Abstract
Mobile and social technologies are providing new opportunities to document, characterize, and gather impressions of urban environments. In this article, we present a study that examines urban perceptions of three cities in central Mexico; the study integrates a mobile crowdsourcing framework to collect geo-localized images of urban environments by a local youth community, an online crowdsourcing platform to gather impressions of urban environments along 12 physical and psychological dimensions, and a deep learning framework to automatically infer human impressions of outdoor urban scenes. Our study resulted in a collection of 7,000 geo-localized images containing outdoor scenes and views of each city’s built environment, including touristic, historical, and residential neighborhoods, and 144,000 individual judgments from Amazon Mechanical Turk. Statistical analyses show that outdoor environments can be assessed in terms of interrater agreement for most of the urban dimensions by the observers of crowdsourced images. Furthermore, we proposed a methodology to automatically infer human perceptions of outdoor scenes using a variety of low-level image features and generic deep learning (CNN) features. We found that CNN features consistently outperformed all the individual low-level image features for all the studied urban dimensions. We obtained a maximum R2 of 0.49 using CNN features; for 9 out of 12 labels, the obtained R2 values exceeded 0.44.
- 2017. Caminos de la Villa. https://www.caminosdelavilla.org/.Google Scholar
- 2017. Delimitacion de las zonas metropolitanas de Mexico 2010. http://www.conapo.gob.mx/es/CONAPO/Zonas_metropolitanas_2010. {Online; Accessed: 15-March-2018}.Google Scholar
- 2017. FixMyStreet. https://www.fixmystreet.com.Google Scholar
- 2017. Map Kibera. http://mapkibera.org.Google Scholar
- 2017. SeeClickFix. http://seeclickfix.com.Google Scholar
- 2017. UNICEF Statistics. https://www.unicef.org/infobycountry/mexico_statistics.html.Google Scholar
- 2017. Ushahidi. http://www.ushahidi.com.Google Scholar
- Sean M. Arietta, Alexei Efros, Ravi Ramamoorthi, Maneesh Agrawala, et al. 2014. City forensics: Using visual elements to predict non-visual city attributes. IEEE Transactions on Visualization and Computer Graphics 20, 12 (2014), 2624--2633. Google ScholarDigital Library
- Michael D. M. Bader, Stephen J. Mooney, Yeon Jin Lee, Daniel Sheehan, Kathryn M. Neckerman, Andrew G. Rundle, and Julien O. Teitler. 2015. Development and deployment of the computer assisted neighborhood visual assessment system (CANVAS) to measure health-related neighborhood conditions. Health 8 Place 31 (2015), 163--172.Google Scholar
- Burcu Baykurt. 2012. Redefining citizenship and civic engagement: Political values embodied in FixMyStreet.com. Selected Papers of Internet Research 1 (2012).Google Scholar
- Leo Breiman. 2001. Random forests. Machine Learning 45, 1 (2001), 5--32. Google ScholarDigital Library
- Egon Brunswik. 1956. Perception and the Representative Design of Psychological Experiments. University of California Press.Google Scholar
- Jaime S, Cardoso and Joaquim F. Costa. 2007. Learning to classify ordinal data: The data replication method. Journal of Machine Learning Research 8, Jul (2007), 1393--1429. Google ScholarDigital Library
- Manuel Castells et al. 2014. Reconceptualizing Development in the Global Information Age. Oxford University Press.Google Scholar
- Will Connors. 2015. Google, Microsoft Expose Brazil’s Favelas. http://on.wsj.com/1V3X2qI.Google Scholar
- Terry C. Daniel. 2001. Whither scenic beauty? Visual landscape quality assessment in the 21st century. Landscape and Urban Planning 54, 1--4 (2001), 267--281.Google ScholarCross Ref
