检索结果-内蒙古大学图书馆

Machine learning and image processing to monitor strain and tensile forces with mechanochromic sensors

EXPERT SYSTEMS WITH APPLICATIONS 2023年 212卷

作者： de Castro, Lucas D. C. Scabini, Leonardo Ribas, Lucas C. Bruno, Odemir M. Oliveira Jr, Osvaldo N. Univ Sao Paulo Sao Carlos Inst Phys BR-13566590 Sao Carlos SP Brazil Sao Paulo State Univ Inst Biosci Humanities & Exact Sci BR-15054000 Sao Jose Do Rio Preto SP Brazil

A computer vision (CV) system is proposed for real-time prediction of strain by monitoring the color-changing feature of mechanochromic sensors. Pictures of the sensors subjected to calibration tensile tests were treated with standard image processing methods and analyzed using supervised machine learning (ML) algorithms. Visual strain sensing was demonstrated by linear regression models capable of learning a relation between the applied strain and the reflected structural color. The ElasticNet regression model provided the highest accuracy in the strain prediction task, with a remarkable performance in monitoring real-time strain variation of sensors during a tensile-relaxion cycle. Using calibration curves, the predicted strain can also be employed for estimating the tensile force applied on the mechanochromic sensors. Taken together these results point to potential intelligent systems for noninvasive in-situ visual monitoring of deformations and tensions.

关键词： Sensors Mechanochromic Computer vision Machine learning image processing

来源：评论

学校读者我要写书评

暂无评论

real-time Automated Pothole Detection and Localization with deep learning and Geolocation Integration for Improved Road Safety and Maintenance 4th

Real-Time Automated Pothole Detection and Localization with ...

引用

4th International Conference on Advanced Network Technologies and Intelligent Computing-ANTIC-Annual

作者： Rao, Abhishek S. Karthik, Pai B. H. Shyvalanai, B. S. Nayak, Trupthi D. Vaishnavi, R. Thanisha NITTE NMAM Inst Technol NMAMIT Dept Informat Sci & Engn Nitte 574110 Karnataka India

ISBN: (纸本)9783031837920;9783031837937

real-time identification of road damage, particularly potholes, is essential for enhancing road safety and minimizing vehicle damage. Traditional road inspection methods are often labor-intensive and inefficient. To overcome these limitations, we propose an automated system that leverages deep learning to detect potholes in real-time from video input. This system can detect potholes under varying lighting conditions, specifically the YOLO (You Only Look Once) model, utilizing advanced computer vision techniques, including daylight, darkness, and vehicle headlights. The system aims to improve road monitoring by automatically identifying potholes and notifying authorities of their locations. By integrating geolocation services, the system pinpoints pothole locations using latitude and longitude coordinates and sends real-time alerts via a Telegram bot. Additionally, image enhancement techniques are employed to optimize detection performance in low-light conditions. The system has demonstrated high accuracy in detecting large potholes and identifying multiple potholes within a single frame. Through automated pothole detection and location sharing, this solution has the potential to significantly enhance road maintenance efficiency, thereby improving road safety and reducing accidents caused by road damage.

关键词： Pothole Detection real-time Video processing deep learning Computer Vision Low-light image Enhancement

来源：评论

学校读者我要写书评

暂无评论

learning binary and sparse permutation-invariant representations for fast and memory efficient whole slide image search

引用

COMPUTERS IN BIOLOGY AND MEDICINE 2023年第1期162卷 107026-107026页

作者： Hemati, Sobhan Kalra, Shivam Babaie, Morteza Tizhoosh, H. R. Univ Waterloo Kimia Lab Waterloo ON Canada Mayo Clin Rhazes Lab Artificial Intelligence & Informat Rochester MN 55905 USA

Considering their gigapixel sizes, the representation of whole slide images (WSIs) for classification and retrieval systems is a non-trivial task. Patch processing and multi-Instance learning (MIL) are common approaches to analyze WSIs. However, in end-to-end training, these methods require high GPU memory consumption due to the simultaneous processing of multiple sets of patches. Furthermore, compact WSI representations through binary and/or sparse representations are urgently needed for real-time image retrieval within large medical archives. To address these challenges, we propose a novel framework for learning compact WSI representations utilizing deep conditional generative modeling and the Fisher Vector Theory. The training of our method is instance-based, achieving better memory and computational efficiency during the training. To achieve efficient large-scale WSI search, we introduce new loss functions, namely gradient sparsity and gradient quantization losses, for learning sparse and binary permutation-invariant WSI representations called Conditioned Sparse Fisher Vector (C-deep-SFV), and Conditioned Binary Fisher Vector (C-deep-BFV). The learned WSI representations are validated on the largest public WSI archive, The Cancer Genomic Atlas (TCGA) and also Liver-Kidney-Stomach (LKS) dataset. For WSI search, the proposed method outperforms Yottixel and Gaussian Mixture Model (GMM)-based Fisher Vector both in terms of retrieval accuracy and speed. For WSI classification, we achieve competitive performance against state-of-art on lung cancer data from TCGA and the public benchmark LKS dataset.

