{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T13:37:57Z","timestamp":1778679477918,"version":"3.51.4"},"reference-count":40,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2018,10,23]],"date-time":"2018-10-23T00:00:00Z","timestamp":1540252800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000780","name":"European Commission","doi-asserted-by":"publisher","award":["727688"],"award-info":[{"award-number":["727688"]}],"id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>(1) Background: Evidence-based policymaking requires data about the local population\u2019s socioeconomic status (SES) at detailed geographical level, however, such information is often not available, or is too expensive to acquire. Researchers have proposed solutions to estimate SES indicators by analyzing Google Street View images, however, these methods are also resource-intensive, since they require large volumes of manually labeled training data. (2) Methods: We propose a methodology for automatically computing surrogate variables of SES indicators using street images of parked cars and deep multiple instance learning. Our approach does not require any manually created labels, apart from data already available by statistical authorities, while the entire pipeline for image acquisition, parked car detection, car classification, and surrogate variable computation is fully automated. The proposed surrogate variables are then used in linear regression models to estimate the target SES indicators. (3) Results: We implement and evaluate a model based on the proposed surrogate variable at 30 municipalities of varying SES in Greece. Our model has      R 2  = 0.76     and a correlation coefficient of     0.874     with the true unemployment rate, while it achieves a mean absolute percentage error of     0.089     and mean absolute error of     1.87     on a held-out test set. Similar results are also obtained for other socioeconomic indicators, related to education level and occupational prestige. (4) Conclusions: The proposed methodology can be used to estimate SES indicators at the local level automatically, using images of parked cars detected via Google Street View, without the need for any manual labeling effort.<\/jats:p>","DOI":"10.3390\/jimaging4110125","type":"journal-article","created":{"date-parts":[[2018,10,24]],"date-time":"2018-10-24T02:59:40Z","timestamp":1540349980000},"page":"125","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Image-Based Surrogates of Socio-Economic Status in Urban Neighborhoods Using Deep Multiple Instance Learning"],"prefix":"10.3390","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2461-1928","authenticated-orcid":false,"given":"Christos","family":"Diou","sequence":"first","affiliation":[{"name":"Multimedia Understanding Group, Electrical and Computer Engineering Department, Aristotle University of Thessaloniki, 54124 Thessaloniki, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4209-1230","authenticated-orcid":false,"given":"Pantelis","family":"Lelekas","sequence":"additional","affiliation":[{"name":"Multimedia Understanding Group, Electrical and Computer Engineering Department, Aristotle University of Thessaloniki, 54124 Thessaloniki, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8220-8486","authenticated-orcid":false,"given":"Anastasios","family":"Delopoulos","sequence":"additional","affiliation":[{"name":"Multimedia Understanding Group, Electrical and Computer Engineering Department, Aristotle University of Thessaloniki, 54124 Thessaloniki, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2018,10,23]]},"reference":[{"key":"ref_1","unstructured":"Nutley, S.M., Smith, P.C., and Davies, H.T. (2000). What Works? Evidence-Based Policy and Practice in Public Services, Policy Press."},{"key":"ref_2","unstructured":"UK Cabinet Office (1999). Modernising Government."},{"key":"ref_3","unstructured":"Abraham, K.G., and Haskins, R. (2018, October 20). The Promise of Evidence-Based Policymaking. Report of the Commission on Evidence-Based Policymaking, Available online: https:\/\/cep.gov\/cep-final-report.html."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1136\/bmj.325.7361.436","article-title":"\u201cFood deserts\u201d\u2014Evidence and assumption in health policy making","volume":"325","author":"Cummins","year":"2002","journal-title":"Br. Med. J."