A method for the detection of motion in image sequences is presented. In this method, the intensity history at each pixel is convolved with the second derivative in time of a temporal Gaussian smoothing function. The zero crossings in a single frame of the resulting function indicate the positions of moving edges. Intensity changes in time due to illumination effects do not produce zero crossings; thus, they are not interpreted as motion by the present method. It is also shown that the spatial and temporal derivatives of this function can be used to compute the component of the optical flow that is normal to the zero-crossing contours. This computation is also insensitive to nonconvective temporal and spatial variations in the image intensity that are caused by illumination effects.>

A new method for the detection of motion and the computation of optical flow is presented. In the first step of the calculation the intensity history at each pixel is convolved with the second derivative in time of a temporal Gaussian smoothing function. The zero crossings in a single frame of the resulting function indicate the positions of moving edges. Spatial and temporal derivatives of the function at the zero-crossing locations are then used to compute the component of the flow that is normal to the zero-crossing contours. Both the detection of motion and the computation of the normal velocity are insensitive to slow temporal and spatial changes in the image intensity that are caused by illumination effects rather than motion. A framework in which to relate the present work to a number of gradient based flow measurement techniques is also presented.