Global versus Structured Interpretation of Motion: Moving Light Displays Global versus Structured Interpretation of Motion: Moving Light Displays Summary Global versus Structured Interpretation of Motion: Moving Light Displays

Moving light displays (MLDs) have been used extensively to study motion perception and perception of the human gait in particular. MLD perception is largely considered to be structural, i.e., perception depends on identiication of human kinematic structure. However, recent work by Little and Boyd has shown that it is possible to recognize individual people, from their gaits, by non-structural means. They use global shape-of-motion features derived from optical ow in a sequence of gray-scale images. Our goal is to show that shape-of-motion features can be derived equally well from MLD images as from gray-scale images, and to compare the recent results obtained for shape-of-motion recognition with psychophysical observations about MLD perception. The implication is that non-structural shape-of-motion interpretation of gait can be applied to MLDs, allowing us to interpret signiicant MLD results in the context of a known algorithm. Our results shed light on the validity of shape-of-motion features from the psychophysical standpoint as well as suggest an alternative approach to understanding MLD perception. In particular, we nd that characterizing movement in a gait may be treated as the sum of a set of moving points (if this is true then MLD lights need not be placed right at joints). Changes to a subset of the points aaect the sum and consequently aaect the perception of the whole. (A) What is the original contribution of the paper? This paper contributes an explanation of psychophysical observations regarding moving light displays in the context of non-structural shape-of-motion features. The result is that characterizing motion in a gait may be treated as a process of summation, where the sums describe the distribution of optical ow, and the phase relationships important for recognition are preserved in the sums. (B) What is the most closely related work by others? The most closely related work in the computer vision literature is that of Polana and Nelson 12, 14]. In the psychophysical literature, the most recent and relevant work is that of Bertenthal and Pinto 4]. Abstract Moving light displays (MLDs) have been used extensively to study motion perception and perception of the human gait in particular. MLD perception is largely considered to be structural, i.e., perception depends on identiication of human kinematic structure. However, recent work by Little and Boyd has shown that it is possible to recognize individual people, from their gaits, by non-structural means. They use global shape-of-motion features derived from optical ow in …