Height estimation of sugarcane using an unmanned aerial system (UAS) based on structure from motion (SfM) point clouds

Abstract

The use of unmanned aerial systems (UAS) as remote-sensing platforms has tremendous potential for obtaining detailed, site-specific descriptions of crop features, which would be very useful for precision agriculture. In sugarcane plantations, for example, cane height can be an indicator of yield and other parameters because it is highly influenced by the soil, total sugar content, leaf nitrogen content, temperature and light intensity. This article describes the generation of crop surface models (CSMs) from high-resolution images that were obtained using a UAS to estimate sugarcane height. Using a UAS with an on-board RGB camera, we created densified three-dimensional point clouds of the study area in two different flight line directions (North/South and East/West) using structure from motion (SfM) with multi-view stereo (MVS). Then, the digital surface model (DSM) and digital terrain model (DTM) were extracted and used to create CSMs. Maps of sugarcane height were created based on this information. We investigated the influences of different flight line directions (N/S and E/W) on sugarcane height estimations and their accuracy by comparing our maps with ground references. From the validation conducted using both flight lines, the average heights were closer to the field-verified data. The resulting maps showed differences in sugarcane height that were confirmed by field measurements. This method has potential for future use by sugarcane-related industries, researchers and farmers to estimate average crop height.