检索结果-内蒙古大学图书馆

13th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2022

作者： Naik, Praveen M. Rudra, Bhawana Department of Information Technology National Institute of Technology Karnataka Surathkal Mangaluru575025 India

ISBN: (纸本)9781713857938

real time detection of flowers based on their growth cycle is called as phenotype. It is one of the most important methods for judging the maturity of flowers and to estimate their yield. Traditional method involves flower detection and classification of varied species. In this paper, we introduce a new dataset based on flower phenotype. The dataset has images of flowers, classified into bud, fresh and stale. The work will help for identification and localization of classes based on flower phenotype. The detection of flowers at various stages of their life will be more important to harvesting in floriculture field. We propose a state of art deep learning-based approach using YOLOV5 model is used for identifying flowers based on flower phenotype. The images are subsequently augmented using rotation transformation, color balance transformation, brightness transformation and blur processing. The augmented images are used for preparing training sets. Using different versions of YoloV5 the flower image dataset is trained and tested. Primarily, flower phenotype considered has stages like bud formation, blossoming and stale flower. © Grenze Scientific Society, 2022.

关键词： deep learning

来源：评论

学校读者我要写书评

暂无评论

A universal method for solar filament detection from Hα observations using semi-supervised deep learning

引用

ASTRONOMY & ASTROPHYSICS 2024年第/06期686卷

作者： Diercke, Andrea Jarolim, Robert Kuckein, Christoph Manrique, Sergio J. Gonzalez Ziener, Marco Veronig, Astrid M. Denker, Carsten Poetzi, Werner Podladchikova, Tatiana Pevtsov, Alexei A. Inst Sonnenphys KIS Georges Kohler Allee 401 D-79110 Freiburg Germany Natl Solar Observ NSO 3665 Discovery Dr Boulder CO 80303 USA Leibniz Inst Astrophys Potsdam AIP Sternwarte 16 D-14482 Potsdam Germany Univ Potsdam Inst Phys & Astron Karl Liebknecht Str 24-25 D-14476 Potsdam Germany Karl Franzens Univ Graz Inst Phys Univ Platz 5 A-8010 Graz Austria High Altitude Observ HAO 3090 Ctr Green Dr Boulder CO 80301 USA Inst Astrofis Canarias IAC Via Lactea s-n San Cristobal la Laguna 38205 Tenerife Spain Univ La Laguna Dept Astrofis San Cristobal la Laguna 38205 Tenerife Spain Max Planck Inst Sonnensystemforsch Justus Von Liebig Weg 3 D-37077 Gottingen Germany Slovak Acad Sci Astron Inst Tatranska Lomnica 05960 Slovakia Appl AI Co Ltd AAICO C11-Bldg 2 Al Khaleej StAl MuntazahZone 1 Abu Dhabi U Arab Emirates Graz Univ Kanzelhohe Observ Solar & Environm Res Kanzelhohe 19 A-9521 Treffen Am Ossiacher Se Austria Skolkovo Inst Sci & Technol Bolshoy Blvd 30 Bld 1 Moscow 121205 Russia

Filaments are omnipresent features in the solar atmosphere. Their location, properties, and time evolution can provide important information about changes in solar activity and assist in the operational space weather forecast. Therefore, filaments have to be identified in full-disk images and their properties extracted from these images, but manual extraction is tedious and too time-consuming, and extraction with morphological image processing tools produces a large number of false positive detections. Automatic object detection, segmentation, and extraction in a reliable manner would allow for the processing of more data in a shorter time frame. The Chromospheric Telescope (ChroTel;Tenerife, Spain), the Global Oscillation Network Group (GONG), and the Kanzelh & ouml;he Observatory for Solar and Environmental Research (KSO;Austria) provide regular full-disk observations of the Sun in the core of the chromospheric H alpha absorption line. In this paper, we present a deep learning method that provides reliable extractions of solar filaments from H alpha filtergrams. First, we trained the object detection algorithm YOLOv5 with labeled filament data of ChroTel H alpha filtergrams. We used the trained model to obtain bounding boxes from the full GONG archive. In a second step, we applied a semi-supervised training approach where we used the bounding boxes of filaments to train the algorithm on a pixel-wise classification of solar filaments with u-net. We made use of the increased data set size, which avoids overfitting of spurious artifacts from the generated training masks. Filaments were predicted with an accuracy of 92%. With the resulting filament segmentations, physical parameters such as the area or tilt angle could be easily determined and studied. We demonstrated this in an example where we determined the rush-to-the pole for Solar Cycle 24 from the segmented GONG images. In a last step, we applied the filament detection to H alpha observations from KSO and demon

关键词： methods: observational methods: statistical techniques: image processing astronomical databases: miscellaneous catalogs Sun: chromosphere

来源：评论

学校读者我要写书评

暂无评论

Accident detection and road monitoring in real time using deep learning and lane detection algorithms 21

Accident detection and road monitoring in real time using de...

