Detecting Motion in Single Images Using ALISA

Motion analysis often relies on differencing operations that inherently amplify noise and are hindered by the spatial correspondence problem. An alternative approach is proposed using AIJSA (Adaptive learning Image and Signal Analysis) to detect differences in types of motion by classifying the imaging effects of the motion in single frames. With an appropriate feature set, the ALISA engine accumulates a multi-dimensional histogram that estimates the probability density function of a feature space and uses the result as a basis for classification. As a functi(m of image sampling rate and the scale of image structures, the AUSA engine was able to discriminate between a slow moving and fast moving object with a confidence greater than 99%.