Automated content insertion into video scene
First Claim
Patent Images
1. A method for automated content insertion into a video sequence, the method comprising:
- receiving the video sequence comprising a sequence of frames;
automated determination of non-moving pixels in the sequence of frames by eliminating pixels whose values are more than a standard deviation away from a mean computed over a previous several frames so as to generate a background pixel mask which identifies the non-moving pixels; and
automated identification of valid regions comprising the non-moving pixels which are suitable for unobtrusive content insertion,wherein the automated determination of the non-moving pixels comprises tracking moving objects in the sequence of frames and eliminating pixels belonging to the moving objects from the background pixel mask.
3 Assignments
0 Petitions
Accused Products
Abstract
A method for automated content insertion into a video sequence. The video sequence comprising a sequence of frames is received. An automated determination is made of non-moving pixels in the sequence of frames. Thereafter, an automated identification is made of valid regions comprising the non-moving pixels which are suitable for unobtrusive content insertion. Other embodiments, aspects and features are also disclosed.
43 Citations
17 Claims
-
1. A method for automated content insertion into a video sequence, the method comprising:
-
receiving the video sequence comprising a sequence of frames; automated determination of non-moving pixels in the sequence of frames by eliminating pixels whose values are more than a standard deviation away from a mean computed over a previous several frames so as to generate a background pixel mask which identifies the non-moving pixels; and automated identification of valid regions comprising the non-moving pixels which are suitable for unobtrusive content insertion, wherein the automated determination of the non-moving pixels comprises tracking moving objects in the sequence of frames and eliminating pixels belonging to the moving objects from the background pixel mask. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10)
-
-
11. An apparatus configured for automated content insertion into a video stream, the apparatus comprising:
-
a processor for executing computer-readable program code; memory for storing in an accessible manner computer-readable data; computer-readable program code configured to receive the video sequence comprising a sequence of frames; computer-readable program code configured to determine non-moving pixels in the sequence of frames so as to generate a background pixel mask which identifies the non-moving pixels, wherein pixels whose values are more than a standard deviation away from a mean computed over a previous several frames are eliminated in generating the background pixel mask; computer-readable program code configured to track moving objects in the sequence of frames and eliminate pixels belonging to the moving objects from the background pixel mask; and computer-readable program code configured to identify valid regions comprising the non-moving pixels which are suitable for unobtrusive content insertion. - View Dependent Claims (12, 13, 14, 15, 16, 17)
-
Specification