- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Retrieval and Validation of Sea Ice Concentration from AMSR-E/AMSR2 in Polar Regions
摘要： Sea ice concentration (SIC) is an important sea ice parameter of the atmosphere-ice-ocean system in the polar region. Daily 6.25 km AMSR-E/AMSR2 SIC from Bremen University (UB) is one of the widely used SIC products. In this paper, MODIS data and aerial image are used to validate this product. The results show that the daily mean AMSR-E ASI products underestimate SICs about 17.9% based on the aerial image, and underestimate SICs about8.5% based on MODIS image. The sea ice extent (SIE) and sea ice area (SIA) which are derived from SIC by ASI algorithm, Dynamic Tie-point ASI algorithm (DT-ASI) as well as NT algorithm are compared.
关键词： Retrieval,Validation,aerial image,Sea ice concentration,AMSR-E,MODIS
更新于2025-09-23 15:22:29
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia, Spain (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Classification of Rare Building Change Using CNN with Multi-Class Focal Loss
摘要： In the remote sensing, supervised deep learning has recently achieved great success of information extraction. However, it requires a large training data in order to effectively learn. In building change classifications, collecting such training data is an extremely expensive and time-consuming process, because of the rarity of positive classes. Learning of a data set including rare classes has two major problems, (1) class imbalance and (2) overfitting. In this study, we verify the effectiveness of focal loss in the building change classification. From our experimental results, not only the class imbalance but also the overfitting is affected the down-weighting effect of the focal loss. The focal loss automatically adjusts learning speed for each class.
关键词： convolutional neural network,building change,aerial image,focal loss,deep learning
更新于2025-09-10 09:29:36
-
[IEEE 2018 International Symposium ELMAR - Zadar, Croatia (2018.9.16-2018.9.19)] 2018 International Symposium ELMAR - Evaluation of Split-Brain Autoencoders for High-Resolution Remote Sensing Scene Classification
摘要： Self-supervised methods are interesting for remote sensing because there are not many human labeled datasets available, but there is practically unlimited amount of data that can be used for self-supervised learning. In this paper we analyze the use of split-brain autoencoders in the context of remote sensing image classi?cation. W e i nvestigate t he i mportance of training set size, choice of color space and size of the model to the classi?cation accuracy. We show that even with small amount of unlabeled training images, if we ?netune t he w eights learned by the autoencoder, we can achieve almost state of the art results of 89.27% on AID dataset.
关键词： Colorization,Self-supervised learning,Remote sensing,Aerial image classification
更新于2025-09-09 09:28:46
-
[IEEE 2018 Innovations in Intelligent Systems and Applications Conference (ASYU) - Adana, Turkey (2018.10.4-2018.10.6)] 2018 Innovations in Intelligent Systems and Applications Conference (ASYU) - Image Classification of Aerial Images Using CNN-SVM
摘要： Image classification is a very easy task for humans. Even a three years old child can classify an image instantly and without any doubt. However, teaching computers classifying images has been a working area for researchers for a long time because of the intrinsic difficulties of the task for computers. With the rise of deep learning, it has been possible to get better classification performance than before. In this work, we evaluated the performance of convolutional neural network combined with support vector machine for classifying aerial images based on presence of a vehicle.
关键词： unmanned aerial vehicle,vehicle detection,convolutional neural networks,aerial image,Support vector machines,image classification
更新于2025-09-04 15:30:14