检索结果-内蒙古大学图书馆

5th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2024

作者： Patil, Rajendra V. Aggarwal, Renu Shivaji Deore, Shailesh Sunrise University Department of Computer Engineering Rajasthan Alwar India SunRise University Department of Computer Science and Engineering Rajasthan Alwar India SSVPS BSD College of Engineering Department of Computer Engineering Dhule India

ISBN: (纸本)9798350395235

image Segmentation is necessary stage in image investigation. In computer vision, image segmentation is the process of dividing digital image into multiple segments. Dividing the image into various parts simplifies the analysis of image. In numerous image analysis and computer visualization uses, including remote sensing, robot vision, medical image analysis, and pattern recognition, the subdivision of image into segments is an important preprocessing stage. Finding the outlines of objects in the images is the fundamental step in the segmentation of pictures. Zero crossover, Canny, Gradient dependent, zero cross, Laplacian are examples of traditional edge detection techniques. This study presents a novel method based on phase congruency for edge segmentation. As compared to traditional edge detection methods, advantage of phase congruency is its invariance to uneven illumination. To obtain edge segmentation outcomes, edge lines were obtained using phase congruency. Long edges give an approximate sense of the object's arrangement in the picture. Color likeness between edges is determined while short edges are removed. Color similar edges assigned same label. Performance analysis shows that proposed method produces good results for synthetic images and natural real world images in which objects are well separated by boundaries whereas it results in broken edges for images having complex structure. © 2024 IEEE.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Few-Shot Object Detection in remote sensing: Lifting the Curse of Incompletely Annotated Novel Objects

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND remote sensing 2024年 62卷 1页

作者： Zhang, Fahong Shi, Yilei Xiong, Zhitong Zhu, Xiao Xiang Tech Univ Munich Chair Data Sci Earth Observat D-80333 Munich Germany Tech Univ Munich TUM Sch Engn & Design D-80333 Munich Germany Munich Ctr Machine Learning D-80333 Munich Germany

Object detection (OD) is an essential and fundamental task in computer vision (CV) and satellite image processing. Existing deep learning methods have achieved impressive performance thanks to the availability of large-scale annotated datasets. Yet, in real-world applications, the availability of labels is limited. In this article, few-shot OD (FSOD) has emerged as a promising direction, which aims at enabling the model to detect novel objects with only few of them annotated. However, many existing FSOD algorithms overlook a critical issue: when an input image contains multiple novel objects and only a subset of them are annotated, the unlabeled objects will be considered as background during training. This can cause confusions and severely impact the model's ability to recall novel objects. To address this issue, we propose a self-training-based FSOD (ST-FSOD) approach, which incorporates the self-training mechanism into the few-shot fine-tuning process. ST-FSOD aims to enable the discovery of novel objects that are not annotated and take them into account during training. On the one hand, we devise a two-branch region proposal networks (RPNs) to separate the proposal extraction of base and novel objects. On the another hand, we incorporate the student-teacher mechanism into RPN and the region-of-interest (RoI) head to include those highly confident yet unlabeled targets as pseudolabels. Experimental results demonstrate that our proposed method outperforms the state of the art in various FSOD settings by a large margin. The codes will be publicly available at: https://***/zhu-xlab/ST-FSOD.

关键词： Proposals Object detection Feature extraction remote sensing Detectors Training Object recognition Few-shot learning object detection (OD) remote sensing image processing self-training

来源：评论

学校读者我要写书评

暂无评论

Comparison of Deep Learning Methods for Landslide Semantic Segmentation Based on remote sensing images 5

Comparison of Deep Learning Methods for Landslide Semantic S...

引用

5th International Conference on pattern recognition and Artificial Intelligence, PRAI 2022

作者： Liu, Jie Liu, Ying Zhou, Yongxiu Wang, Yiru Chengdu University of Technology Chengdu China College of Computer Science and Cyber Security Chengdu University of Technology Chengdu China Key Laboratory of Earth Exploration and Information Technology of Ministry of Education Chengdu University of Technology Chengdu China

ISBN: (数字)9781665499163

ISBN: (纸本)9781665499163

Comprehensive identification of geological hazards is still one of the most important work in China's disaster prevention, and convolutional neural network is an important tool to realize early intelligent and automatic identification of geological hazards. In order to compare the accuracy of different network structures in landslide remote sensing image recognition, in this paper, U-Net, PSP-Net, Deeplabv3+, Mask R-CNN models are used to realize automatic recognition of landslide remote sensing images, with IOUs of 0.61, 0.67, 0.52 and 0.71 respectively. The results show that the backbone feature extraction network combined with the deep residual structure has better feature extraction ability of landslides, weakening the influence of factors unrelated to landslides. The structure with multi-scale feature fusion can extract landslide areas of different scales, which effectively improves the accuracy of landslide identification in remote sensing images. © 2022 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

