Using deep learning and Google Street View to estimate the demographic makeup of neighborhoods across the United States.
Using deep learning and Google Street View to estimate the demographic makeup of neighborhoods across the United States.
复制标题
DOI：
10.1073/pnas.1700035114
复制
发表时间：
2017-12-12
影响因子：
11.1
通讯作者：
Fei-Fei L
中科院分区：
文献类型：
--
作者：
Gebru T;Krause J;Wang Y;Chen D;Deng J;Aiden EL;Fei-Fei L
我们展示了社会经济属性，如收入、种族、教育和投票模式，可以使用深度学习从谷歌街景图像中检测到的汽车中推断出来。我们的模型通过发现汽车和人之间的联系而起作用。例如，如果一个城市的轿车数量高于皮卡的数量，那么该城市很可能在下一届总统选举中投票给民主党（88%的几率）；如果没有，那么这个城市很可能会投票给共和党（82%的可能性）。美国每年在美国社区调查（ACS）上花费超过2.5亿美元，这是一项劳动密集型的挨家挨户的研究，测量与种族、性别、教育、职业、失业和其他人口因素有关的统计数据。虽然这是一个全面的数据来源，但人口变化和它们在ACS出现之间的滞后可能超过几年。随着数字图像的普及和机器视觉技术的进步，自动化数据分析可能会成为ACS越来越实用的补充。在这里，我们提出了一种方法，通过使用谷歌街景车收集的5000万张街景图像来估计美国200个城市地区的社会经济特征。使用基于深度学习的计算机视觉技术，我们确定了在特定社区遇到的所有机动车辆的品牌、型号和年份。机动车普查的数据总共包含2200万辆汽车（占美国所有汽车的8%），用于准确估计邮政编码和选区级别的收入、种族、教育和投票模式。（美国平均每个辖区约有1000人。）由此产生的关联非常简单而有力。例如，如果在一个城市开车时遇到的轿车数量高于皮卡的数量，那么这个城市在下一届总统选举中很可能会投票给民主党（88%的几率）；否则，他们很可能会投票给共和党（82%）。我们的研究结果表明，监测人口统计数据的自动化系统可以有效地补充劳动密集型方法，具有接近实时的精细空间分辨率测量人口统计数据的潜力。
We show that socioeconomic attributes such as income, race, education, and voting patterns can be inferred from cars detected in Google Street View images using deep learning. Our model works by discovering associations between cars and people. For example, if the number of sedans in a city is higher than the number of pickup trucks, that city is likely to vote for a Democrat in the next presidential election (88% chance); if not, then the city is likely to vote for a Republican (82% chance). The United States spends more than $250 million each year on the American Community Survey (ACS), a labor-intensive door-to-door study that measures statistics relating to race, gender, education, occupation, unemployment, and other demographic factors. Although a comprehensive source of data, the lag between demographic changes and their appearance in the ACS can exceed several years. As digital imagery becomes ubiquitous and machine vision techniques improve, automated data analysis may become an increasingly practical supplement to the ACS. Here, we present a method that estimates socioeconomic characteristics of regions spanning 200 US cities by using 50 million images of street scenes gathered with Google Street View cars. Using deep learning-based computer vision techniques, we determined the make, model, and year of all motor vehicles encountered in particular neighborhoods. Data from this census of motor vehicles, which enumerated 22 million automobiles in total (8% of all automobiles in the United States), were used to accurately estimate income, race, education, and voting patterns at the zip code and precinct level. (The average US precinct contains ∼1,000 people.) The resulting associations are surprisingly simple and powerful. For instance, if the number of sedans encountered during a drive through a city is higher than the number of pickup trucks, the city is likely to vote for a Democrat during the next presidential election (88% chance); otherwise, it is likely to vote Republican (82%). Our results suggest that automated systems for monitoring demographics may effectively complement labor-intensive approaches, with the potential to measure demographics with fine spatial resolution, in close to real time.
登录
查看更多内容
DOI：
10.1126/science.1199644
发表时间：
2011-01-14
期刊：
Science (New York, N.Y.)
影响因子：
--
作者：
Michel JB;Shen YK;Aiden AP;Veres A;Gray MK;Google Books Team;Pickett JP;Hoiberg D;Clancy D;Norvig P;Orwant J;Pinker S;Nowak MA;Aiden EL
通讯作者：
Aiden EL
DOI：
10.1109/tpami.2009.167
发表时间：
2010-09-01
影响因子：
23.6
作者：
Felzenszwalb, Pedro F.;Girshick, Ross B.;Ramanan, Deva
通讯作者：
Ramanan, Deva
DOI：
10.1016/j.tra.2003.10.005
发表时间：
2004-03-01
影响因子：
6.4
作者：
Choo, S;Mokhtarian, PL
通讯作者：
Mokhtarian, PL
影响因子：
56.9
作者：
Jean, Neal;Burke, Marshall;Ermon, Stefano
通讯作者：
Ermon, Stefano
DOI：
10.1073/pnas.1619003114
发表时间：
2017-07-18
影响因子：
11.1
作者：
Naik, Nikhil;Kominers, Scott Duke;Hidalgo, Cesar A.
通讯作者：
Hidalgo, Cesar A.