检索结果-内蒙古大学图书馆

Signal, Information and Data processing (ICSIDP), IEEE International Conference on

作者： Tingting Qiao He Chen Bingqian Chai Wenchao Liu Guijie Qi Yizhuang Xie National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing Institute of Technology Beijing China

ISBN: (数字)9798331515669

ISBN: (纸本)9798331515676

Recent advancements in remote sensing object detection have progressed, but distinguishing objects from complex backgrounds remains difficult, especially for tiny objects. To address this, we introduce the Advanced Scale-Aware Attention (ASA) module, which retains key channel information while minimizing computational cost. This module reorganizes channels into the batch dimension and splits them into multiple sub-features. The ASA module contains three branches: the first encodes weights based on scale and channel relationships. The second and third branches use different convolution kernel sizes to capture features across various receptive fields. These branches collaborate to enhance pixel-level relationships, improving foreground-background contrast. On the AI-TOD dataset, our method improved AP50 by 8.6% over state-of-the-art approaches.

关键词： image resolution Convolution Object detection Feature extraction Data processing Sensors Object recognition Kernel remote sensing Signal resolution

来源：评论

学校读者我要写书评

暂无评论

Deeply Fine-Tune a Convolutional Neural Network in remote sensing image Classification: Easter Africa Countries (EAC) 2

Deeply Fine-Tune a Convolutional Neural Network in Remote Se...

引用

2nd IEEE International Conference on pattern recognition and Machine Learning, PRML 2021

作者： Bosco, Musabe J. Guoyin, Wang Chongqing University of Post and Telecommunication Chongqing Key Laboratory of Computational Intelligence Chongqing China

ISBN: (纸本)9781665443838

remote sensing is resource data accessible and easy to get in different areas without time-consuming. The traditional image recognition task was unlimited to better classification. A convolutional neural network (CNN) was introduced to improve remote sensing image classification accuracy by eliminating the intra-class and class similarity. Training CNN from scratch requires a large annotated dataset that is occasional in the remote sensing area. Transfer learning of CNN weights from another large non-remote sensing dataset can occasionally help overcome typical RS image applications. Transfer learning consists of fine-tuning CNN layers to better the new dataset. In this paper, all of the experiments were done on nine categories for dataset collected in east Africa community countries (EAC) using three state-of-the-art architectures based on the effect of fine-tuning and pre-trained weights of CNN. Results indicate that fine-tuning the entire network is not always a significant way;we compared it with a process of using VGG16-DensNet pre-trained weights and RF as machine learning classified results can be improved up to 97.60. Alternatively, fine-tuning the top blocks can save computational power and produce a more robust classifier. © 2021 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Characterization of Urban Vegetation from an Unmanned Aerial Vehicle (UAV) image 1

引用

2nd International Conference on Unmanned Aerial Systems in Geomatics (UASG)

作者： Kumar, Minakshi Agrawal, Shefali Indian Space Res Org ISRO Indian Inst Remote Sensing IIRS Dehra Dun Uttarakhand India

ISBN: (数字)9783031193095

ISBN: (纸本)9783031193118;9783031193095;9783031193088

Advances in UAV technology and processing made it feasible to obtain ultra high-resolution (UHR) imagery and three-dimensional (3D) data, which can be efficiently used for urban forestry, green space mapping, green infrastructure planning and monitoring with high accuracy and at a cost-effective manner. The conventional feature extraction image analysis techniques fail on UHR UAV images as the geometry of features is very well defined and characterized by a very heterogeneous texture. The approach required for such ultra-high-resolution images should support the cognitive analysis that we use in visual image interpretation, which is a form of knowledge-driven analysis incorporating shape, texture, pattern and contextual information. The present study aims at delineating and extract vegetation types and height estimation using UHR UAV images in parts of urban slums and dense urban environments. The methodology involved utilizes a multiresolution image segmentation to create basic image objects at a scale that allows for homogenous object extraction while maintaining variability. Normalized Differential Green Vegetation (NDGV) and Visible-Band Difference Vegetation Index (VDVI) band ratios are computed by combining the red, green and blue (RGB) spectrum of the UHR image. Digital Surface Model (DSM) and Digital Terrain Model (DTM) were input to the canopy height model (CHM) for height estimation and refinement of different vegetation categories. Crown shape parameters and texture parameters are tested and compared for vegetation characterization and categorization. Results show the 3D data set derived from UAV UHR imagery's potential in detection of treetops, delineation of vegetation and its categorization.

