Postmasking without transcoding
Methods and apparatus, including computer program products, implementing and using techniques providing privacy masks on a video stream. In a video received from a monitoring camera, at least one image region is selected, to which region a privacy mask should be applied. For any image frame in the video that contains the at least one image region, a flag is set to indicate a non-displayed image frame. A forward-predicted image frame referencing the non-displayed image frame is inserted, wherein coding units representing the at least one image region in the forward-predicted image frame collectively provide the privacy mask by obfuscating the at least one image region.
1. A method for providing privacy masks on a video stream, comprising:
in a video received from a monitoring camera, selecting at least one image region in the video to which region a privacy mask should be applied,
for an image frame in the video that contains the at least one image region:
setting a flag for the image frame to indicate a non-displayed image frame; and
inserting a forward-predicted image frame referencing the non-displayed image frame, wherein coding units representing the at least one image region are processed differently from coding units representing areas outside the at least one image region, such that coding units representing the at least one image region are obfuscated to collectively form the privacy mask and coding units representing areas outside the at least one image region are set as skip blocks; and
outputting a video stream including both the non-displayed image frame and the forward-predicted image frame.
2. The method of claim 1 , wherein selecting at least one image region is done by a user.
3. The method of claim 1 , wherein selecting the at least one image region is done automatically, using object detection techniques.
4. The method of claim 1 , wherein the coding units representing the at least one image region in the forward-predicted image frame are arranged to provide obfuscation by introducing artificial motion vectors for the coding units, thereby causing blurring of the at least one image region.
5. The method of claim 1 , wherein the coding units representing the at least one image region in the forward-predicted image frame are arranged to provide obfuscation by replacing the coding units in the at least one image region.
6. The method of claim 1 , wherein the coding units representing the at least one image region in the forward-predicted image frame are arranged to provide obfuscation by replacing the coding units with intrablocks with selected blurring of image data retrieved from the non-displayed image frame, thereby causing blurring of the at least one image region.
7. The method of claim 1 , wherein the monitoring camera is a body worn camera.
8. The method of claim 1 , wherein the video is encoded in one of the following formats: High Efficiency Video Coding, Versatile Video Coding, Essential Video Coding, VP9, and AV1.
9. An encoder system for providing privacy masks on a video stream, the encoder system comprising:
a docking station configured to receive a video from a monitoring camera; and
an encoder configured to:
select at least one image region in the video to which region a privacy mask should be applied,
for an image frame in the video that contains the at least one image region:
set a flag for the image frame to indicate a non-displayed image frame, and
insert a forward-predicted image frame referencing the non-displayed image frame, wherein coding units representing the at least one image region are processed differently from coding units representing areas outside the at least one image region, such that coding units representing the at least one image region are obfuscated to collectively form the privacy mask and coding units representing areas outside the at least one image region are set as skip blocks; and
output a video stream including both the non-displayed image frame and the forward-predicted image frame.
10. A computer program, stored on a non-transitory computer-readable medium, for providing privacy masks on a video stream comprising program instructions corresponding to the steps of:
in a video received from a monitoring camera, selecting at least one image region in the video to which region a privacy mask should be applied,
for an image frame in the video that contains the at least one image region:
setting a flag for the image frame to indicate a non-displayed image frame; and
inserting a forward-predicted image frame referencing the non-displayed image frame, wherein coding units representing the at least one image region are processed differently from coding units representing areas outside the at least one image region, such that coding units representing the at least one image region are obfuscated to collectively form the privacy mask, and coding units representing areas outside the at least one image region are set as skip blocks; and
outputting a video stream including both the non-displayed image frame and the forward-predicted image frame.
11. A non-transitory digital storage medium comprising a computer program as claimed in claim 10 .