Non-parametric Clasification of Pixels Under Varying Outdoor Illumination

Using color for visual recognition outdoors has proven to be a difficult problem, chiefly due to varying illumination. Attempts to classify pixels or image patches in outdoor scenes based on their RGB values often fail, partly because of the inadequacy of the feature set, but partly because of color shifts due to changes in illumination are not well modeled as random noise. Approaches which attempt to recover the “true color” of objects by calculating the color of the incident light (i.e. color-constancy approaches) appear to work in constrained environments, but are not yet applicable to outdoor scenes. We present a technique that uses training images of an object under daylight to learn the shift in color of an object. Our method uses multivariate decision trees for piecewise linear approximation of the region corresponding to the object's appearance in color space. We then classify pixels in outdoor scenes depending on whether they fall within this region, and group clusters of target pixels into regions of interest (ROIs) for a model-based RSTA system. The techniques presented are demonstrated on a challenging task: detecting camouflaged vehicles in outdoor scenes.