引用

4th International Conference on Machine learning and Machine Intelligence, MLMI 2021

作者： Ayman Mounir, Shehab Eldeen Hussein, Walid H. Karam, Omar Software Engineering Faculty of Informatics and Computer Science The British University in Egypt Egypt Computer Science Faculty of Informatics and Computer Science The British University in Egypt Egypt Information Systems Faculty of Informatics and Computer Science The British University in Egypt Egypt

ISBN: (纸本)9781450384247

Automating the monitoring of the roads would mean safer roads for both car drivers and pedestrians. The objectives of the system were to build a real time surveillance system for intelligent roads of the future. The system should be able to detect lane lines, cars, pedestrians and other moving vehicles on the road. In case a car goes off its course, the system should report it as an accident. Relying on machine learning technology, a real time detection based neural network was constructed to be trained on picking up objects in any given scene like cars, buses, pedestrians, bikes and motor bikes. Also, an algorithm was designed to detect lane lines and highlight them on the screen using image processing techniques and edge detection. The system achieved its main required target which is being able to detect objects in almost real time. © 2021 ACM.

关键词： Accidents

来源：评论

学校读者我要写书评

暂无评论

Depth_ASPP_UNet plus +: a novel 2D ESPI phase unwrapping based on convolutional neural network

引用

MEASUREMENT SCIENCE AND TECHNOLOGY 2024年第6期35卷 065202-065202页

作者： Wang, Linlin Liang, Wenjie Xue, Wenke Zhang, Yinwen Wang, Chuanyun Gao, Qian Shenyang Aerosp Univ Artificial Intelligence Coll Shenyang 110136 Peoples R China

Phase unwrapping is a key step in optical metrology and physical optics to obtain accurate phase distributions. In practice, phase images obtained from electronic speckle pattern interferometry (ESPI) exhibit diverse and complex morphology, with significant shape variations and non-uniform densities among different individuals. This takes challenges for accurately extracting phase information and unwrapping the phase. With the progress of deep learning technology in optical image processing, real-time performance and accuracy have become concerned issues. In this paper, an ESPI phase unwrapping method based on convolutional neural network UNet++ is proposed. The proposed network combines the depthwise separable convolution (DSC), atrous spatial pyramid pooling (ASPP), defined as Depth_ASPP_UNet++. In this model, the use of DSC improves network computational efficiency and provides better feature representation capability. In addition, ASPP is introduced to pay more attention to the phase information of the phase image, and then obtain better phase unwrapping results. The experimental results show that our proposed method can obtain excellent results, especially with various of variable density, different noise levels, and different speckle sizes.

关键词： phase unwrapping deep learning convolutional network electronic speckle pattern interferometry optical metrology

来源：评论

学校读者我要写书评

暂无评论

Vision-based Distributed Multi-UAV Collision Avoidance via deep Reinforcement learning for Navigation

Vision-based Distributed Multi-UAV Collision Avoidance via D...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Huang, Huaxing Zhu, Guijie Fan, Zhun Zhai, Hao Cai, Yuwei Shi, Ze Dong, Zhaohui Hao, Zhifeng Shantou Univ Coll Engn Key Lab Digital Signal & Image Proc Guangdong Pro Shantou Peoples R China

ISBN: (数字)9781665479271

ISBN: (纸本)9781665479271

Online path planning for multiple unmanned aerial vehicle (multi-UAV) systems is considered a challenging task. It needs to ensure collision-free path planning in real-time, especially when the multi-UAV systems can become very crowded on certain occasions. In this paper, we presented a vision-based decentralized collision-avoidance policy learning method for multi-UAV systems. The policy takes depth images and inertial measurements as sensory inputs and outputs UAV's steering commands, and it is trained together with the latent representation of depth images using a policy gradient-based reinforcement learning algorithm and autoencoder in the multi-UAV three-dimensional workspaces. Each UAV follows the same trained policy and acts independently to reach the goal without colliding or communicating with other UAVs. We validate our method in various simulated scenarios. The experimental results show that our learned policy can guarantee fully autonomous collision-free navigation for multi-UAV in three-dimensional workspaces, and its navigation performance will not be greatly affected by the increase in the number of UAVs.

