Visual Event Detection pp 111-128 | Cite as
Summary and Discussion of Alternatives
Chapter
Abstract
We have presented a new computational framework and a number of algorithmic components that enable automatic object recognition and event detection and applied it to the detection of deciduous trees in still images, hunts in wildlife documentaries, and landings and rocket launches in general unconstrained commercial video. Before summarizing these topics we will turn to issues concerning the choice of the classifier and the feature set.
Keywords
Video Frame Deciduous Tree Image Patch Foreground Object Neural Network Classifier
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
Preview
Unable to display preview. Download preview PDF.
Copyright information
© Springer Science+Business Media Dordrecht 2001