Chromium Code Reviews
chromiumcodereview-hr@appspot.gserviceaccount.com (chromiumcodereview-hr) | Please choose your nickname with Settings | Help | Chromium Project | Gerrit Changes | Sign out
(839)

Unified Diff: webrtc/modules/video_coding/codecs/h264/h264_encoder_impl.cc

Issue 1306813009: H.264 video codec support using OpenH264/FFmpeg (Closed) Base URL: https://chromium.googlesource.com/external/webrtc.git@master
Patch Set: Misc (WebRtcVideoChannel2::...::ConfigureVideoEncoderSettings care about H264 case) Created 5 years, 3 months ago
Use n/p to move between diff chunks; N/P to move between comments. Draft comments are only viewable by you.
Jump to:
View side-by-side diff with in-line comments
Download patch
Index: webrtc/modules/video_coding/codecs/h264/h264_encoder_impl.cc
diff --git a/webrtc/modules/video_coding/codecs/h264/h264_encoder_impl.cc b/webrtc/modules/video_coding/codecs/h264/h264_encoder_impl.cc
new file mode 100644
index 0000000000000000000000000000000000000000..1ab15d301ef74da462ee48d9c380740ede33a3eb
--- /dev/null
+++ b/webrtc/modules/video_coding/codecs/h264/h264_encoder_impl.cc
@@ -0,0 +1,372 @@
+/*
+ * Copyright (c) 2015 The WebRTC project authors. All Rights Reserved.
+ *
+ * Use of this source code is governed by a BSD-style license
+ * that can be found in the LICENSE file in the root of the source
+ * tree. An additional intellectual property rights grant can be found
+ * in the file PATENTS. All contributing project authors may
+ * be found in the AUTHORS file in the root of the source tree.
+ *
+ */
+
+#include "webrtc/modules/video_coding/codecs/h264/h264_encoder_impl.h"
+
+// OpenH264
+#include "codec_api.h"
+#include "codec_app_def.h"
+#include "codec_def.h"
+
+#include "webrtc/base/checks.h"
+#include "webrtc/base/logging.h"
+#include "webrtc/common_video/libyuv/include/webrtc_libyuv.h"
+
+namespace webrtc {
+
+namespace {
+const bool OPENH264_ENCODER_LOGGING = false;
+} // anonymous namespace
+
+static VideoFrameType EVideoFrameType_to_VideoFrameType(
+ const EVideoFrameType& type) {
stefan-webrtc 2015/09/28 11:19:02 You should be able to pass this by value since it'
hbos 2015/09/30 15:35:18 Done.
+ switch (type) {
+ case videoFrameTypeInvalid:
+ case videoFrameTypeSkip:
+ return kSkipFrame;
stefan-webrtc 2015/09/28 11:19:02 I think we can send videoFrameTypeSkip as a kDelta
hbos 2015/09/30 15:35:18 I don't think the upper layers are notified at all
stefan-webrtc 2015/10/01 08:19:30 Well, kSkipFrame and an h.264 skip-encoded frame i
hbos 2015/10/01 12:19:45 Acknowledged.
+ case videoFrameTypeIDR:
noahric 2015/09/25 00:11:31 IDR == kKeyFrame, right? Also SPS/PPS are treated
stefan-webrtc 2015/09/28 11:19:02 Agree. videoFrameTypeI should however probably be
hbos 2015/09/28 11:33:20 An I-frame is a key frame, and all IDR-frames are
hbos 2015/09/30 15:35:18 @stefan: Ok, kDeltaFrame for videoFrameTypeI it is
+ case videoFrameTypeI:
+ case videoFrameTypeP:
+ case videoFrameTypeIPMixed:
+ return kDeltaFrame;
+ default:
+ LOG(LS_WARNING) << "Unknown EVideoFrameType: " << type;
+ return kDeltaFrame;
+ }
+}
+
+// Copies the encoded bytes from |info| to |encoded_image| and updates the
+// fragmentation information of |frag_header|.