关键词： Multiresolution segmentation Texture parameters Ultra high-resolution images Canopy height model

来源：评论

学校读者我要写书评

暂无评论

An Adaptable Cognitive Microcontroller Node for Fitness Activity recognition 15th

An Adaptable Cognitive Microcontroller Node for Fitness Acti...

引用

15th International Workshop on Design and Architectures for Signal and image processing (DASIP)

作者： Scrugli, Matteo Antonio Blazica, Bojan Meloni, Paolo Univ Cagliari Dept Elect & Elect Engn DIEE Cagliari Italy Jozef Stefan Inst Comp Syst Dept Ljubljana Slovenia

ISBN: (纸本)9783031127489;9783031127472

The new generation of wireless technologies, fitness trackers, and devices with embedded sensors can have a big impact on healthcare systems and quality of life. Among the most crucial aspects to consider in these devices are the accuracy of the data produced and power consumption. Many of the events that can be monitored, while apparently simple, may not be easily detectable and recognizable by devices equipped with embedded sensors, especially on devices with low computing capabilities. It is well known that deep learning reduces the study of features that contribute to the recognition of the different target classes. In this work, we present a portable and battery-powered microcontroller-based device applicable to a wobble board. Wobble boards are low-cost equipment that can be used for sensorimotor training to avoid ankle injuries or as part of the rehabilitation process after an injury. The exercise recognition process was implemented through the use of cognitive techniques based on deep learning. To reduce power consumption, we add an adaptivity layer that dynamically manages the device's hardware and software configuration to adapt it to the required operating mode at runtime. Our experimental results show that adjusting the node configuration to the workload at runtime can save up to 60% of the power consumed. On a custom dataset, our optimized and quantized neural network achieves an accuracy value greater than 97% for detecting some specific physical exercises on a wobble board.

关键词： Adaptive system Fitness activity tracking Sensorimotor training Low power electronics Neural network remote sensing Runtime

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral remote sensing image Classification With CNN Based on Quantum Genetic-Optimized Sparse Representation

引用

IEEE ACCESS 2020年 8卷 99900-99909页

作者： Chen, Huayue Miao, Fang Shen, Xu Chengdu Univ Technol Sch Geophys Chengdu 610059 Peoples R China China West Normal Univ Sch Comp Sci Nanchong 637002 Peoples R China Internet Things Percept & Big Data Anal Key Lab N Nanchong 637002 Peoples R China Chengdu Univ Key Lab Pattern Recognit & Intelligent Informat P Chengdu 610041 Peoples R China

Due to the characteristics of the spectrum integration, information redundancy, spectrum mixing phenomenon and nonlinearity of the hyperspectral remote sensing images, it is a major challenging task to classify the hyperspectral remote sensing images. Therefore, a hyperspectral remote sensing image classification method, named QGASR-CNN is proposed in this paper. In the QGASR-CNN, a quantum genetic-optimized sparse representation method is designed to obtain the over-complete dictionary with sparsity, and achieve the feature sparse representation to construct the sparse feature matrix of hyperspectral remote sensing image pixel groups. Then the convolution neural network(CNN) directly convolutes with image pixels to build the feature mapping relation by using convolution operation. Finally, in order to testify the effectiveness of the QGASR-CNN, the actual hyperspectral remote sensing image datasets are selected in here. The comparison results show that the QGASR-CNN sparsely represents the features of hyperspectral remote sensing images and improves the classification accuracy. It can effectively alleviate the problems of the small samples and 'salt and pepper misclassification'.

