本文探討台北市街景感知指標與住宅租金之關聯性，並進一步檢驗街景環境品質是否能解釋住宅租金差異。隨著街景影像與人工智慧技術的發展，過去較難量化的都市環境感知因素，已可透過街景影像資料轉化為可分析的量化指標。本文以台北市住宅租賃資料為基礎，結合街景感知指標、住宅特徵、建物型態與空間區位變數，建立特徵價格模型，分析 walkability、bikeability、pleasantness、greenness 與 safety 等街景感知指標對住宅租金之影響。
實證結果顯示，街景感知指標與住宅租金之間存在顯著關聯。其中，walkability 對租金具有穩定且顯著的正向影響，顯示步行友善程度較高的住宅周邊環境，通常對租屋市場具有較高吸引力。相對地，bikeability 與 pleasantness 在主要模型中呈現顯著負向關係，可能反映街景感知指標與住宅區位、生活機能或都市空間結構之間存在較複雜的關聯。greenness 與 safety 的估計結果則在加入行政區固定效果、月份固定效果與空間區位控制後較不穩定，顯示其影響可能已部分被區位條件與地區差異吸收。
此外，本文透過替代被解釋變數、限制樣本、替代區位變數與傳統特徵價格模型進行穩健性檢定，結果顯示主要估計結論大致維持一致。本文之研究結果指出，街景感知指標可作為住宅市場研究中衡量鄰里環境品質的重要補充變數，亦有助於理解租屋市場中非傳統住宅屬性如何反映於租金價格之中。

This study examines the relationship between street-view perception indicators and residential rents in Taipei City. Traditional housing market studies usually explain rents through housing characteristics, building types, and locational factors. However, the quality of the surrounding street-level environment may also affect residential desirability. With the development of street-view imagery and artificial intelligence techniques, urban environmental perceptions that were previously difficult to quantify can now be transformed into measurable indicators.
Using residential rental data in Taipei City, this study combines housing characteristics, building type variables, location controls, and five street-view perception indicators: walkability, bikeability, pleasantness, greenness, and safety. A hedonic pricing model is applied to estimate how these indicators are associated with residential rents. The dependent variable is the natural logarithm of rent. The empirical models progressively include housing characteristics,location variables, district fixed effects, and month fixed effects.
The empirical results show that street-view perception indicators are significantly associated with residential rents, but their effects are not uniform. Walkability has a stable and significantly positive relationship with rent, suggesting that pedestrian-friendly environments are valued in Taipei's rental market. In contrast, bikeability and pleasantness are negatively associated with rents in the main specifications. The effects of greenness and safety become less stable after controlling for district fixed effects, month fixed effects, and location variables. Robustness checks using alternative location measures show that the main findings remain broadly consistent.

[1]內政部地政司。內政部不動產交易實價查詢服務網。
[2] 李春長、梁志民、林豐文（2017）。〈捷運系統對鄰近住宅價格之影響—以差異中之差異法估計〉。《台灣土地研究》，20(2)，31–58。
[3] 郭祐誠、林佳慧（2025）。〈男女有別？台北市租屋市場之女性租金優惠〉。《經濟論文叢刊》，53(1)，109–156。
[4] Alonso, W. (1964). Location and land use: Toward a general theory of land rent.Harvard University Press.
[5] Biljecki, F., & Ito, K. (2021). Street view imagery in urban analytics and GIS: Areview.Landscape and Urban Planning, 215, 104217.
[6] Cameron, A. C., & Miller, D. L. (2015). A practitioner’s guide to cluster-robustinference.Journal of Human Resources, 50(2), 317–372.
[7] Can, A. (1992). Specification and estimation of hedonic housing price models. Regional Science and Urban Economics, 22(3), 453–474.
[8] Ceccato, V., & Wilhelmsson, M. (2011). The impact of crime on apartment prices:Evidence from Stockholm, Sweden. Geografiska Annaler: Series B, Human Geography,93(1), 1–23.
[9] Conrow, L., Mooney, S., & Wentz, E. A. (2021). The association between residential housing prices, bicycle infrastructure and ridership volumes. Urban Studies, 58(4),787–808.
[10] Dahir, A., & Le, H. T. K. (2025). Impacts of bicycle facilities on residential property values in 11 US cities. Journal of Transport Geography, 123, 104146.
[11] Danish, M., Labib, S. M., Ricker, B., & Helbich, M. (2025). A citizen science toolkit to collect human perceptions of urban environments using open street view images.Computers, Environment and Urban Systems, 116, 102207.
[12] Debrezion, G., Pels, E., & Rietveld, P. (2007). The impact of railway stations onresidential and commercial property value: A meta-analysis. The Journal of Real Estate Finance and Economics, 35(2), 161–180.
[13] Donovan, G. H., & Butry, D. T. (2010). Trees in the city: Valuing street trees in Portland, Oregon. Landscape and Urban Planning, 94(2), 77–83.
