检索结果-内蒙古大学图书馆

Panoptic SwiftNet: Pyramidal Fusion for real-time Panoptic Segmentation

REMOTE SENSING 2023年第8期15卷 1968-1968页

作者： Saric, Josip Orsic, Marin Segvic, Sinisa Univ Zagreb Fac Elect Engn & Comp Zagreb 10000 Croatia Microblink Zagreb 10000 Croatia

Dense panoptic prediction is a key ingredient in many existing applications such as autonomous driving, automated warehouses, or remote sensing. Many of these applications require fast inference over large input resolutions on affordable or even embedded hardware. We proposed to achieve this goal by trading off backbone capacity for multi-scale feature extraction. In comparison with contemporaneous approaches to panoptic segmentation, the main novelties of our method are efficient scale-equivariant feature extraction, cross-scale upsampling through pyramidal fusion and boundary-aware learning of pixel-to-instance assignment. The proposed method is very well suited for remote sensing imagery due to the huge number of pixels in typical city-wide and region-wide datasets. We present panoptic experiments on Cityscapes, Vistas, COCO, and the BSB-Aerial dataset. Our models outperformed the state-of-the-art on the BSB-Aerial dataset while being able to process more than a hundred 1MPx images per second on an RTX3090 GPU with FP16 precision and TensorRT optimization.

关键词： panoptic segmentation real-time processing satellite imagery deep learning computer vision

来源：评论

学校读者我要写书评

暂无评论

Age Invariant Face Recognition using deep Sub-Pixel Resolution Features

Age Invariant Face Recognition using Deep Sub-Pixel Resoluti...

引用

Information Technology (OCIT), OITS International Conference on

作者： Pratham Khandelwal Ishita Mittal Dakshita Poddar Preety Singh The LNM Institute of Information Technology Jaipur India

Age-invariant face recognition has many real-world applications. Despite significant advances in this field, it is still challenging to accurately predict faces across various ages as a person’s age changes the face significantly over time, leading to a lot of intra-class variations. In this paper, we have attempted to use sub-pixel interpolation over an extracted face, as a pre-processing step for increasing image resolution, for age invariant face recognition. We have employed the Xception deep learning architecture over the Casia - Webface dataset for our experiments. We show that there is a significant enhancement in recognition accuracy when sub-pixel interpolation is used compared to when images are given to the deep learning model without any pre-processing.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design and implementation of a deep learning-based quality detection system for cork discs

Design and implementation of a deep learning-based quality d...

引用

10th International Symposium on Test Automation & Instrumentation (ISTAI 2024)

作者： Liguo Qu Guohao Chen Ke Liu Yuling Liu Jie Wu Hong Zhou School of Physics and Electronic Information Anhui Normal University Wuhu People's Republic of China

ISBN: (数字)9781837241910

High-quality badminton shuttlecock heads are made from cork discs derived from natural oak bark, which exhibit complex cracks and wrinkles, causing inefficiency and inconsistency in quality screening. To address this, we propose a deep learning-based detection algorithm using YOLOv5. The YOLOv5 model was optimized for cork disc characteristics by introducing an attention mechanism to enhance feature representation and designing a post-processing algorithm to improve detection accuracy. The optimized model, trained on a custom cork disc dataset using an NVIDIA RTX3080 GPU, achieved 86.7% mF1 and 81.5% mAP, outperforming other mainstream algorithms. Finally, the system utilizes Nvidia's edge computing device Jetson Nano as the computational core, deploying the YOLOv5 model and designing the graphical interface on Ubuntu 18.04. real-time cork disc image acquisition is achieved using binocular industrial cameras and fiber optic sensors, while a uniformly rotating turntable and diversion device are designed to facilitate the transfer of cork disc. Experimental results show that the system achieves a 92.75% classification accuracy for four quality grades with an inference time of 87.6ms, meeting the requirements for real-time cork disc quality inspection.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Smart library book sorting application with intelligence computer vision technology

引用

LIBRARY HI TECH 2021年第1期39卷 220-232页

作者： Shi, Xiaohua Tang, Kaicheng Lu, Hongtao Shanghai Jiao Tong Univ Lib Shanghai Peoples R China Univ Calif San Diego La Jolla CA 92093 USA Shanghai Jiao Tong Univ Shanghai Peoples R China

