将RTSP流录制为mp4文件

录制程序要继续添加新功能：模拟电视，板卡发送出来的是rtsp流（h264视频+alaw(pcma)音频）。

由于之前做过将rtp流（h264视频+aac音频）录制合成mp4文件（参见http://www.cnblogs.com/chutianyao/archive/2012/04/13/2446140.html），很自然的就决定将其合成为mp4文件。

 

但是有些不同：

（1）需要解析RTSP协议。研究了一下RFC2326，发现也不是很复杂。

　　rtsp分控制流和数据流：控制流就是客户端向服务端发送控制命令，包括查看节目信息、播放、停止节目等，一般是通过TCP协议通信的；数据流就是服务端将音视频数据发送到指定的地址、端口上，我们的音频和视频单独发送到两个不同的端口上，采用的是UDP协议。采用TCP或UDP，在RTSP协议中并没有明确规定，可以根据实际情况确定。

　　控制流采用的是HTTP文本协议，比较简单、方便调试，这个RTSP协议中也没有规定必须使用HTTP，不过一般都是采用HTTP来实现的。

 

　　大致步骤：

　　1. 客户端连接rtsp服务器，发送option方法；服务器返回可用的方法，通常有DESCRIBE,SETUP,PLAY,TEARDOWN等，由于板卡端的rtsp服务程序也是我们自己实现的，可以确保已经实现了这些方法，因此客户端就没有进行检查了；

　　2. 客户端发送DESCRIBE方法，服务器返回RTSP流的相关信息，包括video stream,audio stream的个数、码率、分辨率等参数信息；

　　3. 根据返回的参数信息，客户端决定要播放哪些video stream,audio stream，发送SETUP方法；

　　　我们的RTSP流为：一个alaw audio 和一个h264 video，需要指定音视频数据分别发送到哪个端口上，通过下面的代码来构造发送消息：　

 1 int RTSP::Set_Setup()

 2 {

 3     int nRet = -1;

 4     int m_nIndex = 0;

 5 

 6     if (m_pBuf != NULL)

 7     {

 8 //        if (m_pContentBase == NULL)

 9 //        {

10 //            sprintf(m_pBuf, "SETUP %s/%s %s\r\n", m_strUrl.c_str(), m_pMedia->p_control, RTSP_VERSSION);

11 //        }

12 //        else

13 //        {

14 //            sprintf(m_pBuf, "SETUP %s%s %s\r\n", m_pContentBase, m_pMedia->p_control, RTSP_VERSSION);

15 //        }

16 //        printf("m_pContentBase:%s\n", m_pContentBase);

17 //        printf("m_strUrl:%s\n", m_strUrl.c_str());

18 //        printf("m_pMedia->p_control:%s\n", m_pMedia->p_control);

19 //        printf("m_pBuf:%s\n", m_pBuf);

20         sprintf(m_pBuf, "SETUP %s %s\r\n", m_pMedia->p_control, RTSP_VERSSION);

21 

22         m_nIndex = strlen(m_pBuf);

23         sprintf(m_pBuf + m_nIndex, "CSeq: %d\r\n", m_nSeqNum);

24         m_nIndex = strlen(m_pBuf);

25 

26         if (m_pMedia->i_media_type == VIDEO)

27         {

28             GetVideoPort();

29             sprintf(m_pBuf + m_nIndex, "Transport: %s;%s;client_port=%d-%d\r\n", "RTP/AVP", "unicast", m_nVideoPort, m_nVideoPort + 1);

30             m_nIndex = strlen(m_pBuf);

31         }

32         else if (m_pMedia->i_media_type == AUDIO)

33         {

34             GetAudioPort();

35             sprintf(m_pBuf + m_nIndex, "Transport: %s;%s;client_port=%d-%d\r\n", "RTP/AVP", "unicast", m_nAudioPort, m_nAudioPort + 1);

36             m_nIndex = strlen(m_pBuf);

37         }

38 

39         if (m_pSession[0] != 0)

40         {

41             sprintf(m_pBuf + m_nIndex, "Session: %s\r\n", m_pSession);

42             m_nIndex = strlen(m_pBuf);

43         }

44 

45         sprintf(m_pBuf + m_nIndex, "User-Agent: %s\r\n", USER_AGENT_STR);

46         m_nIndex = strlen(m_pBuf);

47         sprintf(m_pBuf + m_nIndex, "\r\n");

48         m_nIndex = strlen(m_pBuf);

49         m_nBufSize = m_nIndex;

50 

51         nRet = 0;

52     }

53 

54     return nRet;

55 }

 

　　4. SETUP成功之后，通过PLAY命令就可以进行播放了：

 1 int RTSP::Set_Play()

 2 {

 3     int nRet = -1;

 4     int m_nIndex = 0;

 5 

 6     if (m_pBuf != NULL)

 7     {

 8         sprintf(m_pBuf, "PLAY %s %s\r\n", m_strUrl.c_str(), RTSP_VERSSION);

