检索结果-内蒙古大学图书馆

Advancements in underwater imaging through machine learning: Techniques, challenges, and applications

Multimedia Tools and Applications 2024年 1-20页

作者： Naveen, Palanichamy Department of Electrical and Electronics Engineering KPR Institute of Engineering and Technology Coimbatore641407 India

Underwater imaging plays a critical role in various fields such as marine biology, environmental monitoring, underwater archaeology, and defense. However, it faces unique challenges including light absorption and scattering, limited visibility, color distortion, and dynamic underwater conditions. Recent advancements in machine learning have provided powerful tools to address these challenges, significantly improving the quality and analysis of underwater images. This review comprehensively explores the intersection of underwater imaging and machine learning, covering supervised learning, unsupervised learning, deep learning, and reinforcement learning techniques. I discuss key applications such as marine species identification, coral reef monitoring, autonomous underwater navigation, archaeological site exploration, and environmental monitoring. Additionally, I examine publicly available datasets, benchmarking methods, and evaluation metrics essential for developing and accessing machine learning models in this domain. Through detailed case studies and practical implementations, I highlight the strengths and weaknesses of various approaches. Emerging trends such as the integration of AI with robotics, advancements in imaging hardware, and the development of specialized algorithms are also discussed. Future directions include enhanced image processing techniques, interdisciplinary collaborations, and real-time processing capabilities. This review aims to provide a comprehensive overview of the current state of underwater imaging and machine learning, highlighting the potential for continued research and innovation in this rapidly evolving field. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Environmental monitoring

来源：评论

学校读者我要写书评

暂无评论

deep Efficient Continuous Manifold learning for time Series Modeling

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2024年第1期46卷 171-184页

作者： Jeong, Seungwoo Ko, Wonjun Mulyadi, Ahmad Wisnu Suk, Heung-Il Korea Univ Dept Artificial Intelligence Seoul 02841 South Korea Korea Univ Dept Brain & Cognit Engn Seoul 02841 South Korea

Modeling non-euclidean data is drawing extensive attention along with the unprecedented successes of deep neural networks in diverse fields. Particularly, a symmetric positive definite matrix is being actively studied in computer vision, signal processing, and medical image analysis, due to its ability to learn beneficial statistical representations. However, owing to its rigid constraints, it remains challenging to optimization problems and inefficient computational costs, especially, when incorporating it with a deep learning framework. In this paper, we propose a framework to exploit a diffeomorphism mapping between Riemannian manifolds and a Cholesky space, by which it becomes feasible not only to efficiently solve optimization problems but also to greatly reduce computation costs. Further, for dynamic modeling of time-series data, we devise a continuous manifold learning method by systematically integrating a manifold ordinary differential equation and a gated recurrent neural network. It is worth noting that due to the nice parameterization of matrices in a Cholesky space, training our proposed network equipped with Riemannian geometric metrics is straightforward. We demonstrate through experiments over regular and irregular time-series datasets that our proposed model can be efficiently and reliably trained and outperforms existing manifold methods and state-of-the-art methods in various time-series tasks.

关键词： Cholesky space deep learning manifold learning manifold ordinary differential equation multivariate time series modeling symmetric positive definite matrix

来源：评论

学校读者我要写书评

暂无评论

The Application of 6G and Augmented reality Technology in Education and Training

引用

WIRELESS PERSONAL COMMUNICATIONS 2024年 1-19页

作者： Zhang, Yangloucai Bin Azizui, Muhammad Farid Azizul Yan, Cong Univ Teknol Malaysia Fac Built Environm & Surveying Skudai 81200 Malaysia Chengdu Neusoft Univ Sch Digital Art & Design Chengdu 61000 Peoples R China Univ Teknol Malaysia Coll Educ & Surveying Skudai 81200 Malaysia

