Cycling, recognized as a healthy and environmentally beneficial mode of active transport, has gained widespread acceptance and become increasingly popular. Its prevalence is profoundly influenced by the built environment, highlighting an emerging need to explore the associations between built environment factors and cycling behaviour. With the advancement of artificial intelligence, an increasing number of scholars assess the perception of the built environment using street view imagery (SVI), analysing these perceptions in conjunction with survey data. However, the usage of real-world cycling data in assessing the built environment remains limited. In our study, we explore the relationship between the built environment and cycling behaviour by correlating image segmentation analysis results of SVI from the City of Sydney with real-world cycling data from Strava Metro Data (SMD). A multivariate Poisson regression model was applied for this research. Research findings indicate a positive correlation between cycling frequency and factors such as street greenness, presence of bike lane, traffic lights, and on-street parking, while cycling frequency is negatively associated with sky openness, enclosure, street curbs, and traffic sign frame. Therefore, to build a better cycling-friendly city, urban planners and designers should focus on factors that encourage cycling and positively influence cycling behaviour. Moreover, the novel and reliable approach of integrating SVI with real-world cycling data has potential for measuring eye-level built environments in future cycling-friendly city studies.