System for creating a capsule representation of an instructional video

摘要

A method is provided that creates a lecture video capsule containing highlights of an original instructional video based on visual quality and content. The method includes segmenting and recognizing activities in the instructional video using a hidden Markov model (HMM). The activities are classified into three categories: talking head, writing hand and slideshow. The talking head frames are classified as non-content frames, while the writing hand and slideshows are classified as content frames. A non-reference based objective quality assessment of the non-content frames may be performed to detect high quality frames. Statistical parameters of an intensity histogram and a horizontal projection profile (HPP) of the content frames may be used to derive an objective quality measure of the content frames that is used to extract high quality content frames. The selected high quality non-content and content frames form a video clip or capsule, which is a temporally compressed representation of the video.

主权项

1. A system comprising:
a shot detection and recognition engine configured to:
receive a video comprising a plurality of frames, andclassify a frame of the plurality of frames as a non-content frame or a content frame; a frame quality assessment engine configured to assess a quality of the frame by:
dividing a content frame into a plurality of blocks,determining a horizontal projection profile (HPP) for a block of the plurality of blocks,determining an energy of the HPP for the block,summing the energy of the HPP for the block to obtain the energy of the content frame, anddetermining the quality of the content frame based on the HPP and the energy of the content frame; a video frame assessment engine configured to select the frame based on the quality of the frame; and a video creation engine configured to create a video clip including the selected frame and a portion of the plurality of frames surrounding the selected frame.