Method for summarizing a video using motion descriptors
A video and motion technology, applied in the field of video, can solve problems such as not working
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0045] The present invention uses motion features, and optionally color features, to generalize compressed video. Thus, the inductive method of the present invention initially determines these features from compressed video.
[0046] feature extraction
[0047] color features
[0048] The DC coefficients of an I frame can be correctly extracted using known techniques. In the case of P frames and B frames, DC coefficients can be approximated using motion vectors that are not decompressed at all. For example, wishing to refer to Yeo et al. 「 About extracting DC sequence from MPEG video 」 (IEEE ICIP Vol. 2, 1995). In order to extract color features, the YUV values of the DC image can be transformed into another color space.
[0049] Among the most commonly used techniques, color histograms are employed. Color histograms have been widely used in image and video indexing and retrieval. Hope to refer to Smith and wait 「 Automatic Image Retrieval Using Color and Structure ...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 