Recent advances in sequencing technologies for characterizing genome-wide markers, in combination with the high-performance computational infrastructure for statistical modeling, provide unprecedented advantages to dissect the genetic components in controlling phenotypic trait variation. It becomes a bottleneck, however, to cost-effectively characterize the agronomically important phenotypic traits in a large scale. Drone-based high-throughput phenotyping has recently become a prominent method, as it allows large numbers of plants to be analyzed in a time-series manner. In this experiment, we planted the maize association panel in 2018 and 2019 using an incomplete block design. Drone images were collected during different plant developmental stages. To analyze the image data, we developed a drone image processing pipeline to stitch an orthomosaic file and then apply the in-house developed pixel filtration algorithms to remove the non-foliage elements. The remaining pixels at the plot level are then used to produce greenness ratings. Such ratings can provide indications that a given genotype is under drought or nitrogen stress, and may also provide correlations with key developmental stages, such as the onset of flowering or kernel maturity. The plot level time-series phenotypic data obtained from this experiment provide great opportunities to advance plant science and to facilitate plant breeding.