检索结果-内蒙古大学图书馆

IEEE/CVF Conference on Computer Vision and pattern recognition (CVPR)

作者： Botina-Monsalve, D. Benezeth, Y. Miteran, J. Univ Bourgogne Franche Comte ImViA EA7535 Besancon France

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

The acquisition of remote photoplethysmography (rPPG) signals is important in multiple applications. Recently, deep-learning-based approaches such as 3D convolutional networks (3DCNNs) have outperformed traditional hand-crafted methods. However, despite their robust modeling ability, it is well known that large 3DCNN models have high computational costs and may be unsuitable for real-time applications. In this paper, we propose a study of the 3DCNN architecture, finding the best compromise between heart rate measurement precision and inference time. The fast inference is obtained decreasing the input size while the precision performance is obtained introducing a new time and frequency-based loss function by adding the signal-to-noise-ratio component to the regular Pearson's correlation loss function. In addition, changing the input color space from RGB to YUV also improved heart rate measurement precision. Using the VIPL-HR database, we retained the HR mean absolute error at 3.99 bpm which is comparable to 3.87 bpm of the state-of-the-art, while the GPU and CPU inference process improved around 88% from 51.77 ms to 2.32 ms in GPU and from 241.57 ms to 28.65 ms in CPU. The resulting network is called Real-Time rPPG (RTrPPG). We release the RTrPPG source code to encourage reproducibility(1).

关键词： Time-frequency analysis Three-dimensional displays image color analysis Computational modeling Graphics processing units Photoplethysmography Real-time systems

来源：评论

学校读者我要写书评

暂无评论

pattern recognition in Apple Orchards During Dormancy and Bud Development 4th

Pattern Recognition in Apple Orchards During Dormancy and ...

引用

4th International Conference on Smart Multimedia, ICSM 2024

作者： Sehgal, Bhavya Gandhi, Ritik Cheng, Irene Department of Computing Science University of Alberta EdmontonABT6G 2R3 Canada

ISBN: (纸本)9783031824746

Effective management of apple orchards during dormancy and bud development stages is crucial for optimizing fruit production and tree health. Automation using computer vision and deep learning techniques offers a promising solution for tree segmentation and labeling in complex outdoor environments. However, existing methods face challenges in accurately segmenting trees with bare branches and adapting to changing perspectives. This paper presents innovative solutions for bare tree segmentation and labeling, combining depth sensing and advanced image processing with deep learning approaches. The proposed methods address the limitations of current techniques, offering improved accuracy and robustness. We also introduce a novel tree labeling algorithm that utilizes spatial information and YOLOv4 for accurate tree identification and labeling across video frames. Experimental results demonstrate the effectiveness of our approach in handling complex outdoor conditions and bare tree segmentation. Our research contributes to advancing automated orchard management and precise monitoring during dormancy and bud development stages, enhancing fruit quality and overall orchard productivity. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Hyperspectral image Classification Method Using Multifeature Vectors and Optimized KELM

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND remote sensing 2021年 14卷 2781-2795页

作者： Chen, Huayue Miao, Fang Chen, Yijia Xiong, Yijun Chen, Tao Chengdu Univ Technol Minist Educ Key Lab Earth Explorat & Informat Technol Chengdu 610059 Peoples R China China West Normal Univ Sch Comp Sci Nanchong 637002 Peoples R China China West Normal Univ Internet Things Percept & Big Data Anal Key Lab N Nanchong 637002 Peoples R China Internet Things Percept & Big Data Anal Key Lab N Nanchong 637002 Peoples R China

To improve the accuracy and generalization ability of hyperspectral image classification, a feature extraction method integrating principal component analysis (PCA) and local binary pattern (LBP) is developed for hyperspectral images in this article. The PCA is employed to reduce the dimension of the spectral features of hyperspectral images. The LBP with low computational complexity is used to extract the local spatial texture features of hyperspectral images to construct multifeature vectors. Then, the gray wolf optimization algorithm with global search capability is employed to optimize the parameters of kernel extreme learning machine (KELM) to construct an optimized KELM model, which is used to effectively realize a hyperspectral image classification (PLG-KELM) method. Finally, the Indian pines dataset, Houston dataset, and Pavia University dataset and an application of WHU-Hi-LongKou dataset are selected to verify the effectiveness of the PLG-KELM. The comparison experiment results show that the PLG-KELM can obtain higher classification accuracy, and takes on better generalization ability for small samples. It provides a new idea for processing hyperspectral images.

