Blurring privacy masks
AssigneeAxis AB
InventorsViktor Edpalm, Song Yuan
Life of this patent
Estimating the term…
Abstract
Methods and apparatus, including computer program products, implementing and using techniques for encoding a video sequence comprising a plurality of image frames, by an encoder are described. An image frame is received from a video stream. An input is received, which indicates one or more regions in the received image frame for which a privacy mask should be applied. The one or more regions are represented by one or more coding units. The image frame is encoded into an output frame, wherein image data in the one or more regions is replaced by intra-predicted coding units with transformed coefficients set to zero, the intra-predicted coding units are obtained from a prediction stage in the encoder.
Claims11
A method for encoding a video sequence comprising a plurality of image frames, by an encoder, the method comprising:
- receiving an image frame from a video stream;
- receiving an input indicating one or more regions in the received image frame for which a privacy mask should be applied, wherein the one or more regions are represented by one or more coding units;
- generating a simplified representation of the image frame by performing intra-prediction and quantization of the one or more coding units;
- and
- encoding the image frame into an output frame, wherein a transformation coefficient for the one or more coding units is set to zero, thereby replacing the one or more coding units with corresponding untransformed coding units from the simplified representation of the image frame, in the output frame.
An encoder system for encoding a video sequence comprising a plurality of image frames, comprising:
- a receiving module configured to:
- receive an image frame from a video stream,
- receive an input indicating one or more regions in the received image frame for which a privacy mask should be applied, wherein the one or more regions are represented by one or more coding units, and
- generate a simplified representation of the image frame by performing intra-prediction and quantization of the one or more coding units;
- and
- an encoder configured to:
- encode the image frame into an output frame, wherein a transformation coefficient for the one or more coding is set to zero, thereby replacing the one or more coding units with corresponding untransformed coding units from the simplified representation of the image frame, in the output frame.
A computer program product for encoding a video sequence comprising a plurality of image frames, the computer program product comprising a non-transitory computer readable storage medium having program instructions embodied therewith, the program instructions being executable by a processor to cause the processor to perform a method comprising:
- receiving an image frame from a video stream;
- receiving an input indicating one or more regions in the received image frame for which a privacy mask should be applied, wherein the one or more regions are represented by one or more coding units
- generating a simplified representation of the image frame by performing intra-prediction and quantization of the one or more coding units;
- and
- encoding the image frame into an output frame, wherein a transformation coefficient for the one or more coding units is set to zero, thereby replacing the one or more coding units with corresponding untransformed coding units from the simplified representation of the image frame, in the output frame.
Dependencies are inferred from the claim text.