检索结果-内蒙古大学图书馆

5th International Conference on Video, Signal and image processing, VSIP 2023

作者： Jin, Hongmei Cui, Kaihua Jia, Ni Zhang, Hao Shi, Yuying Xi'an University Of Science And Technology China

ISBN: (纸本)9798400709272

In order to solve the problem that existing fatigue driving detection methods have high model complexity and are difficult to deploy to embedded devices, this paper designs and implements a deep learning-based fatigue driving detection experimental system. The system integrates YOLOv5 fatigue detection algorithm and Zero-DCE low-light enhancement algorithm, and is deployed on an embedded development board. Firstly, the requirements of the system are analyzed to clarify the functional requirements of the system;secondly, the architecture, functional modules and interfaces of the system are outlined, and the development environment and interface of the fatigue driving detection terminal and the backend management system are designed in detail;finally, the development and implementation of the software system is completed, and the functionality of the system is tested. The system can detect driver fatigue status in real time and, establish visualization of big data Kanban analysis, real-time dynamic analysis of all kinds of fatigue abnormal information to issue timely alarms. © 2023 ACM.

关键词： deep learning

来源：评论

学校读者我要写书评

暂无评论

Toward a Hardware Implementation of Lidar-based real-time Insect Detection

Toward a Hardware Implementation of Lidar-based Real-time In...

引用

Conference on real-time image processing and deep learning

作者： Vannoy, Trevor C. Rehbein, Elizabeth M. Logan, Riley D. Shaw, Joseph A. Whitaker, Bradley M. Montana State Univ Elect & Comp Engn Bozeman MT 59718 USA Montana State Univ Opt Technol Ctr Bozeman MT 59718 USA

ISBN: (纸本)9781510650817;9781510650800

real-time monitoring of insects has important applications in entomology, such as managing agricultural pests and monitoring species populations-which are rapidly declining. However, most monitoring methods are labor intensive, invasive, and not automated. Lidar-based methods are a promising, non-invasive alternative, and have been used in recent years for various insect detection and classification studies. In a previous study, we used supervised machine learning to detect insects in lidar images that were collected near Hyalite Creek in Bozeman, Montana. Although the classifiers we tested successfully detected insects, the analysis was performed offline on a laptop computer. For the analysis to be useful in real-time settings, the computing system needs to be an embedded system capable of computing results in real-time. In this paper, we present work-in-progress towards implementing our software routines in hardware on a field programmable gate array.

关键词： real-time classification insects lidar machine learning field programmable gate arrays

来源：评论

学校读者我要写书评

暂无评论

real-time Automatic Configuration of Brain MRI: A Comparative Study of SIFT Descriptors and YOLO Neural Network

引用

APPLIED SCIENCES-BASEL 2025年第1期15卷 147-147页

作者： Almeida, Ravison Amaral de Carvalho, Julio Cesar Porto Vieira, Antonio Wilson de Oliveira, Heveraldo Rodrigues D'Angelo, Marcos F. S. V. UNIMONTES State Univ Montes Claros Grad Program Comp Modeling & Syst Av Rui BragaSnVila Mauriceia BR-39401089 Montes Claros Brazil UNIMONTES State Univ Montes Claros Dept Exact Sci Av Rui BragaSnVila Mauriceia BR-39401089 Montes Claros Brazil UNIMONTES State Univ Montes Claros Dept Comp Sci Av Rui BragaSnVila Mauriceia BR-39401089 Montes Claros Brazil

This work presents two approaches to image processing in brain magnetic resonance imaging (MRI) to enhance slice planning during examinations. The first approach involves capturing images from the operator's console during slice planning for two different brain examinations. From these images, Scale-Invariant Feature Transform (SIFT) descriptors are extracted from the regions of interest. These descriptors are then utilized to train and test a model for image matching. The second approach introduces a novel method based on the YOLO (You Only Look Once) neural network, which is designed to automatically align and orient cutting planes. Both methods aim to automate and assist operators in decision making during MRI slice planning, thereby reducing human dependency and improving examination accuracy. The SIFT-based method demonstrated satisfactory results, meeting the necessary requirements for accurate brain examinations. Meanwhile, the YOLO-based method provides a more advanced and automated solution to detect and align structures in brain MRI images. These two distinct approaches are intended to be compared, highlighting their respective strengths and weaknesses in the context of brain MRI slice planning.

