检索结果-内蒙古大学图书馆

Development of Safety Check Support Device for Drivers Using Side Cameras on Rolling Stock

Quarterly Report of RTRI (Railway Technical Research Institute) 2024年第3期65卷 176-181页

作者： Goda, Wataru Mukojima, Hiroki Nagamine, Nozomi Image Analysis Laboratory Information and Communication Technology Division

This paper presents the development of a safety check support device aimed at further enhancing platform safety checks using side cameras installed on rolling stock. The device employs deep learning-based image processing techniques to detect passenger approach on platforms in real-time from camera footage, notifying the driver to assist with safety checks. Additionally, the device is equipped with automatic passenger counting functionality at each station. An overview of the developed device and the results of evaluation experiments are provided. © 2024 Ken-yusha Inc.. All rights reserved.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

learning Scene Representations for Human-assistive Displays Using Self-attention Networks

引用

ACM TRANSACTIONS ON MULtimeDIA COMPUTING COMMUNICATIONS AND APPLICATIONS 2024年第7期20卷 1–26页

作者： Ruiz-Serra, Jaime White, Jack Petrie, Stephen Kameneva, Tatiana Mccarthy, Chris Swinburne Univ Technol Hawthorn Vic Australia Univ Sydney Darlington Durham England Univ Melbourne Parkville Vic Australia

Video-see-through (VST) augmented reality (AR) is widely used to present novel augmentative visual experiences by processing video frames for viewers. Among VST AR systems, assistive vision displays aim to compensate for low vision or blindness, presenting enhanced visual information to support activities of daily living for the vision impaired/deprived. Despite progress, current assistive displays suffer from a visual information bottleneck, limiting their functional outcomes compared to healthy vision. This motivates the exploration of methods to selectively enhance and augment salient visual information. Traditionally, vision processing pipelines for assistive displays rely on hand-crafted, single-modality filters, lacking adaptability to time-varying and environment-dependent needs. This article proposes the use of deep Reinforcement learning (DRL) and Self-attention (SA) networks as a means to learn vision processing pipelines for assistive displays. SA networks selectively attend to task-relevant features, offering a more parameter-and compute-efficient approach to RL-based task learning. We assess the feasibility of using SA networks in a simulation-trained model to generate relevant representations of real-world states for navigation with prosthetic vision displays. We explore two prosthetic vision applications, vision-to-auditory encoding, and retinal prostheses, using simulated phosphene visualisations. This article introduces SA-px, a general-purpose vision processing pipeline using self-attention networks, and SA-phos, a display-specific formulation targeting low-resolution assistive displays. We present novel scene visualisations derived from SA image patches importance rankings to support mobility with prosthetic vision devices. To the best of our knowledge, this is the first application of self-attention networks to the task of learning vision processing pipelines for prosthetic vision or assistive displays.

关键词： Vision processing deep reinforcement learning prosthetic vision display algorithms

来源：评论

学校读者我要写书评

暂无评论

image-based characterization of laser scribing quality using transfer learning

引用

JOURNAL OF INTELLIGENT MANUFACTURING 2023年第5期34卷 2307-2319页

作者： Bisheh, Mohammad Najjartabar Wang, Xinya Chang, Shing, I Lei, Shuting Ma, Jianfeng Kansas State Univ Dept Ind & Manufactruing Syst Engn 2061 Rathbone Hall1701B Platt St Manhattan KS 66506 USA St Louis Univ Dept Aerosp & Mech Engn 3450 Lindell Blvd St Louis MO 63103 USA

Ultrafast laser scribing provides a new microscale materials processing capability. Due to the processing speed and high-quality requirement in modern industrial applications, it is important to measure and monitor quality characteristics in real time during a scribing process. Although deep learning models have been successfully applied for quality monitoring of laser welding and laser based additive manufacturing, these models require a large sample for training and a time-consuming data labelling procedure for a new application such as the laser scribing process. This paper presents a study on image-based characterization of laser scribing quality using a deep transfer learning model for several quality characteristics such as debris, scribe width, and straightness of a scribe line. images taken from the laser scribes on intrinsic Si wafers are examined. These images are labelled in a large and a small dataset, respectively. The large dataset includes 154 and small dataset includes 21 images. A novel transfer deep convolutional neural network (TDCNN) model is proposed to learn and assess scribe quality using the small dataset. The proposed TDCNN is able to overcome the data challenge by leveraging a convolutional neural network (CNN) model already trained for basic geometric features. Appropriate image processing techniques are provided to measure scribe width and line straightness as well as total scribe and debris area using classified images with 96 percent accuracy. Validating model's performance based on the small data set, the model trained with the large dataset has a similar accuracy of 97 percent. The trained TDCNN model was also applied to a different scribing application. With 10 additional images to retrain the model, the model accuracy performs as well as the original model at 96 percent. Based on the proposed TDCNN classification of debris on a scribed image of straight lines, two algorithms are proposed to compute scribe width and straightness. The

