HR: 0830h
AN: B41B-0883    [PDF]
TI: Leaf-Canopy inversion model though a Neural Network algorithm: Application to coffee cherry estimation using UAV images
AU: Ganapol, B D
EM: ganapol@cowboy.ame.arizona.edu
AF: Aerospace and Mechanical Engineering department, University of Arizona, 1130 N. Mountain, tucson, AZ 85721 United States
AU: * Furfaro, R
EM: robertof@email.arizona.edu
AF: Aerospace and Mechanical Engineering department, University of Arizona, 1130 N. Mountain, tucson, AZ 85721 United States
AU: Johnson, L F
EM: ljohnson@mail.arc.nasa.gov
AF: California State University, Monterey bay, NASA Ames, moffet field, CA 94035 United States
AU: Herwitz, S R
EM: sherwitz@mail.arc.nasa.gov
AF: Clark University, NASA Ames, moffet field, CA 94035 United States
AB: Over the past two years, NASA has had great interest in exploring the economic potential of deploying UAVs (Unmanned Aerial Vehicles) as long-duration platforms equipped with high resolution imaging systems for commercial agricultural applications. In October 2002, a team in the Ecosystem Science and Technology Branch at NASA/Ames Research Center prepared and successfully flew a UAV, equipped with off-the-shelf camera systems, over coffee plantations at Kauai (Hawaii). The idea is to help growers to find the best possible harvesting strategy. The most important information that needs to be conveyed to the growers is the percentage of ripe, unripe and overripe cherries in the field. It is of vital importance to devise a robust and reliable "intelligent "algorithm capable of predicting the amount of ripe cherries present in any digital image coming from the onboard cameras. During the campaign, the two UAV camera systems produced digital images that contain information about the down-looking plantation field. These images need to be processed to extract information concerning the percentage of ripe (yellow) cherries. To date, no robust automated algorithm has been developed to perform this task. Currently, every image is viewed by human eyes on a case by case basis. We propose a neural network algorithm that can automate the process in an intelligent way. Biologically inspired Neural Networks are made of elements called "neurons" that can simulate the brain activity during a learning process. The idea is to design an appropriate neural network that learns the relation between the reflectance coming from an image and the percentage of cherries present in a coffee field. We envision a situation in which reflectance from digital images at different wavebands is processed by a trained neural network and the percentage of the different cherries estimated. The key factor is training the network to recognize the reflectance/cherry percentage relation. Over the past few years in collaboration with NASA, we have developed a coupled leaf/canopy model (LCM2) in order to capture the essential biophysical processes associated with the interaction between light and vegetation. LCM2 has recently been modified to include different cherries as absorbing and scattering elements. The model can be fed with different inputs that describe the basic leaf chemistry and the morphology of the fields under consideration (as well as other external variables like sun and view angle) and give canopy reflectance as output. In this way, the model can be run to simulate the reflectance/cherry percentage relation. A set of data points representative of that map can be collected and the neural network trained to learn that relation.
DE: 0400 Biogeosciences
SC: Biogeosciences [B]
MN: 2003 Fall Meeting