This paper proposes an approach for automatic object detection and removal in video sequences based on genetic algorithms (GAs) and spatiotemporal restoration. Given two consecutive frames, first, objects in the current frame are detected and tracked by a GA-based segmentation method. Second, two stages are performed for the restoration of the regions occluded by the detected text regions: temporal and spatial restorations. The performance of object detection is enhanced by the new proposed evolution method based on GAs. The combination of temporal and spatial restoration shows great potential for automatic removal of extracted objects of interest in various kinds of video sequences, and is applicable to many video re-using applications. © Springer-Verlag Berlin Heidelberg 2004.
CITATION STYLE
Kim, E. Y., & Jung, K. (2004). Object detection and removal using genetic algorithms. In Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science) (Vol. 3157, pp. 411–421). Springer Verlag. https://doi.org/10.1007/978-3-540-28633-2_44
Mendeley helps you to discover research relevant for your work.