Submitted to: ASA-CSSA-SSSA Proceedings
Publication Type: Proceedings
Publication Acceptance Date: October 14, 2011
Publication Date: October 18, 2011
Citation: Lan, Y., Zhang, H., Suh, C.P., Westbrook, J.K., Hoffmann, W.C., Yang, C., Huang, Y. 2011. Fusion of remotely sensed data from airborne and ground-based sensors for cotton regrowth study. ASA-CSSA-SSSA Proceedings. CD-ROM. 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 multisensor 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 agricutlural fields in Burleson County, Texas, during the 2010 growing season. The discrimination accuracy of aerial- and ground-based data was examined individually; then a multisensor 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 with 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.