[FFmpeg-devel] [PATCH] liavcodec: add bit-rate support to RoQ video encoder

[Victor Luchits <vluchits@gmail.com>]

The bitrate option (-b:v) can now be used to specify the bit rate
of the video stream of the RoQ encoder.

Original patch by Joseph Fenton aka Chilly Willy

Signed-off-by: Victor Luchits <vluchits@gmail.com>
---
  Changelog                |   1 +
  libavcodec/roqvideo.h    |   1 +
  libavcodec/roqvideodec.c |  16 ++++++
  libavcodec/roqvideoenc.c | 107 +++++++++++++++++++++++++++++++++++----
  libavcodec/version.h     |   2 +-
  5 files changed, 117 insertions(+), 10 deletions(-)

diff --git a/Changelog b/Changelog
index c40b6d08fd..6974312f9d 100644
--- a/Changelog
+++ b/Changelog
@@ -22,6 +22,7 @@ version <next>:
  - ffmpeg CLI -bsf option may now be used for input as well as output
  - ffmpeg CLI options may now be used as -/opt <path>, which is equivalent
    to -opt <contents of file <path>>
+- RoQ video bit rate option support
  
  version 6.1:
  - libaribcaption decoder
diff --git a/libavcodec/roqvideo.h b/libavcodec/roqvideo.h
index 2c2e42884d..6d30bcaada 100644
--- a/libavcodec/roqvideo.h
+++ b/libavcodec/roqvideo.h
@@ -43,6 +43,7 @@ typedef struct RoqContext {
      AVFrame *last_frame;
      AVFrame *current_frame;
      int width, height;
+    int key_frame;
  
      roq_cell cb2x2[256];
      roq_qcell cb4x4[256];
diff --git a/libavcodec/roqvideodec.c b/libavcodec/roqvideodec.c
index bfc69a65c9..b4ade3a43b 100644
--- a/libavcodec/roqvideodec.c
+++ b/libavcodec/roqvideodec.c
@@ -70,6 +70,7 @@ static void roqvideo_decode_frame(RoqContext *ri, GetByteContext *gb)
  
      chunk_start = bytestream2_tell(gb);
      xpos = ypos = 0;
+    ri->key_frame = 1;
  
      if (chunk_size > bytestream2_get_bytes_left(gb)) {
          av_log(ri->logctx, AV_LOG_ERROR, "Chunk does not fit in input buffer\n");
@@ -92,12 +93,14 @@ static void roqvideo_decode_frame(RoqContext *ri, GetByteContext *gb)
  
                  switch(vqid) {
                  case RoQ_ID_MOT:
+                    ri->key_frame = 0;
                      break;
                  case RoQ_ID_FCC: {
                      int byte = bytestream2_get_byte(gb);
                      mx = 8 - (byte >> 4) - ((signed char) (chunk_arg >> 8));
                      my = 8 - (byte & 0xf) - ((signed char) chunk_arg);
                      ff_apply_motion_8x8(ri, xp, yp, mx, my);
+                    ri->key_frame = 0;
                      break;
                  }
                  case RoQ_ID_SLD:
@@ -125,12 +128,14 @@ static void roqvideo_decode_frame(RoqContext *ri, GetByteContext *gb)
                          vqflg_pos--;
                          switch(vqid) {
                          case RoQ_ID_MOT:
+                            ri->key_frame = 0;
                              break;
                          case RoQ_ID_FCC: {
                              int byte = bytestream2_get_byte(gb);
                              mx = 8 - (byte >> 4) - ((signed char) (chunk_arg >> 8));
                              my = 8 - (byte & 0xf) - ((signed char) chunk_arg);
                              ff_apply_motion_4x4(ri, x, y, mx, my);
+                            ri->key_frame = 0;
                              break;
                          }
                          case RoQ_ID_SLD:
@@ -214,6 +219,17 @@ static int roq_decode_frame(AVCodecContext *avctx, AVFrame *rframe,
  
      if ((ret = av_frame_ref(rframe, s->current_frame)) < 0)
          return ret;
+
+    /* Keyframe when no MOT or FCC codes in frame */
+    if (s->key_frame) {
+        av_log(avctx, AV_LOG_VERBOSE, "\nFound keyframe!\n");
+        rframe->pict_type = AV_PICTURE_TYPE_I;
+        avpkt->flags |= AV_PKT_FLAG_KEY;
+    } else {
+        rframe->pict_type = AV_PICTURE_TYPE_P;
+        avpkt->flags &= ~AV_PKT_FLAG_KEY;
+    }
+
      *got_frame      = 1;
  