关键词： Hyperspectral imaging Feature extraction image classification Kernel Principal component analysis Training Internet of Things Gray wolf optimization (GWO) hyperspectral image classification kernel extreme learning machine (KELM) local binary pattern (LBP) optimization principal component analysis (PCA)

来源：评论

学校读者我要写书评

暂无评论

Application of infrared image detection based on high-resolution image processing in motion recognition

引用

Optical and Quantum Electronics 2024年第4期56卷 615-615页

作者： Yu, Lingling Inner Mongolia Normal University Inner Mongolia Hohhot 010022 China

High-resolution remote sensing image fusion technology can combine multiple remote sensing images to display images more richly and accurately, and make them present more comprehensive and accurate image features. Because this technology has a high utilization rate of image processing, it has research significance. The objective of this study is to improve the accuracy and reliability of infrared image processing technology in motion recognition. In order to achieve this goal, this paper focuses on the research of high resolution image processing technology to improve the quality and clarity of infrared images. image enhancement algorithm is used to reduce the noise and blur effect in infrared images, image recovery technology is used to improve the resolution and detail representation ability of infrared images, and finally image segmentation and feature extraction algorithm are used to extract the motion features in infrared images. © 2024, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.

关键词： Action recognition High-resolution image Infrared image detection Sports training

来源：评论

学校读者我要写书评

暂无评论

Automatic detection and identification of ground vehicles with YOLO-based deep learning using MuSES-generated OPIR synthetic imagery 2

Automatic detection and identification of ground vehicles wi...

引用

Artificial Intelligence for Security and Defence Applications II 2024

作者： Klein, Mark D. Edel, Zachary J. Packard, Corey D. Hendrickson, Jacob N. Gibbs, Scott C. ThermoAnalytics Inc. 23440 Airpark Blvd. CalumetMI49913 United States

ISBN: (纸本)9781510681200

Space-based sensor platforms, including both current and planned future satellites, are capable of surveilling Earth-based objects and scenes from high altitudes. Overhead persistent infrared (OPIR) is a growing surveillance technique where thermal-waveband infrared sensors are deployed on orbiting satellites to look down and image the Earth. Challenges include having sufficient image resolution to detect, differentiate and identify ground-based objects while monitoring through the atmosphere. Demonstrations have shown machine learning algorithms to be capable of processing image-based scenes, detecting and recognizing targets amongst surrounding clutter. Performant algorithms must be robustly trained to successfully complete such a complex task, which typically requires a large set of training data on which statistical predictions can be based. Electro-optical infrared (EO/IR) remote sensing applications, including OPIR surveillance, necessitate a substantial image database with suitable variation for adept learning to occur. Diversity in background scenes, vehicle operational state, season, times of day and weather conditions can be included in training image sets to ensure sufficient algorithm input variety for OPIR applications. However, acquiring such a diverse overhead image set from measured sources can be a challenge, especially in thermal infrared wavebands (e.g., MWIR and LWIR) when adversarial vehicles are of interest. In this work, MuSES™ and CoTherm™ are used to generate synthetic OPIR imagery of several ground vehicles with a range of weather, times of day and background scenes. The performance of a YOLO ("you only look once") deep learning algorithm is studied and reported, with a focus on how image resolution impacts algorithm detection/recognition performance. The image resolution of future space-based sensor platforms will surely increase, so this study seeks to understand the sensitivity of OPIR algorithm performance to overhead image resolution.

