An adaptive path classification algorithm for a pepper greenhouse sprayer

Itamar Dar, Yael Edan, Avital Bechar

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

An adaptive path classification algorithm for a pepper greenhouse sprayer working under variable outdoor lighting conditions is described. 22 color features transformations specialized in soil-leafage discrimination extracted from the RGB and HSV 24-bit color images were created. 'Judges Vote', an innovative supervised learning methodology based on decision tree CART, was developed to classify pixels according to their color features into "Path" and "Non-Path" classes. Optimal CART feature selection was implemented by creating several single level trees. Image processing routines (including segmentation, erosion and dilution) were integrated. 12 features were selected from the original 22. Classification tests for seven random daylight videos resulted in 92% correct detection as compared to 89% correct classification obtained with regular CART classification.

Original languageAmerican English
Title of host publicationAmerican Society of Agricultural and Biological Engineers Annual International Meeting 2011, ASABE 2011
PublisherAmerican Society of Agricultural and Biological Engineers
Pages288-302
Number of pages15
ISBN (Print)9781618391568
StatePublished - 1 Jan 2011
EventAmerican Society of Agricultural and Biological Engineers Annual International Meeting 2011 - Louisville, KY, United States
Duration: 7 Aug 201110 Aug 2011

Publication series

NameAmerican Society of Agricultural and Biological Engineers Annual International Meeting 2011, ASABE 2011
Volume1

Conference

ConferenceAmerican Society of Agricultural and Biological Engineers Annual International Meeting 2011
Country/TerritoryUnited States
CityLouisville, KY
Period7/08/1110/08/11

Keywords

  • Adaptive
  • Classification
  • Color
  • Image processing
  • Sprayer
  • Vision

All Science Journal Classification (ASJC) codes

  • Agronomy and Crop Science

Fingerprint

Dive into the research topics of 'An adaptive path classification algorithm for a pepper greenhouse sprayer'. Together they form a unique fingerprint.

Cite this