      /* shuffle frames */
diff --git a/libavcodec/roqvideoenc.c b/libavcodec/roqvideoenc.c
index 0933abf4f9..68ec9ec238 100644
--- a/libavcodec/roqvideoenc.c
+++ b/libavcodec/roqvideoenc.c
@@ -136,6 +136,8 @@ typedef struct RoqEncContext {
      struct ELBGContext *elbg;
      AVLFG randctx;
      uint64_t lambda;
+    uint64_t last_lambda;
+    int lambda_delta;
  
      motion_vect *this_motion4;
      motion_vect *last_motion4;
@@ -887,8 +889,9 @@ static int generate_new_codebooks(RoqEncContext *enc)
      return 0;
  }
  
-static int roq_encode_video(RoqEncContext *enc)
+static int roq_encode_video(AVCodecContext *avctx)
  {
+    RoqEncContext *const enc = avctx->priv_data;
      RoqTempData *const tempData = &enc->tmp_data;
      RoqContext *const roq = &enc->common;
      int ret;
@@ -910,14 +913,14 @@ static int roq_encode_video(RoqEncContext *enc)
  
      /* Quake 3 can't handle chunks bigger than 65535 bytes */
      if (tempData->mainChunkSize/8 > 65535 && enc->quake3_compat) {
-        if (enc->lambda > 100000) {
+        if (enc->lambda > 100000000) {
              av_log(roq->logctx, AV_LOG_ERROR, "Cannot encode video in Quake compatible form\n");
              return AVERROR(EINVAL);
          }
          av_log(roq->logctx, AV_LOG_ERROR,
                 "Warning, generated a frame too big for Quake (%d > 65535), "
-               "now switching to a bigger qscale value.\n",
-               tempData->mainChunkSize/8);
+               "now switching to a bigger qscale value (%d).\n",
+               tempData->mainChunkSize/8, (int)enc->lambda);
          enc->lambda *= 1.5;
          tempData->mainChunkSize = 0;
          memset(tempData->used_option, 0, sizeof(tempData->used_option));
@@ -931,6 +934,80 @@ static int roq_encode_video(RoqEncContext *enc)
  
      remap_codebooks(enc);
  
+    /* bit rate control code - could make encoding very slow */
+    if (avctx->bit_rate) {
+        /* a bit rate has been specified - try to match it */
+        int ftotal = (tempData->mainChunkSize / 8 + tempData->numCB2*6 + tempData->numCB4*4) * avctx->time_base.den * 8;
+        int64_t tol = avctx->bit_rate_tolerance;
+
+        /* tolerance > bit rate, set to 5% of the bit rate */
+        if (tol > avctx->bit_rate)
+            tol = avctx->bit_rate / 20;
+
+        av_log(roq->logctx, AV_LOG_VERBOSE,
+               "\nDesired bit rate (%d kbps), "
+               "Bit rate tolerance (%d), "
+               "Frame rate (%d)\n",
+               (int)avctx->bit_rate, (int)tol, avctx->time_base.den);
+
+        if (ftotal > (avctx->bit_rate + tol)) {
+            /* frame is too big - increase qscale */
+            if (enc->lambda > 100000000) {
+                av_log(roq->logctx, AV_LOG_ERROR, "\nCannot encode video at desired bitrate\n");
+                return AVERROR(EINVAL);
+            }
+            enc->lambda_delta = enc->lambda_delta <= 0 ? 1 : enc->lambda_delta < 65536 ? enc->lambda_delta*2 : 65536;
+            enc->last_lambda = enc->lambda;
+            enc->lambda += enc->lambda_delta;
+            av_log(roq->logctx, AV_LOG_INFO,
+                   "\nGenerated a frame too big for desired bit rate (%d kbps), "
+                   "now switching to a bigger qscale value (%d).\n",
+                   ftotal / 1000, (int)enc->lambda);
+            tempData->mainChunkSize = 0;
+            memset(tempData->used_option, 0, sizeof(tempData->used_option));
+            memset(tempData->codebooks.usedCB4, 0,
+                   sizeof(tempData->codebooks.usedCB4));
+            memset(tempData->codebooks.usedCB2, 0,
+                   sizeof(tempData->codebooks.usedCB2));
+
+            goto retry_encode;
+        } else if (ftotal < (avctx->bit_rate - tol)) {
+            /* frame is too small - decrease qscale */
+            if (enc->lambda <= 1) {
+                av_log(roq->logctx, AV_LOG_WARNING,
+                       "\nGenerated a frame too small for desired bit rate (%d kbps), "
+                       "qscale value cannot be lowered any further (%d).\n",
+                       ftotal / 1000, (int)enc->lambda);
+            } else if ((enc->lambda - enc->last_lambda) == 1) {
+                av_log(roq->logctx, AV_LOG_WARNING,
+                       "\nCannot find qscale that gives desired bit rate within desired tolerance, "
+                       "using lower bitrate (%d kbps) with higher qscale value (%d).\n",
+                       ftotal / 1000, (int)enc->lambda);
+            } else {
+                enc->lambda_delta = 0;
+                if (enc->lambda == enc->last_lambda) {
+                    enc->lambda >>= 1;
+                    enc->last_lambda = enc->lambda;
+                } else {
+                    enc->lambda = enc->last_lambda;
+                    //enc->lambda *= (float)(tempData->mainChunkSize * avctx->time_base.den) / avctx->bit_rate;
+                    av_log(roq->logctx, AV_LOG_INFO,
+                           "\nGenerated a frame too small for desired bit rate (%d kbps), "
+                           "reverting lambda and using smaller inc on qscale (%d).\n",
+                           ftotal / 1000, (int)enc->lambda);
+                }
+                tempData->mainChunkSize = 0;
+                memset(tempData->used_option, 0, sizeof(tempData->used_option));
+                memset(tempData->codebooks.usedCB4, 0,
+                       sizeof(tempData->codebooks.usedCB4));
+                memset(tempData->codebooks.usedCB2, 0,
+                       sizeof(tempData->codebooks.usedCB2));
+
+                goto retry_encode;
+            }
+        }
+    }
+
      write_codebooks(enc);
  
