Generating alerts based upon detector outputs
Systems and methods for generating alerts and enhanced viewing experience features using on-screen data are disclosed. Textual data corresponding to on-screen text is determined from the visual content of video data. The textual data is associated with corresponding regions and frames of the video data in which the corresponding on-screen text was detected. Users can select regions in the frames of the visual content to monitor for a particular triggering item (e.g., a triggering word, name, or phrase). During play back of the video data, the textual data associated with the selected regions in the frames can be monitored for the triggering item. When the triggering item is detected in the textual data, an alert can be generated. Alternatively, the textual data for the selected region can be extracted to compile supplemental information that can be rendered over the playback of the video data or over other video data.
1. A method comprising:
receiving, by a computer system, video data comprising a plurality of frames, wherein each frame comprises a plurality of pixels;
determining, by the computer system, a monitoring region in the plurality of frames, wherein the monitoring region comprises a subset of the plurality of pixels, by associating the subset of the plurality of pixels with a key item comprising a particular pixel pattern;
extracting, by the computer system, pixel data from the subset of the plurality of pixels in the monitoring region in a subset of the plurality of frames;
analyzing, by the computer system, the extracted pixel data from the monitoring region; and
performing, by the computer system, an action based on the analyzing.
2. The method of claim 1 , wherein the analyzing the extracted pixel data comprises:
defining, by the computer system, the key item comprising a particular pixel pattern;
comparing, by the computer system, the pixel data to the particular pixel pattern; and
determining, by the computer system, a match based on the comparing of the pixel data to the particular pixel pattern.
3. The method of claim 2 , wherein the key item comprises a text string, and wherein the particular pixel pattern comprises rendered text corresponding to the text string.
4. The method of claim 3 , wherein the comparing the pixel data to the particular pattern comprises:
performing, by the computer system, a character recognition operation on the pixel data to generate textual data; and
comparing, by the computer system, the textual data to the text string.
5. The method of claim 2 , wherein the performing the action comprises generating, by the computer system, an alert that the key item has been detected.
6. The method of claim 5 , wherein the generating the alert comprises:
generating, by the computer system, an alert message; and
embedding, by the computer system, the alert message in other video data.
7. The method of claim 6 , wherein extracting the pixel data comprises performing, by the computer system, a character recognition operation on the pixel data to generate textual data, and wherein the alert message comprises the textual data.
8. The method of claim 5 , wherein the video data comprises an audio component, and wherein the generating the alert comprises changing, by the computer system, a volume setting associated with the audio component during playback of the video data.
9. The method of claim 2 , wherein the particular pixel pattern comprises an image of an object or a person.
10. The method of claim 2 , wherein the performing the action comprises associating the subset of the plurality of frames with the key item.
11. The method of claim 1 , wherein the performing the action comprises rendering, by the computer system, the subset of the plurality of frames on a display device coupled to the computer system according to a predetermined order.
12. The method of claim 1 , wherein the analyzing the extracted pixel data comprises performing, by the computer system, a character recognition operation on the pixel data to generate textual data.
13. The method of claim 12 , wherein the performing the action comprises embedding, by the computer system, the textual data into other video data, wherein the textual data can be rendered in superimposition over images rendered from the other video data.
14. The method of claim 12 , wherein the plurality of frames are arranged according to ordered positions, and wherein the method further comprises rendering, by the computer system, text, based on the textual data, in superimposition over pixels of the subset of the plurality of frames according to the ordered positions.
15. The method of claim 14 , further comprising:
extracting, by the computer system, additional pixel data from the subset of the plurality of pixels in the monitoring region in another subset of the plurality of frames;
performing, by the computer system, a character recognition operation on the additional pixel data to generate additional textual data; and
rendering, by the computer system, additional text, based on the additional textual data, in superimposition over pixels of the subset of the plurality of frames according to the ordered positions.
16. The method of claim 15 wherein the other subset of the plurality of frames is associated with a first subset of the ordered positions different from a second subset of the ordered positions associated with the subset of the plurality of frames.
17. The method of claim 14 , wherein the text comprises controls for navigating to one or more of the frames in the plurality of frames.
18. A method comprising:
receiving, by a computer system, video data comprising a plurality of frames;
receiving, by the computer system, previously determined detector output data corresponding to the video data, wherein the previously determined detector output data comprises textual data corresponding to images of text detected in corresponding regions of the plurality of frames;
determining, by the computer system, a monitoring region in the plurality of frames, wherein the monitoring region comprises at least one of the regions in the plurality of frames, by associating the at least one of the regions in the plurality of frames with a key item comprising a particular pixel pattern;
defining, by the computer system, a text string; and
for each frame in the plurality of frames:
determining, by the computer system, the textual data from the previously determined detector output data for the monitoring region;
comparing, by the computer system, the textual data with the text string;
determining, by the computer system, a match based on the comparing; and
performing, by the computer system, one or more actions in response to the match.
19. The method of claim 18 , wherein at least one of the one or more actions comprises generating an alert message.
20. An apparatus comprising:
one or more computer processors; and
a non-transitory computer-readable storage medium comprising instructions that when executed control the one or more computer processors to be configured to:
receive video data comprising a plurality of frames, wherein each frame comprises a plurality of pixels;
determine a monitoring region in the plurality of frames, wherein the monitoring region comprises a subset of the plurality of pixels by associating the at least one of the regions in the plurality of frames with a key item comprising a particular pixel pattern;
extract pixel data from the subset of the plurality of pixels in the monitoring region in a subset of the plurality of frames;
analyze the extracted pixel data from the monitoring region; and
perform an action based on the analysis.