检索结果-内蒙古大学图书馆

International Conference on ent Computing and Control Systems (ICICCS)

作者： M. Venkateswarlu G. V. N. Shri Himaja V. Sainath Reddy M. Vineeth Department of Computer Science and Engineering(AI & ML) Vignan Institute of Technology and Science Nalgonda Telangana

ISBN: (数字)9798331512088

ISBN: (纸本)9798331512095

Intelligent transportation is gaining much attention about autonomous driving systems. This research will present a fully developed comprehensive framework to implement the navigation of autonomous vehicles using CARLA. deep learning-based object detection by the use of YOLOv5 is used in the current project, which identifies both real-time vehicle traffic, traffic lights, and obstacles. In parallel, lane detection is achieved through image processing techniques, such as edge detection and Hough Line Transform. The proposed system integrates these capabilities with decision-making algorithms to facilitate responsive vehicle control in dynamic environments. In addition, the validation of autonomous behaviour from a holistic point of view uses third-party camera views. Multiple vehicle traffic simulations add realism to the environment. A pilot function simulates the actual condition, with a synchronized simulation approach for the correct timing in processing and analysing data. The outputs include saved images, processed frames, and videos demonstrating the efficacy of the system under varying scenarios. This research integrates modern computer vision techniques with simulated environments to create a robust testing platform for autonomous navigation. Future research can extend this framework to real-world applications or incorporate advanced reinforcement learning algorithms for enhanced decision-making capabilities.

关键词： YOLO Computer vision Navigation Lane detection Heuristic algorithms Decision making Traffic control Vehicle dynamics Autonomous vehicles Videos

来源：评论

学校读者我要写书评

暂无评论

Semantic segmentation based on deep learning for the detection of Cyanobacterial Harmful Algal Blooms (CyanoHABs) using synthetic images

引用

APPLIED SOFT COMPUTING 2023年 141卷

作者： Barrientos-Espillco, Fredy Gasco, Esther Lopez-Gonzalez, Clara I. Gomez-Silva, Maria J. Pajares, Gonzalo Univ Complutense Madrid Fac Phys Dept Comp Architecture & Automat Madrid 28040 Spain Univ Complutense Madrid Dept Software Engn & Artificial Intelligence Madrid 28040 Spain Univ Complutense Madrid Inst Knowledge Technol Madrid Spain

Cyanobacterial Harmful Algal Blooms (CyanoHABs) in lakes and reservoirs have increased substantially in recent decades due to different environmental factors. Its early detection is a crucial issue to minimize health effects, particularly in potential drinking and recreational water bodies. The use of Autonomous Surface Vehicles (ASVs) equipped with machine vision systems (cameras) onboard, represents a useful alternative at this time. In this regard, we propose an image Semantic Segmentation approach based on deep learning with Convolutional Neural Networks (CNNs) for the early detection of CyanoHABs considering an ASV perspective. The use of these models is justified by the fact that with their convolutional architecture, it is possible to capture both, spectral and textural information considering the context of a pixel and its neighbors. To train these models it is necessary to have data, but the acquisition of real images is a difficult task, due to the capricious appearance of the algae on water surfaces sporadically and intermittently over time and after long periods of time, requiring even years and the permanent installation of the image capture system. This justifies the generation of synthetic data so that sufficiently trained models are required to detect CyanoHABs patches when they emerge on the water surface. The data generation for training and the use of the semantic segmentation models to capture contextual information determine the need for the proposal, as well as its novelty and *** datasets of images containing CyanoHABs patches are generated: (a) the first contains real patches of CyanoHABs as foreground and images of lakes and reservoirs as background, but with a limited number of examples;(b) the second, contains synthetic patches of CyanoHABs generated with state-of-the-art Style-based Generative Adversarial Network Adaptive Discriminator Augmentation (StyleGAN2-ADA) and Neural Style Transfer as foreground and images of lakes

关键词： Cyanobacterial harmful algal blooms Semantic segmentation Generative adversarial network Neural style transfer Convolutional neural networks deep learning Autonomous surface vehicles

来源：评论

学校读者我要写书评

暂无评论

Single-channel, ultraportable, real-time imaging system based on deep learning: a proof-of-concept

Single-channel, ultraportable, real-time imaging system base...