关键词： Laser scribing image processing Transfer learning Process monitoring

来源：评论

学校读者我要写书评

暂无评论

Novel hybrid CNN with Bi-LSTM multi-focus image fusion method based on modified tetrolet transform in MRI and CT images

引用

JOURNAL OF INTELLIGENT & FUZZY SYSTEMS 2023年第4期45卷 6767-6783页

作者： Nisha, A. S. Sivarani, T. S. Arunachala Coll Engn Women Dept CSE Nagercoil Tamil Nadu India Arunachala Coll Engn Women Dept EEE Nagercoil Tamil Nadu India

The process of fusing different images from various imaging modalities into a single, fused image that contains a wealth of information and improves the usability of medical images in real-world applications is known as medical image fusion. The most useful features from data can be automatically extracted by deep learning models. In the recent past, the field of image fusion has been preparing to introduce a deep learning model. In this work we can achieve the multi-Focus medical image fusion by hybrid deep learning models. Here the relevant health care data are collected from database (CT & MRI brain images). Following the input images are pre-processed using sliding window and the abnormal data is eliminated using distribution map method. Further the proposed work comprises 3 steps, 1) the proposed method is used to extract the features from the input image using the modified Tetrolet transform (MMT), which uses a brain image as an input image. This model is capable of identifying anomalous trends in time series data and automatically deriving from the input data characteristics that characterise the system state.2) Propose a novel hybrid model based on CNN with Bi-LSTM (Bi-directional Short Term Memory) multi-focus image fusion method to overcome the difficulty faced by the existing fusion methods. 3) This hybrid model are used to predict the brain tumor present in the fused image. Finally, experimental results are evaluated using a variety of performance measures. From the results, we can see that our suggested model contributes to an increase in predictive performance while also lowering the complexity in terms of storage and processing time.

关键词： CNN with Bi-LSTM hierarchical data fusion deep learning health care applications sliding window modified tetrolet transform multi-focus image fusion

来源：评论

学校读者我要写书评

暂无评论

The JPEG Pleno learning-Based Point Cloud Coding Standard: Serving Man and Machine

引用

IEEE ACCESS 2025年 13卷 43289-43315页

作者： Guarda, Andre F. R. Rodrigues, Nuno M. M. Pereira, Fernando Inst Telecomunicacoes P-1049001 Lisbon Portugal Politecn Leiria ESTG P-2411901 Leiria Portugal Univ Lisbon Inst Super Tecn P-1049001 Lisbon Portugal

Efficient point cloud coding has become increasingly critical for multiple applications such as virtual reality, autonomous driving, and digital twin systems, where rich and interactive 3D data representations may functionally make the difference. deep learning has emerged as a powerful tool in this domain, offering advanced techniques for compressing point clouds more efficiently than conventional coding methods while also allowing effective computer vision tasks performed in the compressed domain thus, for the first time, making available a common compressed visual representation effective for both man and machine. Taking advantage of this potential, JPEG has recently finalized the JPEG Pleno learning-based Point Cloud Coding (PCC) standard offering efficient lossy coding of static point clouds, targeting both human visualization and machine processing by leveraging deep learning models for geometry and color coding. The geometry is processed directly in its original 3D form using sparse convolutional neural networks, while the color data is projected onto 2D images and encoded using the also learning-based JPEG AI standard. The goal of this paper is to provide a complete technical description of the JPEG PCC standard, along with a thorough benchmarking of its performance against the state-of-the-art, while highlighting its main strengths and weaknesses. In terms of compression performance, JPEG PCC outperforms the conventional MPEG PCC standards, especially in geometry coding, achieving significant rate reductions. Color compression performance is less competitive but this is overcome by the power of a full learning-based coding framework for both geometry and color and the associated effective compressed domain processing.

关键词： Transform coding Point cloud compression Encoding Standards image coding Three-dimensional displays Geometry image color analysis Artificial intelligence Codecs JPEG Pleno standard learning-based coding man and machine point cloud coding

