webrtc/video_encoder.h

/*
 *  Copyright (c) 2014 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.
 */

#ifndef WEBRTC_VIDEO_ENCODER_H_
#define WEBRTC_VIDEO_ENCODER_H_

#include <memory>
#include <string>
#include <vector>

#include "webrtc/common_types.h"
#include "webrtc/typedefs.h"
#include "webrtc/video_frame.h"

namespace webrtc {

class RTPFragmentationHeader;
// TODO(pbos): Expose these through a public (root) header or change these APIs.
struct CodecSpecificInfo;
struct VideoCodec;

class EncodedImageCallback {
 public:
  virtual ~EncodedImageCallback() {}

  struct Result {
    enum Error {
      OK,

      // Failed to send the packet.
      ERROR_SEND_FAILED,
    };

    Result(Error error) : error(error) {}
    Result(Error error, uint32_t frame_id) : error(error), frame_id(frame_id) {}

    Error error;

    // Frame ID assigned to the frame. The frame ID should be the same as the ID
    // seen by the receiver for this frame. RTP timestamp of the frame is used
    // as frame ID when RTP is used to send video. Must be used only when
    // error=OK.
    uint32_t frame_id = 0;

    // Tells the encoder that the next frame is should be dropped.
    bool drop_next_frame = false;
  };

  // Callback function which is called when an image has been encoded.
  virtual Result OnEncodedImage(const EncodedImage& encoded_image,
                                const CodecSpecificInfo* codec_specific_info,
                                const RTPFragmentationHeader* fragmentation) {
    return (Encoded(encoded_image, codec_specific_info, fragmentation) == 0)
               ? Result(Result::OK, 0)
               : Result(Result::ERROR_SEND_FAILED);
  }

  // DEPRECATED.
  // TODO(sergeyu): Remove this method.
  virtual int32_t Encoded(const EncodedImage& encoded_image,
                          const CodecSpecificInfo* codec_specific_info,
                          const RTPFragmentationHeader* fragmentation) {
    Result result =
        OnEncodedImage(encoded_image, codec_specific_info, fragmentation);
    return (result.error != Result::OK) ? -1 : (result.drop_next_frame ? 1 : 0);
  }
};

class VideoEncoder {
 public:
  enum EncoderType {
    kH264,
    kVp8,
    kVp9,
    kUnsupportedCodec,
  };

  static VideoEncoder* Create(EncoderType codec_type);

  static VideoCodecVP8 GetDefaultVp8Settings();
  static VideoCodecVP9 GetDefaultVp9Settings();
  static VideoCodecH264 GetDefaultH264Settings();

  virtual ~VideoEncoder() {}

  // Initialize the encoder with the information from the codecSettings
  //
  // Input:
  //          - codec_settings    : Codec settings
  //          - number_of_cores   : Number of cores available for the encoder
  //          - max_payload_size  : The maximum size each payload is allowed
  //                                to have. Usually MTU - overhead.
  //
  // Return value                  : Set bit rate if OK
  //                                 <0 - Errors:
  //                                  WEBRTC_VIDEO_CODEC_ERR_PARAMETER
  //                                  WEBRTC_VIDEO_CODEC_ERR_SIZE
  //                                  WEBRTC_VIDEO_CODEC_LEVEL_EXCEEDED
  //                                  WEBRTC_VIDEO_CODEC_MEMORY
  //                                  WEBRTC_VIDEO_CODEC_ERROR
  virtual int32_t InitEncode(const VideoCodec* codec_settings,
                             int32_t number_of_cores,
                             size_t max_payload_size) = 0;

  // Register an encode complete callback object.
  //
  // Input:
  //          - callback         : Callback object which handles encoded images.
  //
  // Return value                : WEBRTC_VIDEO_CODEC_OK if OK, < 0 otherwise.
  virtual int32_t RegisterEncodeCompleteCallback(
      EncodedImageCallback* callback) = 0;

  // Free encoder memory.
  // Return value                : WEBRTC_VIDEO_CODEC_OK if OK, < 0 otherwise.
  virtual int32_t Release() = 0;

