| ECVision indexed and annotated bibliography of cognitive computer vision publications This bibliography was created by Hilary Buxton and Benoit Gaillard, University of Sussex, as part of ECVision Specific Action 8-1 The complete text version of this BibTeX file is available here: ECVision_bibliography.bib
C. Cedras and M. Shah
ABSTRACT
Motion perception and interpretation plays an important role in the human visual system. It helps us recognize different objects and their motion in a scene, infer their relative depth, their rigidity, etc. In psychology, this process has been studied extensively by Johansson using moving light displays (MLDs). MLDs consist of bright spots attached to the joints of an actor dressed in black, and moving in front of a dark background. The collection of spots carry only 2D information and no structural information, since they are not connected. A set of static spots remained meaningless to observers, while their relative movement created a vivid impression of a person walking, running, dancing, etc. The gender of a person, and even the gait of a friend can be recognized based solely on the motion of those spots. There are two theories about the interpretation of MLD type stimuli, from a psychology point of view. In the first, people use motion information in the MLD to recover the 3D structure and subsequently use the structure for recognition (structure from motion problem). The second theory of motion analysis deals with the direct use of motion information for recognition. In motionbased recognition approach, the emphasis is not on the static structure, and motion information is not extracted one frame at a time. Instead, a sequence containing a large number of frames is used to extract motion information in its continuum. The advantage here is that a longer sequence leads to recognition of higher level movements, like walking or running. This paper provides a review of recent developments in the computer vision aspect of motion based recognition. We will identify two main steps in motionbased recognition. The first step is the extraction of motion information and its organization into motion models. The second step consists of the matching of some unknown input with a model. Several methods for the recognition of objects and motions will then be reported. They include methods such as cyclic motion detection and recognition, lipreading, hand gestures interpretation, motion verb recognition and temporal textures classification. Tracking and recognition of human motion, like walking, skipping, and running, will also be discussed. Finally, we will conclude the paper with some thoughts about future directions for motionbased recognition. |
|
| Site generated on Friday, 06 January 2006
|