发布求助
文献互助 智能选刊 最新文献

IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium最新文献

筛选
英文 中文
Stepwise Refinement Of Low Resolution Labels For Earth Observation Data: Part 2 对地观测数据低分辨率标签的逐步细化:第2部分
IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium Pub Date : 2020-09-26 DOI: 10.1109/IGARSS39084.2020.9547209
D. Cerra, N. Merkle, C. Henry, K. Alonso, P. d’Angelo, S. Auer, R. Bahmanyar, X. Yuan, K. Bittner, M. Langheinrich, Guichen Zhang, M. Pato, Jiaojiao Tian, P. Reinartz
{"title":"Stepwise Refinement Of Low Resolution Labels For Earth Observation Data: Part 2","authors":"D. Cerra, N. Merkle, C. Henry, K. Alonso, P. d’Angelo, S. Auer, R. Bahmanyar, X. Yuan, K. Bittner, M. Langheinrich, Guichen Zhang, M. Pato, Jiaojiao Tian, P. Reinartz","doi":"10.1109/IGARSS39084.2020.9547209","DOIUrl":"https://doi.org/10.1109/IGARSS39084.2020.9547209","url":null,"abstract":"This paper describes the contribution of the DLR team ranking 2nd in Track 2 of the 2020 IEEE GRSS Data Fusion Contest. The semantic classification of multimodal earth observation data proposed is based on the refinement of low-resolution MODIS labels, using as auxiliary training data higher resolution labels available for a validation data set. The classification is initialized with a handcrafted decision tree integrating output from a random forest classifier, and subsequently boosted by detectors for specific classes. The results of the team ranking 3rd in Track 1 of the same contest are reported in a companion paper.","PeriodicalId":444267,"journal":{"name":"IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126835614","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Pyramid Convolutional Neural Networks and Bottleneck Residual Modules for Classification of Multispectral Images 金字塔卷积神经网络与瓶颈残差模块在多光谱图像分类中的应用
IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium Pub Date : 2020-09-26 DOI: 10.1109/IGARSS39084.2020.9324314
Yukun Huang, Jingbo Wei, Wenchao Tang, Chaoqi He
{"title":"Pyramid Convolutional Neural Networks and Bottleneck Residual Modules for Classification of Multispectral Images","authors":"Yukun Huang, Jingbo Wei, Wenchao Tang, Chaoqi He","doi":"10.1109/IGARSS39084.2020.9324314","DOIUrl":"https://doi.org/10.1109/IGARSS39084.2020.9324314","url":null,"abstract":"The newly emerging classifier using deep network architectures and pyramid bottleneck modules exhibits stronger capability than traditional classifiers. However, they are only suitable for color images or hyperspectral images due to the structural, textural and spectral differences against multispectral images. In this paper, a new network is designed for the classification of high-resolution multispectral images. The new network follows the architecture of pyramid residual network, but the input size, filter size, and filter number of each layer are totally different. These designs make the pyramid residual network conforming to the multispectral advantages of spatial resolutions so as to improve classification performance. Experiments on the satellite multispectral data from GF-1 and RapidEye demonstrate the superiority of the new network.","PeriodicalId":444267,"journal":{"name":"IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126921313","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 3
Comparison of Ascat Estimated Snow Thickness on First-Year Sea Ice in the Canadian Arctic with Modeled and Passive Microwave Data 加拿大北极地区Ascat估算第一年海冰积雪厚度与模式和被动微波数据的比较
IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium Pub Date : 2020-09-26 DOI: 10.1109/IGARSS39084.2020.9323947
J. Yackel, T. Geldsetzer, Mallik S. Mahmud, Rory Armstrong, V. Nandan, D. Barber, M. Fuller
{"title":"Comparison of Ascat Estimated Snow Thickness on First-Year Sea Ice in the Canadian Arctic with Modeled and Passive Microwave Data","authors":"J. Yackel, T. Geldsetzer, Mallik S. Mahmud, Rory Armstrong, V. Nandan, D. Barber, M. Fuller","doi":"10.1109/IGARSS39084.2020.9323947","DOIUrl":"https://doi.org/10.1109/IGARSS39084.2020.9323947","url":null,"abstract":"The snow cover on sea ice is an important parameter controlling heat and momentum fluxes in our polar regions. Our understanding of snow thickness distributions on sea ice is severely limited by its vastness and numerous logistical difficulties. As such, we rarely collect enough in situ data from similar geographic locations to