关键词： magnetic resonance imaging deep learning computer vision

来源：评论

学校读者我要写书评

暂无评论

Multispectral image Segmentation in Agriculture: Evaluating deep learning Models with Train-Test Split and Cross-Validation Strategies 7

Multispectral Image Segmentation in Agriculture: Evaluating ...

引用

7th Iberian Robotics Conference

作者： Cardo, Wilgo Barros, Tiago Goncalves, Gil Premebida, Cristiano Nunes, Urbano J. Univ Coimbra Inst Syst & Robot Dept Elect & Comp Engn Coimbra Portugal Univ Coimbra Dept Math Inst Syst Engn & Comp Coimbra Coimbra Portugal

ISBN: (纸本)9798350376371;9798350376364

In agricultural robotics, the integration of multispectral image processing and deep learning (DL) has become the state-of-the-art (SOTA) in crop monitoring, yield estimation, and efficient land management. This work addresses the impact of different DL-segmentation models and evaluation protocols on multispectral imagery datasets collected by a UAV over vineyards. In terms of evaluation protocols, we have considered train-test split, standard k-fold cross-validation, and group k-fold cross-validation. While the first two assume that the training and test data are drawn from the same underlying distribution, the group k-fold cross-validation protocol assumes that each fold represents distinct distributions. Most works either adopt train-test split or k-fold cross-validation under the assumption that both the training and test sets are drawn from the same distribution. However, this assumption is rarely met in real-world applications. Therefore, the objective of this study is to evaluate and compare different evaluation protocols within the context of a real-world agricultural task, highlighting their limitations and weaknesses. Two SOTA DL-based segmentation models, SegNet and deepLabV3, are employed to perform semantic segmentation on datasets of three Vineyards. The models have been trained and tested considering single-modality representations. In addition to the RGB modality, models trained on NDVI, GNDVI and early fusion are also evaluated. The performance of the models are evaluated using the IoU metric across different dataset configurations. The results indicate that the early fusion representation achieves the highest performance across the various splitting protocols, compared to the single-input representations. The results also show that the train-test and random k-fold splitting approaches report similar results. However, when employing group k-fold the performance drops consistently across both models and the modalities. This indicates that the models

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

CUDU-Net: Collaborative up-sampling decoder U-Net for leaf vein segmentation

引用

DIGITAL SIGNAL processing 2024年 144卷

作者： Cai, Wanqiang Wang, Bin Zeng, Fanqing Nanjing Univ Finance Econ Sch Informat Engn Nanjing 210023 Peoples R China Nanjing Univ Finance & Econ Media Comp Lab Nanjing 210023 Peoples R China

Leaf vein is a common visual pattern in nature which provides potential clues for species identification, health evaluation, and variety selection of plants. However, as a critical step in leaf vein pattern analysis, segmenting vein from leaf image remains unaddressed due to its hierarchical curvilinear structure and busy background. In this study, we for the first time design a deep model which is tailored to address the segmentation of overall leaf vein structure. The proposed deep model, termed Collaborative Up-sampling Decoder U-Net (CUDU-Net), is an improved U-Net structure consisting of a fine-tuned ResNet extractor and a collaborative up-sampling decoder. The ResNet extractor utilizes residual module to explore high-dimensional features that are representative and abstract in the hidden layers of the network. The core of CUDU-Net is the collaborative up-sampling decoder which utilizes the complementarity of the bilinear-interpolation and deconvolution, to enhance the decoding capability of the model. The bilinear-interpolation can recovery key veins while the deconvolution actively learns to supplement more fine-grained features of the tertiary veins. In addition, we embed the strip pooling in the skip-connection to distill the vein-related semantics for performance boosting. Two leaf vein segmentation datasets, termed SoyVein500 and CottVein20, are built for model validation and generalization ability test. The extensive experimental results show that our proposed CUDU-Net outperforms the state-of-the-art methods in both segmentation accuracy and generalization ability.