      reconstruct_and_encode_image(enc, roq->width, roq->height,
@@ -991,8 +1068,11 @@ static av_cold int roq_encode_init(AVCodecContext *avctx)
      roq->width  = avctx->width;
      roq->height = avctx->height;
  
+    enc->lambda = 2*ROQ_LAMBDA_SCALE;
      enc->framesSinceKeyframe = 0;
      enc->first_frame = 1;
+    enc->last_lambda = 1;
+    enc->lambda_delta = 0;
  
      roq->last_frame    = av_frame_alloc();
      roq->current_frame = av_frame_alloc();
@@ -1059,10 +1139,13 @@ static int roq_encode_frame(AVCodecContext *avctx, AVPacket *pkt,
  
      enc->frame_to_enc = frame;
  
-    if (frame->quality)
-        enc->lambda = frame->quality - 1;
-    else
-        enc->lambda = 2*ROQ_LAMBDA_SCALE;
+    if (avctx->bit_rate) {
+        /* no specific bit rate desired, use frame quality */
+        if (frame->quality)
+            enc->lambda = frame->quality - 1;
+        else
+            enc->lambda = 2*ROQ_LAMBDA_SCALE;
+    }
  
      /* 138 bits max per 8x8 block +
       *     256 codebooks*(6 bytes 2x2 + 4 bytes 4x4) + 8 bytes frame header */
@@ -1089,7 +1172,7 @@ static int roq_encode_frame(AVCodecContext *avctx, AVPacket *pkt,
      }
  
      /* Encode the actual frame */
-    ret = roq_encode_video(enc);
+    ret = roq_encode_video(avctx);
      if (ret < 0)
          return ret;
  
@@ -1115,6 +1198,11 @@ static const AVClass roq_class = {
      .version    = LIBAVUTIL_VERSION_INT,
  };
  
+static const FFCodecDefault roq_defaults[] = {
+    { "b",                "0" },
+    { NULL },
+};
+
  const FFCodec ff_roq_encoder = {
      .p.name               = "roqvideo",
      CODEC_LONG_NAME("id RoQ video"),
@@ -1129,4 +1217,5 @@ const FFCodec ff_roq_encoder = {
                                                          AV_PIX_FMT_NONE },
      .p.priv_class   = &roq_class,
      .caps_internal        = FF_CODEC_CAP_INIT_CLEANUP,
+    .defaults             = roq_defaults,
  };
diff --git a/libavcodec/version.h b/libavcodec/version.h
index 376388c5bb..581151cda7 100644
--- a/libavcodec/version.h
+++ b/libavcodec/version.h
@@ -30,7 +30,7 @@
  #include "version_major.h"
  
  #define LIBAVCODEC_VERSION_MINOR  37
-#define LIBAVCODEC_VERSION_MICRO 100
+#define LIBAVCODEC_VERSION_MICRO 101
  
  #define LIBAVCODEC_VERSION_INT  AV_VERSION_INT(LIBAVCODEC_VERSION_MAJOR, \
                                                 LIBAVCODEC_VERSION_MINOR, \
-- 
2.25.1

_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel

To unsubscribe, visit link above, or email
ffmpeg-devel-request@ffmpeg.org with subject "unsubscribe".