+// After OpenH264 encoding, the encoded bytes are stored in |info| spread out
+// over a number of layers and "NAL units". Each NAL unit is a fragment starting
+// with the four-byte NAL header {0,0,0,1}. To save bytes, the NAL headers are
noahric 2015/09/25 00:11:31 It's up to you, but it's probably not worth stripp
noahric 2015/09/25 00:11:31 For clarity, I would avoid calling those NAL heade
hbos 2015/09/28 11:33:20 First comment: There are assumptions about the in
stefan-webrtc 2015/09/28 11:53:55 The RTP format for H264 specifies that start codes
hbos 2015/09/30 15:35:18 Oh I see, I misunderstood. I didn't considered not
+// excluded when copying to |encoded_image->_buffer|. However these headers must
+// be included for an H264Decoder to be able to decode the data.
+// When fragments are sent over a network, the receiving end must re-insert
+// the NAL headers before each fragment.
+// For image data encoded and decoded locally, RTPDefragmentize can be used
+// to convert (EncodedImage, RTPFragmentationHeader) with NAL headers excluded
+// to a decodable EncodedImage buffer with NAL headers included.
+static void RTPFragmentize(EncodedImage* encoded_image,
+ const VideoFrame& frame,
+ SFrameBSInfo* info,
+ RTPFragmentationHeader* frag_header) {
+ // Calculate minimum buffer size required to hold encoded data.
+ size_t required_size = 0;
+ for (int iLayer = 0; iLayer < info->iLayerNum; ++iLayer) {
+ const SLayerBSInfo& layerInfo = info->sLayerInfo[iLayer];
+ for (int iNal = 0; iNal < layerInfo.iNalCount; ++iNal) {
+ required_size += (layerInfo.pNalLengthInByte[iNal] - 4);
+ }
+ }
+ if (encoded_image->_size < required_size) {
+ // Increase buffer size. Allocate enough to hold an unencoded image, this
+ // should be more than enough to hold any encoded data of future frames of
+ // the same size (avoiding possible future reallocation due to variations in
+ // required size).
+ encoded_image->_size = CalcBufferSize(
+ VideoType::kI420, frame.width(), frame.height());
+ if (encoded_image->_size < required_size) {
+ // Encoded data > unencoded data, wtf? Allocate required bytes.
noahric 2015/09/25 00:11:31 Consider logging this. You're right, it's pretty W
hbos 2015/09/28 11:33:20 Done.
+ encoded_image->_size = required_size;
+ }
+ if (encoded_image->_buffer != nullptr)
+ delete[] encoded_image->_buffer;
noahric 2015/09/25 00:11:31 Consider storing the buffer separately and with sc
hbos 2015/09/28 11:33:20 Done.
+ encoded_image->_buffer = new uint8_t[encoded_image->_size];
+ }
+
+ // Iterate layers and NAL units, copy encoded data to |encoded_image->_buffer|
+ // and note each NAL unit as a fragment, excluding its NAL header.
+ encoded_image->_length = 0;
+ std::vector<int> frags;
+ for (int iLayer = 0; iLayer < info->iLayerNum; ++iLayer) {
+ int iLayerLen = 0;
+ const SLayerBSInfo& layerInfo = info->sLayerInfo[iLayer];
+ // Copy the layer data to |encoded_image->_buffer|, excluding the 4-byte
+ // NAL headers.
+ for (int iNal = 0; iNal < layerInfo.iNalCount; ++iNal) {
+ // Expecting NAL header constant {0,0,0,1}.
+ DCHECK_EQ(layerInfo.pBsBuf[iLayerLen+0], static_cast<unsigned char>(0));
+ DCHECK_EQ(layerInfo.pBsBuf[iLayerLen+1], static_cast<unsigned char>(0));
+ DCHECK_EQ(layerInfo.pBsBuf[iLayerLen+2], static_cast<unsigned char>(0));
+ DCHECK_EQ(layerInfo.pBsBuf[iLayerLen+3], static_cast<unsigned char>(1));
+
+ memcpy(encoded_image->_buffer + encoded_image->_length,
+ layerInfo.pBsBuf + iLayerLen + 4,
stefan-webrtc 2015/09/28 11:19:02 Do you know if these layers are stored in one chun
hbos 2015/09/30 15:35:18 Done.