UAV/Drone-Based Identification of Geomorphic and Structural Anomalies as Probable Indicators of Economic Mineral Deposits in Girar Area of Lalitpur District, UP, (India)

引用

JOURNAL OF THE INDIAN SOCIETY OF remote sensing 2022年第5期50卷 937-947页

作者： Uniyal, Aniruddha Gond, Abhishek Tiwari, Tarun Pandit, Sanjay Gupta, Chirag Saikhom, Victor Dinkar, Gautam Remote Sensing Applicat Ctr UP Lucknow Uttar Pradesh India NESAC Umiam India DGM Lucknow Uttar Pradesh India

Satellite remote sensing data and UAV/Drone images have been conjunctively used for identification and mapping of probable indicators of economic mineral deposits in Girar area of Lalitpur district. Area of interest for UAV/Drone survey was selected from the digitally enhanced IRS P6 LISS-IV images. Very high-resolution (3.95 cm/pix) UAV/Drone images have been captured, and their photogrammetric processing and DEM generation were performed using Agisoft Metashape software. Subsequently, digital image enhancements such as principal component analysis and some filtering techniques viz. high-pass and low-pass filters using 3 x 3, 5 x 5 kernel have been applied on UAV images. Abrupt changes in regular linear and curvilinear pattern and also in the dimension of the landforms and the macro-level terrain information have also been detected from digitally enhanced and filtered drone data. Anomalous orientation, disposition and abrupt changes in the shape and pattern of landforms, particularly the ridges at some places, have been referred to as geomorphic anomalies. Lineaments with a few hundreds of meters of length have been delineated on spatially enhanced images and DEMs generated from UAV/Drone data. Sudden change in slope and relatively steeper valley walls are distinguishable on UAV data-based Digital Elevation Model (DEM), thereby vindicating the existence of lineaments. Intersections of ENE-WSW and NW-SE trending lineaments in Girar ridge area have been marked as structural anomalies. UAV/Drone images have not only yielded precise information about the spatial extent of anomalies (earlier been identified on IRS P6 LISS-IV satellite images), but have also helped in the identification of smaller geomorphic and structural anomalies, which were otherwise difficult to identify on satellite images. Further, the field investigations have revealed the rock outcrops of Banded Haematite Quartzite (BHQ) within these geomorphic and structural anomalies with BHQ considered to be

关键词： Unmanned aerial vehicle (UAV) image enhancement Lineament Mineral targeting

来源：评论

学校读者我要写书评

暂无评论

pattern recognition and remote sensing techniques applied to Land Use and Land Cover mapping in the Brazilian Savannah

引用

pattern recognition LETTERS 2021年 148卷 54-60页

作者： Fonseca, Leila M. G. Korting, Thales S. Bendini, Hugo do N. Girolamo-Neto, Cesare D. Neves, Alana K. Soares, Anderson R. Taquary, Evandro C. Maretto, Raian V. Natl Inst Space Res INPE Earth Observat & Geoinformat Div Ave Astronautas 1758 BR-12227010 Sao Jos Dos Campos Brazil Univ Twente Fac Geoinformat Sci & Earth Observat ITC Hengelosestr 99 NL-7514 AE Enschede Netherlands

The Brazilian Savannah, or Cerrado, has gained vital importance in the discussions about sustainable land development after the conversion of half of its natural vegetation. For the last two decades, most of the agricultural expansion in Brazil has occurred in this biome. This is related to technological improvements in agriculture as well as to environmental compliance policies that have effectively reduced soybean expansion in the Brazilian Amazon biome. Therefore, remotely sensed imagery, pattern recognition and image processing techniques have been employed to analyze and monitor the land dynamics over Cerrado. In this work, we present a brief review on Land Use and Land Cover mapping (LULC) in the Cerrado biome from an application perspective: natural vegetation, pastureland, agriculture, and deforestation. In this review we selected some studies whose results could contribute to the development of more detailed and accurate LULC maps for the Cerrado biome. (c) 2021 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license ( http://***/licenses/by-nc-nd/4.0/ )

关键词： Earth Observation Agriculture mapping Cerrado Time series Deep Learning Pastureland Deforestation remote sensing