引用

IEEE Symposium (IUS) Ultrasonics

作者： Valentino Meacci Edoardo Bosco Alessandro Ramalli Enrico Boni Piero Tortoli Daniele Mazierli Edoardo Spairani Giulia Matrone Department of Information Engineering University of Florence Florence Italy Department of Electrical Computer and Biomedical Engineering University of Pavia Pavia Italy

There is a growing demand for user-friendly technologies that may empower individuals to independently monitor their physiological parameters. Ultrasound systems are highly promising for healthcare self-monitoring. To address these challenges, in this work, we present the proof of concept (PoC) of a real-time ultraportable system with a single-channel transmission and reception strategy and a deep learning-based image reconstruction method. The PoC uses the ULA-OP 256 scanner, employing a monostatic synthetic aperture focusing technique, along with a convolutional neural network (CNN) trained to generate B-mode images. Testing was carried out using a CNN running on a mid-range graphics processing unit (GPU), both on phantoms and in vivo scenarios, comparing the image quality achieved by the CNN with that of a delay-and-sum (DAS) beamformer. The results highlight that the CNN outperformed the DAS, showing a better image quality. Furthermore, the CNN achieved a real-time frame rate of 37.0 frames per second, proving that ultraportable ultrasound systems are highly promising for the future of self-monitoring instruments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Convolution neural network with low operation FLOPS and high accuracy for image recognition

引用

JOURNAL OF real-time image processing 2021年第4期18卷 1309-1319页

作者： Hsia, Shih-Chang Wang, Szu-Hong Chang, Chuan-Yu Natl Yunlin Univ Sci & Technol Touliu Yunlin Taiwan

The convolution neural network makes deeper and wider for better accuracy, but requires higher computations. When the neural network goes deeper, some information loss is more. To improve this drawback, the residual structure was developed to connect the information of the previous layers. This is a good solution to prevent the loss of information, but it requires a huge amount of parameters for deeper layer operations. In this study, the fast computational algorithm is proposed to reduce the parameters and to save the operations with the modification of DenseNet deep layer block. With channel merging procedures, this solution can reduce the dilemma of multiple growth of the parameter quantity for deeper layer. This approach is not only to reduce the parameters and FLOPs, but also to keep high accuracy. Comparisons with the original DenseNet and RetNet-110, the parameters can be efficiency reduced about 30-70%, while the accuracy degrades little. The lightweight network can be implemented on a low-cost embedded system for real-time application.

关键词： deep learning Convolution neural network DenseNet deeper layer

来源：评论

学校读者我要写书评

暂无评论

Heart Rate Prediction Algorithm of Smart Wearable Device with deep learning

Heart Rate Prediction Algorithm of Smart Wearable Device wit...

引用

image processing and Computer Applications (ICIPCA), IEEE International Conference on

作者： Qi Guo Wei Ding Dalian Polytechnic University Dalian China

ISBN: (数字)9798350360240

ISBN: (纸本)9798350384161

In the field of heart rate prediction for smart wearable devices, an innovative fusion strategy is to combine Actor-Critic reinforcement learning algorithm (AC algorithm) with convolutional neural network (CNN). Using CNN's powerful spatiotemporal feature extraction capability to process continuous heart rate sequence data, it can automatically capture and transform local correlation and hidden patterns in physiological signals into high-level abstract features. On this basis, the actor-critic framework dynamically adjusts the behavior strategy of the model, in which the Actor is responsible for output the heart rate prediction at the next moment according to the current state, and the Critic evaluates and feedbacks the action value of the Actor. The two work together to iteratively optimize model performance and introduce a new Neural Network Actor Critic model (NNAC). This integrated scheme makes full use of the advantages of CNN in the analysis of complex time series data, and combines the real-time learning and feedback mechanism of Actor-Critic algorithm to solve the accurate heart rate prediction problem under the challenges of large individual differences and changing physiological conditions. Through such technology integration, smart wearable devices can predict user heart rate changes more accurately and quickly, thus improving the practicality and intelligence level of health management applications.

关键词： Heart rate Accuracy Reinforcement learning Transforms Predictive models Prediction algorithms Feature extraction Physiology Convolutional neural networks Wearable devices

来源：评论

学校读者我要写书评

暂无评论

Comparison of deep learning Models for Crater Detection Using OHRC Dataset of Chandrayaan-2

Comparison of Deep Learning Models for Crater Detection Usin...