+ (layerInfo.pNalLengthInByte[iNal] - 4) * sizeof(unsigned char));
+ encoded_image->_length += (layerInfo.pNalLengthInByte[iNal] - 4);
+ frags.push_back(layerInfo.pNalLengthInByte[iNal] - 4);
+
+ iLayerLen += layerInfo.pNalLengthInByte[iNal];
+ }
+ }
+
+ frag_header->VerifyAndAllocateFragmentationHeader(frags.size());
+ for (size_t i = 0, off = 0; i < frags.size(); ++i) {
+ frag_header->fragmentationOffset[i] = off;
+ frag_header->fragmentationLength[i] = frags[i];
+ off += frags[i];
stefan-webrtc 2015/09/28 11:19:02 frags -> fragments off -> offset
hbos 2015/09/30 15:35:18 Done.
+ }
+}
+
+void H264EncoderImpl::RTPDefragmentize(
stefan-webrtc 2015/09/28 11:19:02 Is this a test function? In that case I would move
hbos 2015/09/30 15:35:18 (Removed, no longer needed due to including start
+ const EncodedImage& encoded_image,
+ const RTPFragmentationHeader* frag_header,
+ uint8_t* enc_buffer_with_nal, size_t enc_buffer_with_nal_length) {
+ DCHECK_GE(enc_buffer_with_nal_length,
+ RTPDefragmentizeBufferLengthWithNAL(encoded_image, frag_header));
+ const unsigned char nal_header[] = { 0, 0, 0, 1 };
+ for (size_t i = 0; i < frag_header->fragmentationVectorSize; ++i) {
+ DCHECK_LE(frag_header->fragmentationOffset[i] +
+ frag_header->fragmentationLength[i],
+ encoded_image._length);
+
+ // Insert a NAL header constant {0,0,0,1}.
+ memcpy(enc_buffer_with_nal, nal_header, 4);
+ // Copy fragment data.
+ memcpy(enc_buffer_with_nal + 4,
+ encoded_image._buffer + frag_header->fragmentationOffset[i],
+ frag_header->fragmentationLength[i]);
+
+ enc_buffer_with_nal += (4 + frag_header->fragmentationLength[i]);
+ }
+}
+
+size_t H264EncoderImpl::RTPDefragmentizeBufferLengthWithNAL(
stefan-webrtc 2015/09/28 11:19:02 Same with this.
hbos 2015/09/30 15:35:18 (Removed, no longer needed due to including start
+ const EncodedImage& encoded_image,
+ const webrtc::RTPFragmentationHeader* frag_header) {
+ return encoded_image._length +
+ 4 * static_cast<size_t>(frag_header->fragmentationVectorSize);
+}
+
+H264EncoderImpl::H264EncoderImpl()
+ : openh264_encoder_(nullptr),
+ encoded_image_callback_(nullptr) {
+}
+
+H264EncoderImpl::~H264EncoderImpl() {
+ Release();
+}
+
+int32_t H264EncoderImpl::InitEncode(const VideoCodec* codec_settings,
+ int32_t /*number_of_cores*/,
+ size_t /*max_payload_size*/) {
+ if (!codec_settings ||
+ codec_settings->codecType != VideoCodecType::kVideoCodecH264) {
+ return WEBRTC_VIDEO_CODEC_ERR_PARAMETER;
+ }
+ if (codec_settings->maxFramerate == 0)
+ return WEBRTC_VIDEO_CODEC_ERR_PARAMETER;
+ if (codec_settings->width < 1 || codec_settings->height < 1)
+ return WEBRTC_VIDEO_CODEC_ERR_PARAMETER;
+
+ int release_ret = Release();
+ if (release_ret != WEBRTC_VIDEO_CODEC_OK)
+ return release_ret;
+ DCHECK(!openh264_encoder_);
+
+ // Create encoder.
