09-02-2017 дата публикации
Номер: US20170039729A1
Принадлежит:
According to at least one example embodiment, a method and corresponding apparatus of pruning video data comprise detecting motion areas within video frames of the video data based on short-term and long-term variations associated with content of the video data. Motion events, associated with the content of the video data, are then identified based on the motion areas detected, corresponding filtered motion areas, and variation patterns associated with the video data. Based on the motion events identified, a storage pattern for storing video frames of the video data is determined. The video frames are stored according to the determined storage pattern. 1. A method of pruning video data , comprising:detecting, by a computer device, motion areas within video frames of the video data based on short-term and long-term variations associated with content of the video data;identifying motion events associated with the content of the video data based on the motion areas detected, corresponding filtered motion areas, and variation patterns associated with the video data; anddetermining storage periods for the video frames of the video data based on the motion events identified.2. The method as recited in further comprising storing the video frames according to the storage periods determined.3. The method as recited in further comprising identifying the filtered motion areas.4. The method as recited in claim 3 , wherein identifying the filtered motion areas includes:identifying sub-areas associated with repetitive motion within the motion areas identified; andidentifying the filtered motion areas as the motion areas identified excluding the sub-areas associated with repetitive motion.5. The method as recited in further comprising generating one or more motion descriptors for each frame of the video data.6. The method as recited in claim 5 , wherein generating one or more motion descriptors for each frame of the video data includes:generating a first descriptor for each video ...
Подробнее