Model-based neural network algorithm for coffee ripeness prediction using helios UAV aerial images

Roberto Furfaro, Barry D Ganapol, L. F. Johnson, S. Herwitz

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Scopus citations

Abstract

Over the past few years, NASA has had a great interest in exploring the feasibility of using Unmanned Aerial Vehicles (UAVs), equipped with multi-spectral imaging systems, as long-duration platform for crop monitoring. To address the problem of predicting the ripeness level of the Kauai coffee plantation field using UAV aerial images, we proposed a neural network algorithm based on a nested Leaf-Canopy radiative transport Model (LCM2). A model-based, multi-layer neural network using backpropagation has been designed and trained to learn the functional relationship between the airborne reflectance and the percentage of ripe, over-ripe and under-ripe cherries present in the field. LCM2 was used to generate samples of the desired map. Post-processing analysis and tests on synthetic coffee field data showed that the network has accurately leam the map. A new Domain Projection Technique (DPT) was developed to deal with situations where the measured reflectance fell outside the training set. DPT projected the reflectance into the domain forcing the network to provide a physical solution. Tests were conducted to estimate the error bound. The synergistic combination of neural network algorithms and DPT lays at the core of a more complex algorithm designed to process UAV images. The application of the algorithm to real airborne images shows predictions consistent with post-harvesting data and highlights the potential of the overall methodology.

Original languageEnglish (US)
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
EditorsM. Owe, G. D'urso
Volume5976
DOIs
Publication statusPublished - 2005
EventRemote Sensing for Agriculture, Ecosystems, and Hydrology VII - Bruges, Belgium
Duration: Sep 20 2005Sep 22 2005

Other

OtherRemote Sensing for Agriculture, Ecosystems, and Hydrology VII
CountryBelgium
CityBruges
Period9/20/059/22/05

    Fingerprint

Keywords

  • Canopy Model
  • Crop Management
  • Neural Networks
  • Radiative Transfer
  • Remote Sensing in Agriculture
  • UAV

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Condensed Matter Physics

Cite this

Furfaro, R., Ganapol, B. D., Johnson, L. F., & Herwitz, S. (2005). Model-based neural network algorithm for coffee ripeness prediction using helios UAV aerial images. In M. Owe, & G. D'urso (Eds.), Proceedings of SPIE - The International Society for Optical Engineering (Vol. 5976). [59760X] https://doi.org/10.1117/12.627420