|
|
Changes:
* New imxv4l2videosink element
Currently only supports input physically contiguous memory blocks
as input (so, for example, no videotestsrc)
* New Pango-based overlay elements using G2D for rendering
* gstimxcommon library is now public
Necessary when implementing external sinks to retrieve the mapped
physical memory address from gstreamer buffers
(NOTE: ABI may change in the next few releases until this is stabilized)
* New optional ability to use GstPhysMemory from gst-plugins-bad
* imxv4l2videosrc:
* Add checks for V4L XRGB555X and GStreamer NV61 pixel formats
* Add UYVY support and make it the new default
UYVY works better with IPU-based deinterlacing, since with I420,
deinterlaced frames may exhibit a green band at the bottom, which
is apparently an IPU bug related to the plane offsets.
* Fix compile prior to Gstreamer 1.3.1
* v4l2_buffer_pool: Add special case for tw6869 driver
The tw6869 driver requires a different physical address to allow
DMA'able buffers for decreasing latency between chip and display
* v4l2src: add fractional "fps" property
(obsoletes the "fps-n" property)
* Add GstImxV4l2Meta init function
This avoids the g_assert() that was caused by the missing init
function
* Add num-additional-buffers property
This can be useful if capturing video isn't smooth; it sets the
number of internal additional buffers, so if downstream consumes
too many buffers, imxv4l2videosrc might end up doing a blocking
wait until buffers are returned
* imxv4l2src plugin is now called imxv4l2video, because it also
contains imxv4l2videosink
Also, the v4l2 elements can be enabled/disabled in the build
configuration individually now
* compositor:
* Clear output also if the input format has an alpha channel
* Only copy compositor input buffers to DMA memory once
If a single input frame is used for multiple output frames, we would
otherwise copy multiple times which can easily go to the limit of the
memory bandwidth
* vpu:
* Fix leak causd by missing GstVideoCodecState unref
* Release decoder context GCond during flush to fix potential deadlock
* Add memory tag to VPU framebuffer meta to avoid meta related crashes
* Add support for GRAY8 frames as a "fake grayscale mode"
Grayscale is actually encoded as I420, with the U and V planes
filled with 0x80 bytes. This feature also makes libimxvpuapi 0.10.3
the new minimum requirement.
* Remove 8-pixel alignment from width & height sinkcaps
* Framebuffer array: fix memory leak if we got out of memory
* Handle releasing of buffers without assigned framebuffer
This can happen if the buffer is released before it was actually
used, e.g. when renegotiating at the very beginning; prevents
a crash that would otherwise occur
* Add parameter check to avoid encoder crash on flush
* g2d:
* Always enable blending if the input frames have an alpha channel
G2D automatically makes use not only of global alpha, but also of
per-pixel alpha. Therefore, it makes sense to enable blending even
if global alpha is set to 255, as long as the input frames have an
alpha channel. Such blending is useful for composing a video frame
with some partially-transparent overlays for example (not to be
confused with hardware overlays though).
* Add build configuration switches to explicitely specify G2D include
and library paths
* Disable cacheable memory allocation
Several issues were reported with cacheable DMA memory, so it is
turned off, at least for now
* blitter:
* Add property to clear screen to black in blitter sinks
* Add output-rotation property to videotransform base class
* audio:
* Fix SIGFPE when restarting mp3 encoder
* Fix reference counting for caps
* Mark static codec caps as may be leaked
This gets rid of the false positive in the leak tracer
* misc:
* Update waf to 1.9.3 to fix compilation with Python 3.4+
Signed-off-by: Carlos Rafael Giani <dv@pseudoterminal.org>
Signed-off-by: Otavio Salvador <otavio@ossystems.com.br>
|
