ABSTRACT
Street frontage quality is an important element in urban design as it contributes to the interest, social life and success of public spaces. To collect the data needed to evaluate street frontage quality at the city or regional level using traditional survey method is both costly and time consuming. As a result, this research proposes a pipeline that uses convolutional neural network to classify the frontage of a street image through the case study of Greater London. A novelty of the research is it uses both Google streetview images and 3D-model generated streetview images for the classification. The benefit of this approach is that it can provide a framework to test different urban parameters to help evaluate future urban design projects. The research finds encouraging results in classifying urban frontage quality using deep learning models. This research also finds that augmenting the baseline model with images produced from a 3D-model can improve slightly the accuracy of the results. However these results should be taken as preliminary, where we acknowledge several limitations such as the lack of adversarial analysis, labeled data, or parameter tuning. Despite these limitations, the results of the proof-of-concept study is positive and carries great potential in the application of urban data analytics.
- L Chen, G Papandreou, I Kokkinos, K Murphy, and A.L. Yuille. 2014. Semantic image segmentatiom with deep convolutional nets and fully connected crfs. arXiv preprint arXiv:1412.7062 (2014).Google Scholar
- C Doersch, S Singh, C Wu, and W Hui. 2012. ACM Transactions on Graphics. What makes Paris look like Paris (2012).Google Scholar
- ESRI. 2013. http://www.esri.com/software/cityengine/. (2013).Google Scholar
- J Gehl. 1971. Life between buildings: Using public space. The Danish Architectural Press.Google Scholar
- J. Gehl. 2010. Cities for People. Island Press.Google Scholar
- R Girshick. 2015. Fast R-CNN. IEEE International Conference on Computer Vision (2015). Google ScholarDigital Library
- Google. 2017. https://www.maps.google.com/. (2017). Accessed: 2017.Google Scholar
- E Heffernan, T Heffernan, and W Pan. 2014. The relationship between the quality of active frontages and public perceptions of public spaces. Urban Design international (2014).Google Scholar
- J. Jacobs. 1961. The Death and Life of Great American Cities. Random House Inc.Google Scholar
- Y Jia. 2012. Caffe: An open source convolution architecture for fast feature embedding. http://caffe.berkeleyvision.org. (2012). Accessed: 2016.Google Scholar
- A Krizhevsky, I Sutskever, and G.E Hinton. 2012. Imagenet classification with deep convolutional neural networks. Advances in neural information processing (2012). Google ScholarDigital Library
- Y Li, M Paluri, J Rehg, and P Dollar. 2016. Unsupervised learning of edges. CVPR (2016).Google Scholar
- L Liu, E Silva, C Wu, and W Hui. 2017. A machine learning-based method for the large-scale evaluation of the urban environment. Computers, Environment and Urban Systems (2017).Google Scholar
- N. Naik, J. Philipoom, R. Raskar, and C.A. Hidalgo. 2014. StreetScore - Predicting the Perceived Safety of One Million Streetscapes. In CVPR Workshop on Web-scale Vision and Social Media. Google ScholarDigital Library
- Office of the Deputy Prime Minister. 2005. Safer Places: The Planning System and Crime Prevention. Home Office.Google Scholar
- C Seresinhe, T Preis, and S Moat. 2017. Using deep learning to quantify the beauty of oudoor plaes. Royal Society Open Science (2017).Google Scholar
- Streetscore. 2014. http://streetscore.media.mit.edu. (2014). Accessed: 2016-04-29.Google Scholar
- Llewelyn Davies Yeang and Homes Communities Agency. 2013. Urban Design Compendium. English Partnerships and The Housing Corporation.Google Scholar
- B Zhou, J Lapedriza, A Xiao, A Torralba, and A Oliva. 2014. Learning deep features for scene recognition using places database. Advances in neural information processing (2014). Google ScholarDigital Library
Index Terms
- An application of convolutional neural network in street image classification: the case study of london
Recommendations
Take a Look Around: Using Street View and Satellite Images to Estimate House Prices
Special Section on Advances in Causal Discovery and Inference and Regular PapersWhen an individual purchases a home, they simultaneously purchase its structural features, its accessibility to work, and the neighborhood amenities. Some amenities, such as air quality, are measurable while others, such as the prestige or the visual ...
How to Realize a Compact City: Street Activeness and Agent-based Urban Modeling
SMARTGREENS 2019: Proceedings of the 8th International Conference on Smart Cities and Green ICT SystemsThe purpose of this research is to verify the effectiveness of the combination of the introduction of tramway with introducing a public facility for urban residents and promoting street activeness around it, on urban sprawl. An agent-based model (ABM) ...
Realization of Two Types of Compact City - Street Activeness and Tramway -
PRIMA 2018: Principles and Practice of Multi-Agent SystemsAbstractThe purpose of this research is to verify the effectiveness of the combination of the introduction of a tramway with introducing a public facility for urban residents and implementing a policy to promote activeness around it, on urban sprawl. By ...
Comments