+ if (WelsCreateSVCEncoder(&openh264_encoder_) != 0) {
+ // Failed to create encoder.
+ LOG(LS_ERROR) << "Failed to create OpenH264 encoder";
+ DCHECK(!openh264_encoder_);
+ return WEBRTC_VIDEO_CODEC_ERROR;
+ }
+ DCHECK(openh264_encoder_);
+ if (&codec_settings_ != codec_settings)
noahric 2015/09/25 00:11:31 This won't ever be false, will it?
hbos 2015/09/28 11:33:20 You're right. Fixed.
+ codec_settings_ = *codec_settings;
+
+ if (codec_settings_.targetBitrate == 0)
+ codec_settings_.targetBitrate = codec_settings_.startBitrate;
+
+ // Note: H264 codec specifics are ignored:
+ // - codec_settings->codecSpecific.H264.frameDroppingOn
stefan-webrtc 2015/09/28 11:19:02 Have you taken a look to see if it's possible to c
hbos 2015/09/30 15:35:18 Done.
+ // - codec_settings->codecSpecific.H264.keyFrameInterval
noahric 2015/09/25 00:11:31 Assuming it's set, you don't really want to skip i
stefan-webrtc 2015/09/28 11:19:02 Agree, we should use this.
hbos 2015/09/28 11:33:20 I don't know what to do with these. I believe the
hbos 2015/09/30 15:35:18 Using them both now to set SEncParamExt's bEnableF
+
+ // Initialization parameters.
+ // There are two ways to initialize. There is SEncParamBase (cleared with
+ // memset(&p, 0, sizeof(SEncParamBase)) used in Initialize, and SEncParamExt
+ // which is a superset of SEncParamBase (cleared with GetDefaultParams) used
+ // in InitializeExt. We use SEncParamBase/Initialize.
stefan-webrtc 2015/09/28 11:19:02 Is there a reason why we use those? I think we sh
hbos 2015/09/30 15:35:18 Using SEncParamExt now. iMultileThreadIdc set to a
+ SEncParamBase init_params;
+ memset(&init_params, 0, sizeof(SEncParamBase));
+ if (codec_settings_.mode == kRealtimeVideo) {
+ init_params.iUsageType = CAMERA_VIDEO_REAL_TIME;
+ } else if (codec_settings_.mode == kScreensharing) {
+ init_params.iUsageType = SCREEN_CONTENT_REAL_TIME;
+ } else {
+ return WEBRTC_VIDEO_CODEC_ERR_PARAMETER;
+ }
+ init_params.iPicWidth = codec_settings_.width;
+ init_params.iPicHeight = codec_settings_.height;
+ // iTargetBitrate is in bit/s, targetBitrate is in kbit/s.
+ init_params.iTargetBitrate = codec_settings_.targetBitrate * 1000;
+ // Rate Control mode
+ init_params.iRCMode = RC_QUALITY_MODE;
stefan-webrtc 2015/09/28 11:19:02 I suspect a better choice would be RC_BITRATE_MODE
hbos 2015/09/30 15:35:18 I've noticed that you get really laggy video if th
stefan-webrtc 2015/10/01 08:19:30 I think RC_BITRATE_MODE makes more sense actually.
hbos 2015/10/01 12:19:45 Acknowledged. Removed TODO comment.
+ init_params.fMaxFrameRate = static_cast<float>(codec_settings_.maxFramerate);
noahric 2015/09/25 00:11:31 Not sure how to set these, but there are few other
stefan-webrtc 2015/09/28 11:19:02 CABAC must be false since we only support baseline
hbos 2015/09/28 11:33:20 Those parameters are available if SEncParamExt is
stefan-webrtc 2015/09/28 11:53:55 I think automatic is better. There is no reason th
hbos 2015/09/30 15:35:18 Using keyFrameInterval to set uiIntraPeriod.
+
+ // Initialize.
