Recherche avancée

Sur d’autres sites (10319)

• x264 encoding taking longer when encoding static frames (than

  14 septembre 2015, par Danilo

  ​Hi,
  I’m using x264 for live video streaming and I’ve noticed that the thread
  responsible for encoding uses ​​more cpu (sometimes 50% more with 1920x1080) when the video stream is frozen (i.e. : camera is sending the same frame over an over again) or when I make it encode the same image over and over again.

  This seems somewhat counter intuitive to me, as I would expect x264 to use
  more processing power when encoding complex scenes other then static ones.

  My encoder settings are the following :

  1280x720 fps=25/1 timebase=0/0 bitdepth=8 cabac=0 ref=1 deblock=1:0:0 analyse=0x3:0x113
  
  me=hex subme=2 psy=1 psy_rd=1.00:0.00 mixed_ref=1 me_range=16 chroma_me=1 trellis=1
  
  8x8dct=0 cqm=0 deadzone=21,11 fast_pskip=1 chroma_qp_offset=0 threads=1 lookahead_threads=0
  
  sliced_threads=0 slice_max_size=1190 nr=60 decimate=1 interlaced=0 bluray_compat=0
  
  constrained_intra=0 bframes=0 weightp=0  keyint=1200 keyint_min=120 scenecut=40
  
  intra_refresh=0 rc_lookahead=0 rc=crf mbtree=0 crf=24.0 qcomp=0.60 qpmin=0 qpmax=69
  
  qpstep=4 vbv_maxrate=1024 vbv_bufsize=350 crf_max=35.0 nal_hrd=none

  I created a github gist based on the example.c encoder bundled in x264’s
  source code and tested encoding times with it. (You can find it here :
  https://gist.github.com/danilogr/ab4976ff4e0831ab274b)

  Average encoding time for the static scene is 38% bigger than for a scene
  with movements. (You can find my test case and also the output from my test
  encoder on the link above).

  ​​
  ​I’ve also noticed that by setting ​​scenecut=0, subme=0, trellis=0 and me=dia I can get rid of this problem​, but with noticeable quality​ decrease.

  ​
  ​Could anyone, please, shed some light on the reasons for this odd behavior ?
  ​Also, what can be done in order to avoid this situation without a major decrease in quality ?​

• x264 encoding taking longer when encoding static frames (than

  14 septembre 2015, par Danilo

  ​Hi,
  I’m using x264 for live video streaming and I’ve noticed that the thread
  responsible for encoding uses ​​more cpu (sometimes 50% more with 1920x1080) when the video stream is frozen (i.e. : camera is sending the same frame over an over again) or when I make it encode the same image over and over again.

  This seems somewhat counter intuitive to me, as I would expect x264 to use
  more processing power when encoding complex scenes other then static ones.

  My encoder settings are the following :

  1280x720 fps=25/1 timebase=0/0 bitdepth=8 cabac=0 ref=1 deblock=1:0:0 analyse=0x3:0x113
  
  me=hex subme=2 psy=1 psy_rd=1.00:0.00 mixed_ref=1 me_range=16 chroma_me=1 trellis=1
  
  8x8dct=0 cqm=0 deadzone=21,11 fast_pskip=1 chroma_qp_offset=0 threads=1 lookahead_threads=0
  
  sliced_threads=0 slice_max_size=1190 nr=60 decimate=1 interlaced=0 bluray_compat=0
  
  constrained_intra=0 bframes=0 weightp=0  keyint=1200 keyint_min=120 scenecut=40
  
  intra_refresh=0 rc_lookahead=0 rc=crf mbtree=0 crf=24.0 qcomp=0.60 qpmin=0 qpmax=69
  
  qpstep=4 vbv_maxrate=1024 vbv_bufsize=350 crf_max=35.0 nal_hrd=none

  I created a github gist based on the example.c encoder bundled in x264’s
  source code and tested encoding times with it. (You can find it here :
  https://gist.github.com/danilogr/ab4976ff4e0831ab274b)

  Average encoding time for the static scene is 38% bigger than for a scene
  with movements. (You can find my test case and also the output from my test
  encoder on the link above).

  ​​
  ​I’ve also noticed that by setting ​​scenecut=0, subme=0, trellis=0 and me=dia I can get rid of this problem​, but with noticeable quality​ decrease.

  ​
  ​Could anyone, please, shed some light on the reasons for this odd behavior ?
  ​Also, what can be done in order to avoid this situation without a major decrease in quality ?​

• How to stream RPI a RPI Cam with ffmpeg for 24/7 to youtube stable and reliable

  6 mai 2021, par John Paden

  As a part of a project to bird-watch, I use RPICam
(https://github.com/silvanmelchior/RPi_Cam_Web_Interface)
on an Pi4. Resolution is 854x480, 25 fps. Works fine, stable 24/7.

  


  To share the videos not only in the intranet but on youtube, I use ffmpeg.
Other infrastructure : 1GBLAN, high speed extenal network connection, pi has stable power supply (no yellow flashes).

  


  After a lot of reading and testing, this command line produces a bitrate of about 2500 kbits and a speed of 1.

  


  ffmpeg -hide_banner -i http://xx.xx.xx.xx/cam_pic_new.php -deinterlace -re -acodec pcm_s16le -ac 2 -f s16le -i /dev/zero -f h264_omx -c:a aac -ar 48000 -ac 2 -b:a 384k -c:v h264_omx -b:v 2.5M -profile:v high -force_key_frames "expr:gte(t,n_forced/2)" -s 854x480 -pix_fmt yuv420p -strict experimental -use_editlist 0 -movflags +faststart -f flv rtmp ://a.rtmp.youtube.com/live2/xxx-xxx-xxx-xxx-xxx

  


  IF it starts correctly. As Youtube rules suggest to limit streams to under 24h to keep them, a regular reset of the tream - or the pi - is required.
On the youtube side this is controlled by
Often a restart (no matter of a "sudo restart" or just a restart of the ffmpeg command) results in youtube studio showing a green button (Stream status very good) and a second green button (Very good connection). But instead, the circle turns around ongoingly and it states 'Streaming Software can be connected now, viewers can find the stream once it has started'.
In short - how does youtube understand to start the transmission, or to reset if it still some sort of busy ?