  // Encode an I420 image (as a part of a video stream). The encoded image
  // will be returned to the user through the encode complete callback.
  //
  // Input:
  //          - frame             : Image to be encoded
  //          - frame_types       : Frame type to be generated by the encoder.
  //
  // Return value                 : WEBRTC_VIDEO_CODEC_OK if OK
  //                                <0 - Errors:
  //                                  WEBRTC_VIDEO_CODEC_ERR_PARAMETER
  //                                  WEBRTC_VIDEO_CODEC_MEMORY
  //                                  WEBRTC_VIDEO_CODEC_ERROR
  //                                  WEBRTC_VIDEO_CODEC_TIMEOUT
  virtual int32_t Encode(const VideoFrame& frame,
                         const CodecSpecificInfo* codec_specific_info,
                         const std::vector<FrameType>* frame_types) = 0;

  // Inform the encoder of the new packet loss rate and the round-trip time of
  // the network.
  //
  // Input:
  //          - packet_loss : Fraction lost
  //                          (loss rate in percent = 100 * packetLoss / 255)
  //          - rtt         : Round-trip time in milliseconds
  // Return value           : WEBRTC_VIDEO_CODEC_OK if OK
  //                          <0 - Errors: WEBRTC_VIDEO_CODEC_ERROR
  virtual int32_t SetChannelParameters(uint32_t packet_loss, int64_t rtt) = 0;

  // Inform the encoder about the new target bit rate.
  //
  // Input:
  //          - bitrate         : New target bit rate
  //          - framerate       : The target frame rate
  //
  // Return value                : WEBRTC_VIDEO_CODEC_OK if OK, < 0 otherwise.
  virtual int32_t SetRates(uint32_t bitrate, uint32_t framerate) = 0;

  virtual int32_t SetPeriodicKeyFrames(bool enable) { return -1; }
  virtual void OnDroppedFrame() {}
  virtual bool SupportsNativeHandle() const { return false; }
  virtual const char* ImplementationName() const { return "unknown"; }
};

// Class used to wrap external VideoEncoders to provide a fallback option on
// software encoding when a hardware encoder fails to encode a stream due to
// hardware restrictions, such as max resolution.
class VideoEncoderSoftwareFallbackWrapper : public VideoEncoder {
 public:
  VideoEncoderSoftwareFallbackWrapper(VideoCodecType codec_type,
                                      webrtc::VideoEncoder* encoder);

  int32_t InitEncode(const VideoCodec* codec_settings,
                     int32_t number_of_cores,
                     size_t max_payload_size) override;

  int32_t RegisterEncodeCompleteCallback(
      EncodedImageCallback* callback) override;

  int32_t Release() override;
  int32_t Encode(const VideoFrame& frame,
                 const CodecSpecificInfo* codec_specific_info,
                 const std::vector<FrameType>* frame_types) override;
  int32_t SetChannelParameters(uint32_t packet_loss, int64_t rtt) override;

  int32_t SetRates(uint32_t bitrate, uint32_t framerate) override;
  void OnDroppedFrame() override;
  bool SupportsNativeHandle() const override;
  const char* ImplementationName() const override;

 private:
  bool InitFallbackEncoder();

  // Settings used in the last InitEncode call and used if a dynamic fallback to
  // software is required.
  VideoCodec codec_settings_;
  int32_t number_of_cores_;
  size_t max_payload_size_;

  // The last bitrate/framerate set, and a flag for noting they are set.
  bool rates_set_;
  uint32_t bitrate_;
  uint32_t framerate_;

  // The last channel parameters set, and a flag for noting they are set.
  bool channel_parameters_set_;
  uint32_t packet_loss_;
  int64_t rtt_;

  const EncoderType encoder_type_;
  webrtc::VideoEncoder* const encoder_;

  std::unique_ptr<webrtc::VideoEncoder> fallback_encoder_;
  std::string fallback_implementation_name_;
  EncodedImageCallback* callback_;
};
}  // namespace webrtc
#endif  // WEBRTC_VIDEO_ENCODER_H_