Purpose Book sorting system is one of specific application in smart library scenarios, and it now has been widely used in most libraries based on RFID (radio-frequency identification devices) technology. Book identification processing is one of the core parts of a book sorting system, and the efficiency and accuracy of book identification are extremely critical to all libraries. In this paper, the authors propose a new image recognition method to identify books in libraries based on barcode decoding together with deep learning optical character recognition (OCR) and describe its application in library book identification processing. Design/methodology/approach The identification process relies on recognition of the images or videos of the book cover moving on a conveyor belt. Barcode is printed on or attached to the surface of each book. deep learning OCR program is applied to improve the accuracy of recognition, especially when the barcode is blurred or faded. The approach the authors proposed is robust with high accuracy and good performance, even though input pictures are not in high resolution and the book covers are not always vertical. Findings The proposed method with deep learning OCR achieves best accuracy in different vertical, skewed and blurred image conditions. Originality/value Experiment demonstrates that the accuracy of the proposed method is high in real-time test and achieves good accuracy even when the barcode is blurred. deep learning is very effective in analyzing image content, and a corresponding series of methods have been formed in video content understanding, which can be a greater advantage and play a role in the application scene of intelligent library.

关键词： Smart library Book sorting system Computer vision deep learning OCR Video analysis

来源：评论

学校读者我要写书评

暂无评论

Automated detection and segmentation of cracks in concrete surfaces using joined segmentation and classification deep neural network

引用

CONSTRUCTION AND BUILDING MATERIALS 2023年 408卷

作者： Tabernik, Domen Suc, Matic Skocaj, Danijel Univ Ljubljana Fac Comp & Informat Sci Vecna Pot 113 Ljubljana Slovenia

Automated quality control of pavement and concrete surfaces is essential for maintaining structural integrity and consistency in the construction and infrastructure industries. This paper presents a novel deep learning model designed for automated quality control of these surfaces during both construction and maintenance phases. The model employs per-pixel segmentation and per-image classification, integrating both local and broader context information. Additionally, we utilize the classification results to improve segmentation during both training and inference stages. We evaluated the proposed model on a publicly available dataset containing more than 7,000 images of pavement and concrete cracks. The model achieved a Dice score of 81% and an intersection-over-union of 71%, surpassing publicly available state-of-the-art methods by at least 6-7 percentage points. An ablation study confirms that leveraging classification information enhances overall segmentation performance. Furthermore, our model is computationally efficient, processing over 30 FPS for 512 x 512 images, making it suitable for real-time applications on medium-resolution images. Code and the corrected dataset ground truths are publicly available: https://***/vicoslab/***.

关键词： Concrete crack segmentation deep learning Encoder-decoder architecture Automated quality control Joint segmentation and classification

来源：评论

学校读者我要写书评

暂无评论

Data Augmentation Techniques for Machine learning Applied to Optical Spectroscopy Datasets in Agrifood Applications: A Comprehensive Review

引用

SENSORS 2023年第20期23卷 8562-8562页

作者： Moises, Ander Gracia Pascual, Ignacio Vitoria Gonzalez, Jose Javier Imas Zamarreno, Carlos Ruiz Univ Publ Navarra Dept Elect Elect & Commun Engn Campus Arrosadia Pamplona 31006 NA Spain Pyroistech SL C Tajonar 22 Pamplona 31006 NA Spain Univ Publ Navarra Inst Smart Cities Campus Arrosadia Pamplona 31006 NA Spain