关键词： Hyperspectral imaging Feature extraction Convolution Genetic algorithms Data mining Hyperspectral remote sensing image classification sparse representation convolutional neural network quantum genetic

来源：评论

学校读者我要写书评

暂无评论

Application Research of Attention Mechanism in remote sensing image Classification

Application Research of Attention Mechanism in Remote Sensin...

引用

International Conference on Applied Machine Learning (ICAML)

作者： Hui Feng Yabin Li Qiaochan Yu Mingrui Zhang China Waterborne Transport Research Institute Beijing China Qingdao Shipping Development Research Institute Qingdao China

The image classification as the key technology in the remote sensing system is mainly based on the image with the characteristics of the electromagnetic wave radiation information of the ground object to distinguish and identify the category of the ground object. The computer classification of remote sensing images is to achieve the purpose of automatic classification and recognition of ground objects through numerical processing of pixels. A high-precision remote sensing image classification method is a prerequisite for various applications. Compared with manual calibration of images, which is time-consuming and laborious, it is necessary to use machine learning methods to automatically process images.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A General Model for Large-Scale Paddy Rice Mapping by Combining Biological Characteristics, Deep Learning, and Multisource remote sensing Data

引用

IEEE Journal of Selected Topics in Applied Earth Observations and remote sensing 2025年 18卷 14705-14717页

作者： Zhenjie Liu Jialin Liu Yingyue Su Xiangming Xiao Jingwei Dong Luo Liu Hubei Key Laboratory of Intelligent Geo-Information Processing School of Computer Science China University of Geosciences Wuhan China Guangdong Province Key Laboratory for Agricultural Resources Utilization South China Agricultural University Guangzhou China Department of Microbiology and Plant Biology Center for Earth Observation and Modeling University of Oklahoma Norman OK USA Key Laboratory of Land Surface Pattern and Simulation Institute of Geographic Sciences and Natural Resources Research Chinese Academy of Sciences Beijing China

Due to the influences combined with global climate change and human activity, paddy rice area and distribution have undergone dramatic changes. Currently, many approaches for paddy rice mapping rely on the prior knowledge of paddy rice phenology or require widely distributed ground samples of paddy rice, which are limited for large-scale applications. In this work, we propose a general paddy rice mapping (GPRM) model by combining biological characteristics, deep learning, and multisource remote sensing data. The proposed GPRM first utilizes the normalized difference vegetation index and land surface water index to acquire large-scale remote sensing dataset in key phenology periods of paddy rice, such as the transplanting period and peak vegetative growth period. Then, a general model using object-based deep neural networks is developed and trained by the remote sensing dataset and the ground reference data collected in one region (e.g., Guangdong Province), which can be directly applied for generating 10-m paddy rice maps in other regions with different climate conditions and complex cropping systems (e.g., Jiangxi Province and Heilongjiang Province). The results demonstrate that the GPRM can realize remarkable performance of paddy rice mapping in China. The overall accuracies are over 99%, and the user accuracy, producer accuracy, and Kappa coefficient vary from 0.77 to 0.93, 0.94 to 0.97, 0.9 to 0.95, respectively. Overall, the GPRM is has significant promise for large-scale paddy rice mapping with complex cropping systems, thus supporting global agricultural development strategies and food security.

关键词： Deep learning Climate change Earth Observing System Phenology Crops Human activity recognition Terrain mapping

来源：评论

学校读者我要写书评

暂无评论

Guided Depth Super-Resolution by Deep Anisotropic Diffusion

Guided Depth Super-Resolution by Deep Anisotropic Diffusion

引用

Conference on Computer Vision and pattern recognition (CVPR)

作者： Nando Metzger Rodrigo Caye Daudt Konrad Schindler Photogrammetry and Remote Sensing ETH Zurich

