Learning to Map Nearly Anything

Looking at the world from above, it is possible to estimate many properties of a given location, including the type of land cover and the expected land use. Historically, such tasks have relied on relatively coarse-grained categories due to the diffi-culty of obtaining fine-grained annotations. In this work, we propose an easily extensible approach that makes it possible to estimate fine-grained properties from overhead imagery. In particular, we propose a cross-modal distillation strategy to learn to predict the distribution of fine-grained properties from overhead imagery, without requiring any manual annotation of overhead imagery. We show that our learned models can be used directly for applications in mapping and image localization.

[1]  Serge J. Belongie,et al.  Learning deep representations for ground-to-aerial geolocalization , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Scott Workman,et al.  Wide-Area Image Geolocalization with Aerial Reference Imagery , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[3]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[4]  Scott Workman,et al.  Predicting Ground-Level Scene Layout from Aerial Imagery , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Stefan Lee,et al.  Predicting Geo-informative Attributes in Large-Scale Image Collections Using Convolutional Neural Networks , 2015, 2015 IEEE Winter Conference on Applications of Computer Vision.

[7]  Connor Greenwell,et al.  What Goes Where: Predicting Object Distributions from Above , 2018, IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium.

[8]  Gim Hee Lee,et al.  CVM-Net: Cross-View Matching Network for Image-Based Ground-to-Aerial Geo-Localization , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[9]  Scott Workman,et al.  A Multimodal Approach to Mapping Soundscapes , 2018, IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium.

[10]  Jian Sun,et al.  Identity Mappings in Deep Residual Networks , 2016, ECCV.

[11]  Bolei Zhou,et al.  Places: A 10 Million Image Database for Scene Recognition , 2018, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  Pietro Perona,et al.  Microsoft COCO: Common Objects in Context , 2014, ECCV.

[13]  Serge J. Belongie,et al.  Cross-View Image Geolocalization , 2013, CVPR.