检索结果-内蒙古大学图书馆

RailPC: A large-scale railway point cloud semantic segmentation dataset

CAAI Transactions on Intelligence Technology 2024年第6期9卷 1548-1560页

作者： Tengping Jiang Shiwei Li Qinyu Zhang Guangshuai Wang Zequn Zhang Fankun Zeng Peng An Xin Jin Shan Liu Yongjun Wang Jiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application Nanjing Normal UniversityNanjingChina Technology Innovation Center for Integrated Applications in Remote Sensing and Navigation Ministry of Natural ResourcesNanjingChina Eastern Institute of Technology(EIT) NingboChina Tianjin Key Laboratory of Rail Transit Navigation Positioning and Spatio-temporal Big Data Technology TianjinChina College of Computer Science and Engineering Northwest Normal UniversityLanzhouChina Mckelvey School of Engineering Washington University in St.LouisSt.LouisMissouriUSA School of Electronic and Information Engineering Ningbo University of TechnologyNingboChina

Semantic segmentation in the context of 3D point clouds for the railway environment holds a significant economic value,but its development is severely hindered by the lack of suitable and specific ***,the models trained on existing urban road point cloud datasets demonstrate poor generalisation on railway data due to a large domain gap caused by non-overlapping special/rare categories,for example,rail track,track bed *** harness the potential of supervised learning methods in the domain of 3D railway semantic segmentation,we introduce RailPC,a new point cloud *** provides a large-scale dataset with rich annotations for semantic segmentation in the railway ***,RailPC contains twice the number of annotated points compared to the largest available mobile laser scanning(MLS)point cloud dataset and is the first railway-specific 3D dataset for semantic *** covers a total of nearly 25 km railway in two different scenes(urban and mountain),with 3 billion points that are finely labelled as 16 most typical classes with respect to railway,and the data acquisition process is completed in China by MLS *** extensive experimentation,we evaluate the performance of advanced scene understanding methods on the annotated dataset and present a synthetic analysis of semantic segmentation *** on our findings,we establish some critical challenges towards railway-scale point cloud semantic *** dataset is available at https://***/NNU-GISA/GISA-RailPC,and we will continuously update it based on community feedback.

关键词： data benchmark MLS point clouds railway scene semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

A Seasonal-Series Lstm Network for Irregular Urban Function Zone Recognition Using Sentinel-2 Images

SSRN

引用

SSRN 2024年

作者： Hu, Ting Han, Mengyu Guo, Zixuan School of Remote Sensing and Geomatics Engineering Nanjing University of Information Science and Technology Nanjing210044 China Technology Innovation Center for Integration Application in Remote Sensing and Navigation Ministry of Natural Resources Nanjing210044 China Jiangsu Engineering Center for Collaborative Navigation/ Positioning and Smart Applications Nanjing210044 China

Urban Functional Zone (UFZ) is the fundamental unit for urban planning and management, which plays a crucial role in improving urban management efficiency and optimizing urban layout. The classification of UFZs has benefited from the rich information and fine features provided by high spatial resolution (HSR) remote sensing images. The seasonal variations of ground objects differ across different UFZs. However, HSR remote sensing images typically lack seasonal information and come with high acquisition costs. Therefore, this study proposes a classification framework for UFZ based on all-seasonal Sentinel-2 remote sensing images, learning the spectral-spatial-temporal features for detailed mapping of UFZs. Firstly, to balance the significant scale difference of block (i.e., the fundamental mapping unit) size in 10-meter resolution remote sensing images, an adaptive gradient perception (AGP) mechanism is used to guide the feature extraction of different-scale blocks. Secondly, the bag of visual words (BOVW) model is employed to extract block-level spectral-spatial features. Thirdly, a seasonal series LSTM network is proposed to capture block-level temporal dynamic information, particularly focusing on the spectral-temporal patterns of different UFZs. The proposed framework is applied to UFZ classification in four typical cities in China. The overall accuracy (OA) for all cases reaches around 93%, which is an improvement of approximately 7% compared to other methods. Our results demonstrate the superiority and portability of this framework, as well as the significant potential of open-source remote sensing images in large-scale UFZ mapping. © 2024, The Authors. All rights reserved.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Estimation of winter wheat chlorophyll content by combing canopy spectrum red edge parameters with random forest machine learning

