Recherche avancée

Sur d’autres sites (7080)

• lavfi/dnn_classify : add filter dnn_classify for classification based on detection...

  17 mars 2021, par Guo, Yejun

  lavfi/dnn_classify : add filter dnn_classify for classification based on detection bounding boxes
  classification is done on every detection bounding box in frame's side data,
  
  which are the results of object detection (filter dnn_detect).
  Please refer to commit log of dnn_detect for the material for detection,
  
  and see below for classification.
   download material for classifcation :
  
  wget https://github.com/guoyejun/ffmpeg_dnn/raw/main/models/openvino/2021.1/emotions-recognition-retail-0003.bin
  
  wget https://github.com/guoyejun/ffmpeg_dnn/raw/main/models/openvino/2021.1/emotions-recognition-retail-0003.xml
  
  wget https://github.com/guoyejun/ffmpeg_dnn/raw/main/models/openvino/2021.1/emotions-recognition-retail-0003.label
   run command as :
  
  ./ffmpeg -i cici.jpg -vf dnn_detect=dnn_backend=openvino:model=face-detection-adas-0001.xml:input=data:output=detection_out:confidence=0.6:labels=face-detection-adas-0001.label,dnn_classify=dnn_backend=openvino:model=emotions-recognition-retail-0003.xml:input=data:output=prob_emotion:confidence=0.3:labels=emotions-recognition-retail-0003.label:target=face,showinfo -f null -
  We'll see the detect&classify result as below :
  
  [Parsed_showinfo_2 @ 0x55b7d25e77c0]   side data - detection bounding boxes :
  
  [Parsed_showinfo_2 @ 0x55b7d25e77c0] source : face-detection-adas-0001.xml, emotions-recognition-retail-0003.xml
  
  [Parsed_showinfo_2 @ 0x55b7d25e77c0] index : 0,  region : (1005, 813) -> (1086, 905), label : face, confidence : 10000/10000.
  
  [Parsed_showinfo_2 @ 0x55b7d25e77c0]            classify :  label : happy, confidence : 6757/10000.
  
  [Parsed_showinfo_2 @ 0x55b7d25e77c0] index : 1,  region : (888, 839) -> (967, 926), label : face, confidence : 6917/10000.
  
  [Parsed_showinfo_2 @ 0x55b7d25e77c0]            classify :  label : anger, confidence : 4320/10000.
  Signed-off-by : Guo, Yejun <yejun.guo@intel.com>
  

  • [DH] configure
  • [DH] doc/filters.texi
  • [DH] libavfilter/Makefile
  • [DH] libavfilter/allfilters.c
  • [DH] libavfilter/vf_dnn_classify.c

• Evolution #2923 : Remplacement d’un document et date du document

  21 mars 2013, par - Equipement

  Bonjour, Les rédacteurs en question disposent de la possibilité manuelle de modifier la date de chaque document. Ils souhaitent que, lorsqu’ils remplacent un document par une version plus récente, la date du document soit automatiquement modifiée (avec la date du dépôt de la dernière version). (...)

• ffmpeg streaming simultaneously synchronized delay to multiple social networks

  4 avril 2021, par Jintor

  I'm able to stream simultaneously using ffmpeg to youtube, twitter, facebook, twitch ... simultaneously BUT the issue is the following : each network have their own delay

  


  in 1 network : 15 seconds delay, an other : 10 seconds delay, etc

  


  I tried 2 different ways

  


  • 1 ffmpeg per network => Signal is strong and stable

  


  • 1 ffmpeg with tee muxer to many at once => horrible, unstable, 1 network accepts it and some other says signal poor or too low bitrate...

  


  ----------- for example I use this for each social network ------------------------------

  


  /usr/bin/ffmpeg -re -i input.mp4 -deinterlace -c:v libx264 -pix_fmt yuv420p 
-preset veryfast -tune zerolatency -c:a aac -b:a 128k -ac 2 -crf 18 -r 30 -g 60  
-b:v 2369k -minrate 2369k -maxrate 2369k -ar 44100 -qscale:v 2 -vf "scale=-2:1080" 
-profile:v main -bufsize 2369k -f flv "rtmp://a.rtmp.youtube.com/live2/key"


  


  ---

  


  


  • I know that it's a case by case basis and not easy to do, but Is there a way to "fake" a delay with ffmpeg (like youtube->x delay, facebook-> y delay, etc) ?

    


  


  • or is there any synchronizing mechanism or timing option in ffmpeg ?

    


  


  • or any other approach ?