In response to the increasing demand on in-season crop inventory, this study presents results of early season crop identification and acreage estimates based on a random forest classifier using RADARSAT-2 fine quad (FQ) SAR data. Thirty RADARSAT-2 FQ SAR scenes acquired over Indian Head, Canada, during the 2009 AgriSAR campaign led by the European Space Agency (ESA) were analyzed. Consistent with results from other researches, this study revealed that the highest classification accuracies are achieved in mid to late season (early July to mid August) when most of the crops experiencing vegetative growth and early reproduction. In addition by incorporating multi-beam images, an increase in classification accuracy of 2% to 12% can be achieved. For images acquired close in time, shallower incidence angles usually give better classification accuracy compared with steeper incidence angles. In order to achieve optimal classification performance, both multi-temporal and multi-beam acquisitions should be combined. For major crops such as canola, spring wheat, lentil, and field peas, over 85% accuracies can be reached early in the growing season (early July) when multi-temporal multi-beam RADARSAT-2 FQ data are used.
[1]
Heather McNairn,et al.
Crop Change Assessment Using Polarimetric RADARSAT-2 Data
,
2011
.
[2]
Heather McNairn,et al.
The Contribution of ALOS PALSAR Multipolarization and Polarimetric Data to Crop Classification
,
2009,
IEEE Transactions on Geoscience and Remote Sensing.
[3]
Mahesh Pal,et al.
Random forest classifier for remote sensing classification
,
2005
.
[4]
Heather McNairn,et al.
Integration of optical and Synthetic Aperture Radar (SAR) imagery for delivering operational annual crop inventories
,
2009
.
[5]
Johannes R. Sveinsson,et al.
Random Forest Classification of Remote Sensing Data
,
2006
.