Detection of canola flowering using proximal and aerial remote sensing techniques

In plant breeding, the time and length of flowering are important phenotypes that determine the seed yield potential in plants. Currently, flowering traits are visually assessed, which can be time-consuming, less accurate and subjective. To address this challenge, in this study, proximal and remote sensing with an unmanned aerial vehicle (UAV) were applied to monitor the canola flowers in a breeding trial with 35 varieties. Visible digital images (RGB) acquired were processed to extract the flowering features. The results indicated that flowering features extracted from both proximal and aerial images were significantly and positively correlated (P < 0.0001) with each other and with visual ratings. In general, aerial imaging overestimated canola flowering rates, which could be resulting from lower resolution at measured altitude (30 m), and rendered lower correlation coefficients (r = 0.53 – 0.62) with visual ratings. Proximal sensing resulted in better estimation of canola flowering with r ranging from 0.65 to 0.91. This study indicated that remote sensing can be used for high-throughput phenotyping of canola flowers with confidence. High-throughput phenotyping techniques will potentially improve the throughput and objectivity of detecting flowers in canola and other crops, and contribute to the development of new cultivars in breeding programs and yield estimation in precision agriculture.