关键词： Whole slide imaging image representation Fisher Vector Theory Multiple-instance learning

来源：评论

学校读者我要写书评

暂无评论

Object detection and recognition using deep learning-based techniques

引用

IET COMMUNICATIONS 2023年第13期17卷 1589-1599页

作者： Sharma, Preksha Gupta, Surbhi Vyas, Sonali Shabaz, Mohammad Model Inst Engn & Technol Jammu J&K India Univ Petr & Energy Studies Dehra Dun Uttarakhand India Arba Minch Univ Arba Minch Ethiopia

Object detection has received a lot of academic attention in recent years because of its tight association with video analysis and picture interpretation. With the fast growth of deep learning, more powerful tools capable of learning semantic, high-level, and deeper features are being offered to address difficulties in traditional architectures. These models react differently in terms of network design, training approach, and optimization function, among other things. This study describes multiple deep learning models and their characteristics for object detection in pictures and videos. Convolutional Neural Networks (CNN), models based on Region proposal, and models based on regression/classification are the many deep learning approaches. The study also discusses how deep learning approaches differ from one another and their weaknesses in comparison to the prior model. Face identification, pedestrian detection, autonomous driving, and other applications of object detection are also explored in this work. From the study, it was found that object recognition is a group of tasks for recognizing items in digital pictures. R-CNNs, or Region-based Convolutional Neural Networks, are a class of algorithms for tackling object localization and recognition problems that are optimized for model performance. You Only Look Once, or YOLO is a second family of object identification systems geared for speed and real-time application.

关键词： convolutional neural networks (CNN) deep learning image processing object-detection

来源：评论

学校读者我要写书评

暂无评论

real-time quantification of activated sludge concentration and viscosity through deep learning of microscopic images

引用

ENVIRONMENTAL SCIENCE AND ECOTECHNOLOGY 2025年 24卷 100527页

作者： Li, Hewen Tao, Yu Xu, Tiefu Wang, Hongcheng Yang, Min Chen, Ying Wang, Aijie Harbin Inst Technol Sch Ecoenvironm Shenzhen 518055 Peoples R China Heilongjiang Univ Sch Civil Engn Harbin 150080 Peoples R China

The parameters of activatedg sludge are crucial for the daily operation of wastewater treatment plants (WWTPs). In particular, mixed liquor suspended solids (MLSS) and apparent viscosity provide metrics for the biomass and rheological properties of activated sludge. Traditional methods for determining these parameters are time-consuming, require separate measurements for each index, and fail to provide realtime data for future 'smart' WWTPs. Here we show a real-time online microscopic image data analysis system that quantitatively identifies MLSS and apparent viscosity. Microscopic videos of activated sludge are captured in lab-scale sequencing batch reactors under chemical oxygen demand shock, yielding 41482 high-quality images. The Xception convolutional neural network architecture is used to establish both qualitative and quantitative correlations between these microscopic images and MLSS/apparent viscosity. The accuracies of qualitative identification for MLSS and apparent viscosity are both higher than 97%, and the quantitative correlation coefficients are 0.95 and 0.96, respectively. This quantitative correlation between microscopic images of activated sludge and its physical parameters, specifically MLSS and apparent viscosity, provides a basis for real-time online measurements of activated sludge parameters in WWTPs. (c) 2025 The Authors. Published by Elsevier B.V. on behalf of Chinese Society for Environmental Sciences, Harbin Institute of Technology, Chinese Research Academy of Environmental Sciences. This is an open access article under the CC BY-NC-ND license (http://***/licenses/by-nc-nd/4.0/).

