Associations between Street-View Perceptions and Housing Prices: Subjective vs. Objective Measures Using Computer Vision and Machine Learning Techniques

Abstract

This study investigated the extent to which subjectively and objectively measured street-level perceptions complement or conflict with each other in explaining property value. Street-scene perceptions can be subjectively assessed from self-reported survey questions, or objectively quantified from land use data or pixel ratios of physical features extracted from street-view imagery. Prior studies mainly relied on objective indicators to describe perceptions and found that a better street environment is associated with a price premium. While very few studies have addressed the impact of subjectively-assessed perceptions. We hypothesized that human perceptions have a subtle relationship to physical features that cannot be comprehensively captured with objective indicators. Subjective measures could be more effective to describe human perceptions, thus might explain more housing price variations. To test the hypothesis, we both subjectively and objectively measured six pairwise eye-level perceptions (i.e., Greenness, Walkability, Safety, Imageability, Enclosure, and Complexity). We then investigated their coherence and divergence for each perception respectively. Moreover, we revealed their similar or opposite effects in explaining house prices in Shanghai using the hedonic price model (HPM). Our intention was not to make causal statements. Instead, we set to address the coherent and conflicting effects of the two measures in explaining people’s behaviors and preferences. Our method is high-throughput by extending classical urban design measurement protocols with current artificial intelligence (AI) frameworks for urban-scene understanding. First, we found the percentage increases in housing prices attributable to street-view perceptions were significant for both subjective and objective measures. While subjective scores explained more variance over objective scores. Second, the two measures exhibited opposite signs in explaining house prices for Greenness and Imageability perceptions. Our results indicated that objective measures which simply extract or recombine individual streetscape pixels cannot fully capture human perceptions. For perceptual qualities that were not familiar to the average person (e.g., Imageability), a subjective framework exhibits better performance. Conversely, for perceptions whose connotation are self-evident (e.g., Greenness), objective measures could outperform the subjective counterparts. This study demonstrates a more holistic understanding for street-scene perceptions and their relations to property values. It also sheds light on future studies where the coherence and divergence of the two measures could be further stressed.

Measuring the perceptual features of coastal streets: a case study in Qingdao, China

“…Nowadays, the urban construction has changed from 'speed first' to 'quality-oriented' in China (Tang et al 2016, Huai et al 2018, Cheng and Wang 2021. The urban environment is increasingly linked to public well-being (Dubey et al 2016, Xu et al 2022. Meanwhile, scholars pay more attention to the human perceptual experience in urban space (Long and Ye 2016, Hao and Long 2017, Dai et al 2021.…”

Women-oriented Evaluation of Perceived Safety of Walking Routes Between Home and Mass Transit: A Case Study and Methodology Test in Guangzhou

“…This is because both the volunteers and SVIs in this dataset were sourced from non-Chinese regions. Therefore, the number of volunteers in many Chinese urban perception studies will be limited, and the number of volunteers in these studies is mostly within 50 [7,43,52,58,62,63]. (2) Xu et al [14] confirmed in a study in Shanghai, China, that there was some similarity between students' and residents' perceptions of safety, and their correlation coefficient R for SVI scores was 0.93 (p < 0.01).…”

Integrating Street Views, Satellite Imageries and Remote Sensing Data Into Economics and the Social Sciences

“…In housing research, it is crucial to explore the relationship between socioeconomic environments and human settlement. Bin et al (2020), Chen et al (2020), Fu et al (2019), Kang, Stice-Lawrence, and Wong (2021), Law et al (2019), Li et al (2021), Lyu et al (2022), Wang (2023), Wu et al (2022), Xu et al (2022), Yao et al (2018) and Ye et al (2019) utilised street views to estimate housing prices and proposed a neural networks-based methodology to address the issues that the economists had to manually categorise each view in the past and providing new insights into the assessment of human settlement values. Meanwhile, Johnson et al (2020), Kostic and Jevremovic (2020) and Qiu et al (2022) found that houses with better street or property design come at a price premium, meaning that proposed methods can efficiently describe visible characteristics.…”