+ if (openh264_encoder_->Initialize(&init_params) != 0) {
+ // Failed to initialize.
stefan-webrtc 2015/09/28 11:19:02 No need for this comment.
hbos 2015/09/30 15:35:18 Done.
+ LOG(LS_ERROR) << "Failed to initialize OpenH264 encoder";
+ Release();
+ return WEBRTC_VIDEO_CODEC_ERROR;
+ }
+ if (OPENH264_ENCODER_LOGGING) {
+ int trace_level = WELS_LOG_DETAIL;
+ openh264_encoder_->SetOption(ENCODER_OPTION_TRACE_LEVEL,
+ &trace_level);
noahric 2015/09/25 00:11:31 What's the default? If nothing, then consider sett
hbos 2015/09/28 11:33:20 It has a default value it uses, WELS_LOG_DEFAULT (
+ }
+
+ // Initialize encoded image.
+ // Default buffer size: size of unencoded data (should be large enough).
+ encoded_image_._size = CalcBufferSize(
+ VideoType::kI420, codec_settings_.width, codec_settings_.height);
+ encoded_image_._buffer = new uint8_t[encoded_image_._size];
+ encoded_image_._completeFrame = true;
+ encoded_image_._encodedWidth = 0;
+ encoded_image_._encodedHeight = 0;
+ encoded_image_._length = 0;
+ return WEBRTC_VIDEO_CODEC_OK;
+}
+
+int32_t H264EncoderImpl::Release() {
+ if (openh264_encoder_) {
+ int uninit_ret = openh264_encoder_->Uninitialize();
+ if (uninit_ret != 0) {
+ LOG(LS_WARNING) << "OpenH264 encoder's Uninitialize() returned "
+ << "unsuccessful: " << uninit_ret;
+ }
+ WelsDestroySVCEncoder(openh264_encoder_);
+ openh264_encoder_ = nullptr;
+ }
+ if (encoded_image_._buffer != nullptr) {
+ delete[] encoded_image_._buffer;
+ encoded_image_._buffer = nullptr;
+ }
+ return WEBRTC_VIDEO_CODEC_OK;
+}
+
+int32_t H264EncoderImpl::RegisterEncodeCompleteCallback(
+ EncodedImageCallback* callback) {
+ encoded_image_callback_ = callback;
+ return WEBRTC_VIDEO_CODEC_OK;
+}
+
+int32_t H264EncoderImpl::SetRates(uint32_t bitrate, uint32_t framerate) {
+ if (bitrate <= 0 || framerate <= 0) {
+ return WEBRTC_VIDEO_CODEC_ERR_PARAMETER;
+ }
+ codec_settings_.targetBitrate = bitrate;
+ codec_settings_.maxFramerate = framerate;
+ return WEBRTC_VIDEO_CODEC_OK;
+}
+
+int32_t H264EncoderImpl::Encode(
+ const VideoFrame& frame, const CodecSpecificInfo* codec_specific_info,
+ const std::vector<VideoFrameType>* frame_types) {
+ if (!IsInitialized())
+ return WEBRTC_VIDEO_CODEC_UNINITIALIZED;
+ if (frame.IsZeroSize())
+ return WEBRTC_VIDEO_CODEC_ERR_PARAMETER;
+ if (!encoded_image_callback_) {
+ LOG(LS_WARNING) << "InitEncode() has been called, but a callback function "
+ << "has not been set with RegisterEncodeCompleteCallback()";
+ return WEBRTC_VIDEO_CODEC_UNINITIALIZED;
+ }
+
+ // Make |codec_settings_|'s size reflect the latest frame's size.
+ if (codec_settings_.width != frame.width() ||
noahric 2015/09/25 00:11:31 That won't be right if simulcast is used, will it?
hbos 2015/09/28 11:33:20 Sorry, I'm not sure I follow your simulcast commen
+ codec_settings_.height != frame.height()) {
+ codec_settings_.width = frame.width();
+ codec_settings_.height = frame.height();
+ }
+
+ // Set encoder options.
