A method and apparatus for detecting fine movement of a subject in video images, and for distinguishing over noise and other image artefacts. The video images are processed to detect movement of image features through the sequence and to calculate how spatially distributed those moving features are across the image. The movement tracks of the features may be subject to principal component analysis and a spatial dispersion measure calculated by the product of the distance between tracked image features and the contributions of those image features to the most significant principal components. If the spatial dispersion measure is high then this is indicative of feature movement being dispersed widely across the image, whereas if it is low, it is indicative of the main feature movements being concentrated in one part of the image, and thus more likely to represent subject movement than noise.