引用

Nongye Gongcheng Xuebao/Transactions of the Chinese Society of Agricultural engineering 2024年第4期40卷 166-176页

作者： Wang, Zhen Li, Yingxue Wu, Fang Zou, Xiaochen School of Remote Sensing and Surveying Engineering Nanjing University of Information Science and Technology Nanjing210044 China Technology Innovation Center of Integration Applicaitons in Remote Sensing and Navigation Ministry of Natural Resources P.R. China Nanjing210044 China Jiangsu Engineering Center for Collaborative Navigation/Positioning and Smart Applications Nanjing210044 China School of Ecology and Applied Meteorology Nanjing University of Information Science and Technology Nanjing210044 China Xinghua Meteorological Bureau Xinghua225700 China

The sudden increase in vegetation canopy reflectance from low reflectance in red band to near infrared band forms the red-edge spectral characteristics, which is unique to healthy vegetation. Many parameters that can describe this characteristic have been designed and developed as important indicators of crop growth and nutrition status. However, few studies have systematically compared and evaluated the applicability of these red-edge parameters to estimate winter wheat leaf CHL values at different growth stages and nitrogen application levels. In this study, canopy spectral reflectance and leaf CHL of winter wheat at 4 key growth stages (jointing stage, heading stage, flowering stage and filling stage) and 3 nitrogen application levels were obtained through a 4-year field experiment. The sensitivity of 47 spectral red-edge parameters to CHL was evaluated, and the relative importance of spectral red-edge parameters was used to optimize the random forest machine learning model to estimate winter wheat CHL. The results showed that the sensitivity of spectral red edge parameter to CHL was affected by the growth period and nitrogen application level of winter wheat, and the correlation R2 between the best red edge parameter and CHL in a single growth period was between 0.39 and 0.89. The best red-edge parameter in the whole growth period was NDDRmid, and the coefficient of determination between it and CHL was 0.76. The sensitivity was the highest in filling stage, and the coefficient of determination between the best red edge parameter RVI5 and CHL was 0.89 and the R2 between red edge parameters REPRpi, NDDRmid, RVI2, RVI4, RVI5, RVI6, NDRE, RVI12 and RVI13 with CHL were all higher than 0.80. Nitrogen application level increased the sensitivity of red-edge parameter to CHL. At single nitrogen application level, the coefficient of determination between best red edge parameter and CHL was between 0.75 and 0.81. At N1 and N2 conditions the best red-edge parameter is NDDRm

关键词： Nitrogen

来源：评论

学校读者我要写书评

暂无评论

Cross-Resolution Land Cover Classification Using Outdated Products and Transformers

arXiv

引用

arXiv 2024年

作者： Ni, Huan Zhao, Yubin Guan, Haiyan Jiang, Cheng Jie, Yongshi Wang, Xing Shen, Yiyang School of Remote Sensing & Geomatics Engineering Nanjing University of Information Science & Technology Nanjing210044 China Technology Innovation Center of Integration Applications in Remote Sensing and Navigation Ministry of Natural Resources Nanjing210044 China Jiangsu Engineering Center for Collaborative Navigation Positioning and Smart Applications Nanjing210044 China Beijing Key Laboratory of Advanced Optical Remote Sensing Technology Beijing Institute of Space Mechanics and Electricity Beijing100094 China