Performing super-resolution of a depth image using the guidance from an RGB image is a problem that concerns several fields, such as robotics, medical imaging, and remote sensing. While deep learning methods have achieved good results in this problem, recent work highlighted the value of combining modern methods with more formal frameworks. In this work, we propose a novel approach which combines guided anisotropic diffusion with a deep convolutional network and advances the state of the art for guided depth super-resolution. The edge transferring/enhancing properties of the diffusion are boosted by the contextual reasoning capabilities of modern networks, and a strict adjustment step guarantees perfect adherence to the source image. We achieve unprecedented results in three commonly used benchmarks for guided depth superresolution. The performance gain compared to other methods is the largest at larger scales, such as × 32 scaling. Code 1 1 https://***/prs-eth/Diffusion-Super-Resolution for the proposed method is available to promote reproducibility of our results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Tiansuan Constellation: Intelligent Software-Defined Microsatellite with Orbital Attention for Sustainable Development Goals

Tiansuan Constellation: Intelligent Software-Defined Microsa...

引用

International Conference on Big Data Intelligence and Computing, DataCom 2022

作者： Tang, Yingxi National Remote Sensing Laboratory and Earth Big Data Laboratory Zhicheng International Academy Beijing100032 China

ISBN: (纸本)9789819922321

Space flight, which we anticipate as SpaceX does, has the potential to address the challenge of human life in the near future. The first stage towards interstellar travel is to establish a satellite network, which could deliver worldwide internet access to every location on the planet. However, satellites are not as smart as everyone thinks! Because the satellite industry faces severe problems including Cost, Speed, Vacuum environment, Energy, Computing power, Hardware stability, Software lightweight, Model optimization, Data set related, etc., these are all obstacles to upgrading the local calculation to orbital computation. And because this research category involves the scientific research secrets of various countries, many related materials are kept confidential and difficult to access publicly. Although AI researchers have enthusiasm for the application of deep learning in the field of remote sensing data, the processing speed and scale of remote sensing image information have been improved. However, the above research work belongs to ground-oriented processing, and the orbital application is still blank! The visual models currently popularly used on the ground are evaluated, and their respective computing power requirements are analyzed for possibilities in orbit. Experiments on genuine microsatellites are hampered by the high expense of deployment and unknown risks associated with space technology. Our Tiansuan constellation, fortunately, can facilitate experimentation on real satellite networks. We introduce our brand-new integrated hybrid Orbital Deep Neural Network Model WolongPro 1.0 system based on edge computing and 2.0 research concept scheme about Spintronics, which can have human attention on disaster risk reduction. The attention of the orbital satellite can be focused on reporting early warning of perils, instead of transmitting high-resolution pictures and then analyzing them by computer or manually on the ground, to improve the recognition accura

关键词： remote sensing

来源：评论

学校读者我要写书评

暂无评论

How Do Human Detect Targets of remote sensing images with Visual Attention?

SSRN

引用

SSRN 2024年

作者： He, Bing Qin, Tong Shi, Bowen Dong, Weihua Ghent University Belgium

Human visual attention is the basis of target recognition, change detection and classification in remote sensing images. However, the human visual attention of remote sensing images during target detection remains uninvestigated. In this study, we simultaneously collected eye tracking and electroencephalography (EEG) data of 40 experts during target detection in 1000 remote sensing images. We quantified their attention in different stages of target detection (i.e., target search, selection, and identification) from their eye movements and brain activities. The eye-tracking results indicated that hue and brightness were crucial visual features that guided visual search for remote sensing images. The size of the target also affected the allocation of human attention resources. Particularly, participants tended to miss the targets that were smaller than 4% of the whole image area. The fixation event-related potentials (FRPs) in temporal and parietal brain regions further distinguished the attention of targets and distractors, which could be attributed to the process of memory and processing. Our findings offer new visual and neural evidence for human attention in target detection of remote sensing images, which not only contribute to the performance of attention-based algorithms in remote sensing interpretation, but also provide an empirical basis for guiding human-machine intelligent fusion. © 2024, The Authors. All rights reserved.

关键词： Electroencephalography

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：