Learning deep representations for ground-to-aerial geolocalization

By Tsung-Yi Lin, Yin Cui, Serge J. Belongie, James Hays. 2015

418 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

CPlaNet: Enhancing Image Geolocalization by Combinatorial Partitioning of Maps (2018, background): “Cross-view geolocation recognition makes additional use of satellite or aerial imagery to determine query locations [37,38,39,40].”
Revisiting IM2GPS in the Deep Learning Era (2017, methodology): “In [18, 34, 37], images of the same scene from the ground viewpoint and overhead viewpoint are embedded in the same feature space through deep learning DML; the resulting system then does localization by image retrieval using reference database of aerial images.”
PlaNet - Photo Geolocation with Convolutional Neural Networks (2016, methodology): “[36] use CNNs to learn a joint embedding for ground and aerial images and localize a query image by matching it against a database of aerial images.”
Visual7W: Grounded Question Answering in Images (2015, background): “The 7W questions roughly correspond to an array of standard vision tasks: what [9, 15, 39], where [24, 50], when [30, 32], who [35, 42], why [33], how [23, 31] and which [16, 17].”
Learning Visual Clothing Style with Heterogeneous Dyadic Co-Occurrences (2015, methodology): “Then, we show how to train a Siamese CNN to learn a feature transformation from the image space into the latent style space.”
Siamese network features for image matching (2016, positive): “A very interesting idea and implementation were proposed in [8].”
Comparative Deep Learning of Hybrid Representations for Image Recommendations (2016, background): “In view of the limitation of hand-crafted image features such as those designed in [4, 15, 20, 28], more and more research focuses on designing effective deep learning models to extract image representations automatically [17, 21, 31].”
Localizing and Orienting Street Views Using Overhead Imagery (2016, methodology): “Some similar attempts to collect a dataset for cross-view images matching task are [20, 34], but neither are publicly available.”
Fine-Grained Categorization and Dataset Bootstrapping Using Deep Metric Learning with Humans in the Loop (2015, background): “Recently, it has been successfully applied to variety of problems including face recognition and verification [39, 36], image retrieval [44], semantic hashing [29], product design [4], geo-localization [31] and style matching [41].”
Deep-learning in Mobile Robotics - from Perception to Control Systems: A Survey on Why and Why not (2016, methodology): “…reciprocally provide much more possibility for interesting ideas, like matching the ground-level image with a database collected from aerial robots (Lin et al., 2015) and using 2D occupancy grids constructed by Lidar to classify the place categorization (into a corridor, doorway, room, etc.)…”
Predicting Ground-Level Scene Layout from Aerial Imagery (2016, background): “Recent work on cross-view image geolocalization [17, 18, 32, 33] has shown that convolutional neural networks are capable of extracting features from aerial imagery that can be matched to features extracted from ground imagery.”
Composing Text and Image for Image Retrieval - an Empirical Odyssey (2018, methodology): “Cross-modal image retrieval allows using other types of query, examples include text to image retrieval [52], sketch to image retrieval [42] or cross view image retrieval [26], and event detection [19].”
Lending Orientation to Neural Networks for Cross-View Geo-Localization (2019, background): “Paper [17, 29] tackled the ground to bird-eye view (45-degree oblique views) matching problem, which is a relatively easier task in the sense that more overlaps (e.”
Cross-View Image Matching for Geo-Localization in Urban Environments (2017, methodology): “To demonstrate the advantage of using building matching for cross-view image geo-localization, we conduct an experiment by training a Siamese network to match full images directly, which was used in the existing methods such as [11, 22, 25].”