Nov 20 2017
Unmanned aerial systems (UAS), commonly known as drones, could assist farmers in determining if their crop is growing satisfactorily, based on a recent study conducted by University of Tennessee Institute of Agriculture researchers.
Shawn Butler, a graduate student at the University of Tennessee College of Agricultural Sciences and Natural Resources, analyzes cotton research plots from his laptop thanks to images obtained with an unmanned aerial system (UAS), also called a drone. This research could help farmers improve crop monitoring. Photo by G. Rowsey, courtesy UTIA.
The study focused on examining the potential of a UAS to precisely and accurately determine plant populations of cotton. Producers regularly assess plant populations early in the growing season in order to determine the state of their crop, and also explore what management decisions are needed in order to guarantee an optimal harvest. This is most frequently performed by counting the number of plants within a chosen distance and repeating those counts in varied locations all through the field in order to find an average.
This traditional approach is reliant upon a highly uniform plant population across the entire field and can be influenced by human bias, theoretically, an aerial approach could provide spatially dense information on plant populations across large areas quickly and remove human bias.
Shawn Butler, graduate student in the University of Tennessee College of Agricultural Sciences and Natural Resources.
For two years, researchers studied plant stands of emerging cotton via manual counting and also via images obtained from both multi-spectral and digital cameras mounted beneath a quad-copter. The quad-copter was flown at changing altitudes ranging from 30 to 120 m.
Of the two camera systems examined, the images generated from the multi-spectral camera established to be a lot more accurate in estimating plant populations, with accuracy greater than 93%. However, according to researchers the red, green, blue (RGB) images generated by the less-expensive digital camera still appeared to be promising with accuracy greater than 85% using scripted programming and current methods.
“Based on initial results, the aerial imagery provided by either RGB or multi-spectral sensors may be a sufficient tool to improve accuracy and efficiency of plant stand assessment,” says Butler. “The most impactful difference to the end user in deciding a method to use will be the cost between the two camera systems.”
Crop monitoring is a big obstacle for many producers, we want to continue to evaluate tools and methodologies that have the potential to help farmers overcome monitoring challenges, improve response time and increase profitability.
Tyson Raper, project leader and assistant professor with the UT Department of Plant Sciences. “
This research was presented by Butler at the 2017 International CSSA, ASA and SSSA Annual Meeting, “Managing Global Resources for a Secure Future,” held in Tampa, Florida. The meeting was hosted by the American Society of Agronomy, Crop Science Society of America and Soil Science Society of America.
The study was carried out at three locations – the West Tennessee AgResearch and Education Center in Jackson and the UT AgResearch and Education centers at Milan and Ames Plantation. Other team members involved in the project include Mike Buschermohle, Interim Assistant Dean of UT Extension. Partial support for this project was provided by Cotton Incorporated.
The University of Tennessee Institute of Agriculture touches lives and provides Real. Life. Solutions. through its mission of research, teaching and extension.