|ZHANG, HUIHUI - Texas A&M University|
Submitted to: Computers and Electronics in Agriculture
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 1/18/2013
Publication Date: 4/1/2013
Citation: Zhang, H., Lan, Y., Suh, C.P., Westbrook, J.K., Hoffmann, W.C., Yang, C., Huang, Y. 2013. Fusion of remotely sensed data from airborne and ground-based sensors to enhance detection of cotton plants. Computers and Electronics in Agriculture. 93:55-59.
Interpretive Summary: Remote sensing technologies have been widely used for detecting crop conditions or soil properties by optical sensors or instruments from ground-based, airborne and space-borne platforms. However, few studies have applied multisensory fusion techniques to incorporate aerial imagery with ground-based remote sensing data. In this study, we investigated the potential of multisensor fusion of ground-based and airborne imagery data for remote detection and discrimination of cotton plants from corn and soybean plants. Multisensor fusion of ground-based sensor data and airborne imagery increased the accuracy of remotely classifying crop types. These results suggest data fusion techniques could greatly enhance the capability to detect volunteer cotton plants occurring in cultivated and non-cultivated habitats.
Technical Abstract: The study investigated the use of aerial multispectral imagery and ground-based hyperspectral data for the discrimination of different crop types and timely detection of cotton plants over large areas. Airborne multispectral imagery and ground-based spectral reflectance data were acquired at the same time over three large agricultural fields in Burleson Co., Texas, during the 2010 growing seasons. The discrimination accuracy of aerial- and ground-based data was examined individually; then a multi-sensor data fusion technique was applied on both datasets in order to improve the accuracy of discrimination. The individual classification accuracy of data taken with the aerial- and ground-based sensors were 90% and 93.3%, respectively. In comparison, the accuracy of discriminating crop types with fused data was 100% in the calibration and only 3.33% misclassification in the cross-validation. These results suggest data fusion techniques could greatly enhance our ability to detect volunteer cotton plants occurring in cultivated and non-cultivated habitats.