Video privacy using machine learning

1. A computer-implemented method for providing video privacy, the method comprising:

receiving first video data captured by a video camera;

determining a first context for the first video data;

determining that the first context matches a privacy context from a set of privacy contexts identified using machine learning, wherein at least one of the privacy contexts in the set of privacy contexts is identified based on correlating identified contexts with user-initiated pausing of video streaming; and

blocking, in response to the first context matching the privacy context, at least a portion of second video data captured by the video camera subsequent to the first video data.

2. The method of claim 1 , further comprising:

while blocking the at least a portion of the second video data, determining a second context for the second video data;

determining that the second context does not match a privacy context from the set of privacy contexts; and

removing the block applied to the second video data for third video data captured by the video camera subsequent to the second video data.

3. The method of claim 1 , wherein determining that the first context matches the privacy context comprises:

predicting a future user action based on the first context, and determining the predicted user action matches an action flagged for privacy protection.

4. The method of claim 1 , wherein at least one of the privacy contexts in the set of privacy contexts is based on a user-added privacy tag.

5. The method of claim 4 , wherein the privacy tag is provided by a user with an interface of an augmented reality device.

6. The method of claim 1 , wherein the video camera is part of an augmented reality device.

7. The method of claim 1 , wherein blocking of at least a portion of the second video data prevents the at least a portion of the second video data from being processed by an external augmented reality process.

8. The method of claim 1 , wherein the determining the context for the captured first data is based on identifying one or more objects using image recognition.

9. The method of claim 1 , wherein the determining the first context for the first video data is based on audio data associated with the first video data.

10. A system for providing privacy in an augmented reality environment comprising:

a memory; and

a processor communicatively coupled to the memory, wherein the memory comprises instructions which, when executed by the processor, cause the processor to perform a method comprising:

receiving first video data captured by a video camera;

determining a first context for the first video data;

determining that the first context matches a privacy context from a set of privacy contexts identified using machine learning, wherein at least one of the privacy contexts in the set of privacy contexts is identified based on correlating identified contexts with user-initiated pausing of video streaming; and

blocking, in response to the first context matching the privacy context, at least a portion of second video data captured by the video camera subsequent to the first video data.

11. The system of claim 10 , wherein determining that the first context matches the privacy context comprises:

predicting a user action based on the first context; and

determining the predicted user action matches an action flagged for privacy protection.

12. The system of claim 10 , wherein the method further comprises:

while blocking the at least a portion of the second video data, determining a second context for the second video data;

determining that the second context does not match a privacy context from the set of privacy contexts; and

removing the block applied to the second video data for third video data captured by the video camera subsequent to the second video data.

13. The system of claim 10 , wherein blocking the at least a portion of the second video data prevents the at least a portion of the second video data from being processed by an external augmented reality process.

14. A computer program product for providing privacy in an augmented reality environment, the computer program product comprising a computer readable storage medium having program instructions embodied therein, the program instruction executable by a processor to perform a method comprising:

receiving first video data captured by a video camera;

determining a first context for the first video data;

determining that the first context matches a privacy context from a set of privacy contexts identified using machine learning, wherein at least one of the privacy contexts in the set of privacy contexts is identified based on correlating identified contexts with user-initiated pausing of video streaming; and

blocking, in response to the first context matching the privacy context, at least a portion of second video data captured by the video camera subsequent to the first video data.

15. The computer program product of claim 14 , wherein determining that the first context matches the privacy context comprises:

predicting a user action based on the first context; and

determining the predicted user action matches an action flagged for privacy protection.

16. The computer program product of claim 14 , wherein the method further comprises:

while blocking the at least a portion of the second video data, determining a second context for the second video data;

determining that the second context does not match a privacy context from the set of privacy contexts; and

removing the block applied to the second video data for third video data captured by the video camera subsequent to the second video data.

17. The computer program product of claim 14 , wherein blocking the at least a portion of the second video data prevents the at least a portion of the second video data from being processed by an external augmented reality process.