关键词： Leaves vein segmentation deep learning U-Net Bilinear-interpolation decoder Deconvolution decoder

来源：评论

学校读者我要写书评

暂无评论

Cartoonify real-time images using machine learning

Cartoonify real-time images using machine learning

引用

International Conference on Artificial Intelligence, Blockchain, Computing and Security, ICABCS 2023

作者： Umarani, V. Jagadeesh Raj, M. Garshan Kumar, K. Vasanth Reddy, Somu Department of Computer Science and Engineering Saveetha Engineering College Tamil Nadu Chennai India

ISBN: (纸本)9781032669663

The image process is a technique for applying certain operations to a photograph in order to produce an enhanced image or extract some useful information from it. It’s a type of signal processing where the input is a picture and the output could be either an image or features that are associated with that image. Tools for processing images include Numpy, Scikit image, and OpenCV. Generative modeling involves mechanically identifying and then mastering the variations or styles on input traces in a way similar to how the model may be used to induce or affair new exemplifications that credibly might be drawn from the first dataset. It is associated with nursing unattended literacy tasks in machine literacy. © 2024, CRC Press/Balkema. All rights reserved.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

Air Purification Robotics using Cloud and deep Q Networks for Autonomous Systems 1

Air Purification Robotics using Cloud and Deep Q Networks fo...

引用

1st International Conference on Innovative Sustainable Technologies for Energy, Mechatronics and Smart Systems, ISTEMS 2024

作者： Reddy, Elangovan Guruva Damodhar, T. S. Balaji Yuvaraj, S. Vathani, B. Santha Sivakumar, S. Malathi, N. Koneru Lakshmaiah Education Foundation Department of Artificial Intelligence and Data Science Andhra Pradesh Vaddeswaram India Madanapalle Institute of Technology and Science Department of Electrical and Electronics Engineering Andhra Pradesh Madanapalle India Srm Institute of Science and Technology Faculty of Engineering and Technology Department of Electronics and Communication Engineering Tamil Nadu Kattankulathur India Mahalashmi Women's College of Arts and Science Department of Management Studies Tamil Nadu Chennai India Department of Computer Science Tamil Nadu Perambalur India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Department of Computer Science and Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350384246

Rising urban air pollution poses serious health dangers. Through robots, cloud computing, and deep reinforcement learning, this research proposes a new air purification method. The suggested autonomous system analyzes real-time air quality parameters and optimizes air purification tactics using cloud-based data processing. Advanced sensors and purification processes allow robotic agents to intelligently adapt to shifting pollution patterns in dynamic settings. Robots use deep Q Networks (DQN) to learn and change their purifying tactics based on past data and environmental input. Cloud computing and deep learning improve air purification efficiency and enable real-time pollution response decision-making. The autonomous system is scalable and adaptable to varied urban environments since it requires little human involvement. The cloud-based design lets autonomous agents communicate and coordinate to improve air quality. Experimental findings show that the suggested strategy improves air purification over previous approaches. This system advances environmental robotics and lays the groundwork for intelligent, autonomous systems that handle urban air quality and pollution issues. © 2024 IEEE.

关键词： Robotics

来源：评论

学校读者我要写书评

暂无评论

Neuromorphic Chiplet Architecture for Wide Area Motion imagery processing 6

Neuromorphic Chiplet Architecture for Wide Area Motion Image...

引用

6th Argentine Conference on Electronics (CAE)

作者： Andreou, Andreas G. Figliolia, Tomas Sanni, Kayode Murray, Thomas S. Tognetti, Gaspar Mendat, Daniel R. Molin, Jamal L. Villemur, Martin Pouliquen, Philippe O. Julian, Pedro Etienne-Cummings, Ralph Doxas, Isidoros Johns Hopkins Univ Dept Elect & Comp Engn Baltimore MD 21218 USA BAE Syst London England Johns Hopkins Univ Baltimore MD 21218 USA

ISBN: (纸本)9798350305081

We present the system architecture for real-time processing of data that originates in large format tiled imaging arrays used in wide area motion imagery ubiquitous surveillance. High performance and high throughput is achieved through approximate computing and fixed point variable precision (6 bits to 18 bits) arithmetic. The architecture implements a variety of processing algorithms in what we consider today as Third Wave AI and Machine Intelligence ranging from convolutional networks (CNNs) to linear and non-linear morphological processing, probabilistic inference using exact and approximate Bayesian methods and deep Neural Networks based classification. The processing pipeline is implemented entirely using event based neuromorphic and stochastic computational primitives. An emulation of the system architecture demonstrated processing in real-time 160 x 120 raw pixel data running on a reconfigurable computing platform (5 Xilinx Kintex-7 FPGAs). The reconfigurable computing implementation was developed to emulate the computational structures for a 2.5D System chiplet design, that was fabricated in the 55nm GF CMOS technology. To optimize for energy efficiency of a mixed level system, a general energy aware methodology is applied through the design process at all levels from algorithms and architecture all the way down to technology and devices, while at the same time keeping the operational requirements and specifications for the task at focus.