关键词： Activated sludge MLSS Viscosity image deep learning

来源：评论

学校读者我要写书评

暂无评论

YOLO-VG: an efficient real-time recyclable waste detection network

引用

JOURNAL OF real-time image processing 2025年第2期22卷 1-15页

作者： Song, Limei Yu, Haibo Yang, Yangang Tong, Yu Ren, Siyuan Ye, Chenchao Tiangong Univ Tianjin Key Lab Intelligent Control Elect Equipmen Tianjin 300387 Peoples R China Tianjin Univ Technol & Educ Sch Mech Engn Tianjin 300222 Peoples R China

In the task of sorting waste using robots, it is necessary to determine the location and category information of waste. The key to the efficient work of the waste sorting robot lies in the accuracy of the target recognition. Traditional waste detection algorithms suffer from high computational cost, low detection accuracy, and poor adaptability, which cannot meet the actual detection needs. Therefore, this paper proposes an efficient and lightweight algorithm YOLO-VG based on the current mainstream algorithm YOLOv8s for waste detection and classification. The algorithm replaces the conventional convolution in the backbone network with GSConv to reduce redundant information and improve the model's inference process. ODConv replaces the regular convolution in the neck network to enhance the model's adaptability and generalization ability, thereby reducing the risk of overfitting. Additionally, the VoV-Ghost structure is introduced in the neck network to replace the original C2f, making the model more lightweight and efficient, meeting the requirements of real-time object detection in embedded devices or resource-constrained environments. Finally, the ECA attention mechanism is introduced to improve the ability of information interaction between feature channels in the model, thereby better capturing important information between images or features. Experimental results on the recyclable waste dataset demonstrate that the proposed YOLO-VG achieves a 24.6% improvement in computational efficiency, a 20.4% reduction in model size, and an mAP0.5 of 88.4%, surpassing the performance of the original YOLOv8s. These results indicate that YOLO-VG not only demonstrates excellent detection performance and stability, but also exhibits significant potential for widespread application in the field of waste sorting.

关键词： deep learning Object detection Waste recognition Lightweighting

来源：评论

学校读者我要写书评

暂无评论

A plant disease classification using one-shot learning technique with field images

引用

MULtimeDIA TOOLS AND APPLICATIONS 2023年第20期83卷 58935-58960页

作者： Saad, Mohamed H. Salman, Ahmed E. Egyptian Atom Energy Author Natl Ctr Radiat Res & Technol NCRRT Radiat Biol Dept Cairo Egypt

Early diagnosis of plant diseases is crucial for preventing plagues and mitigating their effects on crops. The most precise automatic methods for identifying plant diseases using images of plant fields are powered by deep learning. Big image datasets should always be gathered and annotated for these methods to work, which is often not technically or financially feasible. This paper offers one-shot learning (OSL) techniques for plant disease classification with limited datasets utilizing Siamese Neural Network (SNN). There are five different crop kinds in the dataset: grape, wheat, cotton, cucumber, and corn. Five sets of images showing both healthy and diseased crops are used to represent each of the new crops. The dataset's includes 25 classes with 875 leaf images. Data augmentation techniques are used to enhance the size and dimension of the plant leaf disease image dataset. To provide effective segmentation, this paper provides a unique method for region-based image segmentation that divides an image into its most prominent regions. It also addresses issues with earlier region-based segmentation methods. SVM-based classifiers have better generalization properties as their efficiency does not depend on the number of features. Such merit is beneficial in primary diagnostics decisions to check if the input image is included in the database or not to reduce the consumed time. OSL was applied and compared to standard fine-tuning transfer learning utilizing Siamese networks and triplet loss. Siamese provides superior classification accuracy and localization accuracy with minimal errors than other approaches. The proposed approach has a total processing time of 5 ms, which makes it appropriate for real-time applications. In terms of specificity, sensitivity, precision, accuracy, MCC, and F-measure, the proposed approach beats all current machine learning algorithms for small training sets.

关键词： Plant Disease Classification SVM Siamese One-Shot learning Fine-Tuning deep learning

来源：评论

学校读者我要写书评

暂无评论

An Impact Study of deep learning-based Low-light image Enhancement in Intelligent Transportation Systems

An Impact Study of Deep Learning-based Low-light Image Enhan...