[14] Dubey, A., Naik, N., Parikh, D., Raskar, R., & Hidalgo, C. A. (2016). Deep learning the city: Quantifying urban perception at a global scale. In Proceedings of the European Conference on Computer Vision.
[15] Ewing, R., & Cervero, R. (2010). Travel and the built environment: A meta-analysis.Journal of the American Planning Association, 76(3), 265–294.
[16] Ewing, R., & Handy, S. (2009). Measuring the unmeasurable: Urban design qualities related to walkability. Journal of Urban Design, 14(1), 65–84.
[17] Freeman, A. M. III. (1979). Hedonic prices, property values and measuring environmental benefits: A survey of the issues. The Scandinavian Journal of Economics,81(2), 154–173.
[18] Gilderbloom, J. I., Riggs, W. W., & Meares, W. L. (2015). Does walkability matter?An examination of walkability’s impact on housing values, foreclosures and crime.Cities, 42, 13–24.
[19] Goodman, A. C. (1978). Hedonic prices, price indices and housing markets. Journal of Urban Economics, 5(4), 471–484.
[20] Kang, Y., Zhang, F., Gao, S., Lin, H., & Liu, Y. (2020). A review of urban physical environment sensing using street view imagery in public health studies. Annals of GIS, 26(3), 261–275.
[21] Kim, E. J., & Kim, H. (2020). Neighborhood walkability and housing prices: A correlation study. Sustainability, 12(2), 593.
[22] Kuroda, Y., & Sugasawa, T. (2023). The value of scattered greenery in urban areas:A hedonic analysis in Japan. Environmental and Resource Economics, 85(2), 523–586.
[23] Lancaster, K. J. (1966). A new approach to consumer theory. Journal of Political Economy, 74(2), 132–157.
[24] Li, W., Joh, K., Lee, C., Kim, J.-H., Park, H., & Woo, A. (2015). Assessing benefits of neighborhood walkability to single-family property values: A spatial hedonic study in Austin, Texas. Journal of Planning Education and Research, 35(4), 471–488.
[25] Liou, F.-M., Yang, S.-Y., Chen, B., & Hsieh, W.-P. (2016). The effects of mass rapid transit station on the house prices in Taipei: The hierarchical linear model of individual growth. Pacific Rim Property Research Journal, 22(1), 3–16.
[26] Malpezzi, S. (2003). Hedonic pricing models: A selective and applied review. In T. O’Sullivan & K. Gibb (Eds.), Housing economics and public policy (pp. 67–89).Blackwell Science.
[27] Metz, N. E. (2015). Effect of distance to schooling on home prices. Review of Regional Studies, 45(2), 151–171.
[28] Naik, N., Philipoom, J., Raskar, R., & Hidalgo, C. (2014). Streetscore: Predicting the perceived safety of one million streetscapes. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops.
[29] Qiu, W., Zhang, Z., Liu, X., Li, W., Li, X., Xu, X., & Huang, X. (2022). Subjective or objective measures of street environment, which are more effective in explaining housing prices? Landscape and Urban Planning, 221, 104358.
[30] Ridker, R. G., & Henning, J. A. (1967). The determinants of residential property values with special reference to air pollution. The Review of Economics and Statistics, 49(2), 246–257.
[31] Rosen, S. (1974). Hedonic prices and implicit markets: Product differentiation in pure competition. Journal of Political Economy, 82(1), 34–55.
[32] Sirmans, G. S., Macpherson, D. A., & Zietz, E. N. (2005). The composition of hedonic pricing models. Journal of Real Estate Literature, 13(1), 1–44.
[33] Witte, A. D., Sumka, H. J., & Erekson, H. (1979). An estimate of a structural hedonic price model of the housing market: An application of Rosen’s theory of implicit markets. Econometrica, 47(5), 1151–1173.
[34] Yang, L., Wang, B., Zhou, J., & Wang, X. (2018). Walking accessibility and property prices. Transportation Research Part D: Transport and Environment, 62, 551–562.
[35] Ye, Y., Zeng, W., Shen, Q., Zhang, X., & Lu, Y. (2019). The visual quality of streets:A human-centred continuous measurement based on machine learning algorithms and street view images. Environment and Planning B: Urban Analytics and City Science, 46(8), 1439–1457.
[36] Zhang, Y., & Dong, R. (2018). Impacts of street-visible greenery on housing prices:Evidence from a hedonic price model and a massive street view image dataset in Beijing. ISPRS International Journal of Geo-Information, 7(3), 104.
[37] Zietz, J., Zietz, E. N., & Sirmans, G. S. (2008). Determinants of house prices: A quantile regression approach. The Journal of Real Estate Finance and Economics, 37(4), 317–333.
[38] Putra, I. G. B., Kuo, P.-F., Susanta, F. F., Tedjo, B. H., & Lord, D. (2026).GeoShapley-based interpretation of older adult pedestrian fatal vs injury crash frequency in dense urban environments. Accident Analysis and Prevention, 230,108450.