Estimating evapotranspiration (ET) using satellite data provides a way to monitor and optimize water use, which is a critical management objective in water-limited regions and during times of drought. In contrast to most studies that look at ET in agricultural areas, we explored ET in urban areas using vegetation indices derived from high-resolution WorldView-2 (WV2) imagery. The study site was Veale Gardens in Adelaide, Australia, for which five WV2 images from March 2012 to January 2013 were analyzed. Normalized Difference Vegetation Index (NDVI) values were derived for each category of landscape cover: trees, shrubs, turf grasses, impervious pavements, and water bodies. Evapotranspiration rates for these landscape types were estimated through field monitoring. The relationships between the mean NDVI for the entire Veale Gardens and for each vegetation cover NDVI were compared with the field-estimated urban landscape evapotranspiration rates. Water stress conditions in January 2013 decreased the correlation between ET and NDVI: the highest relationships of ET-Landscape NDVI were only r2 = 0.66 (for shrubs) and r2 = 0.63 (for trees). However, when the January data were excluded, there was a significant increased correlation between ET and NDVI. The highest correlation for ET-Landscape NDVI was found for the entire Veale Gardens (r2 = 0.95) and the lowest (r2 = 0.88) was for the turf land cover. In support of the feasibility of ET estimation by WV2 over a longer period, a recently developed algorithm that estimates evapotranspiration rates based on the Enhanced Vegetation Index (EVI) from MODIS was employed. The results revealed a significant positive relationship between ETMODIS and ETWV2 (r2 = 0.9857). This finding indicates that the relationship between NDVI derived from high-resolution WorldView-2 imagery and ground-based validation approaches could provide an effective predictive tool for determining ET rates from unstressed mixed urban landscapes.