+ int video_format = EVideoFormatType::videoFormatI420;
+ openh264_encoder_->SetOption(ENCODER_OPTION_DATAFORMAT,
+ &video_format);
+ SBitrateInfo target_bitrate;
+ memset(&target_bitrate, 0, sizeof(SBitrateInfo));
+ target_bitrate.iLayer = SPATIAL_LAYER_ALL,
+ target_bitrate.iBitrate = codec_settings_.targetBitrate * 1000;
+ openh264_encoder_->SetOption(ENCODER_OPTION_BITRATE,
+ &target_bitrate);
noahric 2015/09/25 00:11:31 Why not just set these in SetRates?
hbos 2015/09/28 11:33:20 Done.
+ float max_framerate = static_cast<float>(codec_settings_.maxFramerate);
+ openh264_encoder_->SetOption(ENCODER_OPTION_FRAME_RATE,
+ &max_framerate);
+
+ // EncodeFrame input.
+ SSourcePicture picture;
+ memset(&picture, 0, sizeof(SSourcePicture));
+ picture.iPicWidth = frame.width();
+ picture.iPicHeight = frame.height();
+ picture.iColorFormat = video_format;
+ picture.uiTimeStamp = frame.timestamp();
+ picture.iStride[0] = frame.stride(kYPlane);
+ picture.iStride[1] = frame.stride(kUPlane);
+ picture.iStride[2] = frame.stride(kVPlane);
+ picture.pData[0] = const_cast<uint8_t*>(frame.buffer(kYPlane));
+ picture.pData[1] = const_cast<uint8_t*>(frame.buffer(kUPlane));
+ picture.pData[2] = const_cast<uint8_t*>(frame.buffer(kVPlane));
+
+ // EncodeFrame output.
+ SFrameBSInfo info;
+ memset(&info, 0, sizeof(SFrameBSInfo));
+
+ // Encode!
+ if (openh264_encoder_->EncodeFrame(&picture, &info) != 0) {
noahric 2015/09/25 00:11:30 It's probably worth capturing the return and loggi
hbos 2015/09/28 11:33:20 Done.
+ LOG(LS_ERROR) << "OpenH264 frame encoding failed (EncodeFrame)";
+ return WEBRTC_VIDEO_CODEC_ERROR;
+ }
+
+ encoded_image_._encodedWidth = frame.width();
+ encoded_image_._encodedHeight = frame.height();
+ encoded_image_._timeStamp = frame.timestamp();
+ encoded_image_.capture_time_ms_ = frame.render_time_ms();
+ encoded_image_._frameType = EVideoFrameType_to_VideoFrameType(
+ info.eFrameType);
+
+ // Split encoded image up into fragments. This also updates |encoded_image_|.
+ RTPFragmentationHeader frag_header;
+ RTPFragmentize(&encoded_image_, frame, &info, &frag_header);
+
+ // Encoder can skip frames to save bandwidth in which case
+ // |encoded_image_._length| == 0.
+ if (encoded_image_._length > 0) {
+ // Deliver encoded image.
+ encoded_image_callback_->Encoded(encoded_image_, codec_specific_info,
+ &frag_header);
+ }
+ return WEBRTC_VIDEO_CODEC_OK;
+}
+
+bool H264EncoderImpl::IsInitialized() {
+ return openh264_encoder_ != nullptr;
+}
+
+int32_t H264EncoderImpl::SetChannelParameters(
+ uint32_t packet_loss, int64_t rtt) {
+ return WEBRTC_VIDEO_CODEC_OK;
+}
+
+int32_t H264EncoderImpl::SetPeriodicKeyFrames(bool enable) {
+ return WEBRTC_VIDEO_CODEC_OK;
+}
+
+int32_t H264EncoderImpl::CodecConfigParameters(uint8_t* buffer, int32_t size) {
+ return WEBRTC_VIDEO_CODEC_OK;
+}
+
+void H264EncoderImpl::OnDroppedFrame() {
+}
+
+} // namespace webrtc

Powered by Google App Engine
This is Rietveld 408576698