Machine learning (ML) and deep learning (DL) have achieved great success in different tasks. These include computer vision, image segmentation, natural language processing, predicting classification, evaluating time series, and predicting values based on a series of variables. As artificial intelligence progresses, new techniques are being applied to areas like optical spectroscopy and its uses in specific fields, such as the agrifood industry. The performance of ML and DL techniques generally improves with the amount of data available. However, it is not always possible to obtain all the necessary data for creating a robust dataset. In the particular case of agrifood applications, dataset collection is generally constrained to specific periods. Weather conditions can also reduce the possibility to cover the entire range of classifications with the consequent generation of imbalanced datasets. To address this issue, data augmentation (DA) techniques are employed to expand the dataset by adding slightly modified copies of existing data. This leads to a dataset that includes values from laboratory tests, as well as a collection of synthetic data based on the real data. This review work will present the application of DA techniques to optical spectroscopy datasets obtained from real agrifood industry applications. The reviewed methods will describe the use of simple DA techniques, such as duplicating samples with slight changes, as well as the utilization of more complex algorithms based on deep learning generative adversarial networks (GANs), and semi-supervised generative adversarial networks (SGANs).

关键词： optical spectroscopy agrifood industry artificial intelligence data augmentation (DA) generative adversarial networks (GANs)

来源：评论

学校读者我要写书评

暂无评论

Detection of Electronic Devices in real images using deep learning Techniques 5

Detection of Electronic Devices in real images using Deep Le...

引用

5th International Conference on Computer, Communication, and Signal processing, ICCCSP 2021

作者： Krijeshan, G. Raghul, P. Nachiappan, N.N. Beulah, A. Priyadharshini, R. Sri Sivasubramaniya Nadar College of Engineering Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9781665432771

Object Detection from real world scenario is a subset of Computer Vision, that uses state-of-the-art algorithms and techniques in deep learning to identify and locate the objects in an image or video. Latest advancements in deep learning, especially Convolutional Neural Networks (CNN) and in the field of image processing has further improved the process of object detection. deep learning algorithms that are developed over the years aim to solve several challenges associated with object detection which includes localizing the object in an image, classifying the object correctly with a high confidence score and realtime detection of objects. The performance of the existing algorithms involves a tradeoff between accuracy and detection speed. Algorithms like Faster Region based Convolutional Neural Networks (R-CNN) and Single Shot Detector (SSD) that achieved high accuracy in classifying objects were slow in detecting the objects. Such algorithms were not able to keep up with the pace of detection with video input in realtime and thus were not suitable for implementation in critical applications. The drawbacks associated with these algorithms can be eliminated by following a unified one-state approach. The approach is to fully identify and classify the required objects of interest by passing the image only once through the network. This approach thus decreases detection time considerably. You Only Look Once (YOLO) family of algorithms is one such single shot detector that uses CNNs to detect objects. In our work, we have used the YOLOv3 algorithm to develop a model that detects electronic devices. The model was also tested against realtime input from webcam and mean Average Precision (mAP) of YOLOv3 has been computed and compared with another model developed using Faster R-CNN. © 2021 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

An efficient joint framework assisted by embedded feature smoother and sparse skip connection for hyperspectral image classification

引用

INFRARED PHYSICS & TECHNOLOGY 2023年 135卷

作者： Li, Chunchao Tang, Xuebin Shi, Lulu Peng, Yuanxi Zhou, Tong Natl Univ Def Technol Coll Comp Sci & Technol State Key Lab High Performance Comp Chang Sha 410073 Peoples R China Natl Univ Def Technol Coll Adv Interdisciplinary Studies Chang Sha 410073 Peoples R China

deep neural network (DNN) methods play an essential role in hyperspectral classification. However, the massive parameters and vast computing overhead of DNN needs to be reduced when facing the deployment with limited storage and computing resources for real-time response applications, especially considering the high dimensionality of hyperspectral image. So, applying dimension reduction (DR) methods is a crucial pre-processing method in various studies. Still, most of them ignore the feature restoration after the data transformation by DR. In neural networks, many works still involve sophisticated skip connections and dense feature reuse, which can lead to feature redundancy and increase computational complexity, especially when DR methods have been applied first. Motivated by these issues, an efficient joint framework assisted by embedded feature smoother (FS) and sparse skip connection (SSC) is proposed in this article. Instead of directly feeding DR data into the subsequent network, we embedded a computing-cheap FS based on isotropic total variation to restore and enhance the spatial features. Furthermore, we proposed a SSC 3D convolution neural network to complete spatial-spectral feature representation and classification. The SSC is embodied in the design of log2n-skip connection to concatenate feature maps instead of dense connection, pruning the number of channels and reducing the model parameters. Experimental results show that the embedded FS significantly improves classification accuracy and is superior to other processing methods. Our framework offers much superior to other state-of-the-art deep learning-based methods considering classification performance and lightweight aspects, especially when using few training samples. Moreover, considering detailed processing steps, our framework has a competitively cheaper time consumption.

