidence theory facilitated the transformation of LSTM-predicted multi-source quality data between quantitative and qualitative, enabling comprehensive risk assessment and warning considerations. The findings revealed that the prediction results and the actual data were both at the highest level, indicating a high likelihood of a collapse incident. Lastly, the developed BIM-integrated platform offered a dynamic approach to risk assessment and real -time control, serving as a potential reference for warning risks in construction. This study is a pioneering study to assess and predict risk by cohesively integrating various methods and realizing a practical BIM platform. This study not only provides new measures to mitigate risks in construction but also advocates for the wider inte-gration of multi-source quality statistical data into risk management.

关键词： LSTM deep learning D-S evidence theory Multi-source quality statistical data Risk assessment and prediction

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：