Multitask Learning of Height and Semantics From Aerial Images

Carvalho Marcela; Le Saux Bertrand; Trouve-Peloux Pauline; Champagnat Frederic; Almansa Andres

首页> 外文期刊>IEEE Geoscience and Remote Sensing Letters >Multitask Learning of Height and Semantics From Aerial Images

【24h】

Multitask Learning of Height and Semantics From Aerial Images

机译：空中图像高度和语义的多任务学习

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相似文献
相关主题

摘要

Aerial or satellite imagery is a great source for land surface analysis, which might yield land-use maps or elevation models. In this letter, we present a neural network framework for learning semantics and local height together. We show how this joint multitask learning benefits to each task on the large data set of the 2018 Data Fusion Contest. Moreover, our framework also yields an uncertainty map that allows assessing the prediction of the model. Code is available at https://github.com/marcelampc/mtl_aerial_images

机译：空中或卫星图像是土地表面分析的重要来源，可能会产生土地使用地图或高程模型。在这封信中，我们为学习语义和局部高度提供了一个神经网络框架。我们展示了对2018年数据融合比赛的大型数据集的每个任务的联合多任务如何获益。此外，我们的框架还产生了不确定性地图，允许评估模型的预测。代码可在https://github.com/marcelampc/mtl_aerial_images获得

著录项

来源
《IEEE Geoscience and Remote Sensing Letters》 |2020年第8期|1391-1395|共5页
作者
Carvalho Marcela; Le Saux Bertrand; Trouve-Peloux Pauline; Champagnat Frederic; Almansa Andres;
展开▼
作者单位

Univ Paris Saclay ONERA DTIS F-91123 Palaiseau France;

Univ Paris Saclay ONERA DTIS F-91123 Palaiseau France;

Univ Paris Saclay ONERA DTIS F-91123 Palaiseau France;

Univ Paris Saclay ONERA DTIS F-91123 Palaiseau France;

Univ Paris 05 MAP5 F-75006 Paris France;

展开▼
收录信息
原文格式 PDF
正文语种 eng
中图分类
关键词
Semantics; Task analysis; Training; Estimation; Predictive models; Decoding; Land surface; Aerial imagery; deep learning; multitask learning; neural networks; semantic segmentation; single view depth estimation;

机译：语义;任务分析;训练;预测模型;解码;陆地面;空中图像;深度学习;多族学习;神经网络;语义分割;单视图深度估计;单视图深度估计;单视图深度估计;

相似文献

外文文献
中文文献
专利

1. Vehicle Instance Segmentation From Aerial Image and Video Using a Multitask Learning Residual Fully Convolutional Network [J] . Lichao Mou, Xiao Xiang Zhu IEEE Transactions on Geoscience and Remote Sensing. . 2018,第11期

机译：使用多任务学习残差全卷积网络从航空图像和视频进行车辆实例分割
2. Deep multi-task learning for a geographically-regularized semantic segmentation of aerial images [J] . Volpi Michele, Tuia Devis ISPRS Journal of Photogrammetry and Remote Sensing . 2018,第OCTa期

机译：深度多任务学习，用于航空图像的地理规则语义分割
3. Saliency-constrained semantic learning for airport target recognition of aerial images [J] . Zhao Danpei, Shi Jun, Wang Jiajia, Journal of Applied Remote Sensing . 2015,第Null期

机译：显着性语义学习用于航空图像的机场目标识别
4. Joint height estimation and semantic labeling of monocular aerial images with CNNS [C] . Shivangi Srivastava, Michele Volpi, Devis Tuia 2017 IEEE International Geoscience and Remote Sensing Symposium . 2017

机译：CNNS对单眼航拍图像的联合高度估计和语义标记
5. Negotiating the semantic gap in an MPEG-7 aerial image database. [D] . Li, Xin. 2005

机译：协商MPEG-7航拍图像数据库中的语义间隙。
6. Molecular subgrouping of medulloblastoma based on few-shot learning of multitasking using conventional MR images: a retrospective multicenter study [O] . Xi Chen, Zhen Fan, Kay Ka-Wai Li, 2020

机译：基于使用常规MR图像的多任务处理的几次射击学习的Medulloblastoma的分子亚组：回顾性多中心研究
7. Multitask Learning of Height and Semantics From Aerial Images [O] . Marcela Carvalho, Bertrand Le Saux, Pauline Trouve-Peloux, 2020

机译：空中图像高度和语义的多任务学习

Multitask Learning of Height and Semantics From Aerial Images

摘要

著录项

相似文献

相关主题

期刊订阅