- Djellel Difallah, Elena Filatova, and Panos Ipeirotis. 2018. Demographics and dynamics of mechanical Turk workers. In Proceedings of the 11th ACM International Conference on Web Search and Data Mining (WSDM’18), Marina Del Rey, CA. ACM, 135--143. Google ScholarDigital Library
- Carl Doersch, Saurabh Singh, Abhinav Gupta, Josef Sivic, and Alexei Efros. 2012. What makes Paris look like Paris? ACM Transactions on Graphics 31, 4 (2012). Google ScholarDigital Library
- Abhimanyu Dubey, Nikhil Naik, Devi Parikh, Ramesh Raskar, and Cesar A. Hidalgo. 2016. Deep learning the city: Quantifying urban perception at a global scale. In Proceedings of the European Conference on Computer Vision, Amsterdam. Springer, 196--212.Google Scholar
- Gustavo Esteva and Madhu Suri Prakash. 2014. Grassroots Postmodernism: Remaking the Soil of Cultures. Zed Books Ltd.Google Scholar
- Eibe Frank and Mark Hall. 2001. A simple approach to ordinal classification. In Proceedings of the European Conference on Machine Learning, Freiburg. Springer, 145--156. Google ScholarDigital Library
- Lindsay T. Graham and Samuel D. Gosling. 2011. Can the ambiance of a place be determined by the user profiles of the people who visit it. In Proceedings of the International AAAI Conference on Web and Social Media, Barcelona. AAAI.Google Scholar
- Kotaro Hara et al. 2013. Combining crowdsourcing and Google Street View to identify street-level accessibility problems. In Proceedings of the CHI, Paris. ACM, 631--640. Google ScholarDigital Library
- Susan Jamieson et al. 2004. Likert scales: How to (ab)use them. Medical Education 38, 12 (2004), 1217--1218.Google ScholarCross Ref
- Bin Jin, Maria V Ortiz Segovia, and Sabine Susstrunk. 2016. Image aesthetic predictors based on weighted CNNs. In Proceedings of the IEEE International Conference on Image Processing (ICIP’16), Phoenix. IEEE, 2291--2295.Google ScholarCross Ref
- Frederic Jurie and Bill Triggs. 2005. Creating efficient codebooks for visual recognition. In Proceedings of the 10th IEEE International Conerence on Computer Vision (ICCV’05), Beijing. Vol. 1. IEEE, 604--610. Google ScholarDigital Library
- Rachel Kaplan, Stephen Kaplan, and Terry Brown. 1989. Environmental preference: A comparison of four domains of predictors. Environment and Behavior 21, 5 (1989), 509--530.Google ScholarCross Ref
- Stephen Kaplan. 1988. Perception and landscape: Conceptions and misconceptions. Environmental Aesthetics: Theory, Research, and Application (1988), 45--55.Google Scholar
- Stephen F. King and Paul Brown. 2007. Fix my street or else: Using the internet to voice local public service concerns. In Proceedings of the 1st International Conference on Theory and Practice of Electronic Governance, Macao SAR. ACM, 72--80. Google ScholarDigital Library
- Pall J. Lindal et al. 2013. Architectural variation, building height, and the restorative quality of urban residential streetscapes. Journal of Environmental Psychology 33 (2013), 26--36.Google ScholarCross Ref
- Laura J. Loewen et al. 1993. Perceived safety from crime in the urban environment. Journal of Environmental Psychology 13, 4 (1993), 323--331.Google ScholarCross Ref
- Andrés Monroy-Hernández et al. 2013. The new war correspondents: The rise of civic media curation in urban warfare. In Proceedings of the ACM Conference on Computer Supported Cooperative Work and Social Computing, San Antonio, TX. ACM, 1443--1452. Google ScholarDigital Library
- Nikhil Naik, Jade Philipoom, Ramesh Raskar, and Cesar Hidalgo. 2014. Streetscore-predicting the perceived safety of one million streetscapes. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, Columbus. IEEE, 779--785. Google ScholarDigital Library
- Joan Iverson Nassauer. 1983. Framing the landscape in photographic simulation. Journal of Environmental Management 17, 1 (1983), 1--16.Google Scholar
