Hyperspectral remote sensing imagery was collected over a soybean field in central Illinois in mid-June 2001 before canopy closure. Estimates of percent vegetation cover were generated through the processing of RGB (red, green, blue) digital images collected on the ground with an automated crop mapping system. A comparative study was completed to test the ability of broad-band, narrow-band, and derivative-based vegetation indices to predict percent soybean cover at levels less than 70%. Though remote sensing imagery is commonly analyzed using reference data collected at random points over a scene of interest, the analysis of the hyperspectral imagery in this research was performed on a pixel-by-pixel basis over the field area covered by the automated crop mapping system. Narrow-band and derivative-based indices utilizing the finer spectral detail of hyperspectral data performed better than the older broad-band indices developed for use with multispectral data. Specifically, second-derivative indices measuring the curvature in the green region (514-556 nm), longer wavelength red region (640-694 nm), and short wavelength NIR (712-778 nm) performed well. Narrow-band indices, based on the standard ratio index equations, which used values from the blue (472-490 nm) and green (514-550 nm) regions, also performed well for many of the datasets. The performance of all indices was shown to suffer over areas of brighter soil background, and the use of ratio-based narrow-band indices that did not incorporate NIR reflectance values performed best in this case.