 9         m_nIndex = strlen(m_pBuf);

10         sprintf(m_pBuf + m_nIndex, "CSeq: %d\r\n", m_nSeqNum);

11         m_nIndex = strlen(m_pBuf);

12         sprintf(m_pBuf + m_nIndex, "Session: %s\r\n", m_pSession);

13         m_nIndex = strlen(m_pBuf);

14         sprintf(m_pBuf + m_nIndex, "Range: npt=0.000-\r\n");

15         m_nIndex = strlen(m_pBuf);

16         sprintf(m_pBuf + m_nIndex, "User-Agent: %s\r\n", USER_AGENT_STR);

17         m_nIndex = strlen(m_pBuf);

18         sprintf(m_pBuf + m_nIndex, "\r\n");

19         m_nIndex = strlen(m_pBuf);

20         m_nBufSize = m_nIndex;

21 

22         nRet = 0;

23     }

24 

25     return nRet;

26 }

　　这样我们就可以在刚才指定的端口上接收UDP的音视频数据了。

 更详细的可以参考rtsp协议的实现。

 

（2）合成MP4.

我们已经知道音视频格式分别为:alaw(pcma), h264;查看文档发现，mp4v2刚好支持这两种格式，剩下就很简单了：

 1 bool COutputATV::CreateMp4File(string filename)

 2 {

 3     m_Mp4File = MP4CreateEx(filename.c_str());

 4     if (m_Mp4File == MP4_INVALID_FILE_HANDLE)

 5     {

 6         return false;

 7     }

 8 

 9     MP4SetTimeScale(m_Mp4File, 90000);

10     m_nVideoTrack = MP4AddH264VideoTrack(m_Mp4File,

11                                          90000,                                     //timescale

12                                          3214,                                       //sample duration:/*(90000 / 25)*/

13                                                                                           /*  NOTICE:

14                                                                                            *  why 3214? read the commets below.

15                                                                                            */

16                                          320,                                         //width:

17                                          240,                                         //height:

18                                          0x64, //sps[1] AVCProfileIndication

19                                          0x00, //sps[2] profile_compat

20                                          0x1f, //sps[3] AVCLevelIndication

21                                          3); // 4 bytes length before each NAL unit

22     if (m_nVideoTrack == MP4_INVALID_TRACK_ID)

23     {

24         LOG(LOG_TYPE_ERROR, "CreateMp4File():MP4AddH264VideoTrack() failed.");

25         return false;

26     }

27     MP4SetVideoProfileLevel(m_Mp4File, 0x7F);

28 

29     m_nAudioTrack = MP4AddALawAudioTrack(m_Mp4File,

30                                          8000,  //timescale

31                                          500);  //sampleDuration.

32     /* NOTICE:

33      * in standard release of mp4v2 library(v1.9.1, and trunk-r479),the function MP4AddALawAudioTrack() does not specify the 3rd param:

34      * 'sampleDuration', it calculate a fixed duration value with the following formula:

35      *                      uint32_t fixedSampleDuration = (timeScale * 20)/1000; // 20mSec/Sample

36      * please read the source code of MP4AddALawAudioTrack().

37      * they can do it in this way because RFC3551 defines PCMA(a-law) as 20msec per sample, so the duration is a fixed value, please read RFC

38      * 3551:http://www.ietf.org/rfc/rfc3551.txt

39      * but, the souce boards' we used does not follow the RFC specifition, we found the sample duration value is 500.

40      * (why the param is 500? every rtp packet contains  a timestamp, the duration is the difference of two samples(not rtp packets), the same as

41      * h264 tracks in rtp). SO:

42      * I modified the declarion of MP4AddALawAudioTrack(), add the 3rd param:'sampleDuration', to pass the actual duration value,I also modified

43      * the implmention of MP4AddALawAudioTrack().

44      *

45      * as a result:

46      * ***************************               IMPORTANT                ***************************

47      * when distribute the Record software, you MUST use the mp4v2 library distribute with it,

48      * please DO NOT use the standard release download from network!

49      * ***********************************************************************************

50      *

51      * we use the default value of duration when creating mp4 file, we will modify it later when begin to write the first two samples with its

52      * actual value.

53      *

54      * Added by:Zhengfeng Rao.

55      * 2012-05-08

56      */

57 

58     MP4SetTrackIntegerProperty(m_Mp4File,

59                                m_nAudioTrack,

60                                "mdia.minf.stbl.stsd.alaw.channels",

61                                 1);

62 

63     if (m_nAudioTrack == MP4_INVALID_TRACK_ID)

64     {

65         LOG(LOG_TYPE_ERROR, "CreateMp4File():MP4AddAudioTrack() failed.");

66         return false;

67     }

68     MP4SetAudioProfileLevel(m_Mp4File, 0x02);

69 

70     return true;

71 }

 

写音视频数据：

  1 void COutputATV::DecodeRtp(unsigned char *pbuf, int datalength)

  2 {

  3     if((pbuf == NULL) || (datalength <= 0))

  4     {

  5         return;

  6     }

  7 

  8     rtp_header_t rtp_header;

  9     char cType = pbuf[0];

 10 

 11     //the 1st byte indicate the node is audio/video, it's added by the input thread, so we need to remove it.