关键词： learning systems Training Navigation Reinforcement learning Autonomous aerial vehicles Path planning Robustness

来源：评论

学校读者我要写书评

暂无评论

deep Analysis of EIT Dataset to Classify Apnea and Non-Apnea Cases in Neonatal Patients

引用

IEEE ACCESS 2021年 9卷 25131-25139页

作者： Vahabi, Nafiseh Yerworth, Rebecca Miedema, Martijn van Kaam, Anton Bayford, Richard Demosthenous, Andreas UCL Dept Elect & Elect Engn London WC1E 6BT England UCL Dept Med Phys & Biomed Engn London WC1E 6BT England Univ Amsterdam Emma Childrens Hosp Amsterdam UMC NL-1012 WX Amsterdam Netherlands Middlesex Univ Dept Nat Sci London NW4 4BT England

Electrical impedance tomography (EIT) is a non-invasive imaging modality that can provide information about dynamic volume changes in the lung. This type of image does not represent structural lung information but provides changes in regions over time. EIT raw datasets or boundary voltages are comprised of two components, termed real and imaginary parts, due to the nature of cell membranes of the lung tissue. In this paper, we present the first use of EIT boundary voltage data obtained from infants for the automatic detection of apnea using machine learning, and investigate which components contain the main features of apnea events. We selected 15 premature neonates with an episode of apnea in their breathing pattern and applied a hybrid classification model that combines two established methods;a pre-trained transfer learning method with a convolutional neural network with 50 layers deep (ResNet50) architecture, and a support vector machine (SVM) classifier. ResNet50 training was undertaken using an imageNet dataset. The learnt parameters were fed into the SVM classifier to identify apnea and non-apnea cases from neonates' EIT datasets. The performance of our classification approach on the real part, the imaginary part and the absolute value of EIT boundary voltage datasets were investigated. We discovered that the imaginary component contained a larger proportion of apnea features.

关键词： Tomography Pediatrics image reconstruction Lung Electrodes Support vector machines Training Apnea classification algorithm EIT data analysis electrical impedance tomography pre-trained ResNet50 transfer learning algorithm

来源：评论

学校读者我要写书评

暂无评论

基于图像处理-深度学习的孵前种鸭蛋外部品质在线无损检测

引用

农业工程学报 2023年第2期39卷 233-241页

作者：王巧华徐步云田文强陈远哲范维刘世伟华中农业大学工学院武汉430070 农业农村部长江中下游农业装备重点实验室武汉430070

种鸭蛋的品质影响着孵化率和健雏率,挑选优质种鸭蛋孵化不仅可以减少孵化占用的资源,还可以及时将不适宜孵化的种鸭蛋筛选出另做它用,避免其孵化失败造成浪费。为了对不同外部品质的孵前种鸭蛋进行检测分级,该研究设计了一种基于图像处... 详细信息

种鸭蛋的品质影响着孵化率和健雏率,挑选优质种鸭蛋孵化不仅可以减少孵化占用的资源,还可以及时将不适宜孵化的种鸭蛋筛选出另做它用,避免其孵化失败造成浪费。为了对不同外部品质的孵前种鸭蛋进行检测分级,该研究设计了一种基于图像处理和深度学习的种鸭蛋外部品质检测系统。在传送轨道上获取种鸭蛋的透射图像后,选取多张鸭蛋图像中的最大长轴计算形状特征,通过交错值衡量大小头相似度;在伽马变换平衡图像颜色后,使用HSV分割提取脏污特征图来计算脏污面积;采用自适应阈值分割和脏污特征图掩膜对图像样本数据进行预处理,搭建裂纹识别网络CrackNet来识别脏污鸭蛋的裂纹。结果表明,该检测系统可计算种鸭蛋的大小、蛋形指数、脏污面积和大小头相似度,检测表面裂纹,计算所得长轴和蛋形指数的均方误差仅0.2202 mm^(2)和0.000058,CrackNet的裂纹识别准确率为98.03%,研究结果可为入孵前种鸭蛋的筛选工作提供技术支持。

关键词：图像处理深度学习种鸭蛋在线无损检测外部品质检测

来源：评论

学校读者我要写书评

暂无评论

Closed-loop feedback control of microfluidic cell manipulation via deep-learning integrated sensor networks

引用

LAB ON A CHIP 2021年第10期21卷 1916-1928页

作者： Wang, Ningquan Liu, Ruxiu Asmare, Norh Chu, Chia-Heng Civelekoglu, Ozgun Sarioglu, A. Fatih Georgia Inst Technol Sch Elect & Comp Engn Atlanta GA 30332 USA Georgia Inst Technol Parker H Petit Inst Bioengn & Biosci Atlanta GA 30332 USA Georgia Inst Technol Inst Elect & Nanotechnol Atlanta GA 30332 USA