determine if and how the snow thickness distribution changes spatiotemporally. Geophysical changes in snow cover manifest as differences in dielectric properties, which are detectable in microwave emission and backscatter. Active microwave remote sensing offers improved spatial resolution when compared to passive microwave approaches. We apply our recently developed method that exploits the indirect thermodynamic control of the snow cover on near ice surface geophysical properties. The variance of C-band (5.3 GHz HH-polarization) microwave backscatter in winter (prior to melt) is assessed and is then used to estimate relative snow cover thickness and distribution. We assess the capability of our approach over landfast, first-year sea ice in the Canadian Arctic Archipelago and evaluate and compare our method against the Canadian Regional Ice Ocean Prediction system and AMSR2 passive microwave snow thickness estimates. Results demonstrate that this method can separate thick snow from thin snow on thick FYI within a thickness range of 5 to 45 cm at a spatial resolution of less than 5 km.","PeriodicalId":444267,"journal":{"name":"IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114959153","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A Novel Framework of CNN Integrated with Adaboost for Remote Sensing Scene Classification 结合Adaboost的CNN遥感场景分类新框架
IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium Pub Date : 2020-09-26 DOI: 10.1109/IGARSS39084.2020.9324261
Xudong Hu, Penglin Zhang, Qi Zhang
{"title":"A Novel Framework of CNN Integrated with Adaboost for Remote Sensing Scene Classification","authors":"Xudong Hu, Penglin Zhang, Qi Zhang","doi":"10.1109/IGARSS39084.2020.9324261","DOIUrl":"https://doi.org/10.1109/IGARSS39084.2020.9324261","url":null,"abstract":"Deep learning is a powerful means to recognize remote sensing image scene categories. In this study, a deep convolutional neural network (CNN) based ensemble method is proposed. Firstly, a CNN architecture composed of the feature layer and the classifier layer is designed. Then the classifier layer of CNN is treated as base-learner and integrated with the AdaBoost technique to construct a CNN-AdaBoost ensemble framework. The proposed method is compared with the CNN-SVM and fine-tuned VGG16. The experiment results on UC Merced land-use dataset show that the CNN-AdaBoost achieves an improved overall accuracy by 4.46% against the sole CNN. Also, our method outperforms another two paradigms. Therefore, the proposed CNN based ensemble method is promising for image representations regarding remote sensing image scene classification.","PeriodicalId":444267,"journal":{"name":"IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115025009","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 9
The Research of Leaf Area Index Analyzer based on Embedded Platform 基于嵌入式平台的叶面积指数分析仪的研究
IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium Pub Date : 2020-09-26 DOI: 10.1109/IGARSS39084.2020.9323721
Peicheng Wang, Bo Gao, Xun Gong, L. Tong, Yuan Sun, Xingfa Gu
{"title":"The Research of Leaf Area Index Analyzer based on Embedded Platform","authors":"Peicheng Wang, Bo Gao, Xun Gong, L. Tong, Yuan Sun, Xingfa Gu","doi":"10.1109/IGARSS39084.2020.9323721","DOIUrl":"https://doi.org/10.1109/IGARSS39084.2020.9323721","url":null,"abstract":"With the continuous development of optical lens and imaging chip technology, the fisheye camera method has been widely studied in the world because of its characteristics of TRAC instrument and LAI-2200C coronal analyzer. To obtain the critical ecological parameter of the leaf area index at low cost, a synchronous LAI-2200C leaf area index hemispheric image acquisition system was proposed in this paper. The system consists of an embedded platform, a low-cost image sensor, and a fisheye lens, fixed to the LAI-2200C optical sensor detector, triggered by the LAI-2200C synchronous of hemispheric vegetation image. This study used the system to measure the coronary photos of the tall shrubs in the Chengdu area at different times. It used an image processing algorithm to analyze and obtain LAI. The results show that there is a significant linear correlation between LAI and LAI-2200C measurements obtained by the Fisheye Camera Method (DH-P) (R2= 0.814), the average square root error is 0.278.The test results show that the system can effectively collect the image of the vegetation canopy can be low-cost, and obtain a leaf area index results with minor error.","PeriodicalId":444267,"journal":{"name":"IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115036468","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Soil Moisture Mapping with Polarimetric SAR in Huanghe Delta of China 黄河三角洲土壤水分偏振SAR制图
IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium Pub Date : 2020-09-26 DOI: 10.1109/IGARSS39084.2020.9324034
Lihua Lan, Tingting Zhang, Y. Shao, Zhengshan Ju, Xun Chai
{"title":"Soil Moisture Mapping with Polarimetric SAR in Huanghe Delta of China","authors":"Lihua Lan, Tingting Zhang, Y. Shao, Zhengshan Ju, Xun Chai","doi":"10.1109/IGARSS39084.2020.9324034","DOIUrl":"https://doi.org/10.1109/IGARSS39084.2020.9324034","url":null,"abstract":"The objective of this paper is to use the partial least squares regression as a modeling method to establish the relationship between soil moisture and polarimetric decomposition parameters which are obtained by T3 matrix and $mathrm{H}/mathrm{A}/alpha$ polarimetric decomposition with full-polarization RADARSAT-2 SAR image. The results show that the parameter set of T3 matrix have the minimum accuracy comparing with the other three decomposition ways of the $mathrm{H}/mathrm{A}/alpha$. The best results of the $mathrm{H}/mathrm{A}/alpha$ is the Eigenvector parameter set. However, it is still lower than the inversion of parameter combinations with R2 of 0.84 for calibration and R2 of 0.77 for validation. It indicates that the polarimetric decomposition parameters can be used for mapping soil moisture in Huanghe Delta.","PeriodicalId":444267,"journal":{"name":"IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115328796","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Wind Vector and Wave Height Retrieval in Inland Waters Using CYGNSS 利用CYGNSS反演内陆水域风矢量和波高
IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium Pub Date : 2020-09-26 DOI: 10.1109/IGARSS39084.2020.9323481
Eric Loria, A. O'Brien, V. Zavorotny, C. Zuffada
{"title":"Wind Vector and Wave Height Retrieval in Inland Waters Using CYGNSS","authors":"Eric Loria, A. O'Brien, V. Zavorotny, C. Zuffada","doi":"10.1109/IGARSS39084.2020.9323481","DOIUrl":"https://doi.org/10.1109/IGARSS39084.2020.9323481","url":null,"abstract":"Spaceborne GNSS Reflectometry (GNSS-R) measurements over inland waters have exhibited strong coherent scattering. The strong reflected signal from a relatively small spatial extent (several km) is highly sensitive to surface waves. This sensitivity can be leveraged to estimate wave height profiles across inland waters. Coupled with a wind wave model, retrievals of wind vector can be performed using a forward model approach. The surface waves play a significant role in nearshore ecosystems, affecting sediment resuspension, biomass production, and fish habitat, among others. This paper details a novel approach to estimating surface wave profiles and wind vectors using the passive, bistatic radar receiver aboard CYGNSS. The first ever retrieval of wind vector and wave height of an inland water body using spaceborne GNSS-R will be shown using raw signals recorded onboard CYGNSS.","PeriodicalId":444267,"journal":{"name":"IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115538975","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 2
Learning Multi-Label Aerial Image Classification Under Label Noise: A Regularization Approach Using Word Embeddings 在标签噪声下学习多标签航空图像分类:一种使用词嵌入的正则化方法
IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium Pub Date : 2020-09-26 DOI: 10.1109/IGARSS39084.2020.9324069
Yuansheng Hua, Sylvain Lobry, Lichao Mou, D. Tuia, Xiaoxiang Zhu
