TY - JOUR
T1 - Application of low altitude remote sensing (LARS) platform for monitoring crop growth and weed infestation in a soybean plantation
AU - Samseemoung, Grianggai
AU - Soni, Peeyush
AU - Jayasuriya, Hemantha P.W.
AU - Salokhe, Vilas M.
N1 - Funding Information:
Acknowledgments The authors thank Asian Institute of Technology (AIT), School of Environment, Resources and Development, Agricultural Systems and Engineering, Pathumthani, for providing experimental facilities. This work was financially supported by Rajamangala University of Technology Thanya-buri (RMUTT), Faculty of Engineering, Agricultural Engineering, Klong 6, Thanyaburi, Pathumthani, Thailand.
PY - 2012/12
Y1 - 2012/12
N2 - Crop growth and weed infestation in a soybean field were monitored by processing low altitude remote sensing (LARS) images taken from crane-mounted and unmanned radio controlled helicopter-mounted platforms. Images were taken for comparison between true color (R-G-B) and color-infrared (NIR) digital cameras acquired at different heights above ground. All LARS images were processed to estimate vegetation-indices for distinguishing stages of crop growth and estimating weed density. LARS images from the two platforms (low-dynamic and high-dynamic) were evaluated. It was found that crane-mounted RGBC and NIRC platforms resulted in better quality images at lower altitudes (<10 m). This makes the crane-mounted platform an attractive option in terms of specific low altitude applications at an inexpensive cost. Helicopter-mounted RGBH and NIRH images were found suitable at altitudes >10 m. Comparison of NDVIC and NDVIH images showed that NDVI values at 28 DAG (days after germination) exhibited a strong relationship with altitudes used to capture images (R 2 of 0.75 for NDVIC and 0.79 for NDVIH). However, high altitudes (>10 m) decreased NDVI values for both systems. Higher R 2 values (≥0.7) were also obtained between indices estimated from crane-and helicopter-mounted images with those obtained using an on-ground spectrometer, which showed an adequate suitability of the proposed LARS platform systems for crop growth and weed infestation detection. Further, chlorophyll content was well correlated with the indices from these images with high R 2 values (>0.75) for 7, 14, 21 and 28 DAG.
AB - Crop growth and weed infestation in a soybean field were monitored by processing low altitude remote sensing (LARS) images taken from crane-mounted and unmanned radio controlled helicopter-mounted platforms. Images were taken for comparison between true color (R-G-B) and color-infrared (NIR) digital cameras acquired at different heights above ground. All LARS images were processed to estimate vegetation-indices for distinguishing stages of crop growth and estimating weed density. LARS images from the two platforms (low-dynamic and high-dynamic) were evaluated. It was found that crane-mounted RGBC and NIRC platforms resulted in better quality images at lower altitudes (<10 m). This makes the crane-mounted platform an attractive option in terms of specific low altitude applications at an inexpensive cost. Helicopter-mounted RGBH and NIRH images were found suitable at altitudes >10 m. Comparison of NDVIC and NDVIH images showed that NDVI values at 28 DAG (days after germination) exhibited a strong relationship with altitudes used to capture images (R 2 of 0.75 for NDVIC and 0.79 for NDVIH). However, high altitudes (>10 m) decreased NDVI values for both systems. Higher R 2 values (≥0.7) were also obtained between indices estimated from crane-and helicopter-mounted images with those obtained using an on-ground spectrometer, which showed an adequate suitability of the proposed LARS platform systems for crop growth and weed infestation detection. Further, chlorophyll content was well correlated with the indices from these images with high R 2 values (>0.75) for 7, 14, 21 and 28 DAG.
KW - Crane-mounted image acquisition
KW - Crop growth monitoring
KW - Helicopter-mounted image acquisition
KW - NDVI
KW - Weed detection
UR - http://www.scopus.com/inward/record.url?scp=84868629417&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84868629417&partnerID=8YFLogxK
U2 - 10.1007/s11119-012-9271-8
DO - 10.1007/s11119-012-9271-8
M3 - Article
AN - SCOPUS:84868629417
SN - 1385-2256
VL - 13
SP - 611
EP - 627
JO - Precision Agriculture
JF - Precision Agriculture
IS - 6
ER -