引用

Remote Sensing Symposium (InGARSS), 2020 IEEE India Geoscience and

作者： Harshaditya Gaur Shaifali Garg Vinay Kumar Indian Institute of Remote Sensing Dehradun Uttarakhand India

ISBN: (数字)9798350390346

ISBN: (纸本)9798350390353

The Orbital High-Resolution Camera (OHRC), with a spatial resolution of 25 cm, is one of the most sophisticated optical sensors available for lunar exploration, capturing detailed observations of the lunar surface. This data is crucial for lunar missions to define safe and unsafe regions such as craters, ridges and boulders. The deep learning approach eliminates the need for manual intervention and streamlines the analysis of large lunar datasets. The combination of planetary data and modern processing techniques has significantly improved the accuracy and efficiency of crater detection, enabling detailed and large-scale analyses of planetary surfaces. The study area undertaken for the application of deep learning models for automated crater detection is the landing site of the NASA Apollo 12 (April 1967) and Surveyor 3 (November 1969) missions. Models such as YOLOv8 and Mask R-CNN were applied to detect medium to large-sized craters. The YOLOv8 model result outperformed the Mask R-CNN result by providing higher accuracy and faster execution time. This study contributes valuable insights to the planetary science community by highlighting the robustness of different deep learning models for crater analysis using optical datasets from the Chandrayaan- 2 lunar mission by ISRO, India.

关键词： deep learning Training Accuracy Moon Data models Robustness real-time systems Optical sensors Spatial resolution Surface treatment

来源：评论

学校读者我要写书评

暂无评论

Automated Recognition of Optic Disc and Blood Vessels in Diabetic Fundoscopy images Using real-time image Analysis

Automated Recognition of Optic Disc and Blood Vessels in Dia...

引用

IEEE Conference on Multimedia Information processing and Retrieval (MIPR)

作者： Kaixuan Li Wei-Bang Chen Yongjin Lu Xiaoliang Wang He Gao Department of Computer Science Virginia State University Petersburg VA USA Department of Mathematics and Statistics Oakland University Rochester MI USA Department of Computer Science SUNY Oswego Oswego NY USA

ISBN: (数字)9798350351422

ISBN: (纸本)9798350351439

Diabetic retinopathy (DR) is a sight-threatening condition associated with diabetes, characterized by damage to the retinal blood vessels. Key to the automation of DR staging is the identification of various symptoms directly or closely associated with retinal blood vessels, as well as the number of these symptoms in the four quadrants of the retina separated by the optic disc. Therefore, precise identification of the optic disc (OD) and blood vessels in fundus images is crucial for DR stage diagnosis but is often time-consuming and requires expert analysis. This study introduces a thresholding-based approach for the automated localization of the OD and the detection of blood vessels in fundus images of diabetic patients. Our algorithm is more robust than some deep learning-based algorithms, achieving more accurate results, particularly in advanced DR stages where the resemblance between various symptoms and blood vessels complicates the extraction of blood vessels. Additionally, our computer vision system can achieve OD localization and blood vessel segmentation in real time. The experimental results on a dataset selected by an ophthalmologist from a Kaggle dataset, ensuring data quality, show that the proposed algorithm can achieve an accuracy higher than 94% for both OD localization and blood vessel detection, outperforming some state-of-the-art algorithms.

关键词： Location awareness image segmentation Accuracy image recognition Information processing Blood vessels Retina Optical imaging real-time systems Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

HunCRC: annotated pathological slides to enhance deep learning applications in colorectal cancer screening

引用

SCIENTIFIC DATA 2022年第1期9卷 370页

作者： Pataki, Balint Armin Olar, Alex Ribli, Dezso Pesti, Adrian Kontsek, Endre Gyongyosi, Benedek Bilecz, Agnes Kovacs, Tekla Kovacs, Kristof Attila Kramer, Zsofia Kiss, Andras Szocska, Miklos Pollner, Peter Csabai, Istvan Eotvos Lorand Univ ELTE Dept Phys Complex Syst Budapest Hungary Semmelweis Univ Dept Pathol 2 Budapest Hungary Semmelweis Univ Hlth Serv Management Training Ctr Budapest Hungary Eotvos Lorand Univ MTA ELTE Stat & Biol Phys Res Grp Dept Biol Phys Budapest Hungary