来源：评论

学校读者我要写书评

暂无评论

image Deblurring With image Blurring

引用

IEEE TRANSACTIONS ON image processing 2023年 32卷 5595-5609页

作者： Li, Ziyao Gao, Zhi Yi, Han Fu, Yu Chen, Boan Wuhan Univ Sch Remote Sensing & Informat Engn Wuhan 430079 Peoples R China Natl Univ Singapore Sch Comp Singapore 117417 Singapore Univ Calif Los Angeles Henry Samueli Sch Engn & Appl Sci Los Angeles CA 90095 USA

deep learning (DL) based methods for motion deblurring, taking advantage of large-scale datasets and sophisticated network structures, have reported promising results. However, two challenges still remain: existing methods usually perform well on synthetic datasets but cannot deal with complex real-world blur, and in addition, over- and under-estimation of the blur will result in restored images that remain blurred and even introduce unwanted distortion. We propose a motion deblurring framework that includes a Blur Space Disentangled Network (BSDNet) and a Hierarchical Scale-recurrent Deblurring Network (HSDNet) to address these issues. Specifically, we train an image blurring model to facilitate learning a better image deblurring model. Firstly, BSDNet learns how to separate the blur features from blurry images, which is adaptable for blur transferring, dataset augmentation, and ultimately directing the deblurring model. Secondly, to gradually recover sharp information in a coarse-to-fine manner, HSDNet makes full use of the blur features acquired by BSDNet as a priori and breaks down the non-uniform deblurring task into various subtasks. Moreover, the motion blur dataset created by BSDNet also bridges the gap between training images and actual blur. Extensive experiments on real-world blur datasets demonstrate that our method works effectively on complex scenarios, resulting in the best performance that significantly outperforms many state-of-the-art approaches.

关键词： deep learning disentanglement representation image deblurring image blurring scale-recurrent

来源：评论

学校读者我要写书评

暂无评论

SqueezeSlimU-Net: An Adaptive and Efficient Segmentation Architecture for real-time UAV Weed Detection

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2025年 18卷 5749-5764页

作者： Machidon, Alina L. Krasovec, Andraz Pejovic, Veljko Machidon, Octavian M. Univ Ljubljana Fac Comp & Informat Sci Ljubljana 1000 Slovenia Inst Jozef Stefan Comp Syst Dept Ljubljana 1000 Slovenia

The limited processing capacity of computing equipment that is usually mounted on unmanned aerial vehicles (UAVs) often prevents real-time execution of computer vision tasks, such as image segmentation. In this article, we introduce SqueezeSlimU-Net (SSU-Net), an adaptive and efficient deep learning (DL) model designed to enhance UAV capabilities in performing complex image segmentation tasks under resource constraints, thereby advancing real-time UAV vision-a crucial technology in fields, such as precision agriculture. SSU-Net combines benefits of three specialized DL architectures: the semantic segmentation capabilities of the U-Net architecture, the computational efficiency of SqueezeNet's fire modules, and the dynamic adaptability of slimmable neural networks. This integration allows SSU-Net to adjust its network width in real-time, thus striking the balance between inference accuracy and computational load based on the operational parameters such as task requirements and UAV's battery life. To validate SSU-Net's efficacy, we applied it to a weed detection task using two UAV-collected datasets and tested it on an edge computing platform for UAVs. Our experiments show that SSU-Net can reduce inference energy consumption by up to 65% with only a minimal 2% reduction in accuracy. A comparative evaluation with other state-of-the-art DL image segmentation approaches shows that SSU-Net achieves on par weed detection performance while requiring significantly fewer model parameters. In addition, SSU-Net outperforms state-of-the-art network pruning techniques in balancing accuracy and resource usage. Timing benchmarks show SSU-Net fostering real-time weed detection even on low-resource UAVs, making it ideal for UAV remote sensing applications.

关键词： Adaptive neural networks computational effi- ciency image segmentation precision agriculture precision agriculture real-time unmanned aerial vehicle (UAV) vision real-time unmanned aerial vehicle (UAV) vision weed detection weed detection weed detection

来源：评论

学校读者我要写书评

暂无评论

Modern deep learning Techniques for Big Medical Data processing in Cloud

引用

IEEE ACCESS 2025年 13卷 62005-62028页

作者： Shakor, Mohammed Y. Khaleel, Mustafa Ibrahim Univ Garmian Coll Comp & Informat Technol Informat Technol Dept Kalar 46021 Iraq Univ Sulaimani Coll Sci Dept Comp Sulaymaniyah 46001 Iraq

The recent advancements in Machine learning (ML) and deep learning (DL) provide a new dimension in biomedical big data analysis, while the cloud computing technologies present the breakthroughs of handling massive data from hardware, software, and storage. Therefore, in this paper, an examination of the characteristics and challenges of big data is conducted with, highlighting the need for sophisticated analytical approaches. The paper then explores a wide spectrum of ML techniques, including unsupervised, supervised, and reinforcement learning methods, and their applications in big data contexts. This study explores recent advancement in DL architectures, while examining their effectiveness. Furthermore, we will show main challenges and limitations associated with using ML and DL in big data settings, including computational complexity, issues of data quality, model interpretability, and ethical concerns. Finally, it concludes by discussing the trends and future directions that are upcoming, including federated learning, explainable AI, and edge computing. Additionally, an experimental case study is presented to validate our approach, demonstrating its effectiveness in real-world healthcare scenarios through improved diagnostic accuracy and reduced computational time. Results have shown that the incorporation of DL techniques, such as CNN and RNN, forms the basis for large-scale analytics in medical data analytics due to their great contribution toward the development of accuracy and scalability. In specific research on disease prediction and medical image diagnosis within the healthcare industry, there was an improvement in diagnostics by up to 20%, with a reduction in computation time achieved via cloud-based architecture. These developments demonstrate the high extent of integration between DL and cloud computing in handling the challenge of bulk medical datasets and providing practical insight for both researchers and health professionals.