关键词： image resolution

来源：评论

学校读者我要写书评

暂无评论

A Convolutional Fully Connected Structure with Hard Sample Memory Pool for Land Use Classification 32

A Convolutional Fully Connected Structure with Hard Sample M...

引用

Conference on pattern recognition and Tracking XXXII

作者： Xie, Dong Depoian, Arthur C., II Jaques, Lorenzo E. Bailey, Colleen P. Univ North Texas Dept Elect Engn Denton TX 76207 USA

ISBN: (数字)9781510643086

ISBN: (纸本)9781510643086

As one of the classic fields of computer vision, image classification has been booming with the improvement of chip performance and algorithm efficiency. With the rapid progress of deep learning in recent decades, remote sensing land cover and land use image classification has ushered in a golden period of development. This paper presents a new deep learning classifier to classify remote sensing land cover and land use images. The approach first uses multi-layer convolutional neural networks to extract the image features, attached through a fully-connected neural network to generate the sample loss. Then, a hard sample memory pool is created to collect the samples with large losses during the training. A batch of hard samples is randomly extracted from the memory pool to participate in the training of the convolutional fully connected model so that the model becomes more robust. Our method is validated by testing the classic remote sensing land cover and land use dataset. Compared with the previous popular classification algorithm, our algorithm can classify images more accurately with a shorter training iteration.

关键词： computer vision remote sensing deep learning neural networks land use classification

来源：评论

学校读者我要写书评

暂无评论

A Multi-Level Convolution Pyramid Semantic Fusion Framework for High-Resolution remote sensing image Scene Classification and Annotation

引用

IEEE ACCESS 2021年 9卷 18195-18208页

作者： Sun, Xiongli Zhu, Qiqi Qin, Qianqing Wuhan Univ State Key Lab Informat Engn Surveying Mapping & R Wuhan 430072 Peoples R China China Univ Geosci Sch Geog & Informat Engn Wuhan 430074 Peoples R China State Key Lab Resources & Environm Informat Syst Beijing Peoples R China

High spatial resolution (HSR) imagery scene classification has become a hot research topic in remote sensing. Scene classification method based on the handcrafted features, such as the bag-of-visual-words (BoVW) model, describes an image by extracting local features of the scene and mapping them to the dictionary space, but usually uses a shallow structure and loses the spatial distribution characteristics of the scene. The method based on deep learning extracts hierarchical features to describe the scene, which can maintain the spatial position information well. However, deep features in different levels have scale recognition restrictions for multi-scale ground objects, and cannot understand complex scenes well. In this paper, the multi-level convolutional pyramid semantic fusion (MCPSF) framework is proposed for HSR imagery scene classification. Differing from previous scene classification methods, which integrate the feature of different levels directly, of which the fusion features have large differences in both sparsity and eigenvalue magnitude, MCPSF integrates multi-level semantic features extracted by BoVW model and convolutional neural network (CNN) model. In MCPSF, two convolution pyramid feature expression strategies are proposed to enhance the ability of capturing multi-scale land objects, i.e., local and convolutional pyramid based BoVW (LCPB) model and local and convolutional pyramid based pooling-stretched (LCPP) model. The effectiveness of the proposed method is verified on 21-class UC Merced (UCM) dataset and 30-class Aerial image Dataset (AID). The framework was also transferred toa case study of scene annotation in Wuhan. The proposed framework significantly improves the performance when compared with other state-of-the-art methods.

