Independent Motion: The Importance of History

We consider a problem central in aerial visual surveil lance applications detection and tracking of small independently moving objects in long and noisy video sequences We directly use spatiotemporal image inten sity gradient measurements to compute an exact model of background motion This allows the creation of ac curate mosaics over many frames and the de nition of a constraint violation function which acts as an in dicator of independent motion A novel temporal in tegration method maintains con dence measures over long subsequences without computing the optic ow re quiring object models or using a Kalman lter The mosaic acts as a stable feature frame allowing pre cise localization of the independently moving objects We present a statistical analysis of the e ects of image noise on the constraint violation measure and nd a good match between the predicted probability distribu tion function and the measured sample frequencies in