Plant height measurement using UAV-based aerial RGB and LiDAR images in soybean.

Abstract

Phenotypic traits like plant height are crucial in assessing plant growth and physiological performance. Manual plant height measurement is labor and time-intensive, low throughput, and error-prone. Hence, aerial phenotyping using aerial imagery-based sensors combined with image processing technique is quickly emerging as a more effective alternative to estimate plant height and other morphophysiological parameters. Studies have demonstrated the effectiveness of both RGB and LiDAR images in estimating plant height in several crops. However, there is limited information on their comparison, especially in soybean (Glycine max [L.] Merr.). As a result, there is not enough information to decide on the appropriate sensor for plant height estimation in soybean. Hence, the study was conducted to identify the most effective sensor for high throughput aerial phenotyping to estimate plant height in soybean. Aerial images were collected in a field experiment at multiple time points during soybean growing season using an Unmanned Aerial Vehicle (UAV or drone) equipped with RGB and LiDAR sensors. Our method established the relationship between manually measured plant height and the height obtained from aerial platforms. We found that the LiDAR sensor had a better performance (R² = 0.83) than the RGB camera (R² = 0.53) when compared with ground reference height during pod growth and seed filling stages. However, RGB showed more reliability in estimating plant height at physiological maturity when the LiDAR could not capture an accurate plant height measurement. The results from this study contribute to identifying ideal aerial phenotyping sensors to estimate plant height in soybean during different growth stages.