Plant breeding requires phenotyping throughout the growing season for multiple traits in large, multilocation field trials. This large-scale phenotyping produces the data necessary to select lines with a desirable combination of traits. However, manual phenotyping can be labor-intensive, costly, and imprecise. The use of unmanned aerial vehicles (UAVs) equipped with sensors to assist breeding programs in field data collection offers potential to overcome challenges with manual phenotyping. UAV imaging also offers opportunities to monitor and measure field trials in ways not previously possible. However, approaches to most effectively use UAV image data to support field trial evaluation are still lacking. In this research, the CanNAM population, a diverse nested association mapping (NAM) hexaploid wheat population, was imaged with a UAV equipped with a multispectral sensor and high-resolution digital camera at three locations at multiple time points throughout phenological development in the 2020 and 2021 growing seasons. The software Plotvision was used to extract individual plot images from sensor data, and manually engineered features were then extracted including spectral summary statistics, spectral indices (for example, NDVI), and textural features. Textural features like “dissimilarity”, which can be derived from a grey-level co-occurrence matrix (GLCM), showed considerable variation throughout the growing season. Dissimilarity was correlated with grain yield (kg/ha) at multiple time points and environments. Relationships between other image features and manually measured phenotypes were also explored. Genotyping data was generated for the CanNAM population and significant associations with single nucleotide polymorphism (SNP) markers were identified for many image features, including dissimilarity. We are currently applying machine learning approaches to train prediction models and to model spatial variation to improve selection accuracy. Results from this project will help guide the application of high throughput digital phenotyping technologies to improve methods of selection in wheat breeding programs.