Histopathology is the gold standard method for staging and grading human tumors and provides critical information for the oncoteam's decision making. Highly-trained pathologists are needed for careful microscopic analysis of the slides produced from tissue taken from biopsy. This is a time-consuming process. A reliable decision support system would assist healthcare systems that often suffer from a shortage of pathologists. Recent advances in digital pathology allow for high-resolution digitalization of pathological slides. Digital slide scanners combined with modern computer vision models, such as convolutional neural networks, can help pathologists in their everyday work, resulting in shortened diagnosis times. In this study, 200 digital whole-slide images are published which were collected via hematoxylin-eosin stained colorectal biopsy. Alongside the whole-slide images, detailed region level annotations are also provided for ten relevant pathological classes. The 200 digital slides, after pre-processing, resulted in 101,389 patches. A single patch is a 512 x 512 pixel image, covering 248 x 248 mu m(2) tissue area. Versions at higher resolution are available as well. Hopefully, HunCRC, this widely accessible dataset will aid future colorectal cancer computer-aided diagnosis and research.

关键词：

来源：评论

学校读者我要写书评

暂无评论

real-time multiple spatiotemporal action localization and prediction approach using deep learning

引用

NEURAL NETWORKS 2020年 128卷 331-344页

作者： Hammam, Ahmed Ali Soliman, Mona M. Hassanien, Aboul Ella Cairo Univ Fac Comp & Artificial Intelligence Cairo Egypt Sci Res Grp Egypt Cairo Egypt

Detecting the locations of multiple actions in videos and classifying them in real-time are challenging problems termed "action localization and prediction" problem. Convolutional neural networks (ConvNets) have achieved great success for action localization and prediction in still images. A major advance occurred when the AlexNet architecture was introduced in the imageNet competition. ConvNets have since achieved state-of-the-art performances across a wide variety of machine vision tasks, including object detection, image segmentation, image classification, facial recognition, human pose estimation, and tracking. However, few works exist that address action localization and prediction in videos. The current action localization research primarily focuses on the classification of temporally trimmed videos in which only one action occurs per frame. Moreover, nearly all the current approaches work only offline and are too slow to be useful in real-world environments. In this work, we propose a fast and accurate deep-learning approach to perform real-time action localization and prediction. The proposed approach uses convolutional neural networks to localize multiple actions and predict their classes in real time. This approach starts by using appearance and motion detection networks (known as "you only look once" (YOLO) networks) to localize and classify actions from RGB frames and optical flow frames using a two-stream model. We then propose a fusion step that increases the localization accuracy of the proposed approach. Moreover, we generate an action tube based on frame level detection. The frame by frame processing introduces an early action detection and prediction with top performance in terms of detection speed and precision. The experimental results demonstrate this superiority of our proposed approach in terms of both processing time and accuracy compared to recent offline and online action localization and prediction approaches on the challenging UCF-101-24

关键词： deep learning Action localization Action prediction Spatiotemporal YOLO network Optical flow

来源：评论

学校读者我要写书评

暂无评论

ClassVision: AI-Powered Classroom Attendance System

ClassVision: AI-Powered Classroom Attendance System

引用

International Conference on Digital Data processing (DDP)

作者： Ankit Kumar Aggarwal Veerabhadra Rao Marellapudi Ovadia Sutton Youshan Zhang Artificial Intelligence Yeshiva University NY USA

ISBN: (数字)9798331515706

ISBN: (纸本)9798331515713

Students and working professionals have to go through the attendance process every day. Traditional methods of marking attendance using pen and paper or online platforms are human-intensive and time-consuming. To address the challenges in manual attendance processes, this research explores the use of face detection (FD) and face recognition (FR) technology to automate the attendance process, particularly in educational settings, and build a ClassVision course attendance system. We also propose an automated attendance system featuring a human-computer interaction (HCI) and user-friendly web interface that utilizes real-time image processing to identify and recognize students in classrooms and automatically record their attendance. We identified RetinaFace as the best face detection model, and when combined with Face Recognition for verification, it provided the most promising results with a cropped embedding of 50×50 pixels. Our proposed framework achieves a detection accuracy of 99.4% and a recognition accuracy of 90.3%. Unlike deep learning methods that require students to be present closely in front of the camera to capture attendance, our pioneering research aims to capture attendance seamlessly during ongoing classes, redefining the framework of attendance tracking systems. Source code is available at https://***/Course-Attendance-Robot.

关键词： Training Human computer interaction Accuracy image recognition Face recognition Source coding Feature extraction Cameras real-time systems Facial features

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：