Urban forests and vegetation are fundamental for developing resilient cities. Thus, the effective management and protection of urban trees and greenery are essential. Nowadays, urban trees are experiencing atypical amount of natural and human-induced stresses which affects their functionality, productivity and survival. The current methods for monitoring the health of urban trees mainly comprises of manual inspection by arborists and remote sensing. However, all these methods are riddled with various challenges involving scalability, spatio-temporal resolutions and quality of assessment. The goal of this thesis was to develop a method which can autonomously measure the health of trees on a city-wide scale with high spatio-temporal resolutions at low costs. To achieve this goal, we first performed an in-depth survey and comparative analysis of the existing state-of-the-art techniques for tree health measurement, identified a research gap and based on this, developed a novel system to measure tree health autonomously from ground level in urban cities. The system can be deployed both in a drive-by sensing paradigm on moving vehicles such as taxis and garbage trucks or be carried by humans in a citizen science paradigm. A computer vision model developed using transfer learning and traditional image processing techniques were employed to fuse the data collected by low cost thermal and multispectral imaging sensors on the edge devices. The approach was evaluated through data collection experiments performed in Cambridge, USA. Comparison with parameters in ground truth datasets revealed several significant relationships. Thus, motivating various studies in the future along with potential large-scale deployment of this technique in cities and municipalities around the world.