关键词： Hyperspectral image classification Feature smoother Sparse skip connection Lightweight neural network Efficient processing

来源：评论

学校读者我要写书评

暂无评论

Fully Unsupervised Dynamic MRI Reconstruction via Diffeo-Temporal Equivariance

Fully Unsupervised Dynamic MRI Reconstruction via Diffeo-Tem...

引用

IEEE International Symposium on Biomedical Imaging

作者： Andrew Wang Mike Davies Institute for Imaging Data and Communications School of Engineering University of Edinburgh Scotland

ISBN: (数字)9798331520526

ISBN: (纸本)9798331520533

Reconstructing dynamic MRI image sequences from undersampled accelerated measurements is crucial for faster and higher spatiotemporal resolution real-time imaging of cardiac motion, free breathing motion and many other applications. Classical paradigms, such as gated cine MRI, assume periodicity, disallowing imaging of true motion. Supervised deep learning methods are fundamentally flawed as, in dynamic imaging, ground truth fully-sampled videos are impossible to truly obtain. We propose an unsupervised framework to learn to reconstruct dynamic MRI sequences from undersampled measurements alone by leveraging natural geometric spatiotemporal equivariances of MRI. Dynamic Diffeomorphic Equivariant Imaging (DDEI) significantly outperforms state-of-the-art unsupervised methods such as SSDU on highly accelerated dynamic cardiac imaging. Our method is agnostic to the underlying neural network architecture and can be used to adapt the latest models and post-processing approaches. Our code and video demos are at https://***/Andrewwango/ddei.

关键词： Magnetic resonance imaging Dynamics Imaging Biomedical measurement Logic gates Loss measurement Spatiotemporal phenomena image reconstruction Unsupervised learning Videos

来源：评论

学校读者我要写书评

暂无评论

Building Collapse Detection Based on Satellite Remote Sensing images

Building Collapse Detection Based on Satellite Remote Sensin...

引用

International Conference on Digital Data processing (DDP)

作者： Can Dong Wenyin Song Rui Liu Zaozhuang Engineering Quality and Safety Service Center Jinan China Shandong Quality Inspection and Testing Center of Construction Engineering Co. Ltd Jinan China

ISBN: (数字)9798331515706

ISBN: (纸本)9798331515713

Due to the obvious diversity and complexity of damage patterns, geometries, and spatial scales of urban building complex earthquake hazards, conventional identification and assessment methods are less generalizable in real post-earthquake scenarios. Compared with time-range signals such as kinetic acceleration, image/video data provide a new source of perceptual information for accurately assessing the post-earthquake damage of urban building complexes. To realize the integrated, comprehensive, and rapid identification and assessment of the structural damage of urban buildings after an earthquake, this paper proposes a geometrically constrained deep learning framework for seismic damage identification and assessment of buildings based on computer vision. It systematically carries out a multi-scale seismic damage identification and assessment method that associates the “building group, building unit, and structural component” with the “building group, building unit, and structural component”. This paper proposes a geometrically constrained deep learning framework for seismic damage identification and assessment based on computer vision and systematically researches the identification and assessment of “building groups-building units-structural components”. A method for finely identifying densely distributed small-target buildings and rapid assessment of the collapse state after an earthquake based on satellite remote sensing images at high altitudes is proposed. A semantic segmentation network for post-earthquake building cluster identification and assessment is built, the influence law of the weight coefficients of the GCE loss on the segmentation performance of the model is systematically investigated, and the geometric feature optimization performance of the GCE loss in the training process and the multi-level feature extraction ability are analyzed, which verifies the effectiveness and accuracy of the geometrically constrained deep learning method for multi-scale

关键词： deep learning Training Satellites Semantic segmentation Buildings Earthquakes Feature extraction Remote sensing Optimization Drones

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：