It is fairly comm.on in video sequences that a mostly fixed background (scene) is imaged with or without independently moving objects. The dominant background changes in the image plane mostly due to camera operations an.d motion (zoom, pan, tilt, track etc.). In. this paper we address the problem, of computation of the domin,ant image transformation over time and demonstrafe how fhis can be eflectively used for e@-cient video represen.tation through video m.osaicing and im.ag e regist rat ion.We formulate fhe problem of dominant component estimation as that of model-based robust estimation usin,g M-estimators with direct, multi-resolution methods. In addition i o 2 0 affine and plane projective models, that have been used in the past f o r describing image motion using direct methods, we also employ a true 3 0 model of motion and scene structure imaged with umalibrated cameras. This model parameterizes the image motion as that due to a planar component and a parallax component. For rigid 3 0 scenes imaged under camera motion only, least squares &S) methods with th.e plane and parallax parameterization are also presen.ted. Furthermore, in the context of robusf estimation, in contrast with previous approaches for similar problems, our algorithm employs an automatic computation of a scale parameter that is crucial in rejecting the non-dominant components as outliers.A common scenario in video sequences is that of a mostly fixed background being imaged with or without independently moving objects. The dominant background changes in t,he image plane mostly due to camera operations and motion (zoom, pan, tilt, track etc.). In this paper we address the problem of computation of t,he dominant image transformation over t,ime and demonstrate how this can be effectively used for efficient, video representation for indexing and annotation
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.