FUSION OF SENSED DATA FROM AIRBORNE
AND GROUND-BASED SENSORS FOR COTTON REGROWTH
by
H Zhang, Yubin Lan, C
Suh, J Westbrook, C Hoffmann, R Lacey
Contact: Yubin Lan
Agricultural Engineer
Aerial Application Technology
USDA-ARS
2771 F&B Road
College Station, TX 77845
Yubin.lan@ars.usda.gov
(979) 260-3759
Summary: The need to minimize populations of overwintering boll
weevils, Anthonomus grandis
Boheman, is widely recognized by eradication
programs. One tactic to reduce
overwintering survival of boll weevils is timely post-harvest crop
destruction. Even where cotton plants, Gossypium hirsutum L., are
destroyed after harvest, regrowth from stalks or growth of volunteer plants
from un-harvested seed can occur when environmental conditions permit. Timely detection and remediation of volunteer
cotton plants in both cultivated and non-cultivated habitats is critical for
completing boll weevil eradication in Central and South Texas. The study investigates the use of aerial
imagery and ground-based remotely sensed data for the discrimination of
different crop species and timely detection of cotton plants over large areas.
Airborne multispectral imagery and handheld hyperspectral
data were acquired at multiple times over two large agricultural farms in
Brazos County in Texas during the 2010 growing season. The performances of
imagery data and handheld data for the discrimination were examined
individually; then multisensor data fusion technique
was applied on both aerial and ground datasets in order to improve the accuracy
of the discrimination. The overall results indicate the potential of multisensor data fusion of remotely sensed data from
different sensors as an effective tool for cotton regrowth studies.
Select
for a copy of the Paper