关键词： Chiplets 2.5D architecture neuromorphic processing mixed signal design event based processing wide area image processing

来源：评论

学校读者我要写书评

暂无评论

DeTrack: In-model Latent Denoising learning for Visual Object Tracking 38

DeTrack: In-model Latent Denoising Learning for Visual Objec...

引用

38th Conference on Neural Information processing Systems, NeurIPS 2024

作者： Zhou, Xinyu Li, Jinglun Hong, Lingyi Jiang, Kaixun Guo, Pinxue Ge, Weifeng Zhang, Wenqiang Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai China Shanghai Engineering Research Center of AI & Robotics Academy for Engineering and Technology Fudan University Shanghai China

Previous visual object tracking methods employ image-feature regression models or coordinate autoregression models for bounding box prediction. image-feature regression methods heavily depend on matching results and do not utilize positional prior, while the autoregressive approach can only be trained using bounding boxes available in the training set, potentially resulting in suboptimal performance during testing with unseen data. Inspired by the diffusion model, denoising learning enhances the model's robustness to unseen data. Therefore, We introduce noise to bounding boxes, generating noisy boxes for training, thus enhancing model robustness on testing data. We propose a new paradigm to formulate the visual object tracking problem as a denoising learning process. However, tracking algorithms are usually asked to run in real-time, directly applying the diffusion model to object tracking would severely impair tracking speed. Therefore, we decompose the denoising learning process into every denoising block within a model, not by running the model multiple times, and thus we summarize the proposed paradigm as an in-model latent denoising learning process. Specifically, we propose a denoising Vision Transformer (ViT), which is composed of multiple denoising blocks. In the denoising block, template and search embeddings are projected into every denoising block as conditions. A denoising block is responsible for removing the noise in a predicted bounding box, and multiple stacked denoising blocks cooperate to accomplish the whole denoising process. Subsequently, we utilize image features and trajectory information to refine the denoised bounding box. Besides, we also utilize trajectory memory and visual memory to improve tracking stability. Experimental results validate the effectiveness of our approach, achieving competitive performance on several challenging datasets. The proposed in-model latent denoising tracker achieve real-time speed, rendering denoising learning

关键词：

来源：评论

学校读者我要写书评

暂无评论

Self-supervised learning-based Algorithm for Chinese image Caption Generation in Electric Robot Inspection processing 7

Self-supervised Learning-based Algorithm for Chinese Image C...

引用

7th International Conference on Automation Electronics and Electrical Engineering

作者： Qian Ping Zhang Yong Cao Yang Zhou Gang Qi Zhongyi State Grid Dongtou Power Supply Co Dept Management Hangzhou Peoples R China State Grid Zhejiang Elect Power Dept Equipment Hangzhou Peoples R China State Grid Jiaxing Power Supply Co Dept Operat & Maintenance Jiaxing Zhejiang Peoples R China State Grid Zhejiang Elect Power Jiaxing Power Sup Dept Operat & Inspect Jiaxing Zhejiang Peoples R China State Grid Zhejiang Elect Power Jiaxing Power Sup Dept Operat Jiaxing Zhejiang Peoples R China

ISBN: (数字)9798350377033

ISBN: (纸本)9798350377040;9798350377033

Electric robot will obtain a large amount of image information during inspection, and if these images are checked whether there are faults in power inspection is time-consuming and labor-intensive. There is an urgent need for power image Chinese title generation technology to solve it. However, existing image Chinese title generation methods face the problems of small training data sets, differences in specific applications, and few methods for generating Chinese titles for power images. To this end, this paper proposes a self-supervised learning-based image Chinese title generation algorithm for fault detection in electric robot inspection. Specifically, a contrastive learning-based model to automatically capture the semantic relationship between images and text. Then, we propose an end-to-end encoding-decoding model combined with an attention mechanism to obtain Chinese title generation for inspection images. The effectiveness of the proposed algorithm is experimentally verified on two real datasets.

关键词： self-supervised learning attention mechanism encoder-decoder image caption generation electric robot Semantic feature

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：