Detecting known video entities utilizing fingerprints
View Patent ↗In general, in one aspect, the disclosure describes a method for detecting a known video entity within a video stream. The method includes receiving a video stream and continually creating statistical parameterized representations for windows of the video stream. The statistical parameterized representation windows are continually compared to windows of a plurality of fingerprints. Each of the plurality of fingerprints includes associated statistical parameterized representations of a known video entity. A known video entity in the video stream is detected when a particular fingerprint of the plurality of fingerprints has at least a threshold level of similarity with the video stream.
1. A method for replacing a portion of a video stream with a targeted advertisement, the method comprising:
receiving a video stream at a set-top box;
continually creating statistical parameterized representations for windows of the video stream at the set-top box;
continually comparing the statistical parameterized representations to windows of a plurality of fingerprints, wherein each of the plurality of fingerprints includes associated statistical parameterized representations of known video content;
detecting the known video content in the video stream when a particular fingerprint of the plurality of fingerprints has at least a threshold level of similarity with the statistical parameterized representations;
selecting the targeted advertisement based on the known video content; and
replacing the known video content in the video stream with the selected targeted advertisement when the known video content has been detected.
2. The method of claim 1 , wherein said receiving includes receiving a non-digital video stream and further comprising digitizing the video stream.
3. The method of claim 1 , wherein said creating includes creating statistical parameterized representations for less than an entire image.
4. The method of claim 1 , wherein the statistical parameterized representations are color coherence vectors.
5. The method of claim 1 , wherein the statistical parameterized representations are color histograms.
6. The method of claim 1 , wherein the statistical parameterized representations are randomly highly subsampled representations of an image.
7. The method of claim 1 , wherein the known video content includes advertisements.
8. The method of claim 1 , wherein the known video content includes at least some subset of advertisement intros, advertisement outros, channel idents, and sponsorships.
9. The method of claim 1 , wherein said detecting includes detecting an advertisement opportunity in the video stream when said comparing indicates that a fingerprint associated with an advertisement or an advertisement intro has at least a threshold level of similarity with the statistical parameterized representations of the video stream.
10. The method of claim 1 , wherein said comparing only proceeds to a next window for a subset of the plurality of fingerprints that do not meet or exceed a maximum level of dissimilarity.
11. The method of claim 1 , further comprising screening out fingerprints having greater than a maximum level of dissimilarity with the statistical parameterized representation window.
12. The method of claim 1 , wherein said detecting is subsequent to comparing at least a defined number of windows of the particular fingerprint.
13. The method of claim 1 , wherein the known video content includes known programming content.
14. The method of claim 1 , wherein the known video content contains at least two colors.
15. The method of claim 1 , wherein the known video content includes content containing detectable motion.
16. A system for replacing a portion of a video stream with a targeted advertisement, the system comprising:
a receiver to receive a video stream;
memory for storing a plurality of fingerprints, wherein each of the plurality of fingerprints includes associated statistical parameterized representations of known video content and to store a plurality of targeted advertisements; and
a processor to
continually create statistical parameterized representations for windows of the video stream;
continually compare the statistical parameterized representations to windows of the plurality of fingerprints;
detect the known video content in the video stream when a particular fingerprint of the plurality of fingerprints has at least a threshold level of similarity with statistical parameterized representations;
select the targeted advertisement based on the known video content; and
replace the known video content in the video stream with the selected targeted advertisement.
17. The system of claim 16 , wherein the windows of the video stream and the windows of the plurality of fingerprints are portions of an image.
18. The system of claim 16 , wherein the statistical parameterized representations include at least some subset of color coherence vectors, color histograms, and randomly highly subsampled representations of an image.
19. The system of claim 16 , wherein the known video segments include at least some subset of advertisements, advertisement intros, sponsorship messages, advertisement outros, and channel idents.
20. A computer program product, comprising a physical computer readable medium having a computer readable program code embodied therein, said computer readable program code adapted to be executed to implement a method of replacing a portion of a video stream with a targeted advertisement, said method comprising:
continually creating statistical parameterized representations for windows of a received video stream;
continually comparing the statistical parameterized representations to windows of a plurality of fingerprints, wherein each of the plurality of fingerprints includes associated statistical parameterized representations of known video content;
detecting the known video content in the video stream when a particular fingerprint of the plurality of fingerprints has at least a threshold level of similarity with the statistical parameterized representations;
Selecting the targeted advertisement based on the contents of the detected known video content; and
replacing the known video content in the video stream with the selected targeted advertisement.
21. The computer program of claim 20 , wherein the windows of the video stream and the windows of the plurality of fingerprints are for less than an entire image.
22. The computer program of claim 20 , wherein the statistical parameterized representations are at least some subset of color coherence vectors, color histograms or highly subsampled representations of an image.
23. The computer program of claim 20 , wherein the known video segments are at least some subset of advertisements, advertisement intros, sponsorship messages, advertisement outros, and channel idents.