SYSTEMS AND METHODS FOR VIDEO CODING OF FEATURES USING SUBPICTURES
Systems and methods for video coding of visual features that uses picture structures such as subpictures to independently encode individual features or groups of features are disclosed. An encoding method includes extracting a plurality of features from an image, representing each of the image features as a two-dimensional feature unit, grouping the feature units into at least one subpicture of the frame, and encoding the video frame into a bitstream. A compatible decoder for reconstructing the sequence of features is also provided.
1 . A method for encoding features into a video frame, the video frame being partitionable into a plurality of subpictures, comprising:
processing an image to extract a plurality of features;
representing each of the image features as a two-dimensional feature unit;
grouping the feature units into at least one subpicture of the frame; and
encoding the video frame into a bitstream.
2 . The method of claim 1 , wherein the processing of an image includes a convolutional neural network (CNN) having a plurality of processing layers and wherein features are extracted as an output of each layer.
3 . The method of claim 2 , wherein the grouping step includes selecting feature units based on at least one of (1) features representing similar spatial characteristics, (2) features that represent similar object types, (3) features that are extracted using the same filters, (4) features from spatially neighboring regions; (5) features from the same layer of the CNN, and (6) features that relate to a specific task on the decoder side.
4 . The method of claim 1 , wherein parameters of the feature units in the at least one subpicture are signaled in the bitstream.
5 . The method of claim 4 , wherein the parameters include at least one of: (1) a flag that signals if feature units are present; (2) the number of feature units in the subpicture; (3) the position and dimensions of each feature unit, in sequence; and (4) a feature unit type identifier.
6 . (canceled)
7 . A method for decoding a video signal, the method comprising:
receiving an encoded bistream having at least one frame partitioned with a plurality of subpictures, the subpictures having a plurality of feature units arranged therein;
identifying at least one subpicture having a plurality of feature units spatially arranged therein;
reconstructing a sequence of feature units from spatially arranged feature units in the subpicture.
8 . The method of claim 7 , wherein the reconstructing further comprises ordering the feature units based on a predetermined mapping.
9 . The method of claim 7 , wherein the reconstructing further comprises ordering the feature units base on information signalled in the encoded bitstream.
10 . The method of claim 7 wherein each subpicture comprising the frame has at least one feature unit.
11 . (canceled)
12 . A hybrid video decoder comprising:
a demultiplexor, the demultiplexor receiving an encoded bistream having a video substream and a feature substream, the feature substream having at least one frame partitioned with a plurality of subpictures, the subpictures having a plurality of feature units arranged therein;
a video decoder receiving the video substream and providing video output for a human viewer;
a feature decoder, the feature decoder receiving the feature substream, the feature decoder:
identifying at least one subpicture having a plurality of feature units spatially arranged therein; and
reconstructing a sequence of feature units from spatially arranged feature units in the subpicture.