{"title":"Learning Multi-Label Aerial Image Classification Under Label Noise: A Regularization Approach Using Word Embeddings","authors":"Yuansheng Hua, Sylvain Lobry, Lichao Mou, D. Tuia, Xiaoxiang Zhu","doi":"10.1109/IGARSS39084.2020.9324069","DOIUrl":"https://doi.org/10.1109/IGARSS39084.2020.9324069","url":null,"abstract":"Training deep neural networks requires well-annotated datasets. However, real world datasets are often noisy, especially in a multi-label scenario, i.e. where each data point can be attributed to more than one class. To this end, we propose a regularization method to learn multi-label classification networks from noisy data. This regularization is based on the assumption that semantically close classes are more likely to appear together in a given image. Hereby, we encode label correlations with prior knowledge and regularize noisy network predictions using label correlations. To evaluate its effectiveness, we perform experiments on a mutli-label aerial image dataset contaminated with controlled levels of label noise. Results indicate that networks trained using the proposed method outperform those directly learned from noisy labels and that the benefits increase proportionally to the amount of noise present.","PeriodicalId":444267,"journal":{"name":"IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115992647","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 14
Semi-Automatic Classification of Building From Low-Density Lidar Data and Worldview-2 Images Through OBIA Technique 基于OBIA技术的低密度激光雷达数据和Worldview-2图像的建筑半自动分类
IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium Pub Date : 2020-09-26 DOI: 10.1109/IGARSS39084.2020.9323916
Chiara Zarro, S. Ullo, G. Meoli, M. Focareta
{"title":"Semi-Automatic Classification of Building From Low-Density Lidar Data and Worldview-2 Images Through OBIA Technique","authors":"Chiara Zarro, S. Ullo, G. Meoli, M. Focareta","doi":"10.1109/IGARSS39084.2020.9323916","DOIUrl":"https://doi.org/10.1109/IGARSS39084.2020.9323916","url":null,"abstract":"In this paper, an in-depth study is presented regarding an innovative methodology on which the authors have invested several months of research, as evidenced by their recent references on similar topics. A semi-automatic classification of the buildings in urban area is analyzed, when Light Detection And Ranging (LiDAR) data are combined to Very High Resolution (VHR) WorldView-2 (WV-2) images and an Object-Based Image Analysis (OBIA) technique is used. The aim of the data fusion from different sensor types is to realize an effective and limited-cost product for protection and management of environmental and natural resources, to meet the needs of many institutions, such as municipalities, provinces and regions, and for applications in the context of risk analysis, territorial planning and local development. This procedure may be extended to large areas of the territory, resulting into a reduction of the processing time for the building detection, with respect to a human visual or manual photointerpretation. Interesting results and further implications will be presented and discussed.","PeriodicalId":444267,"journal":{"name":"IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116068249","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 5
A Comparative Study of Deep Learning Loss Functions for Multi-Label Remote Sensing Image Classification 深度学习损失函数在多标签遥感图像分类中的比较研究
IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium Pub Date : 2020-09-26 DOI: 10.1109/IGARSS39084.2020.9323583
Hichame Yessou, Gencer Sumbul, B. Demir
{"title":"A Comparative Study of Deep Learning Loss Functions for Multi-Label Remote Sensing Image Classification","authors":"Hichame Yessou, Gencer Sumbul, B. Demir","doi":"10.1109/IGARSS39084.2020.9323583","DOIUrl":"https://doi.org/10.1109/IGARSS39084.2020.9323583","url":null,"abstract":"This paper analyzes and compares different deep learning loss functions in the framework of multi-label remote sensing (RS) image scene classification problems. We consider seven loss functions: 1) cross-entropy loss; 2) focal loss; 3) weighted cross-entropy loss; 4) Hamming loss; 5) Huber loss; 6) ranking loss; and 7) sparseMax loss. All the considered loss functions are analyzed for the first time in RS. After a theoretical analysis, an experimental analysis is carried out to compare the considered loss functions in terms of their: 1) overall accuracy; 2) class imbalance awareness (for which the number of samples associated to each class significantly varies); 3) convexibility and differentiability; and 4) learning efficiency (i.e., convergence speed). On the basis of our analysis, some guidelines are derived for a proper selection of a loss function in multi-label RS scene classification problems.","PeriodicalId":444267,"journal":{"name":"IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116527872","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 24
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：481959085
Book学术官方微信