Water scarcity due to climate change, drought, and rising water demands from non-agricultural sectors, is threatening food production. Innovations in irrigation water management are required to optimize agricultural water use in water stressed regions of the world, and this requires more refined techniques of irrigation scheduling. The present study tends to investigate the integration of multispectral and thermal data for mapping crop water stress for precision irrigation management of vegetable crops. Airborne campaigns were conducted on a commercial tomato farm in Leamington, Southern Ontario, in 2017 growing seasons to obtain multispectral and thermal images of plant canopy. Irrigation was scheduled by dividing the field into three (3) sections consisting of 100%, 70%, and 50% of full replenishment of water in the root zone to field capacity, in order to induce mild to severe water stress on the tomato plants. One hundred (100) plants were selected from each of the three sections of the field, using a systematic grid sampling technique, and were georeferenced for identification in the acquired images. Plant stress parameters including canopy temperature, stomatal conductance, leaf area index (LAI), relative water content, and equivalent water thickness were measured from the selected plants, concurrently with the airborne campaigns. This is an on-going research work, and advanced data and image analysis techniques would be used to integrate the multispectral and thermal data for mapping crop water stress, in order provide more precise information about the plant water status. The result would be used to develop a field based algorithm for implementing near real-time irrigation scheduling based on remotely sensed data, and provide irrigators with an advanced tool for decision making.