Large-scale high-resolution land cover classification is a prerequisite for constructing Earth system models and addressing ecological and resource issues. Advancements in satellite sensor technology have led to an improvement in spatial resolution and wider coverage areas. Nevertheless, the lack of high-resolution labeled data is still a challenge, hindering the large-scale application of land cover classification methods. In this paper, we propose a Transformer-based weakly supervised method for cross-resolution land cover classification using outdated data. First, to capture long-range dependencies without missing the fine-grained details of objects, we propose a U-Net-like Transformer based on a reverse difference mechanism (RDM) using dynamic sparse attention. Second, we propose an anti-noise loss calculation (ANLC) module based on optimal transport (OT). Anti-noise loss calculation identifies confident areas (CA) and vague areas (VA) based on the OT matrix, which relieves the impact of noises in outdated land cover products. By introducing a weakly supervised loss with weights and employing unsupervised loss, the RDM-based U-Net-like Transformer was trained. Remote sensing images with 1 m resolution and the corresponding ground-truths of six states in the United States were employed to validate the performance of the proposed method. The experiments utilized outdated land cover products with 30 m resolution from 2013 as training labels, and produced land cover maps with 1 m resolution from 2017. The results show the superiority of the proposed method compared to state-of-the-art methods. The code is available at https://***/yu-ni1989/ANLC-Former. © 2024, CC BY-NC-ND.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

High-Precision Retrieval Of Total Precipitable Water Under Clear-Sky Using Fy-4b Agri Data and Era5 Reanalysis Data

SSRN

引用

SSRN 2024年

作者： Zhang, Jianhang Wang, Xinzhi Zhou, Yi Cui, Xiwang Gu, Yanbiao School of Remote Sensing and Geomatics Engineering Nanjing University of Information Science and Technology Nanjing210044 China Jiangsu Province Engineering Research Center of Collaborative Navigation/Positioning and Smart Applications Nanjing210044 China Changzhou Ruide Instrument Co. Ltd Changzhou213004 China Institute of Deep Perception Technology Wuxi214111 China

Atmospheric water vaper plays a pivotal role in the climate system of Earth. It is usually quantified using Total Precipitable Water (TPW). Fengyun-4B(FY-4B) is the first operational satellite of China's FY-4 series that equipped with the Advanced Geosynchronous Radiation Imager (AGRI). This study aims to retrieve the TPW under clear-sky using the observation data from the AGRI and the TPW product from ERA5 reanalysis data. We constructed four models based on the random forest, gradient boosting decision tree, elastic network regression algorithm, and regression analysis method, respectively. Then, we validated the precision of the models using ERA5-TPW and TPW products from International GNSS Service (IGS). The results indicate that the random forest model performs best for both land and ocean regions. In ocean region, the Root Mean Square Error (RMSE) is 2.279 mm, compared to the ERA5-TPW. In land region, RMSE are 0.972 mm and 2.844 mm, compared to the ERA5-TPW and the GNSS-TPW. © 2024, The Authors. All rights reserved.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

MetaSegNet: Metadata-collaborative Vision-Language Representation Learning for Semantic Segmentation of Remote Sensing Images

arXiv

引用

arXiv 2023年

作者： Wang, Libo Dong, Sijun Chen, Ying Meng, Xiaoliang Fang, Shenghui Fei, Songlin School of Remote Sensing and Geomatics Engineering Nanjing University of Information Science and Technology Technology Innovation Center of Integration Applications in Remote Sensing and Navigation Ministry of Natural Resources China Jiangsu Engineering Center for Collaborative Navigation/Positioning and Smart Applications Nanjing210044 China School of Remote Sensing and Information Engineering Wuhan University Wuhan430079 China China Telecom Research Institute Shanghai200120 China Purdue University West LafayetteIN47907 United States

Semantic segmentation of remote sensing images plays a vital role in a wide range of Earth Observation applications, such as land use land cover mapping, environment monitoring, and sustainable development. Driven by rapid developments in artificial intelligence, deep learning (DL) has emerged as the mainstream for semantic segmentation and has achieved many breakthroughs in the field of remote sensing. However, most DL-based methods focus on unimodal visual data while ignoring rich multimodal information involved in the real world. Non-visual data, such as text, can gather extra knowledge from the real world, which can strengthen the interpretability, reliability, and generalization of visual models. Inspired by this, we propose a novel metadata-collaborative segmentation network (MetaSegNet) that applies vision-language representation learning for semantic segmentation of remote sensing images. Unlike the common model structure that only uses unimodal visual data, we extract the key characteristic (e.g. the climate zone) from freely available remote sensing image metadata and transfer it into geographic text prompts via the generic ChatGPT. Then, we construct an image encoder, a text encoder, and a crossmodal attention fusion subnetwork to extract the image and text feature and apply image-text interaction. Benefiting from such a design, the proposed MetaSegNet not only demonstrates superior generalization in zero-shot testing but also achieves competitive accuracy with the state-of-the-art semantic segmentation methods on the large-scale OpenEarthMap dataset (70.4% mIoU) and the Potsdam dataset (93.3% mean F1 score) as well as the LoveDA dataset (52.0% mIoU). Copyright © 2023, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