The short evolution of 6G and augmented reality (AR) technology heralds a transformative era in education and training, promising to redefine traditional learning paradigms using immersive, interactive reports. This paper explores the integration of advanced capsule networks (CapsNet) architectures with semantic segmentation techniques to cope with the inherent annoying conditions of applying 6G and AR in academic contexts. CapsNets, well known for its efficiency in discerning spatial hierarchies and relationships, are paired with semantic segmentation to enhance object recognition and interplay within AR environments. It offers a deep, contextual understanding essential for growing dynamic, personalised learning studies. The synergy among this technology allows for the unique delineation and classification of each image pixel into corresponding object training, facilitating seamless interaction among virtual content and the real world. Need of the highly dependable, low-latency communication exchange skills of 6G, this combination guarantees powerful processing of complex scenes in real-time, crucial for preserving student engagement and facilitating adaptive learning pathways. The paper discusses optimisation techniques for real-time performance, including version pruning and effective routing mechanisms, to cope with the computational needs of CapsNets and semantic segmentation. Moreover, it highlights the role of 6G in assisting the bandwidth and latency necessities critical for deploying these state-of-the-art AI models in AR-based instructional programs. Through this integration, we aim to release new potentials for personalised, context-aware learning experiences, which can considerably enhance knowledge retention, engagement, and accessibility in education and training across various fields.

关键词： 6G Augmented reality Capsule networks Semantic segmentation Training Personalised learning

来源：评论

学校读者我要写书评

暂无评论

Analysis of Students' Class Status Based on deep learning 20th

Analysis of Students' Class Status Based on Deep Learning

引用

20th Chinese Intelligent Systems Conference

作者： Liu, Qunpo Zhang, Xiaojie Wu, Hongpei Henan Polytech Univ Jiaozuo 454003 Henan Peoples R China Henan Int Joint Lab Direct Drive & Control Intell 2001 Century Ave Jiaozuo 454003 Henan Peoples R China

ISBN: (纸本)9789819786565;9789819786541;9789819786534

Aiming at the problem that it is difficult for teachers to obtain accurate classroom status in daily teaching process, which is not conducive to making targeted adjustments to teaching methods, this paper proposes a deep learning-based student class status analysis system. The system uses camera to capture classroom video, and uses image recognition, target detection, deep learning and other technologies to detect the behavioral state of students in the classroom in real time and concentration information, and through the statistical analysis of the collected data, it helps the teacher to get timely feedback in the classroom, and better judge the learning state and concentration of students. In order to realize the real-time and accuracy of the system design, the system in the paper introduces the OpenPose model into the YOLOv5 network to identify the students' skeletal keypoints, and synthesizes the results of the processing of the YOLOv5 model and the OpenPose model to make an analysis of the students' classroom behaviors and concentration. The experimental results show that the loss curve can achieve good convergence, and the AP and mAP can reach 95.1% and 88.0%, respectively.

关键词： Student status detection deep learning YOLOv5 OpenPose

来源：评论

学校读者我要写书评

暂无评论

Multi-Stream Scheduling of Inference Pipelines on Edge Devices - a DRL Approach

引用

ACM TRANSACTIONS ON DESIGN AUTOMATION OF ELECTRONIC SYSTEMS 2024年第6期29卷 1-36页

作者： Pereira, Danny Ghosh, Sumana Dey, Soumyajit Indian Inst Technol Kharagpur Comp Sci & Engn Kharagpur West Bengal India Indian Stat Inst Comp & Commun Sci Div Kolkata West Bengal India

Low-power edge devices equipped with Graphics processing Units (GPUs) are a popular target platform for real-time scheduling of inference pipelines. Such application-architecture combinations are popular in Advanced Driver-assistance Systems for aiding in the real-time decision-making of automotive controllers. However, the real-time throughput sustainable by such inference pipelines is limited by resource constraints of the target edge devices. Modern GPUs, both in edge devices and workstation variants, support the facility of concurrent execution of computation kernels and data transfers using the primitive of streams, also allowing for the assignment of priority to these streams. This opens up the possibility of executing computation layers of inference pipelines within a multi-priority, multi-stream environment on the GPU. However, manually co-scheduling such applications while satisfying their throughput requirement and platform memory budget may require an unmanageable number of profiling runs. In this work, we propose a deep Reinforcement learning (DRL)-based method for deciding the start time of various operations in each pipeline layer while optimizing the latency of execution of inference pipelines as well as memory consumption. Experimental results demonstrate the promising efficacy of the proposed DRL approach in comparison with the baseline methods, particularly in terms of real-time performance enhancements, schedulability ratio, and memory savings. We have additionally assessed the effectiveness of the proposed DRL approach using a real-time traffic simulation tool IPG CarMaker.