关键词： Big Data Medical diagnostic imaging Cloud computing Medical services Computer architecture Reviews Bioinformatics Heuristic algorithms Ethics deep learning Big data medical data DL cloud computing clustering classification CNN SVM ANN DNN

来源：评论

学校读者我要写书评

暂无评论

PhenoAI: A deep learning Python framework to process close-range time-lapse PhenoCam data

引用

ECOLOGICAL INFORMATICS 2025年 88卷

作者： Kumar, Akash Khare, Siddhartha Rossi, Sergio Indian Inst Technol Roorkee Dept Civil Engn Geospatial Engn Haridwar 247667 Uttarakhand India Bhoomicam Pvt Ltd Haridwar 247667 Uttarakhand India Univ Quebec Chicoutimi Dept Sci Fondamentales Lab Ecosyst Terr Boreaux Chicoutimi PQ Canada

Close-range digital repeat photography is a powerful technique for studying phenology and the seasonal dynamics of plants. However, the processing of PhenoCam images is time-consuming and requires substantial human expertise. This paper describes PhenoAI, a Python framework that automates the processing of time-series PhenoCam images. The package consists of four modules: (i) image quality control, (ii) vegetation segmentation using deep learning, (iii) greenness index calculation, and (iv) parameter extraction. These modules are consistent with the standard and established methodologies used in the literature. We demonstrate the application of the PhenoAI package in a case study by analyzing black spruce [Picea mariana (Mill.) B.S.P.] phenology in Quebec, Canada, over five years (2017-2021). The result revealed that the Start of Season (SOS) of Green Chromatic Coordinate (GCC) occurred in the third week of May (DOY 144 +/- 5), End of Season (EOS) occurred in the end of September (DOY 269 +/- 20) and day of maximum greenness occurred in the first week of July (DOY 183 +/- 5). The findings correlate with the previous studies in the same region and species, confirming the ability of the PhenoAI to replicate field observations accurately. PhenoAI is an open-source software package that can be customized to suit specific research needs, reduces significantly the processing time, and simplifies the workflow, making it accessible for use by new users for close range observations taken by PhenoCam. PhenoAI will enhance efficiency and accuracy of data extraction for scientists using phenological data for ecological and forestry research.

关键词： Close-range Remote Sensing GCC Forest Phenology PhenoCam Python deep learning

来源：评论

学校读者我要写书评

暂无评论

real-time and accurate deep learning-based multi-organ nucleus segmentation in histology images

引用

JOURNAL OF real-time image processing 2024年第2期21卷 43-43页

作者： Ahmed, Noha Y. Egyptian Atom Energy Author EAEA Radiat Engn Dept Cairo Egypt

Automated nucleus segmentation is considered the gold standard for diagnosing some severe diseases. Accurate instance segmentation of nuclei is still very challenging because of the large number of clustered nuclei, and the different appearance of nuclei for different tissue types. In this paper, a neural network is proposed for fast and accurate instance segmentation of nuclei in histopathology images. The network is inspired by the Unet and residual nets. The main contribution of the proposed model is enhancing the classification accuracy of nuclear boundaries by moderately preserving the spatial features by relatively d the size of feature maps. Then, a proposed 2D convolution layer is used instead of the conventional 3D convolution layer, the core of CNN-based architectures, where the feature maps are first compacted before being convolved by 2D kernel filters. This significantly reduces the processing time and avoids the out of memory problem of the GPU. Also, more features are extracted when getting deeper into the network without degrading the spatial features dramatically. Hence, the number of layers, required to compensate the loss of spatial features, is reduced that also reduces the processing time. The proposed approach is applied to two multi-organ datasets and evaluated by the Aggregated Jaccard Index (AJI), F1-score and the number of frames per second. Also, the formula of AJI is modified to reflect the object- and pixel-level errors more accurately. The proposed model is compared to some state-of-the-art architectures, and it shows better performance in terms of the segmentation speed and accuracy.

关键词： Unet Residual learning Convolution layer Nuclei instance segmentation Histology images

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：