avutil: add ROI (Region Of Interest) data struct and bump version

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@intel.com>
Signed-off-by: Derek Buitenhuis <derek.buitenhuis@gmail.com>

3 files changed, 37 insertions, 1 deletions

diff --git a/libavutil/frame.c b/libavutil/frame.c
index 34a6210d9e..dcf1fc3d17 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_REGIONS_OF_INTEREST: return "Regions Of Interest";
     }
     return NULL;
 }
diff --git a/libavutil/frame.h b/libavutil/frame.h
index 582ac470b2..8d0dfedebb 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 AVRegionOfInterest type, the number of
+     * array element is implied by AVFrameSideData.size / AVRegionOfInterest.self_size.
+     */
+    AV_FRAME_DATA_REGIONS_OF_INTEREST,
 };
 
 enum AVActiveFormatDescription {
@@ -201,6 +207,35 @@ typedef struct AVFrameSideData {
 } AVFrameSideData;
 
 /**
+ * Structure to hold Region Of Interest.
+ *
+ * self_size specifies the size of this data structure. This value
+ * should be set to sizeof(AVRegionOfInterest). EINVAL is returned if self_size is zero.
+ *
+ * Number of pixels to discard from the top/bottom/left/right border of
+ * the frame to obtain the region of interest of the frame.
+ * They are encoder dependent and 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, and base rule here:
+ * returns EINVAL if AVRational.den is zero.
+ * the value (num/den) range is [-1.0, 1.0], clamp to +-1.0 if out of range.
+ * 0 means no picture quality change,
+ * negtive offset asks for better quality (and the best with value -1.0),
+ * positive offset asks for worse quality (and the worst with value 1.0).
+ * How to explain/implement the different quilaity requirement is encoder dependent.
+ */
+typedef struct AVRegionOfInterest {
+    uint32_t self_size;
+    int top;
+    int bottom;
+    int left;
+    int right;
+    AVRational qoffset;
+} AVRegionOfInterest;
+
+/**
  * 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 f9976151a7..1fcdea95bf 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, \