Skip to main content
ARS Home » Research » Publications at this Location » Publication #250320
Title: Evaluating high resolution SPOT 5 satellite imagery for crop identification

Author
item Yang, Chenghai
item Everitt, James
item MURDEN, DALE - Rio Farms, Inc

Submitted to: Computers and Electronics in Agriculture
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 12/19/2010
Publication Date: 2/9/2011
Citation: Yang, C., Everitt, J.H., Murden, D. 2011. Evaluating high resolution SPOT 5 satellite imagery for crop identification. Computers and Electronics in Agriculture. 75:347-354.

Interpretive Summary: The types of crops and their areas grown in a region are the most basic information for crop management and agricultural planning. A high resolution SPOT 5 satellite image was evaluated for crop identification in south Texas. Two subset images covering a variety of crops (corn, cotton, grain sorghum and sugarcane) and non-crop cover types were classified to distinguish the crops. Accuracy assessment showed that 91% and 87% of the image pixels were correctly identified on the classification maps for the two subset images, respectively. These results indicate that SPOT 5 satellite imagery can be a useful data source for identifying crop types and estimating crop areas at a regional scale.

Technical Abstract: High resolution satellite imagery offers new opportunities for crop monitoring and assessment. A SPOT 5 image with four spectral bands (green, red, near-infrared, and mid-infrared) and 10-m pixel size covering intensively cropped areas in south Texas was evaluated for crop identification. Two images with pixel sizes of 20 m and 30 m were also generated from the original image to simulate coarser resolution satellite imagery. Two subset images covering a variety of crops with different growth stages were extracted from the satellite image and four supervised classification techniques, including minimum distance, Mahalanobis distance, maximum likelihood, and spectral angle mapper, were applied to the 10-m subset images and the two coarser resolution images to identify crop types. The effect of the mid-infrared band on classification was also studied. Accuracy assessment showed that the 10-m, four-band images based on maximum likelihood resulted in the best overall accuracy values of 91% and 87% for the two sites. The 20-m and 30-m images had essentially the same accuracy values as the 10-m images, though the inclusion of the mid-infrared band significantly increased classification results. These results indicate that SPOT 5 multispectral imagery can be a useful data source for identifying crop types and estimating crop areas.