[FFmpeg-devel] [PATCH V4 1/2] avutil: add ROI data struct and bump version

[Guo, Yejun]

The encoders such as libx264 support different QPs offset for different MBs,
it makes possible for ROI-based encoding. It makes sense to add support
within ffmpeg to generate/accept ROI infos and pass into encoders.

Typical usage: After AVFrame is decoded, a ffmpeg filter or user's code
generates ROI info for that frame, and the encoder finally does the
ROI-based encoding.

The ROI info is maintained as side data of AVFrame.

Signed-off-by: Guo, Yejun <yejun.guo at intel.com>
---
 libavutil/frame.c   |  1 +
 libavutil/frame.h   | 23 +++++++++++++++++++++++
 libavutil/version.h |  2 +-
 3 files changed, 25 insertions(+), 1 deletion(-)

diff --git a/libavutil/frame.c b/libavutil/frame.c
index 34a6210..bebc50e 100644
--- a/libavutil/frame.c
+++ b/libavutil/frame.c
@@ -841,6 +841,7 @@ const char *av_frame_side_data_name(enum AVFrameSideDataType type)
     case AV_FRAME_DATA_QP_TABLE_DATA:               return "QP table data";
 #endif
     case AV_FRAME_DATA_DYNAMIC_HDR_PLUS: return "HDR Dynamic Metadata SMPTE2094-40 (HDR10+)";
+    case AV_FRAME_DATA_ROIS: return "Regions Of Interest";
     }
     return NULL;
 }
diff --git a/libavutil/frame.h b/libavutil/frame.h
index 582ac47..3460b01 100644
--- a/libavutil/frame.h
+++ b/libavutil/frame.h
@@ -173,6 +173,12 @@ enum AVFrameSideDataType {
      * volume transform - application 4 of SMPTE 2094-40:2016 standard.
      */
     AV_FRAME_DATA_DYNAMIC_HDR_PLUS,
+
+    /**
+     * Regions Of Interest, the data is an array of AVROI type, the array size
+     * is implied by AVFrameSideData::size / sizeof(AVROI).
+     */
+    AV_FRAME_DATA_ROIS,
 };
 
 enum AVActiveFormatDescription {
@@ -201,6 +207,23 @@ typedef struct AVFrameSideData {
 } AVFrameSideData;
 
 /**
+ * Structure to hold Region Of Interest.
+ *
+ * top/bottom/left/right are coordinates at frame pixel level.
+ * They will be extended internally if the codec requires an alignment.
+ * If the regions overlap, the last value in the list will be used.
+ *
+ * qoffset is quant offset, it is encoder dependent.
+ */
+typedef struct AVROI {
+    size_t top;
+    size_t bottom;
+    size_t left;
+    size_t right;
+    int qoffset;
+} AVROI;
+
+/**
  * This structure describes decoded (raw) audio or video data.
  *
  * AVFrame must be allocated using av_frame_alloc(). Note that this only
diff --git a/libavutil/version.h b/libavutil/version.h
index f997615..1fcdea9 100644
--- a/libavutil/version.h
+++ b/libavutil/version.h
@@ -79,7 +79,7 @@
  */
 
 #define LIBAVUTIL_VERSION_MAJOR  56
-#define LIBAVUTIL_VERSION_MINOR  25
+#define LIBAVUTIL_VERSION_MINOR  26
 #define LIBAVUTIL_VERSION_MICRO 100
 
 #define LIBAVUTIL_VERSION_INT   AV_VERSION_INT(LIBAVUTIL_VERSION_MAJOR, \
-- 
2.7.4