- L. S. Nguyen, S. Ruiz-Correa, M. Schmid Mast, and D. Gatica-Perez. 2017. Check out this place: Inferring ambiance from AirBnB photos. IEEE Transactions on Multimedia 99 (2017), 1--1.Google Scholar
- Timo Ojala, Matti Pietikainen, and Topi Maenpaa. 2002. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Transactions on Pattern Analysis and Machine Intelligence 24, 7 (2002), 971--987. Google ScholarDigital Library
- Aude Oliva and Antonio Torralba. 2001. Modeling the shape of the scene: A holistic representation of the spatial envelope. International Journal of Computer Vision 42, 3 (2001), 145--175. Google ScholarDigital Library
- Vicente Ordonez and Tamara L. Berg. 2014. Learning high-level judgments of urban perception. In Proceedings of the European Conference on Computer Vision, Zurich. Springer, 494--510.Google Scholar
- Kate Painter. 1996. The influence of street lighting improvements on crime, fear and pedestrian street use, after dark. Landscape and Urban Planning 35, 2 (1996), 193--201.Google ScholarCross Ref
- Karl Pearson. 1901. LIII. On lines and planes of closest fit to systems of points in space. The London, Edinburgh, and Dublin Philosophical Magazine and Journal of Science 2, 11 (1901), 559--572.Google ScholarCross Ref
- Lorenzo Porzi, Samuel Rota Bulò, Bruno Lepri, and Elisa Ricci. 2015. Predicting and understanding urban perception with convolutional neural networks. In Proceedings of the 23rd ACM International Conference on Multimedia, Brisbane. ACM, 139--148. Google ScholarDigital Library
- D. Quercia, N. O'Hare, and H. Cramer. 2014. Aesthetic capital: What makes London look beautiful, quiet, and happy? In Proceedings of the ACM Conference on Computer Supported Cooperative Work and Social Computing, Vancouver, BC. ACM, 945--955. Google ScholarDigital Library
- Ali Razavian, Hossein Azizpour, Josephine Sullivan, and Stefan Carlsson. 2014. CNN features off-the-shelf: An astounding baseline for recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus. IEEE, 806--813. Google ScholarDigital Library
- Joel Ross et al. 2010. Who are the crowdworkers? Shifting demographics in mechanical Turk. In Proceedings of the Extended Abstracts on Human Factors in Computing Systems (CHI’10), Atlanta. ACM, 2863--2872. Google ScholarDigital Library
- Salvador Ruiz-Correa, Darshan Santani, and Daniel Gatica-Perez. 2014. The young and the city: Crowdsourcing urban awareness in a developing country. In Proceedings of the 1st International Conference on IoT in Urban Space (Urb-IoT), Rome. ACM, 74--79. Google ScholarDigital Library
- Salvador Ruiz-Correa, Darshan Santani, Beatriz Ramirez-Salazar, Itzia Ruiz-Correa, Fatima Alba Rendon-Huerta, Carlo Olmos-Carrillo, Brisa Carmina Sandoval-Mexicano, Angel Humberto Arcos-Garcia, Rogelio Hasimoto-Beltran, and Daniel Gatica-Perez. 2017. Sensecityvity: Mobile crowdsourcing, urban awareness, and collective action in Mexico. IEEE Pervasive Computing 16, 2 (2017), 44--53. Google ScholarDigital Library
- James A. Russell. 1978. Evidence of convergent validity on the dimensions of affect. Journal of Personality and Social Psychology 36, 10 (1978), 1152.Google ScholarCross Ref
- James A. Russell. 1979. Affective space is bipolar. Journal of Personality and Social Psychology 37, 3 (1979), 345.Google ScholarCross Ref
- James A. Russell et al. 1980. A description of the affective quality attributed to environments. Journal of Personality and Social Psychology 38, 2 (1980), 311.Google ScholarCross Ref
- Philip Salesses, Katja Schechtner, and Cesar A. Hidalgo. 2013. The collaborative image of the city: Mapping the inequality of urban perception. PLoS ONE 8, 7 (07 2013), e68400.Google Scholar
- Robert J. Sampson et al. 2004. Seeing disorder: Neighborhood stigma and the social construction of “broken windows”. Social Psychology Quarterly 67, 4 (2004), 319--342.Google ScholarCross Ref
