Google Street View: Capturing the World at Street Level

By Dragomir Anguelov, Carole Dulong, Daniel Filip, Christian Früh, Stéphane Lafon, R. Lyon, Abhijit S. Ogale, Luc Vincent, Josh Weaver, Josh Weaver. 2010

756 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Geography, Planning and Development, Ocean Engineering

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

In Geography, Planning and Development

Xiaoxiang Zhu

In Ocean Engineering

Citations in the corpus

Ontological supervision for fine grained classification of Street View storefronts (2015, methodology): “Since its launch in 2007, Google Street View [28] [1] has been used by the computer vision community as both a test bed for algorithms [19] [31] and a source from which data is extracted and analyzed [12] [34] [21] [10] [6].”
SEAN: Image Synthesis With Semantic Region-Adaptive Normalization (2019, positive): “we use a dataset of 30, 000 façade images collected from Google Street View [3].”
Learning deep representations for ground-to-aerial geolocalization (2015, methodology): “First, we project 2D street-view image to 3D world coordinates system by leveraging the heading direction of street-view car and pixel-wise coarse depth planes from Anguelov et al. [1].”
Reading Digits in Natural Images with Unsupervised Feature Learning (2011, methodology): “In addition to serving millions of users daily with panoramic imagery [26], Street View images taken worldwide are used to improve the accuracy of maps and address geocoding.”
Computer Vision for Autonomous Vehicles: Problems, Datasets and State-of-the-Art (2017, background): “Metric Maps: The Google Street View project (Anguelov et al. (2010)) is a prominent example for a large collection of panoramic imagery in cities around the world.”
Visualizing the Consequences of Climate Change Using Cycle-Consistent Adversarial Networks (2019, methodology): “In our prototype, we are able to generate images of the projected impact of ﬂooding by training a CycleGAN network (Zhu et al., 2017) on Google Street View images of both ﬂooded and unﬂooded streets and houses (Anguelov et al., 2010).”
Building Instance Classification Using Street View Images (2018, methodology): “Given these GPS coordinates, we can download the corresponding Google StreetView images [55] which show fac¸ade structures of individual buildings, since the retrieved images can display these speciﬁc locations by the closest panoramas.”