关键词： Convolutional neural network edge device GPU deep reinforcement learning real-time scheduling

来源：评论

学校读者我要写书评

暂无评论

TSDN: Two-Stage Raw Denoising in the Dark

引用

IEEE TRANSACTIONS ON image processing 2023年 32卷 3679-3689页

作者： Chen, Wenshu Huang, Yujie Wang, Mingyu Wu, Xiaolin Zeng, Xiaoyang Fudan Univ Coll Microelect State Key Lab ASIC & Syst Shanghai 200000 Peoples R China Shanghai ExploreX Technol Co Ltd Shanghai 200120 Peoples R China McMaster Univ Dept Elect & Comp Engn Hamilton ON L8G 4K1 Canada Shanghai ExploreX Technol Co Ltd Shanghai 200120 Peoples R China

Denoising is one of the most significant procedures in the image processing pipeline. Nowadays, deep-learning-based algorithms have achieved superior denoising quality than traditional algorithms. However, the noise becomes severe in the dark environment, where even the SOTA algorithms fail to achieve satisfactory performance. Besides, the high computational complexity of deep-learning-based denoising algorithms makes them hardware unfriendly and difficult to process high-resolution images in real-time. To address these issues, a novel low-light RAW denoising algorithm Two-Stage-Denoising (TSDN), is proposed in this paper. In TSDN, denoising consists of two procedures: noise removal and image restoration. Firstly, in the noise-removal stage, most noise is removed from the image, and an intermediate image that is easier for the network to recover the clean image is obtained. Then, in the restoration stage, the clean image is restored from the intermediate image. The TSDN is designed to be light-weight for real-time and hardware friendly. However, the tiny network will be insufficient for satisfactory performance if directly trained from scratch. Therefore, we present an Expand-Shrink-learning (ESL) method to train the TSDN. In the ESL method, firstly, the tiny network is expanded to a larger one with similar architecture but more channels and layers, which enhances the learning ability of the network because of more parameters. Secondly, the larger network is shrunk and restored to the original small network in fine-grained learning procedures, including Channel-Shrink-learning (CSL) and Layer-Shrink-learning (LSL). Experimental results demonstrate that the proposed TSDN achieves better performance (PSNR and SSIM) than other SOTA algorithms in the dark environment. Besides, the model size of TSDN is one-eighth of that of the U-Net for denoising (a classical denoising network).

关键词： image processing denoising light-weight network

来源：评论

学校读者我要写书评

暂无评论

Recognition of vehicle license plates in highway scenes with deep fusion network and connectionist temporal classification

引用

IET image processing 2024年第13期18卷 4066-4080页

作者： Hua, Liru Ma, Xinyi Zhao, Chihang Zhang, Bailing Su, Zijun Wu, Yuhang Southeast Univ Sch Transportat Nanjing 210096 Peoples R China NingboTech Univ Sch Comp & Data Engn Ningbo Peoples R China

License plate recognition is crucial in Intelligent Transportation Systems (ITS) for vehicle management, traffic monitoring, and security inspection. In highway scenarios, this task faces challenges such as diversity, blurriness, occlusion, and illumination variation of license plates. This article explores Recurrent Neural Networks based on Connectionist Temporal Classification (RNN-CTC) for license plate recognition in challenging highway conditions. Four neural network models: ResNet50, ResNeXt, InceptionV3, and SENet, all combined with RNN-CTC are comparatively evaluated. Furthermore, a novel architecture named ResNet50 deep Fusion Network using Connectionist Temporal Classification (ResNet50-DFN-CTC) is proposed. Comparative and ablation experiments are conducted using the Highway License Plate Dataset of Southeast University (HLPD-SU). Results demonstrate the superior performance of ResNet50-DFN-CTC in challenging highway conditions, achieving 93.158% accuracy with a processing time of 7.91 ms, outperforming other tested models. This research contributes to advancing license plate recognition technology for real-world highway applications under adverse conditions. We propose a novel architecture named ResNet50 deep Fusion Network using Connectionist Temporal Classification (ResNet50-DFN-CTC). Comparative and ablation experiments are conducted using the Highway License Plate Dataset of Southeast University (HLPD-SU). Results demonstrate the superior performance of ResNet50-DFN-CTC in challenging highway conditions, achieving 93.158% accuracy with a processing time of 7.91 ms, outperforming other tested models. This research contributes to advancing license plate recognition technology for real-world highway applications under adverse conditions. image

关键词： computer vision image classification image recognition neural nets pattern recognition

来源：评论

学校读者我要写书评

暂无评论

A Survey on deep learning Based Forest Environment Sound Classification at the Edge

