Recherche avancée

Sur d’autres sites (233)

• Text recognition from each frame of long Video Stream [closed]

  19 mars 2020, par Shashikant Sharma

  I am a naive android app developer who comes from reactJS background and it’s my First project in android. I have a requirement to develop an android app that needs to capture all of time intervals at which a particular text appears in the video stream. Actually I am not able to find the approach in order to proceed for the app development. I know it sounds stupid to post such a question on such portal but I am not asking for any source code or link to GitHub repo.
  (NOTE : Video stream would be 30min+ log and Text that needs to be recognized would appear at a fixed position in the video).

• How can I develop Image recognition program

  18 juillet 2017, par SeongHyun Lee

  My program will recognize the advertisement between each TV Programs.
  But I don’t know how to recognize the ads.
  I had Sound Recognition in mind but It’s so difficult.
  I’m using FFmpeg Library.
  There is VideoState struct Reference.

  typedef struct VideoState {
  
  SDL_Thread *read_tid;
  
  SDL_Thread *video_tid;
  
  SDL_Thread *refresh_tid;
  
  AVInputFormat *iformat;
  
  int no_background;
  
  int abort_request;
  
  int force_refresh;
  
  int paused;
  
  int last_paused;
  
  int que_attachments_req;
  
  int seek_req;
  
  int seek_flags;
  
  int64_t seek_pos;
  
  int64_t seek_rel;
  
  int read_pause_return;
  
  AVFormatContext *ic;
  
  
  
  int audio_stream;
  
  
  
  int av_sync_type;
  
  double external_clock; /* external clock base */
  
  int64_t external_clock_time;
  
  
  
  double audio_clock;
  
  double audio_diff_cum; /* used for AV difference average computation */
  
  double audio_diff_avg_coef;
  
  double audio_diff_threshold;
  
  int audio_diff_avg_count;
  
  AVStream *audio_st;
  
  PacketQueue audioq;
  
  int audio_hw_buf_size;
  
  DECLARE_ALIGNED(16,uint8_t,audio_buf2)[AVCODEC_MAX_AUDIO_FRAME_SIZE * 4];
  
  uint8_t silence_buf[SDL_AUDIO_BUFFER_SIZE];
  
  uint8_t *audio_buf;
  
  uint8_t *audio_buf1;
  
  unsigned int audio_buf_size; /* in bytes */
  
  int audio_buf_index; /* in bytes */
  
  int audio_write_buf_size;
  
  AVPacket audio_pkt_temp;
  
  AVPacket audio_pkt;
  
  struct AudioParams audio_src;
  
  struct AudioParams audio_tgt;
  
  struct SwrContext *swr_ctx;
  
  double audio_current_pts;
  
  double audio_current_pts_drift;
  
  int frame_drops_early;
  
  int frame_drops_late;
  
  AVFrame *frame;
  
  
  
  enum ShowMode {
  
      SHOW_MODE_NONE = -1, SHOW_MODE_VIDEO = 0, SHOW_MODE_WAVES, 
  
  SHOW_MODE_RDFT, SHOW_MODE_NB
  
  } show_mode;
  
  int16_t sample_array[SAMPLE_ARRAY_SIZE];
  
  int sample_array_index;
  
  int last_i_start;
  
  RDFTContext *rdft;
  
  int rdft_bits;
  
  FFTSample *rdft_data;
  
  int xpos;
  
  
  
  SDL_Thread *subtitle_tid;
  
  int subtitle_stream;
  
  int subtitle_stream_changed;
  
  AVStream *subtitle_st;
  
  PacketQueue subtitleq;
  
  SubPicture subpq[SUBPICTURE_QUEUE_SIZE];
  
  int subpq_size, subpq_rindex, subpq_windex;
  
  SDL_mutex *subpq_mutex;
  
  SDL_cond *subpq_cond;
  
  
  
  double frame_timer;
  
  double frame_last_pts;
  
  double frame_last_duration;
  
  double frame_last_dropped_pts;
  
  double frame_last_returned_time;
  
  double frame_last_filter_delay;
  
  int64_t frame_last_dropped_pos;
  
  double video_clock;                          ///< pts of last decoded frame 
  
  / predicted pts of next decoded frame
  
  int video_stream;
  
  AVStream *video_st;
  
  PacketQueue videoq;
  
  double video_current_pts;                    ///< current displayed pts 
  
  (different from video_clock if frame fifos are used)
  
  double video_current_pts_drift;              ///< video_current_pts - time 
  
  (av_gettime) at which we updated video_current_pts - used to have running 
  
  video pts
  
  int64_t video_current_pos;                   ///< current displayed file pos
  
  VideoPicture pictq[VIDEO_PICTURE_QUEUE_SIZE];
  
  int pictq_size, pictq_rindex, pictq_windex;
  
  SDL_mutex *pictq_mutex;
  
  SDL_cond *pictq_cond;
  
  #if !CONFIG_AVFILTER
  
  struct SwsContext *img_convert_ctx;
  
  #endif
  
  
  
  char filename[1024];
  
  int width, height, xleft, ytop;
  
  int step;
  
  
  
  #if CONFIG_AVFILTER
  
  AVFilterContext *in_video_filter;           ///< the first filter in the 
  
  video chain
  
  AVFilterContext *out_video_filter;          ///< the last filter in the 
  
  video chain
  
  int use_dr1;
  
  FrameBuffer *buffer_pool;
  
  #endif
  
  
  
  int refresh;
  
  int last_video_stream, last_audio_stream, last_subtitle_stream;
  
  
  
  SDL_cond *continue_read_thread;
  
  
  
  enum V_Show_Mode v_show_mode;
  
  } VideoState;

  What can I use for My Program.... I really need your help.. Thank you !!!

• Encountered problems when trying to run the code of article "Compressed Video Action Recognition", beginner, need some guidance, thanks a lot

  27 décembre 2018, par Wonderful

  Here is the problem I encountered.
  enter image description here