A workflow was developed to explore the potential use of Phase One RGB for weed mapping in a herbicide efficacy trial in wheat. Images with spatial resolution of 0.8 mm were collected in July 2020 over an area of nearly 2000 square meters (66 plots). The study site was on a research farm at the University of Saskatchewan, Canada. Wheat was seeded on June 29, 2020, at a rate of 75 seeds per square meter with a row spacing of 30.5 cm. The weed species seeded in the trial were kochia, wild oat, wild mustard, and false cleavers; however, this workflow was only applied to wild mustard. Using pre-emergence herbicide treatments, weeds were seeded in strips between crop rows. The target was to create an automated tool for weed vs wheat discrimination without sample collection. Color Index of Vegetation Index (CIVE) and Excess Green Index (ExG) were used to separate green features (crop + weed) and the background. Multiple spatial algorithms (image segmentation, line detection, distance map, convolution image filter, morphology filter (back-head), local extrema, image thresholding) were compiled in an automated workflow in eCognition software (version 9.5). Accuracy assessment was conducted using random labelling points and reported in a confusion matrix. Preliminary results of the proposed workflow achieved an overall accuracy of 96% (kappa = 0.95). No sample or training was needed to implement the workflow. This process has  potential as a semi-automated image labelling or sample collection tool for image classification using machine learning. Nonetheless, the workflow was conducted on one experimental site and a single UAV flying date. Future work should aim to improve the workflow towards the generalization of the algorithms’ parameters and use multiple date/field imagery, ensuring the transferability of the workflow to other experiments.