Real Time Video Shot Detection and Summarization. Face and Motion Detection Approaches

      Аннотация: Nowadays, all human beings largely depending on the media to know the information about the things that are happening across the globe. Due to the constraint of time and commitment every individual may not find time to go through entire media coverage regarding the happenings in the society. Hence, there is a need to have storing options with our communication devices like TV and others to watch only the desired highlights or only interesting events. In the case of TV news, the overall video stored in the storing device consists of anchors, reporters, advertisements, etc. and all of them may not be interested to watch by a viewer. In order to view the interesting events, there is a need to identify and classify any videos with the help of frame analysis there is a number of methods are generally used for this purpose such as face detection eye detection, histogram, etc. Most of the advanced technologies like Tata Sky, Dish TV, Sun Direct, etc. works basically on storing concept. Instead of watching the whole video, we can use video shot detection for the summarization of only anchors, non-anchors, text detection, and other related video contents that are required for a viewer.

Ключевые слова: Video Shot Detection, Sports Video, News Video, Moving Text Detection, face detection