Advertisement

Citizen Visual Search Engine: Detection and Curation of Urban Objects

  • Immanuel KohEmail author
  • Jeffrey Huang
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 1028)

Abstract

Increasingly, the ubiquity of satellite imagery has made the data analysis and machine learning of large geographical datasets one of the building blocks of visuospatial intelligence. It is the key to discover current (and predict future) cultural, social, financial and political realities. How can we, as designers and researchers, empower citizens to understand and participate in the design of our cities amid this technological shift? As an initial step towards this broader ambition, a series of creative web applications, in the form of visual search engines, has been developed and implemented to data mine large datasets. Using open sourced deep learning and computer vision libraries, these applications facilitate the searching, detecting and curating of urban objects. In turn, the paper proposes and formulates a framework to design truly citizen-centric creative visual search engines – a contribution to citizen science and citizen journalism in spatial terms.

Keywords

Deep learning Computer vision Satellite imagery Citizen science Artificial intelligence 

References

  1. 1.
    Kurgan, L.: Close up at a Distance: Mapping, Technology and Politics. Zone Books, New York (2013)Google Scholar
  2. 2.
    Weizman, E.: Forensic Architecture: Violence at the Threshold of Detectability. Zone Books, New York (2017)Google Scholar
  3. 3.
    Quadros, A., Underwood, J., Douillard, B.: Sydney Urban Objects Dataset, Australian Centre for Field Robotics (2013). http://www.acfr.usyd.edu.au/papers/SydneyUrbanObjectsDataset.shtml
  4. 4.
    SpaceNet on Amazon Web Services (AWS). “Datasets.” The SpaceNet Catalog. https://spacenetchallenge.github.io/datasets/datasetHomePage.html. Accessed 30 Apr 2018
  5. 5.
    Odell, J.: Mayes County. Google (2016). https://datacentermurals.withgoogle.com/mayescounty
  6. 6.
    Worse than Malaria. The Economist. https://www.economist.com/middle-east-and-africa/2015/10/24/worse-than-malaria. Accessed 24 Oct 2015
  7. 7.
    Dstl Satellite Imagery Feature Detection: Can you train an eye in the sky? Kaggle (2016). https://www.kaggle.com/c/dstl-satellite-imagery-feature-detection/data
  8. 8.
    Project Sunroof - Solar Calculator. Google. https://www.google.com/get/sunroof. Accessed 29 Dec 2018
  9. 9.
    Wie Viel Strom Und Wärme Kann Mein Dach Produzieren? Bundesamt für Energie BFE, Sonnendach.ch. http://www.sonnendach.ch. Accessed 29 Dec 2018
  10. 10.
    Groß, B.: The Big Atlas of LA Pools, June 2013. https://benedikt-gross.de/projects/the-big-atlas-of-la-pools
  11. 11.
    GlobalXplorer° (2016). https://www.globalxplorer.org/
  12. 12.
    Lieberman, Z., Felsen, M., and Google Data Arts Team: Land Lines (2016). https://lines.chromeexperiments.com/

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.École polytechnique fédérale de Lausanne (EPFL)LausanneSwitzerland

Personalised recommendations