JOURNAL of the JAPANESE SOCIETY of AGRICULTURAL MACHINERY
Online ISSN : 1884-6025
Print ISSN : 0285-2543
ISSN-L : 0285-2543
Development of Crop Growth Mapping System Using Machine Vision (Part 1)
Producing Entire Crop Rows Image by Montaging Continuous Images
Takashi KATAOKAToshihiro KANEKOHiroshi OKAMOTOMasaki TERAWAKIShun-ichi HATA
Author information
JOURNAL FREE ACCESS

2004 Volume 66 Issue 5 Pages 74-82

Details
Abstract

The objective of this study was to develop a crop growth mapping system. A color CCD camera mounted on an agricultural vehicle acquired the crop rows' video images. An entire image of the crop rows was produced by montaging continuous video images. An index named as CIVE (Color Index of Vegetation Extraction) was tested to extract the features of the crops from the images and the overlap positions between the continuous two images were detected.
The information of the crop positions in the field was also an important index to make the crop growth map. This position accuracy in the entire crop rows' image was studied. The maximum error of positioning was ±1.5m, and the average of its R. M. S, error was calculated as 0.8m in the entire image of the crop rows of 160m length. This entire image was produced by montaging 640 images. It was summarized that this positioning accuracy was enough to produce the crop growth map.

Content from these authors
© The Japanese Society of Agricultural Machinery
Previous article Next article
feedback
Top