引用

Conference on Multimodal image Exploitation and learning

作者： Jinadu, Obafemi Rajeev, Srijith Panetta, Karen A. Agaian, Sos S. Tufts Univ Dept Elect & Comp Engn Medford MA 02155 USA City Univ New York Dept Comp Sci New York NY USA

ISBN: (纸本)9781510673854;9781510673847

images and videos captured in poor illumination conditions are degraded by low brightness, reduced contrast, color distortion, and noise, rendering them barely discernable for human perception and ultimately negatively impacting computer vision system performance. These challenges are exasperated when processing video surveillance camera footage, using this unprocessed video data as-is for real-time computer vision tasks across varying environmental conditions within Intelligent Transportation Systems (ITS), such as vehicle detection, tracking, and timely incident detection. The inadequate performance of these algorithms in real-world deployments incurs significant operational costs. Low-light image enhancement (LLIE) aims to improve the quality of images captured in these unideal conditions. Groundbreaking advancements in LLIE have been recorded employing deep-learning techniques to address these challenges, however, the plethora of models and approaches is varied and disparate. This paper presents an exhaustive survey to explore a methodical taxonomy of state-of-the-art deep learning-based LLIE algorithms and their impact when used in tandem with other computer vision algorithms, particularly detection algorithms. To thoroughly evaluate these LLIE models, a subset of the BDD100K dataset, a diverse real-world driving dataset is used for suitable image quality assessment and evaluation metrics. This study aims to provide a detailed understanding of the dynamics between low-light image enhancement and ITS performance, offering insights into both the technological advancements in LLIE and their practical implications in real-world conditions. The project Github repository can be accessed here.

关键词： low-light image enhancement deep learning image restoration computer vision

来源：评论

学校读者我要写书评

暂无评论

Online News-Based Economic Sentiment Index

引用

IEEE TRANSACTIONS ON BIG DATA 2025年第3期11卷 1464-1474页

作者： Kang, Nathaniel Min, Dongeun Cho, Yonghun Ko, Dong-Whan Kim, Hyun Hak Choeh, Joon Yeon Im, Jongho Yonsei Univ Dept Stat Data Sci Seoul 03722 South Korea Korea Natl Def Univ Nonsan South Korea Kookmin Univ Dept Econ Seoul 02707 South Korea Sejong Univ Dept Software Seoul 05006 South Korea

The accurate prediction of industry trends has become increasingly challenging because of unforeseen events. To address this challenge, this study proposes a deep learning approach to generate an economic sentiment index by integrating Natural Language processing (NLP) models and image-clustering techniques. We first employ sampling techniques to create standardized online news datasets. Feature engineering techniques from the Korean Bidirectional Encoder Representations from Transformers (KoBERT) model are then used to generate relevance and sentiment scores for the textual data. Further, to enhance visualization and clustering, we transform the textual data into joint plot images, which are grouped into distinct clusters based on news categories. Finally, using Multi-criteria Decision Analysis, the various scores and cluster information are synthesized to generate the final economic sentiment index. This approach improves visualization and enhances the interpretability of the generated index. The proposed algorithm is applied to construct a new economic sentiment index for the Information and Communications Technology (ICT) industry in South Korea.

关键词： Economics Indexes Biological system modeling Industries Accuracy Sentiment analysis Surveys real-time systems deep learning Data models Data fusion deep learning economic index forecasting KoBERT

来源：评论

学校读者我要写书评

暂无评论

Automating quality control: real-time defect detection and automated decision-making with ai and doosan robotics

引用

INTERNATIONAL JOURNAL OF INTELLIGENT ROBOTICS AND APPLICATIONS 2025年 1-15页

作者： Chaabani, Ameni Cherif, Raef Yaddaden, Yacine Univ Quebec Rimouski Dept Math Data Sci & Engn Rimouski PQ G5L 3A1 Canada

In today's manufacturing industry, there is a growing need for precise and efficient quality control systems. This article proposes a real-time solution for identifying missing or damaged parts in a can by integrating computer vision, deep learning networks, robotics, and artificial intelligence. A collaborative robotic system was used to improve manufacturing efficiency. The system consists of a Doosan robot equipped with a 2.5D vision system and suction end-effectors for accurate object manipulation. The study involved collecting and augmenting a dataset using the Hough Transformation technique to isolate individual cans. Three pre-trained models, namely VGG16, MobileNet, and ResNet101, were used to detect defects on the can top through transfer learning. The performance of the models was evaluated in terms of accuracy, speed, and efficiency. The algorithm was successfully integrated into the robot, enabling it to perform real-time defect detection and classification autonomously. The implementation of this system showcased significant improvements in defect detection, highlighting the potential of automated technologies in industrial applications. The study also explores the implications of these findings for future enhancements, including the potential for increased system precision and the broader application of computer vision and artificial intelligence in manufacturing processes.

关键词： Computer vision Doosan robotics real-time object detection Artificial intelligence Automated decision-making Manufacturing efficiency image processing

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：