PPP models and performances from single-to quad-frequency BDS observations

引用

Satellite navigation 2020年第1期1卷 179-191页

作者： Shuanggen Jin Ke Su Shanghai Astronomical Observatory Chinese Academy of SciencesShanghai 200030China School of Remote Sensing and Geomatics Engineering Nanjing University of Information Science and TechnologyNanjing 210044China Jiangsu Engineering Center for Collaborative Navigation/Positioning and Smart Applications Nanjing 210044China University of Chinese Academy of Sciences Beijing 100049China

Nowadays,China BeiDou navigation Satellite System(BDS)has been developed well and provided global services with highly precise positioning,navigation and timing(PNT)as well as unique short-message communication,particularly global system(BDS-3)with higher precision multi-frequency *** precise point positioning(PPP)can provide the precise position,receiver clock,and zenith tropospheric delay(ZTD)with a stand-alone receiver compared to the traditional double differenced relative positioning mode,which has been widely used in PNT,geodesy,meteorology and so ***,it has a lot of challenges for multi-frequency BDS PPP with different strategies and more unknown *** this paper,the detailed PPP models using the single-,dual-,triple-,and quad-frequency BDS observations are presented and ***,BDS system and PPP method are ***,the stochastic models of time delay bias in BDS-2/BDS-3 PPP including the neglection,random constant,random walk and white noise are ***,three single-frequency,four dual-frequency,four triple-frequency and four quad-frequency BDS PPP models are ***,the BDS PPP models progress and performances including theoretical comparison of the models,positioning performances,precise time and frequency transfer,ZTD,inter-frequency bias(IFB)and differential code bias(DCB)are presented and evaluated as well as future *** results show that the multi-frequency BDS observations will greatly improve the PPP performances.

关键词： BDS GNSS PPP IFB ZTD DCB

来源：评论

学校读者我要写书评

暂无评论

Precipitable water vapor retrieved from FY-3G/MWRI-RM observations using machine learning models

引用

Advances in Space Research 2025年

作者： Yuxin Liu Xinzhi Wang Yi Zhou Atta ur Rahman School of Remote Sensing and Geomatics Engineering Nanjing University of Information Science and Technology Nanjing 210044 China Jiangsu Province Engineering Research Center of Collaborative Navigation/Positioning and Smart Applications Nanjing 210044 China School of Computer and Software Nanjing University of Information Science and Technology Nanjing 210044 China

Water vapor is an essential component of the Earth’s atmosphere, and accurate retrieval of precipitable water vapor (PWV) is critical to understanding the Earth’s climate and hydrological cycle. In this study, we use the global Fengyun-3G/Micro-Wave Radiation Imager-Rainfall Mission (FY-3G/MWRI-RM) L1 data from October 2023 to August 2024 to construct a high-precision PWV retrieval model. Three machine learning algorithms are used to construct our models:Random Forests (RF), Light Gradient Boosting Machine (Light GBM), and Gradient Boosting Regression (GBR), due to their ability to handle complex relationships between brightness temperature data and PWV retrieval with high precision. Then, the precision of retrieved PWV is evaluated using the fifth generation of European Centre for Medium-Range Weather Forecasts Atmospheric Reanalysis (ERA5) PWV and radiosonde PWV. Light GBM demonstrated the highest accuracy with root-mean-square error (RMSE) of 2.151 mm over the ocean compared to ERA5 PWV, outperforming GBR and RF. RF demonstrated the highest accuracy with RMSE of 2.323 mm over land compared to ERA5 PWV, outperforming Light GBM and GBR. In addition, this study compares the FY-3G/MWRI-RM PWV with Advanced Microwave Scanning Radiometer 2 (AMSR2) TPW and AMSR2 PWL. FY-3G/MWRI-RM retrieved PWV demonstrated higher precision compared to AMSR2 water vapor products when validated against ERA5 PWV.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Weighted Mean Temperature Model by Integrating FY-4B GIIRS and ERA5 Reanalysis Data

