Merge remote-tracking branch 'upstream/master'

Author: Sibras

Changelog

@@ -2,6 +2,9 @@ Entries are sorted chronologically from oldest to youngest within each release,
 releases are sorted from youngest to oldest.
 
 version <next>:
+
+
+version 4.4:
 - AudioToolbox output device
 - MacCaption demuxer
 - PGX decoder

compat/atomics/win32/stdatomic.h

@@ -96,7 +96,7 @@ do {                                    \
     atomic_load(object)
 
 #define atomic_exchange(object, desired) \
-    InterlockedExchangePointer(object, desired);
+    InterlockedExchangePointer((PVOID volatile *)object, (PVOID)desired)
 
 #define atomic_exchange_explicit(object, desired, order) \
     atomic_exchange(object, desired)

configure

@@ -3555,6 +3555,7 @@ derain_filter_select="dnn"
 deshake_filter_select="pixelutils"
 deshake_opencl_filter_deps="opencl"
 dilation_opencl_filter_deps="opencl"
+dnn_detect_filter_select="dnn"
 dnn_processing_filter_select="dnn"
 drawtext_filter_deps="libfreetype"
 drawtext_filter_suggest="libfontconfig libfribidi"

doc/APIchanges

@@ -14,6 +14,12 @@ libavutil:     2017-10-21
 
 
 API changes, most recent first:
+2021-04-17 - xxxxxxxxxx - lavu 56.73.100 - frame.h detection_bbox.h
+  Add AV_FRAME_DATA_DETECTION_BBOXES
+
+2021-04-06 - xxxxxxxxxx - lavf 58.78.100 - avformat.h
+  Add avformat_index_get_entries_count(), avformat_index_get_entry(),
+  and avformat_index_get_entry_from_timestamp().
 
 2021-03-21 - xxxxxxxxxx - lavu 56.72.100 - frame.h
   Deprecated av_get_colorspace_name().

doc/decoders.texi

@@ -293,6 +293,8 @@ Enabled by default.
 @table @option
 @item compute_clut
 @table @option
+@item -2
+Compute clut once if no matching CLUT is in the stream.
 @item -1
 Compute clut if no matching CLUT is in the stream.
 @item 0

doc/demuxers.texi

@@ -243,11 +243,12 @@ which streams to actually receive.
 Each stream mirrors the @code{id} and @code{bandwidth} properties from the
 @code{<Representation>} as metadata keys named "id" and "variant_bitrate" respectively.
 
-@section flv, live_flv
+@section flv, live_flv, kux
 
 Adobe Flash Video Format demuxer.
 
 This demuxer is used to demux FLV files and RTMP network streams. In case of live network streams, if you force format, you may use live_flv option instead of flv to survive timestamp discontinuities.
+KUX is a flv variant used on the Youku platform.
 
 @example
 ffmpeg -f flv -i myfile.flv ...

doc/encoders.texi

@@ -1268,6 +1268,10 @@ disabled
 A description of some of the currently available video encoders
 follows.
 
+@section a64_multi, a64_multi5
+
+A64 / Commodore 64 multicolor charset encoder. @code{a64_multi5} is extended with 5th color (colram).
+
 @section GIF
 
 GIF image/animation encoder.

doc/ffmpeg.texi

@@ -1243,7 +1243,9 @@ by name, or it can create a new device as if
 were called immediately before.
 
 @item -hwaccels
-List all hardware acceleration methods supported in this build of ffmpeg.
+List all hardware acceleration components enabled in this build of ffmpeg.
+Actual runtime availability depends on the hardware and its suitable driver
+being installed.
 