Microfluidic technologies have long enabled the manipulation of flow-driven cells en masse under a variety of force fields with the goal of characterizing them or discriminating the pathogenic ones. On the other hand, a microfluidic platform is typically designed to function under optimized conditions, which rarely account for specimen heterogeneity and internal/external perturbations. In this work, we demonstrate a proof-of-principle adaptive microfluidic system that consists of an integrated network of distributed electrical sensors for on-chip tracking of cells and closed-loop feedback control that modulates chip parameters based on the sensor data. In our system, cell flow speed is measured at multiple locations throughout the device, the data is interpreted in real-time via deep learning-based algorithms, and a proportional-integral feedback controller updates a programmable pressure pump to maintain a desired cell flow speed. We validate the adaptive microfluidic system with both static and dynamic targets and also observe a fast convergence of the system under continuous external perturbations. With an ability to sustain optimal processing conditions in unsupervised settings, adaptive microfluidic systems would be less prone to artifacts and could eventually serve as reliable standardized biomedical tests at the point of care.

关键词： Sensor networks

来源：评论

学校读者我要写书评

暂无评论

deep learning based Asbestos Fiber Detection

Deep Learning based Asbestos Fiber Detection

引用

IEEE Applied imagery Pattern Recognition Workshop (AIPR)

作者： Biswas, Soma Biswas, Debmalya Nanoscope AI Lausanne Switzerland Cognizant Technol Solut Lausanne Switzerland

ISBN: (纸本)9781665424714

Airborne respirable fibers, such as asbestos are hazardous to health. Occupational health and safety guidelines and laws require detection and identification of all the asbestos containing materials. However, detection and identification of asbestos fibers is a complex, time-consuming and expensive process. In this work, we present a deep learning based Semantic Segmentation model that is able to automate the asbestos analysis process, reducing the turnaround time from hours to minutes. The proposed deep neural network provides end-to-end automation of the analysis process, starting with transforming the input Scanning Electron Microscope (SEM) images, to identifying and counting the number of fibers in the image, to masking the identified fiber regions and re-arranging for efficient processing by Energy Dispersive Spectroscopy (EDS). Finally, we provide implementation details of a U-Net based Semantic Segmentation model that is able to detect and count asbestos fibers (air sample) in SEM images with up to 95% accuracy.

关键词： Asbestos Testing deep learning Computer Vision Semantic Segmentation Microscopy image Analysis

来源：评论

学校读者我要写书评

暂无评论

An improved faster R-CNN algorithm for assisted detection of lung nodules

引用

COMPUTERS IN BIOLOGY AND MEDICINE 2023年第1期153卷 106470-106470页

作者： Xu, Jing Ren, Haojie Cai, Shenzhou Zhang, Xiaoping Zhejiang Gongshang Univ Sch Stat & Math Hangzhou 310018 Peoples R China Zhejiang Gongshang Univ Collaborat Innovat Ctr Stat Data Engn Technol & Ap Hangzhou 310018 Peoples R China

The morbidity and mortality of lung cancer are increasing rapidly in every country in the world, and pulmonary nodules are the main symptoms of lung cancer in the early stage. If we can diagnose pulmonary nodules in time at the early stage and follow up and treat suspicious patients, we can effectively reduce the incidence of lung cancer. CT (Computed Tomography) has been applied to the screening of many diseases because of its high resolution. Pulmonary nodules show white round shadows in CT images. With the popularity of CT equipment, doctors need to review a large number of imaging results every day. Doctors will misjudge and miss the lesions because of reviewing CT scanning results for a long time. At this time, the method of automatic detection of pulmonary nodules by computer can relieve the pressure of doctors in reviewing CT scan *** lung nodule detection methods, such as gray threshold method and region growing method, divide the detection process into two steps: extracting candidate regions and eliminating false regions. In addition, the traditional detection method can only operate on a single image, which leads to the inability of this method to detect the batch scanning results in real time. With the continuous development of computer equipment per-formance and artificial intelligence, the relationship between medical image processing and deep learning is getting closer and closer. In deep learning, object detection methods such as Faster R-CNN?YOLO can complete parallel detection of batch images, and deep structure can fully extract the features of input images. Compared with traditional lung nodule detection methods, it has the characteristics of high efficiency and high precision. Faster R-CNN is a classical and high-precision two-stage object detection method. In this paper, an improved Faster R-CNN model is proposed. On the basis of Faster R-CNN, multi-scale training strategy is used to fully mine the features of different scale spa

关键词： deep learning CT imaging Lung nodule detection Faster R-CNN Small object detection

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：