来源：评论

学校读者我要写书评

暂无评论

Exploring the potential of UAV hyperspectral image for estimating soil salinity: Effects of optimal band combination algorithm and random forest

引用

SPECTROCHIMICA ACTA PART A-MOLECULAR AND BIOMOLECULAR SPECTROSCOPY 2022年第0期279卷 121416页

作者： Zhu, Chuanmei Ding, Jianli Zhang, Zipeng Wang, Zheng Xinjiang Univ Coll Geog & Remote Sensing Sci Urumqi 830046 Peoples R China Xinjiang Univ Xinjiang Key Lab Oasis Ecol Urumqi 830046 Peoples R China Higher Educ Inst Key Lab Smart City & Environm Modelling Urumqi 830046 Peoples R China

Hyperspectral remote sensing by unmanned aerial vehicle (UAV) is an important technical tool for rapid, ac-curate, and real-time monitoring of soil salinity in arid zone agroecosystems. However, the key to effective soil salinity (electrical conductivity, EC) prediction by UAV visible and near-infrared (Vis-NIR) spectroscopy depends on the selection of effective features selection techniques and robust prediction characteristics algorithms. Therefore, in this study, two advanced feature selection methods and two commonly used modeling methods were applied to predict and characterize the spatial patterns of soil salinity (EC). The aim of this study was to explore the predictive performance of different feature band selection methods and to identify a robust soil salinity mapping strategy. The results demonstrated that standard normal variate (SNV) pre-processing broad-ened the absorption characteristics of the spectrum. Compared with competitive adaptive reweighted sampling (CARS), the optimal band combination algorithm (OBCA) strengthened the correlation with soil salinity and had a higher variable importance in the modeling. Random forest (RF) was more stable in mapping the spatial pattern of surface soil salinity compared to the partial least squares regression model (PLSR). Our results confirm the effectiveness of OBCA and RF in the developing UAV remote sensing models for surface soil salinity estimation and mapping.

关键词： Visibleandnear-infraredspectroscopy Featureselection CompetitiveadaptiveReweightedsampling Digitalsoilmapping Soilsalinity

来源：评论

学校读者我要写书评

暂无评论

GLA-ViT: A Global Contextual Attention Based for remote sensing image Scene Classification

GLA-ViT: A Global Contextual Attention Based for Remote Sens...

引用

International Symposium on Parallel and Distributed processing with Applications, ISPA

作者： Hao Yuan Kun Liu Qinghao Peng Benli Zou Can Wang Meishu Li School of Information Science and Engineering University of Jinan Jinan China China High-Resolution Earth Observation System Shandong Center of Data and Application Jinan China

ISBN: (数字)9798331509712

ISBN: (纸本)9798331509729

remote sensing image Scene Classification (RSISC) is a critical area of research in remote sensing that is dedicated to categorizing remote sensing images into specific semantic classes based on their content. Despite the Convolutional Neural Networks’ (CNNs) effectiveness in feature extraction and classification, they face challenges in exploring contextual information necessary for a comprehensive understanding of remote sensing scenes. To address this limitation, a novel model based on the Transformer architecture has attracted considerable attention from researchers. The Transformer model has shown promise in extracting contextual information within remote sensing (RS) scenes. However, the original Transformer model’s performance in RS scene classification has been subpar due to the diverse content types and scales present in remote sensing scenes. To overcome these challenges, a context-based approach for remote sensing image scene classification called GLA-ViT is proposed. The GLA-ViT model integrates local and global self-attention modules to enhance its ability to capture intricate details and contextual information in remote sensing images, while also maintaining computational efficiency. Additionally, GLA-ViT incorporates an improved MFused-MBConv module to enhance the model’s recognition capabilities in complex scenes. Experimental results on well-known datasets such as AID, UCM, and NWPU-RESISC45 demonstrate the superior performance of GLA-ViT in remote sensing image scene classification related tasks.

关键词： Scene classification Computational modeling Face recognition Semantics Computer architecture Transformers Feature extraction Computational efficiency remote sensing Context modeling

来源：评论

学校读者我要写书评

暂无评论

Research on Target Detection Model of remote sensing image Based on Dual Attention Yolo

Research on Target Detection Model of Remote Sensing Image B...