 @end table
 

doc/ffprobe.xsd

@@ -29,22 +29,18 @@
     </xsd:complexType>
 
     <xsd:complexType name="framesType">
-        <xsd:sequence>
-            <xsd:choice minOccurs="0" maxOccurs="unbounded">
-                <xsd:element name="frame" type="ffprobe:frameType" minOccurs="0" maxOccurs="unbounded"/>
-                <xsd:element name="subtitle" type="ffprobe:subtitleType" minOccurs="0" maxOccurs="unbounded"/>
-            </xsd:choice>
-        </xsd:sequence>
+        <xsd:choice minOccurs="0" maxOccurs="unbounded">
+            <xsd:element name="frame"    type="ffprobe:frameType"/>
+            <xsd:element name="subtitle" type="ffprobe:subtitleType"/>
+        </xsd:choice>
     </xsd:complexType>
 
     <xsd:complexType name="packetsAndFramesType">
-        <xsd:sequence>
-            <xsd:choice minOccurs="0" maxOccurs="unbounded">
-                <xsd:element name="packet" type="ffprobe:packetType" minOccurs="0" maxOccurs="unbounded"/>
-                <xsd:element name="frame" type="ffprobe:frameType" minOccurs="0" maxOccurs="unbounded"/>
-                <xsd:element name="subtitle" type="ffprobe:subtitleType" minOccurs="0" maxOccurs="unbounded"/>
-            </xsd:choice>
-        </xsd:sequence>
+        <xsd:choice minOccurs="0" maxOccurs="unbounded">
+            <xsd:element name="packet"   type="ffprobe:packetType"/>
+            <xsd:element name="frame"    type="ffprobe:frameType"/>
+            <xsd:element name="subtitle" type="ffprobe:subtitleType"/>
+        </xsd:choice>
     </xsd:complexType>
 
     <xsd:complexType name="packetType">
@@ -199,6 +195,11 @@
       <xsd:attribute name="clean_effects"    type="xsd:int" use="required" />
       <xsd:attribute name="attached_pic"     type="xsd:int" use="required" />
       <xsd:attribute name="timed_thumbnails" type="xsd:int" use="required" />
+      <xsd:attribute name="captions"         type="xsd:int" use="required" />
+      <xsd:attribute name="descriptions"     type="xsd:int" use="required" />
+      <xsd:attribute name="metadata"         type="xsd:int" use="required" />
+      <xsd:attribute name="dependent"        type="xsd:int" use="required" />
+      <xsd:attribute name="still_image"      type="xsd:int" use="required" />
     </xsd:complexType>
 
     <xsd:complexType name="streamType">

doc/filters.texi

@@ -10127,6 +10127,46 @@ ffmpeg -i INPUT -f lavfi -i nullsrc=hd720,geq='r=128+80*(sin(sqrt((X-W/2)*(X-W/2
 @end example
 @end itemize
 
+@section dnn_detect
+
+Do object detection with deep neural networks.
+
+The filter accepts the following options:
+
+@table @option
+@item dnn_backend
+Specify which DNN backend to use for model loading and execution. This option accepts
+only openvino now, tensorflow backends will be added.
+
+@item model
+Set path to model file specifying network architecture and its parameters.
+Note that different backends use different file formats.
+
+@item input
+Set the input name of the dnn network.
+
+@item output
+Set the output name of the dnn network.
+
+@item confidence
+Set the confidence threshold (default: 0.5).
+
+@item labels
+Set path to label file specifying the mapping between label id and name.
+Each label name is written in one line, tailing spaces and empty lines are skipped.
+The first line is the name of label id 0 (usually it is 'background'),
+and the second line is the name of label id 1, etc.
+The label id is considered as name if the label file is not provided.
+
+@item backend_configs
+Set the configs to be passed into backend
+
+@item async
+use DNN async execution if set (default: set),
+roll back to sync execution if the backend does not support async.
+
+@end table
+
 @anchor{dnn_processing}
 @section dnn_processing
 
@@ -12139,6 +12179,9 @@ Number of mipmaps, default is 3.
 
 @item xmin, ymin, xmax, ymax
 Specifies the rectangle in which to search.
+
+@item discard
+Discard frames where object is not detected. Default is disabled.
 @end table
 
 @subsection Examples
@@ -21760,6 +21803,9 @@ Default is @code{3}.
 Apply cross fade from one input video stream to another input video stream.
 The cross fade is applied for specified duration.
 
+Both inputs must be constant frame-rate and have the same resolution, pixel format,
+frame rate and timebase.
+
 The filter accepts the following options:
 
 @table @option