The Perception of Articulated Motion: Recognizing Moving Light Displays

• Authors: Nigel H. Goddard
• Venue: The Perception of Articulated Motion: Recognizing Moving Light Displays
• Year: 1992

Recognition of motion sequences is a crucial ability for biological and robot vision systems. We present an architecture for the higher-level processes involved in recognition of complex structured motion. The work is focused on modeling human recognition of Moving Light Displays. MLDs are image sequences that contain only motion information at a small number of locations. Despite the extreme paucity of information in these displays, humans can recognize MLDs generated from a variety of common human movements. This dissertation explores the high-level representations and computational processes required for the recognition task. The structures and algorithms are articulated in the language of structured connectionist models. The implemented network can discriminate three human gaits from data generated by several actors. .pp Recognition of any motion involves indexing into stored models of movement. We present a representation for such models, called scenarios, based on coordinated sequences of discrete motion events. A method for indexing into this representation is described. We develop a parallel model of spatial and conceptual attention that is essential for disambiguating the spatially and temporally diffuse MLD data. The major computational problems addressed are: (1) representation of time-varying visual models; (2) integration of visual stimuli over time; (3) gestalt formation in and between spatially-localized feature maps and central movement representations; (4) contextual feedback to lower levels; and (5) the use of attention to focus processing on particular spatial locations and particular high-level representations. Several novel connectionist mechanisms are developed and used in the implementation. .pp In particular, we present advances in connectionist representation of temporal sequences and in using high-level knowledge to control an attentional mechanism. We show that recognition of gait can be achieved directly from motion features, without complex shape information, and that the motion information need not be finely quantized. We show how the "what" and "where" processes in vision can be tightly coupled in a synergistic fashion. These results indicate the value of the structured connectionist paradigm in modeling perceptual processes: no previous computational model has accounted for MLD recognition and we do not know how it would be approached in any other paradigm.