引用

International Conference on Information Systems and Computer Aided Education (ICISCAE)

作者： Fan Xu College of Computer Science and Technology Ocean University of China Qingdao China

ISBN: (数字)9798350350760

ISBN: (纸本)9798350350777

With the widespread application of remote sensing technology, accurate and rapid detection and identification of targets in remote sensing images have become an important research area. Traditional target detection methods often face issues with low recognition accuracy and slow response when dealing with complex backgrounds or small targets. This study proposes an improved YOLO (You Only Look Once) model integrated with a dual attention mechanism to enhance the performance of target detection in remote sensing images. This mechanism utilizes spatial attention to increase the model's sensitivity to target locations, while channel attention enhances the recognition of target features, enabling more accurate identification of small and complex environment targets. The model was tested across multiple remote sensing image datasets, and the results show significant improvements in detection accuracy and real-time performance compared to traditional YOLO models. Additionally, the implementation of the model reveals the potential of the dual attention mechanism in improving the efficiency and accuracy of remote sensing image processing. With further optimization and adjustment, this model is expected to play a significant role in various application scenarios such as environmental monitoring, urban planning, and disaster assessment.

关键词： YOLO Accuracy Attention mechanisms Sensitivity Target recognition Face recognition Computational modeling Urban planning Real-time systems remote sensing

来源：评论

学校读者我要写书评

暂无评论

Landscape Ecological Risk Assessment and Planning Enlightenment of Songhua River Basin Based on Multi-Source Heterogeneous Data Fusion

引用

WATER 2022年第24期14卷 4060-4060页

作者： Zhao, Ying Tao, Zhe Wang, Mengnan Chen, Yuanhua Wu, Rui Guo, Liang Harbin Inst Technol Sch Environm Harbin 150090 Peoples R China Harbin Inst Technol State Key Lab Urban Water Resource & Environm Harbin 150090 Peoples R China Shandong Agr Univ Coll Informat Sci & Engn Tai An 271000 Peoples R China Ecoproduct Dev Res Ctr Co Ltd China Energy Conservat & Environm Protect Grp Beijing 100084 Peoples R China

In this study, the remote sensing images of the 30 km buffer zone from Zhaoyuan to Baidu of the Songhua River, which is rich in land use types and frequent in human activities, were selected as the research object to analyze land use change and driving factors. The objective of this research is to evaluate the ecological risk of watershed landscapes and provide a basis for watershed ecological environment protection and planning. On this basis, the landscape pattern index data were extracted, and a three-dimensional comprehensive index system of the natural, social and landscape pattern was constructed. In addition, based on the spatial principal component analysis (SPCA), data fusion was carried out to improve the accuracy and comprehensiveness of landscape ecological risk assessment results. The risk level of watershed landscape ecology was divided into low ecological risk, medium-low ecological risk, medium ecological risk, medium-high ecological risk, and high ecological risk by the Natural Breaks method. According to the results of the landscape ecological risk assessment and the characteristics of risk sources in each risk level area, the ecological protection and planning enlightenment suitable for each risk level area were obtained. The research content can provide ideas and evidence for environmental managers to formulate ecological risk protection strategies and reduce the impact of ecological risk threats.

关键词： Songhua River Basin multi-source data fusion remote sensing image processing land use landscape ecological risk

来源：评论

学校读者我要写书评

暂无评论

A Novel Actor Dual-Critic Model for remote sensing image Captioning 25

A Novel Actor Dual-Critic Model for Remote Sensing Image Cap...

引用

25th International Conference on pattern recognition (ICPR)

作者： Chavhan, Ruchika Banerjee, Biplab Zhu, Xiao Xiang Chaudhuri, Subhasis Indian Inst Technol Mumbai Maharashtra India Tech Univ Munich Signal Proc Earth Observat Munich Germany

ISBN: (纸本)9781728188089

We deal with the problem of generating textual captions from optical remote sensing (RS) images using the notion of deep reinforcement learning. Due to the high inter-class similarity in reference sentences describing remote sensing data, jointly encoding the sentences and images encourages prediction of captions that are semantically more precise than the ground truth in many cases. To this end, we introduce an Actor Dual-Critic training strategy where a second critic model is deployed in the form of an encoder-decoder RNN to encode the latent information corresponding to the original and generated captions. While all actor-critic methods use an actor to predict sentences for an image and a critic to provide rewards, our proposed encoder-decoder RNN guarantees high-level comprehension of images by sentence-to-image translation. We observe that the proposed model generates sentences on the test data highly similar to the ground truth and is successful in generating even better captions in many critical cases. Extensive experiments on the benchmark remote sensing image Captioning Dataset (RSICD) and the UCM-captions dataset confirm the superiority of the proposed approach in comparison to the previous state-of-the-art where we obtain a gain of sharp increments in both the ROUGE-L and CIDEr measures.

关键词： Optical remote sensing

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：