Urban tree canopy (UTC) is a fundamental component of resilient, sustainable urban structures that define the surface temperature, air quality, stormwater management, biodiversity, and human wellbeing. That said, UTC distribution is skewed, and low-income, marginalized, and high-density neighbourhoods are usually the locations with low canopy cover, high heat action, and low access to restorative green areas. In order to map UTC and measure inequity in cities in India, China, Europe, the Americas, Africa, and Pakistan, this paper reviews multispectral data, LiDAR, UAV imagery, and street-view photographs. These classifier approaches are pixel-based, multi-sensor fusion, deep learning segmentation, LiDAR-guided regression, and phenology. Research is contextualized using a single taxonomy comparing performance and integrating integration using socio-demographic data using environmental justice indicators such as the 3-30-300 rule, Theil indices, and viewable green view indices. The essential limitations are highlighted in a comparative analysis, among which are the susceptibility of NDVI to soil/shading, incomplete socio-economic data, and simplistic assumptions on pollution. Lastly, to propel equable urban planning, future research directions in the multi-modal deep learning, cross-city transfer, the structural equity metrics, and real-time monitoring are described.