Decoder-side region of interest video processing
The disclosure is directed to decoder-side region-of-interest (ROI) video processing. A video decoder determines whether ROI assistance information is available. If not, the decoder defaults to decoder-side ROI processing. The decoder-side ROI processing may estimate the reliability of ROI extraction in the bitstream domain. If ROI reliability is favorable, the decoder applies bitstream domain ROI extraction. If ROI reliability is unfavorable, the decoder applies pixel domain ROI extraction. The decoder may apply different ROI extraction processes for intra-coded (I) and inter-coded (P or B) data. The decoder may use color-based ROI generation for intra-coded data, and coded block pattern (CBP)-based ROI generation for inter-coded data. ROI refinement may involve shape-based refinement for intra-coded data, and motion- and color-based refinement for inter-coded data.
1. A method comprising:
identifying a region of interest (ROI) in encoded video data based on color characteristics of the encoded video data for intra-coded data;
identifying the ROI based on coded block pattern (CBP) characteristics of the encoded video data for inter-coded data;
processing a portion of the encoded video data based on the identified ROI to produce higher visual quality relative to other portions of the encoded video data; and
comparing quantization of the identified ROI with quantization of non-ROI areas of video data, wherein processing includes processing the non-ROI areas if the comparing indicates poor quantization of the non-ROI areas relative to the ROI.
2. The method of claim 1 , further comprising refining the ROI based on shape characteristics of the encoded video data for intra-coded data.
3. The method of claim 1 , further comprising refining the identified ROI based on motion and color characteristics of the encoded video data for inter-coded data.
4. The method of claim 1 , wherein processing the portion of the encoded video data comprises using at least one of enhanced post-processing and enhanced error concealment to the identified ROI.
5. The method of claim 1 , wherein comparing quantization includes analyzing quantization parameter values for luma and chroma components of the encoded video data, and wherein the comparing indicates poor quantization of the non-ROI areas relative to the ROI when average quantization parameter values for luma and chroma components exceed a predetermined threshold value.
6. A device comprising:
a video decoder;
a first module of the video decoder that identifies a region of interest (ROI) in encoded video data based on color characteristics of the encoded video data for intra-coded data;
a second module of the video decoder that identifies the ROI based on coded block pattern (CBP) characteristics of the encoded video data for inter-coded data;
a processing module of the video decoder that processes a portion of the encoded video data based on the identified ROI to produce higher visual quality relative to other portions of the encoded video data, and that compares quantization of the identified ROI with quantization of non-ROI areas of video data, and processes the non-ROI areas if the comparison indicates poor quantization of the non-ROI areas relative to the ROI.
7. The device of claim 6 , wherein the first module refines the ROI based on shape characteristics of the encoded video data for intra-coded data.
8. The device of claim 6 , wherein the second module refines the identified ROI based on motion and color characteristics of the encoded video data for inter-coded data.
9. The device of claim 6 , wherein the processing module processes the portion of the encoded video data using at least one of enhanced post-processing and enhanced error concealment.
10. The device of claim 6 , wherein the processing module compares quantization by analyzing quantization parameter values for luma and chroma components of the encoded video data, and wherein the comparison indicated poor quantization of the non-ROI areas relative to the ROI when average quantization parameter values for luma and chroma components exceed a predetermined threshold value.
11. A device comprising:
means for identifying a region of interest (ROI) in encoded video data based on color characteristics of the encoded video data for intra-coded data;
means for identifying the ROI based on coded block pattern (CBP) characteristics of the encoded video data for inter-coded data;
means for processing a portion of the encoded video data based on the identified ROI to produce higher visual quality relative to other portions of the encoded video data; and
means for comparing quantization of the identified ROI with quantization of non-ROI areas of video data, wherein processing includes processing the non-ROI areas if the comparing indicates poor quantization of the non-ROI areas relative to the ROI.
12. The device of claim 11 , further comprising means for refining the ROI based on shape characteristics of the encoded video data for intra-coded data.
13. The device of claim 11 , further comprising means for refining the identified ROI based on motion and color characteristics of the encoded video data for inter-coded data.
14. The device of claim 11 , wherein processing the portion of the encoded video data comprises using at least one of enhanced post-processing and enhanced error concealment to the identified ROI.
15. The device of claim 11 , wherein comparing quantization includes analyzing quantization parameter values for luma and chroma components of the encoded video data, and wherein the comparing indicates poor quantization of the non-RIO areas relative to the ROI when average quantization parameter values for luma and chroma components exceed a predetermined threshold value.
16. A non-transitory computer-readable medium comprising instructions to cause a processor to:
identify a region of interest (ROI) in encoded video data based on color characteristics of the encoded video data for intra-coded data;
identify the ROI based on coded block pattern (CBP) characteristics of the encoded video data for inter-coded data;
process a portion of the encoded video data based on the identified ROI to produce higher visual quality relative to other portions of the encoded video data; and
compare quantization of the identified ROI with quantization of non-ROI areas of video data, wherein processing includes processing the non-ROI areas if the comparing indicates poor quantization of the non-ROI areas relative to the ROI.
17. The computer-readable medium of claim 16 , further comprising instructions to cause the processor to refine the ROI based on shape characteristics of the encoded video data for intra-coded data.
18. The computer-readable medium of claim 16 , further comprising instructions to cause the processor to refine the identified ROI based on motion and color characteristics of the encoded video data for inter-coded data.
19. The computer-readable medium of claim 16 , wherein processing the portion of the encoded video data comprises using at least one of enhanced post-processing and enhanced error concealment to the identified ROI.
20. The computer-readable medium of claim 16 , wherein comparing quantization includes analyzing quantization parameter values for luma and chroma components of the encoded video data, and wherein the comparing indicates poor quantization of the non-RIO areas relative to the ROI when average quantization parameter values for luma and chroma components exceed a predetermined threshold value.