[论文解读] Take a Look Around

Stephen Law, Brooks Paige+1 more|arXiv (Cornell University)|Nov 14, 2019

Housing Market and Economics参考文献 34被引用 40

一句话总结

本文提出了一种深度学习流程，通过融合街景图像与航空影像及传统住房特征，提升伦敦房屋价格预测的准确性。通过从 Google 地图街景和 Bing 卫星图像中提取视觉城市质量特征，该模型增强了价格估计的准确性，并实现了可解释、可迁移的社区视觉吸引力地图。

ABSTRACT

When 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 impression of a neighborhood, are difficult to quantify. Despite the well-known impacts intangible housing features have on house prices, limited attention has been given to systematically quantifying these difficult to measure amenities. Two issues have led to this neglect. Not only do few quantitative methods exist that can measure the urban environment, but that the collection of such data is both costly and subjective. We show that street image and satellite image data can capture these urban qualities and improve the estimation of house prices. We propose a pipeline that uses a deep neural network model to automatically extract visual features from images to estimate house prices in London, UK. We make use of traditional housing features such as age, size, and accessibility as well as visual features from Google Street View images and Bing aerial images in estimating the house price model. We find encouraging results where learning to characterize the urban quality of a neighborhood improves house price prediction, even when generalizing to previously unseen London boroughs. We explore the use of non-linear vs. linear methods to fuse these cues with conventional models of house pricing, and show how the interpretability of linear models allows us to directly extract proxy variables for visual desirability of neighborhoods that are both of interest in their own right, and could be used as inputs to other econometric methods. This is particularly valuable as once the network has been trained with the training data, it can be applied elsewhere, allowing us to generate vivid dense maps of the visual appeal of London streets.

研究动机与目标

• 为量化影响房屋价格但难以衡量的无形城市设施（如视觉吸引力和社区声望）提供解决方案。
• 通过利用可获取的 Google 地图街景和 Bing 卫星图像数据，克服传统城市质量数据采集成本高、主观性强的挑战。
• 开发一种可扩展、可迁移的方法，将视觉特征与传统住房属性结合，以增强房屋价格预测模型。
• 探究非线性与线性融合方法在房屋价格估计中对模型性能与可解释性的影响。
• 通过将训练好的模型应用于此前未见过的行政区，生成伦敦全境密集且生动的视觉宜人度地图。

提出的方法

• 利用深度神经网络从伦敦住宅区的 Google 地图街景和 Bing 航空图像中自动提取视觉特征。
• 将提取的视觉特征与标准住房特征（如房屋年龄、面积以及通勤至就业中心的便利性）结合，构建统一的回归模型。
• 采用线性与非线性融合技术整合视觉与传统特征，比较其对预测准确性的不同影响。
• 在伦敦各行政区的房屋价格标注数据集上训练模型，使其能够泛化至此前未见过的区域。
• 利用线性模型的可解释性，推导出代表视觉宜人度的代理变量，可用于后续计量经济学分析。
• 通过在全市范围内应用训练好的模型，生成高分辨率、密集的社区视觉吸引力地图。

实验结果

研究问题

• RQ1 从街景与航空图像中提取的视觉特征是否能提升城市环境中房屋价格预测模型的准确性？
• RQ2 在房屋价格估计中，非线性与线性融合方法在整合视觉与传统住房特征方面表现如何比较？
• RQ3 在一组伦敦行政区上训练的模型，能在多大程度上泛化至预测此前未见过行政区的房屋价格？
• RQ4 能否从模型的线性组件中推导出可解释的社区视觉宜人度代理变量？
• RQ5 训练好的模型能否生成整个城市（如伦敦）范围内详细且空间密集的视觉吸引力地图？

主要发现

• 与仅使用传统特征的模型相比，从街景与卫星图像中整合视觉特征能显著提升房屋价格预测的准确性。
• 该模型在未见过的伦敦行政区上表现出良好的泛化能力，证明了所学习视觉表征的稳健性与可迁移性。
• 非线性融合方法在预测性能方面优于线性融合，但线性模型在推导视觉宜人度代理变量方面具有更高的可解释性。
• 该模型成功生成了伦敦全境密集且高分辨率的视觉吸引力地图，揭示了社区宜人度的空间分布模式。
• 从模型线性组件中推导出的可解释代理变量与感知的社区质量具有有意义的对应关系，可进一步用于计量经济学建模。
• 该方法为衡量城市美学与环境质量提供了一种可扩展、成本效益高的替代方案，优于传统主观测量方法。