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Parkhurst, J. (2017). The Politics of Evidence: From Evidence-Based Policy to the Good Governance of Evidence, Taylor & Francis.","DOI":"10.4324\/9781315675008"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"304","DOI":"10.1353\/pbm.0.0085","article-title":"Evidence-based policymaking: a critique","volume":"52","author":"Greenhalgh","year":"2009","journal-title":"Perspect. Biol. Med."},{"key":"ref_7","unstructured":"Williams, J.D. (2011). The 2010 Decennial Census: Background and Issues, Library of Congress, Congressional Research Service."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1109\/MC.2010.170","article-title":"Google street view: Capturing the world at street level","volume":"43","author":"Anguelov","year":"2010","journal-title":"Computer"},{"key":"ref_9","unstructured":"(2018, October 20). Google Street View API Developer Guide. Available online: https:\/\/developers.google.com\/maps\/documentation\/streetview\/intro."},{"key":"ref_10","unstructured":"(2018, October 20). Bing Maps Streetside. Available online: https:\/\/www.microsoft.com\/en-us\/maps\/streetside."},{"key":"ref_11","unstructured":"(2018, October 20). Open Street Cam. Available online: https:\/\/openstreetcam.org\/."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1111\/obr.12384","article-title":"Individual and contextual correlates of obesity-related behaviours and obesity: The SPOTLIGHT project","volume":"17","author":"Lakerveld","year":"2016","journal-title":"Obes. Rev."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1186\/1476-072X-13-52","article-title":"The SPOTLIGHT virtual audit tool: a valid and reliable tool to assess obesogenic characteristics of the built environment","volume":"13","author":"Bethlehem","year":"2014","journal-title":"Int. J. Health Geogr."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1111\/obr.12378","article-title":"Neighbourhood typology based on virtual audit of environmental obesogenic characteristics","volume":"17","author":"Feuillet","year":"2016","journal-title":"Obes. Rev."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"13108","DOI":"10.1073\/pnas.1700035114","article-title":"Using deep learning and Google Street View to estimate the demographic makeup of neighborhoods across the United States","volume":"114","author":"Gebru","year":"2017","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref_16","unstructured":"(2018, October 20). BigO: \u201cBig Data Against Childhood Obesity\u201d. Research Project Funded by the European Community: H2020-727688, 01\/12\/2016\u201330\/11\/2020. Available online: https:\/\/bigoprogram.eu\/."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume":"39","author":"Ren","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (2016, January 27\u201330). Rethinking the inception architecture for computer vision. Proceedings of the IEEE conference on computer vision and pattern recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1016\/j.amepre.2010.09.034","article-title":"Using Google Street View to audit neighborhood environments","volume":"40","author":"Rundle","year":"2011","journal-title":"Am. J. Prev. Med."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1007","DOI":"10.1007\/s11524-010-9505-x","article-title":"Can virtual streetscape audits reliably replace physical streetscape audits?","volume":"87","author":"Badland","year":"2010","journal-title":"J. Urban Health"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1177\/0002716216681488","article-title":"The promise, practicalities, and perils of virtually auditing neighborhoods using Google Street View","volume":"669","author":"Bader","year":"2017","journal-title":"Ann. Am. Acad. Polit. Soc. Sci."},{"key":"ref_22","unstructured":"Goodfellow, I.J., Bulatov, Y., Ibarz, J., Arnoud, S., and Shet, V. (2013). Multi-digit number recognition from street view imagery using deep convolutional neural networks. arXiv."},{"key":"ref_23","unstructured":"(2018, October 20). Google Maps. Available online: https:\/\/maps.google.com."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Wegner, J.D., Branson, S., Hall, D., Schindler, K., and Perona, P. (2016, January 27\u201330). Cataloging public objects using aerial and street-level images-urban trees. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.647"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Zamir, A.R., Darino, A., and Shah, M. (2011, January 18\u201321). Street view challenge: Identification of commercial entities in street view imagery. Proceedings of the 2011 10th International Conference on Machine Learning and Applications and Workshops, Honolulu, HI, USA.","DOI":"10.1109\/ICMLA.2011.181"},{"key":"ref_26","unstructured":"Yu, Q., Szegedy, C., Stumpe, M.C., Yatziv, L., Shet, V., Ibarz, J., and Arnoud, S. (2015). Large scale business discovery from street level imagery. arXiv."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Movshovitz-Attias, Y., Yu, Q., Stumpe, M.C., Shet, V., Arnoud, S., and Yatziv, L. (2015, January 7\u201312). Ontological supervision for fine grained classification of street view storefronts. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298778"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"De Nadai, M., Vieriu, R.L., Zen, G., Dragicevic, S., Naik, N., Caraviello, M., Hidalgo, C.A., Sebe, N., and Lepri, B. (2016, January 15\u201319). Are safer looking neighborhoods more lively?: A multimodal investigation into urban life. Proceedings of the 2016 ACM on Multimedia Conference, Amsterdam, The Netherlands.","DOI":"10.1145\/2964284.2964312"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Dubey, A., Naik, N., Parikh, D., Raskar, R., and Hidalgo, C.A. (2016). Deep learning the city: Quantifying urban perception at a global scale. European Conference on Computer Vision, Springer.","DOI":"10.1007\/978-3-319-46448-0_12"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"337","DOI":"10.1016\/j.apgeog.2015.07.010","article-title":"\u2018Big data\u2019 for pedestrian volume: Exploring the use of Google Street View images for pedestrian counts","volume":"63","author":"Yin","year":"2015","journal-title":"Appl. Geogr."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1016\/j.apgeog.2016.09.024","article-title":"Measuring visual enclosure for street walkability: Using machine learning algorithms and Google Street View imagery","volume":"76","author":"Yin","year":"2016","journal-title":"Appl. Geogr."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Maharana, A., and Nsoesie, E.O. (2017). Using Deep Learning to Examine the Association between the Built Environment and Neighborhood Adult Obesity Prevalence. arXiv.","DOI":"10.1001\/jamanetworkopen.2018.1535"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Gebru, T., Krause, J., Wang, Y., Chen, D., and Deng, J. (2017). Fine-Grained Car Detection for Visual Census Estimation, AAAI.","DOI":"10.1609\/aaai.v31i1.11174"},{"key":"ref_34","unstructured":"(2018, October 20). Google Geocoding API. Available online: https:\/\/developers.google.com\/maps\/documentation\/geocoding\/start."},{"key":"ref_35","unstructured":"(2018, October 20). Faster RCNN Implementation for Tensorflow, FasterRCNN_TF. Available online: https:\/\/github.com\/smallcorgi\/Faster-RCNN_TF."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Girshick, R. (2015, January 7\u201313). Fast R-CNN. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref_37","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv."},{"key":"ref_38","unstructured":"Maron, O., and Lozano-P\u00e9rez, T. (1997, January 1\u20136). A framework for multiple-instance learning. Proceedings of the 1997 conference on Advances in Neural Information Processing Systems, Denver, CO, USA."},{"key":"ref_39","unstructured":"Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., and Isard, M. (2016, January 2\u20134). Tensorflow: A system for large-scale machine learning. Proceedings of the 12th USENIX Conference on Operating Systems Design and Implementation, Savannah, GA, USA."},{"key":"ref_40","unstructured":"(2018, October 20). Hellenic Statistical Authority. Available online: http:\/\/www.statistics.gr\/en\/home\/."}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-433X\/4\/11\/125\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T15:25:42Z","timestamp":1760196342000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-433X\/4\/11\/125"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,10,23]]},"references-count":40,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2018,11]]}},"alternative-id":["jimaging4110125"],"URL":"https:\/\/doi.org\/10.3390\/jimaging4110125","relation":{"has-preprint":[{"id-type":"doi","id":"10.20944\/preprints201808.0154.v1","asserted-by":"object"},{"id-type":"doi","id":"10.20944\/preprints201808.0154.v2","asserted-by":"object"}]},"ISSN":["2313-433X"],"issn-type":[{"value":"2313-433X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,10,23]]}}}