 12     pbuf += 1;

 13     datalength -= 1;

 14     int i_header_size = GetRtpHeader(&rtp_header, pbuf, datalength);

 15 

 16     if(i_header_size <=0 )

 17     {

 18         LOG(LOG_TYPE_ERROR, "COutputATV::DecodeRtp() Invalid header size:%d", i_header_size);

 19         return;

 20     }

 21 

 22     if(cType == 'A')

 23     {

 24         if (rtp_header.i_pt == 0x8)//AUDIO

 25         {

 26             int i_size = datalength - i_header_size;

 27             if (m_nAudioTimeStamp == 0)

 28             {

 29                 m_nAudioTimeStamp = rtp_header.i_timestamp;

 30             }

 31 

 32             if (m_nAudioTimeStamp != rtp_header.i_timestamp)//got a frame

 33             {

 34                 MP4WriteSample(m_Mp4File, m_nAudioTrack, m_pAudioFrame, m_nAudioFrameIndex);

 35                 m_nAudioFrameIndex = 0;

 36 

 37                 m_nAudioTimeStamp = rtp_header.i_timestamp;

 38                 memcpy(m_pAudioFrame + m_nAudioFrameIndex, pbuf + i_header_size, i_size);

 39                 m_nAudioFrameIndex += i_size;

 40             }

 41             else

 42             {

 43                 memcpy(m_pAudioFrame + m_nAudioFrameIndex, pbuf + i_header_size, i_size);

 44                 m_nAudioFrameIndex += i_size;

 45             }

 46         }

 47         else

 48         {

 49             //INVALID packet.

 50         }

 51     }

 52     else if(cType == 'V')

 53     {

 54         if (rtp_header.i_pt == 0x60)// VIDEO

 55         {

 56             char p_save_buf[4096] = {0};

 57             int i_size = RtpToH264(pbuf, datalength, p_save_buf, &m_nNaluOkFlag, &m_nLastPktNum);

 58             if(i_size <= 0)

 59             {

 60                 DumpFrame(pbuf, datalength);

 61                 LOG_PERIOD(LOG_TYPE_WARN, "RtpToH264() Illegal packet, igonred. datalength = %d, i_size = %d", datalength-1, i_size);

 62                 return;

 63             }

 64 

 65             if (m_nVideoTimeStamp == 0)

 66             {

 67                 m_nVideoTimeStamp = rtp_header.i_timestamp;

 68 

 69                 m_nVideoFrameIndex = 0;

 70                 memcpy(m_pVideoFrame + m_nVideoFrameIndex, p_save_buf, i_size);

 71                 m_nVideoFrameIndex += i_size;

 72             }

 73 

 74             if (m_nVideoTimeStamp != rtp_header.i_timestamp || p_save_buf[12] == 0x78)

 75             {

 76                 if (m_nVideoFrameIndex >= 4)

 77                 {

 78                     unsigned int* p = (unsigned int*) (&m_pVideoFrame[0]);

 79                     *p = htonl(m_nVideoFrameIndex - 4);

 80 

 81                    MP4WriteSample(m_Mp4File, m_nVideoTrack, m_pVideoFrame, m_nVideoFrameIndex, MP4_INVALID_DURATION, 0, 1);

 82                     //DumpFrame(m_pVideoFrame, m_nVideoFrameIndex);

 83                 }

 84 

 85                 m_nVideoFrameIndex = 0;

 86                 m_nVideoTimeStamp = rtp_header.i_timestamp;

 87                 memcpy(m_pVideoFrame + m_nVideoFrameIndex, p_save_buf, i_size);

 88                 m_nVideoFrameIndex += i_size;

 89             }

 90             else

 91             {

 92                 //printf("2.3.3*************i_size:%d, m_nVideoFrameIndex:%d\n", i_size, m_nVideoFrameIndex);

 93                 memcpy(m_pVideoFrame + m_nVideoFrameIndex, p_save_buf, i_size);

 94                 m_nVideoFrameIndex += i_size;

 95             }

 96         }

 97         else

 98         {

 99             //INVALID packet.

100         }

101     }

102     else

103     {

104         //INVALID packet.

105     }

106 }

 

需要说明的是：

libmp4v2通过MP4AddALawAudioTrack(mp4file, timescale,sampleDuration)添加alaw音频时,第三个参数sampleDuration是我自己修改libmp4v2库添加的。

因为libmp4v2中 MP4AddALawAudioTrack接口为：MP4AddALawAudioTrack(mp4file, timescale)，sampleDuration是通过如下公式计算得到的：

uint32_t fixedSampleDuration = (timeScale * 20)/1000; // 20mSec/Sample

而这计算出来的值，并不符合我们的实际情况，所以我添加了这第三个参数，可以自己指定sample duration。