Skip to main content
ARS Home » Northeast Area » Beltsville, Maryland (BARC) » Beltsville Agricultural Research Center » Hydrology and Remote Sensing Laboratory » Research » Publications at this Location » Publication #330122
Title: Detection of potato beetle damage using remote sensing from small unmanned aircraft systems

Author
item Hunt Jr, Earle
item RONDON, S.I. - Oregon State University
item TURNER, R - Collaborator
item BRUCE, A - Collaborator
item BRUNGARDT, J - Collaborator

Submitted to: International Conference on Precision Agriculture Abstracts & Proceedings
Publication Type: Proceedings
Publication Acceptance Date: 7/5/2017
Publication Date: 8/3/2016
Citation: Hunt Jr, E.R., Rondon, S., Turner, R., Bruce, A., Brungardt, J. 2016. Detection of potato beetle damage using remote sensing from small unmanned aircraft systems. International Conference on Precision Agriculture Abstracts & Proceedings. http://www.ispag.org/proceedings.

Interpretive Summary:

Technical Abstract: Remote sensing with small unmanned aircraft systems (sUAS) has potential applications in agriculture because low flight altitudes allow image acquisition at very high spatial resolution. We set up experiments at the Oregon State University Hermiston Agricultural Research and Extension Center (HAREC) to assess advantages and disadvantages of sUAS for precision farming. In 2014, we conducted an experiment in irrigated potatoes with 4 levels of artificial infestation by Colorado Potato Beetles. A hexacopter sUAS was flown at two altitudes with a Tetracam Multi Camera Array with 5 bands and one up-looking incident light sensor. After just one day, plant damage was visible, but not correlated with the total number of beetles per plot. Plot-scale spectral vegetation indices, such as NDVI, were not correlated with visible damage. However, the sub-plot area of damage from object-based image analysis was highly correlated. Traditional methods for satellite data may not downscale well for remote sensing from sUAS. Object-based image analysis and computer vision have potential for early detection and reduced cost.