Page Banner

United States Department of Agriculture

Agricultural Research Service

Research Project: USING REMOTE SENSING AND GIS FOR DETECTING AND MAPPING INVASIVE WEEDS IN RIPARIAN AND WETLAND ECOSYSTEMS Title: Mapping an Annual Weed with Color-infrared Photography and Image Analysis

Authors
item Everitt, James
item Yang, Chenghai
item Davis, Michael

Submitted to: Geocarto International
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: June 9, 2009
Publication Date: February 15, 2010
Citation: Everitt, J.H., Yang, C., Davis, M.R. 2010. Mapping an annual weed with color-infrared photography and image analysis. Geocarto International. 25(1):45-52.

Interpretive Summary: The invasion and spread of noxious weeds on rangelands is a major deterrent to management of these areas. Silverleaf sunflower is a tap-rooted annual weed that often forms dense stands on sandy soil rangeland areas in south and southeast Texas. Color-infrared aerial photography coupled with supervised and supervised image analysis techniques was evaluated for detecting and mapping silverleaf sunflower infestations on two study sites in south Texas. Silverleaf sunflower could be readily distinguished on the color-infrared aerial photographs. The supervised image analysis technique was superior to the supervised technique for mapping silverleaf sunflower. Supervised classification of the photographs from the two sites showed that silverleaf sunflower had mean producer’s and user’s accuracies of 95.2% and 91.3%, respectively. These results should be of interest to rangeland resource managers interested in infestation monitoring of noxious plant species on rangelands.

Technical Abstract: Silverleaf sunflower (Helianthus argophyllus Torr. and Gray) is an annual weed found on rangelands in south and southeast Texas. Color-infrared aerial photography and computer image analysis techniques were evaluated for detecting and mapping silverleaf sunflower infestations on a south Texas rangeland area. Supervised and unsupervised image analysis classification techniques were used to classify photographs from two study sites. Supervised classification of the two photographs showed that silverleaf sunflower had mean producer’s and user’s accuracies of 95.2% and 91.3%, respectively. Unsupervised classification of the two photographs had mean producer’s and user’s accuracies for silverleaf sunflower of 65.7% and 80.1%, respectively. These results indicate that the supervised technique is superior to the unsupervised technique for mapping silverleaf sunflower infestations using color-infrared aerial photos.

Last Modified: 8/27/2014
Footer Content Back to Top of Page