关键词： Feature extraction image analysis Semantics remote sensing Visualization Convolution Training High spatial resolution image scene classification bag of visual words feature pyramid multi-level remote sensing

来源：评论

学校读者我要写书评

暂无评论

SAR Self-Enhanced by Electro-optical Network (SARSEEN) 31

SAR Self-Enhanced by Electro-optical Network (SARSEEN)

引用

Conference on Signal processing, Sensor/Information Fusion, and Target recognition XXXI

作者： Tran, Kenneth Sakla, Wesam Krim, Hamid North Carolina State Univ Dept Comp Sci Raleigh NC 27695 USA Lawrence Livermore Natl Lab Ctr Appl Sci Comp Livermore CA 94550 USA North Carolina State Univ Dept Elect & Comp Engn Raleigh NC 27695 USA

ISBN: (数字)9781510651210

ISBN: (纸本)9781510651210;9781510651203

In this work, we investigate the relationship between paired synthetic aperture radar (SAR) and optical images. SAR sensors have the capabilities of penetrating clouds and capturing data at night, whereas optical sensors cannot. Due to this, we are particularly interested in the case where we have access to both modalities during training, but only the SAR during test time. Our goal is to improve the performance of SAR only models by learning a self-generated prior about optical imagery. To that end, we developed a framework that consists of a deep neural network that inputs a SAR image and predicts a Canny edge map of the optical image. The Canny edge map retains structural information about the optical image, while removing superfluous high frequency details that is hard to generate from the SAR image. For downstream tasks, we concatenate the predicted edge map to the original SAR image and use that as the input. Our experiments show that by using this predicted edge map as additional information, we can outperform the same model that is only given the SAR image.

关键词： S AR multimodal fusion remote sensing

来源：评论

学校读者我要写书评

暂无评论

Dense-TNT: Efficient Vehicle Type Classification Neural Network Using Satellite imagery

引用

SENSORS 2024年第23期24卷 7662页

作者： Luo, Ruikang Song, Yaofeng Ye, Longfei Su, Rong Nanyang Technol Univ Sch Elect & Elect Engn Singapore 639798 Singapore

Accurate vehicle type classification plays a significant role in intelligent transportation systems. It is critical to understand the road conditions and usually contributive for the traffic light control system to respond correspondingly to alleviate traffic congestion. New technologies and comprehensive data sources, such as aerial photos and remote sensing data, provide richer and higher-dimensional information. In addition, due to the rapid development of deep neural network technology, image-based vehicle classification methods can better extract underlying objective features when processing data. Recently, several deep learning models have been proposed to solve this problem. However, traditional purely convolution-based approaches have constraints on global information extraction, and complex environments such as bad weather seriously limit their recognition capability. To improve vehicle type classification capability under complex environments, this study proposes a novel Densely Connected Convolutional Transformer-in-Transformer Neural Network (Dense-TNT) framework for vehicle type classification by stacking Densely Connected Convolutional Network (DenseNet) and Transformer-in-Transformer (TNT) layers. Vehicle data for three regions under four different weather conditions were deployed to evaluate the recognition capability. Our experimental findings validate the recognition ability of the proposed vehicle classification model, showing little decay even under heavy fog.

关键词： deep learning transformer remote sensing vehicle classification

来源：评论

学校读者我要写书评

暂无评论

Ground truth to fake geographies: machine vision and learning in visual practices

引用

AI & SOCIETY 2021年第4期36卷 1253-1262页

作者： Gil-Fournier, Abelardo Parikka, Jussi FAMU Prague Czech Republic Univ Southampton Southampton Hants England

This article investigates the concept of the ground truth as both an epistemic and technical figure of knowledge that is central to discussions of machine vision and media techniques of visuality. While ground truth refers to a set of remote sensing practices, it has a longer history in operational photography, such as aerial reconnaissance. Building on a discussion of this history, this article argues that ground truth has shifted from a reference to the physical, geographical ground to the surface of the images echoing earlier points raised by philosopher Jean-Luc Nancy that there is a ground of the image that is central to the task of analysis beyond representational practices. Furthermore, building on the practices of pattern recognition, composite imaging, and different interpretational techniques, we discuss contemporary practices of machine learning that mobilizes geographical earth observation datasets for experimental purposes, including tests such as "fake geography" as well as artistic practices, to show how ground truth is operationalized in such contexts of AI and visual arts.

关键词： remote sensing Machine vision Machine learning Visual culture Operational image

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：