ASABE Technical Library - Abstract

Click on “Download PDF” for the PDF version or on the title for the HTML version.
If you are not an ASABE member or if your employer has not arranged for access to the full-text, view access and subscription options

Spatial-Temporal Crop Height Modeling using High Resolution UAS Imagery

Published by the American Society of Agricultural and Biological Engineers, St. Joseph, Michigan www.asabe.org

Citation:  2026 ASABE Annual International Meeting  2600552.(doi:10.13031/aim.202600552)
Authors:   Kevin Lee, Keith Cherkauer
Keywords:   DSM, UAV, Remote Sensing, CHM, Gaussian Filter

Abstract. Accurate crop height estimation is a critical indicator for assessing crop growth dynamics and biomass development throughout the growing season. This study presents a comprehensive crop height modeling framework using high-resolution Unmanned Aerial System (UAS) imagery for corn and soybean production systems. Crop height was derived by differencing digital surface models (DSM) and digital terrain models (DTM) to generate crop height models (CHM). Ground reference measurements were collected for validation, including first folding leaf and first collar heights for corn and maximum canopy height for soybean. To improve estimation accuracy, spatial and temporal correction techniques were applied using an Inception Grid (IG) and a Gaussian Filter (GF). The IG approach was implemented to mitigate border effects within individual experimental plots, while the GF was applied along the temporal dimension to reduce the influence of transient anomalies. Temporal analysis within a growing season revealed crop-specific structural effects on height Estimation accuracy. Soybean canopies exhibited systematic underestimation, whereas the sharper and more heterogeneous canopy structure of corn resulted in higher spatial variability. The soybean CHM achieved mean absolute percentage errors (MAPE) of 20.0% and 19.8% across raw and corrected datasets, while the corn CHM achieved MAPEs of 9.9% and 14.2%, respectively. These results demonstrate the effectiveness of the proposed correction framework and highlight the importance of accounting for crop-specific canopy structure in UAS-based height estimation.

(Download PDF)    (Export to EndNotes)