- Darshan Santani and Daniel Gatica-Perez. 2015. Loud and trendy: Crowdsourcing impressions of social ambiance in popular indoor urban places. In Proceedings of the 23rd ACM International Conference on Multimedia, Brisbane. ACM, 211--220. Google ScholarDigital Library
- Darshan Santani, Rui Hu, and Daniel Gatica-Perez. 2016. InnerView: Learning place ambiance from social media images. In Proceedings of the ACM Annual Symposium on Computing for Development, London. ACM, 451--455. Google ScholarDigital Library
- Darshan Santani, Salvador Ruiz-Correa, and Daniel Gatica-Perez. 2015. Looking at cities in Mexico with crowds. In Proceedings of the 2015 Annual Symposium on Computing for Development. ACM, 127--135. Google ScholarDigital Library
- Darshan Santani, Salvador Ruiz-Correa, and Daniel Gatica-Perez. 2017. Insiders and outsiders: Comparing urban impressions between population groups. In Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval, Bucharest. ACM, 65--71. Google ScholarDigital Library
- Patrick E. Shrout et al. 1979. Intraclass correlations: Uses in assessing rater reliability. Psychological Bulletin 86, 2 (1979), 420.Google ScholarCross Ref
- Fredrik M. Sjoberg, Jonathan Mellon, and Tiago Peixoto. 2015. The effect of government responsiveness on future political participation. Working Paper No. 1, World Bank's Digital Engagement Evaluation Team.Google Scholar
- S. S. Stevens. 1946. On the theory of scales of measurement. Science 103, 2684 (1946), 677--680.Google Scholar
- Sam Sturgis. 2015. Kids in India are sparking urban planning changes by mapping slums. http://bit.ly/1LtS9S4.Google Scholar
- Antonio Torralba and Alexei A. Efros. 2011. Unbiased look at dataset bias. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’11), Colorado Springs, CO. IEEE, 1521--1528. Google ScholarDigital Library
- Jianxiong Xiao, James Hays, Krista A. Ehinger, Aude Oliva, and Antonio Torralba. 2010. Sun database: Large-scale scene recognition from abbey to zoo. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’10), San Francisco. IEEE, 3485--3492.Google ScholarCross Ref
- Bolei Zhou, Agata Lapedriza, Jianxiong Xiao, Antonio Torralba, and Aude Oliva. 2014. Learning deep features for scene recognition using places database. In Advances in Neural Information Processing Systems. NIPS Foundation, 487--495. Google ScholarDigital Library
- Bolei Zhou, Liu Liu, Aude Oliva, and Antonio Torralba. 2014. Recognizing city identity via attribute analysis of geo-tagged images. In European Conference on Computer Vision, Zurich. Springer, 519--534.Google ScholarCross Ref
Index Terms
- Looking South: Learning Urban Perception in Developing Cities
Recommendations
Quantifying Urban Safety Perception on Street View Images
WI-IAT '21: IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent TechnologyIn the last 40 years, Urban perception has become an important research area covering several fields, such as criminology, psychology, urban planning, Broken windows theory. It aims to analyze and interpret the behavior of the perception in cities. ...
Urban Perception of Commercial Activeness from Satellite Images and Streetscapes
WWW '18: Companion Proceedings of the The Web Conference 2018People can percept social attributes from streetscapes such as safety, richness, and happiness by means of visual perception, which inspires the research in terms of urban perception. To the best of our knowledge, this is the first work focused on ...
Urban Perception: Sensing Cities via a Deep Interactive Multi-task Learning Framework
Social scientists have shown evidence that visual perceptions of urban attributes, such as safe, wealthy, and beautiful perspectives of the given cities, are highly correlated to the residents’ behaviors and quality of life. Despite their significance, ...
Comments