XLXiaojiang Li

Xiaojiang Li

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Xiaojiang Li has a total of 15 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Top Cited Papers
    Open Access

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

    by Xiang Xu, Waishan Qiu, Wenjing Li, Xun Liu, Ziye Zhang, Xiaojiang Li, Dan Luo

    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.


  • Open Access

    Residential Greenspace and Urban Adolescent Substance Use: Exploring Interactive Effects with Peer Network Health, Sex, and Executive Function

    by Jeremy Mennis, Xiaojiang Li, Mahbubur Meenar, J. Douglas Coatsworth, Thomas P. McKeon, Michael J. Mason

    While urban greenspace is increasingly recognized as important to mental health, its role in substance use is understudied. This exploratory study investigates the interaction of greenspace with peer network health, sex, and executive function (EF) in models of substance use among a sample of disadvantaged, urban youth. Adolescents and their parents were recruited from a hospital in the mid-Atlantic region of the U.S. Residential greenspace at the streetscape level was derived from analysis of Google Street View imagery. Logistic regression models were used to test the moderating effect of greenspace on the association between peer network health and substance use, as well as additional moderating effects of sex and EF. The significant negative association of peer network health with substance use occurred only among youth residing in high greenspace environments, a moderating effect which was stronger among youth with high EF deficit. The moderating effect of greenspace did not differ between girls and boys. Greenspace may play an important role in moderating peer influences on substance use among disadvantaged, urban adolescents, and such moderation may differ according to an individual’s level of EF. This research provides evidence of differences in environmental susceptibility regarding contextual mechanisms of substance use among youth, and it informs the development of targeted substance use interventions that leverage social and environmental influences on adolescent substance use.


  • Open Access

    Standardized Green View Index and Quantification of Different Metrics of Urban Green Vegetation

    by Yusuke Kumakoshi, Sau Yee Chan, Hideki Koizumi, Xiaojiang Li, Yuji Yoshimura

    Urban greenery is considered an important factor in sustainable development and people’s quality of life in the city. To account for urban green vegetation, Green View Index (GVI), which captures the visibility of greenery at street level, has been used. However, as GVI is point-based estimation, when aggregated at an area-level by mean or median, it is sensitive to the location of sampled sites, overweighing the values of densely located sites. To make estimation at area-level more robust, this study aims to (1) propose an improved indicator of greenery visibility (standardized GVI; sGVI), and (2) quantify the relation between sGVI and other green metrics. Experiment on an hypothetical setting confirmed that bias from site location can be mitigated by sGVI. Furthermore, comparing sGVI and Normalized Difference Vegetation Index (NDVI) at the city block level in Yokohama city, Japan, we found that sGVI captures the presence of vegetation better in the city center, whereas NDVI is better at capturing vegetation in parks and forests, principally due to the different viewpoints (eye-level perception and top-down eyesight). These tools provide a foundation for accessing the effect of vegetation in urban landscapes in a more robust matter, enabling comparison on any arbitrary geographical scale.