引用

Advances in Space Research 2025年

作者： Xiwang Cui Xinzhi Wang Yi Zhou Fayuan Chen Jianhang Zhang Jie Li School of Remote Sensing and Geomatics Engineering Nanjing University of Information Science and Technology Nanjing 210044 China Jiangsu Province Engineering Research Center of Collaborative Navigation/Positioning and Smart Applications Nanjing 210044 China Changzhou Ruide Instrument Co. Ltd Changzhou 213004 China Beihai Meteorological Administration Beihai 536006 China China Aerospace Planning and DesignGroup Co. Ltd Beijing 102600 China

Weighted mean temperature ( T m ) is a significant parameter of high-precision and high-resolution Global navigation Satellite System Precipitable Water Vapor (GNSS PWV) inversion. We constructed an empirical T m model (called the FY-4BTm) by integrating the Fengyun-4B (FY-4B) Geostationary Interferometric Infrared Sounder (GIIRS) and the ERA5 reanalysis data provided by European Centre for Medium Range Weather Forecasts (ECMWF). Like other studies, the FY-4BTm empirical model takes into account multiple factors such as the longitude, latitude, and elevation, and at high spatial resolutions of 0.5°×0.5°. When compared to the 102 radiosonde data in 2022, the annual mean bias and root mean square error (RMSE) of the FY-4BTm model are 0.53 K and 4.92 K, respectively. The FY-4BTm model performs better than the legacy Bevis and GPT3 models with an improvement of 2.09 K and 1.78 K in T m respectively, especially in the high-latitude regions of the western and northern parts of the study area (73°E∼140°E, 3°N∼55°N). Compared with the ERA5 reanalysis data in 2022, the FY-4BTm’s annual mean bias and RMSE are 0.43 K and 4.16 K, respectively. Its precision is generally the best among the three models, but with a slightly lower stability than that of the Bevis model. With the PWV obtained from GNSS station as the reference, the FY-4BTm model also demonstrates well performance in PWV inversion, with annual mean bias ranging from 0 to 0.2 mm. Therefore, the FY-4BTm model will benefit a lot for GNSS PWV inversion without requiring the users to obtain additional meteorological data.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Sensitivity of CYGNSS-derived soil moisture to global precipitation

Sensitivity of CYGNSS-derived soil moisture to global precip...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Qingyun Yan Shuanggen Jin Weimin Huang Yan Jia Jiangsu Engineering Center for Collaborative Navigation/Positioning and Smart Applications Nanjing China Shanghai Astronomical Observatory Chinese Academy of Sciences Shanghai China Memorial University of Newfoundland St. John's NL Canada Nanjing University of Posts and Telecommunications Nanjing China

ISBN: (数字)9781728163741

ISBN: (纸本)9781728163758

In this paper, the sensitivity of Cyclone Global navigation Satellite System (CYGNSS) data to precipitation is investigated. First, the soil moisture (SM) is estimated from the CYGNSS and Soil Moisture Active Passive (SMAP) data based on a three-layer model. Next, the correlation between the CYGNSS-derived global SM and the precipitation rate is analyzed. The CYGNSS data collected over the land surfaces within ±37° (latitude) during the whole year of 2018 are employed and the CPC Merged Analysis of Precipitation (CMAP) data are adopted. Experimental evaluation proves the sensitivity of CYGNSS-derived SM to precipitation, indicating possible applications of CYGNSS data for detecting rainfall events and estimating precipitation.

关键词： Soil moisture Sensitivity Remote sensing Correlation Vegetation mapping L-band Surface roughness

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：