avdevice/dshow: implement option to use device video timestamps

The dshow avdevice ignores timestamps for video frames provided by the
DirectShow device, instead using wallclock time, apparently because the
implementer of this code had a device that provided unreliable
timestamps. Me (and others) would like to use the device's timestamps.
The new use_video_device_timestamps option for dshow device enables them
to do so. Since the majority of video devices out there probably provide
fine timestamps, this patch sets the default to using the device
timestamps, which means best fidelity timestamps are used by default.
Using the new option, the user can switch this off and revert to the old
behavior, so a fall back remains available in case the device provides
broken timestamps.

add use_video_device_timestamps to docs.

Closes: #8620

Signed-off-by: Diederick Niehorster <dcnieho@gmail.com>
Reviewed-by: Roger Pack <rogerdpack2@gmail.com>

doc/indevs.texi

@@ -625,6 +625,12 @@ Save the currently used video capture filter device and its
 parameters (if the filter supports it) to a file.
 If a file with the same name exists it will be overwritten.
 
+@item use_video_device_timestamps
+If set to @option{false}, the timestamp for video frames will be
+derived from the wallclock instead of the timestamp provided by
+the capture device. This allows working around devices that
+provide unreliable timestamps.
+
 @end table
 
 @subsection Examples

libavdevice/dshow.c

@@ -1310,6 +1310,7 @@ static const AVOption options[] = {
     { "audio_device_save", "save audio capture filter device (and properties) to file", OFFSET(audio_filter_save_file), AV_OPT_TYPE_STRING, {.str = NULL}, 0, 0, DEC },
     { "video_device_load", "load video capture filter device (and properties) from file", OFFSET(video_filter_load_file), AV_OPT_TYPE_STRING, {.str = NULL}, 0, 0, DEC },
     { "video_device_save", "save video capture filter device (and properties) to file", OFFSET(video_filter_save_file), AV_OPT_TYPE_STRING, {.str = NULL}, 0, 0, DEC },
+    { "use_video_device_timestamps", "use device instead of wallclock timestamps for video frames", OFFSET(use_video_device_timestamps), AV_OPT_TYPE_BOOL, {.i64 = 1}, 0, 1, DEC },
     { NULL },
 };
 

libavdevice/dshow_capture.h

@@ -312,6 +312,7 @@ struct dshow_ctx {
     char *audio_filter_save_file;
     char *video_filter_load_file;
     char *video_filter_save_file;
+    int   use_video_device_timestamps;
 
     IBaseFilter *device_filter[2];
     IPin        *device_pin[2];

libavdevice/dshow_pin.c

@@ -309,10 +309,14 @@ long ff_dshow_meminputpin_Receive(DShowMemInputPin *this, IMediaSample *sample)
     if (!sample)
         return E_POINTER;
 
+    priv_data = pin->filter->priv_data;
+    s = priv_data;
+    ctx = s->priv_data;
+
     IMediaSample_GetTime(sample, &orig_curtime, &dummy);
     orig_curtime += pin->filter->start_time;
     IReferenceClock_GetTime(clock, &graphtime);
-    if (devtype == VideoDevice) {
+    if (devtype == VideoDevice && !ctx->use_video_device_timestamps) {
         /* PTS from video devices is unreliable. */
         IReferenceClock_GetTime(clock, &curtime);
     } else {
@@ -322,7 +326,7 @@ long ff_dshow_meminputpin_Receive(DShowMemInputPin *this, IMediaSample *sample)
                like 437650244077016960 which FFmpeg doesn't like.
                TODO figure out math. For now just drop them. */
             av_log(NULL, AV_LOG_DEBUG,
-                "dshow dropping initial (or ending) audio frame with odd PTS too high %"PRId64"\n", curtime);
+                "dshow dropping initial (or ending) frame with odd PTS too high %"PRId64"\n", curtime);
             return S_OK;
         }
         curtime += pin->filter->start_time;
@@ -330,9 +334,6 @@ long ff_dshow_meminputpin_Receive(DShowMemInputPin *this, IMediaSample *sample)
 
     buf_size = IMediaSample_GetActualDataLength(sample);
     IMediaSample_GetPointer(sample, &buf);
-    priv_data = pin->filter->priv_data;
-    s = priv_data;
-    ctx = s->priv_data;
     index = pin->filter->stream_index;
 
     av_log(NULL, AV_LOG_VERBOSE, "dshow passing through packet of type %s size %8d "