引用

ACM COMPUTING SURVEYS 2024年第3期56卷 1-36页

作者： Meedeniya, Dulani Ariyarathne, Isuru Bandara, Meelan Jayasundara, Roshinie Perera, Charith Univ Moratuwa Dept Comp Sci & Engn Moratuwa 10400 Sri Lanka Cardiff Univ Sch Comp Sci & Informat Cardiff CF24 3AA Wales

Forest ecosystems are of paramount importance to the sustainable existence of life on earth. Unique natural and artificial phenomena pose severe threats to the perseverance of such ecosystems. With the advancement of artificial intelligence technologies, the effectiveness of implementing forest monitoring systems based on acoustic surveillance has been established due to the practicality of the approach. It can be identified that with the support of transfer learning, deep learning algorithms outperform conventional machine learning algorithms for forest acoustic classification. Further, a clear requirement to move the conventional cloud-based sound classification to the edge is raised among the research community to ensure real-time identification of acoustic incidents. This article presents a comprehensive survey on the state-of-the-art forest sound classification approaches, publicly available datasets for forest acoustics, and the associated infrastructure. Further, we discuss the open challenges and future research aspects that govern forest acoustic classification.

关键词： Sound processing edge computing deep learning artificial intelligence Internet of Things

来源：评论

学校读者我要写书评

暂无评论

An improved YOLOv8 method for identifying empty cell and unqualified plug seedling

引用

JOURNAL OF real-time image processing 2024年第6期21卷 188页

作者： Li, Lei Yu, Jiajia Lu, Yujun Gu, Yue Liang, Sijia Hao, Shuai Zhejiang Sci Tech Univ Hangzhou 310018 Zhejiang Peoples R China Zhejiang Inst Mech & Elect Engn Hangzhou 310053 Zhejiang Peoples R China Zhejiang Modern Agr Equipment Design & Res Inst Hangzhou 310003 Zhejiang Peoples R China

A lightweight seedling detection model with improved YOLOv8s is proposed to address the seedling identification problem in the replenishment process in industrial vegetable seedling *** CBS module for feature extraction in Backbone and Neck has been replaced with a lightweight depthwise separable convolution (DSC) in order to reduce the number of model parameters and increase the speed of detection. Furthermore, the fifth layer of Backbone has been augmented with efficient multiscale attention (EMA), which can aggregate multi-scale spatial structure information more rapidly through the two branches of the parallel structure, thereby enhancing the extraction of multi-scale features. Ultimately, the computational complexity of the model is further reduced by enhancing the structure of the bottleneck to form the VoVGSCSP module, which replaces the C2f module in Neck. The mAP of the improved model on the test set is 96.2%, its parameters, GFLOPS, and model size are 7.88 M, 20.9, and 16.1 MB, respectively. The detection speed of the algorithm is 116.3 frames per second (FPS), which is higher than that of the original model (107.5 FPS). The results indicate that the improved model can accurately identify empty cell and unqualified seedling in the plug tray in real time and has a smaller number of parameters and GFLOPS, making it suitable for use on embedded or mobile devices for seedling replenishment and contributing to the realization of automated and unmanned seedling replenishment.

关键词： deep learning Seedling recognition YOLOv8s Lightweighting Attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Automatic Merging Method for Sectional Map Based on deep learning

引用

SENSORS AND MATERIALS 2024年第10期36卷 4329页

作者： Liu, Shifan Xing, Chen Dong, Chengwei Li, Yunhan Cao, Peirun Beijing Inst Surveying & Mapping 15 Yangfangdian Rd Beijing 10038 Peoples R China Beijing Key Lab Urban Spatial Informat Engn 15 Yangfangdian Rd Beijing 10038 Peoples R China

Owing to time and scene constraints, a significant number of sectional maps exist in paper form. These maps contain a vast amount of data and hold high information value. However, they often suffer from issues such as annotations, stains, deformation, and missing content during preservation. Traditional processing methods require a large amount of manual image registration, which is extremely inconvenient. In this study, a map image labeling program is designed using OpenCV to prepare a map image dataset, and the U2Net-p algorithm for map segmentation is trained on this dataset. Furthermore, a comprehensive method for automatically merging sectional maps is designed and implemented, which can repair and process sectional maps and seamlessly integrate them into target grids according to map sheet numbering rules. This method has been applied to the production of base maps for natural resource demarcation projects, achieving a stitching accuracy of 96.67% on marked anchor points and considerably improving processing speed. This indicates that our approach has broad application value in the field of automatic stitching and fusion of sectional map images.

关键词： deep learning computer vision sectional map image registration base map production

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：