编程开源技术交流,分享技术与知识

网站首页 > 开源技术 正文

视音频数据处理入门:H.264视频码流解析

wxchong 2024-08-05 01:24:55 开源技术 35 ℃ 0 评论

H.264原始码流(又称为“裸流”)是由一个一个的NALU组成的。他们的结构如下图所示。

其中每个NALU之间通过startcode(起始码)进行分隔,起始码分成两种:0x000001(3Byte)或者0x00000001(4Byte)。如果NALU对应的Slice为一帧的开始就用0x00000001,否则就用0x000001。

H.264码流解析的步骤就是首先从码流中搜索0x000001和0x00000001,分离出NALU;然后再分析NALU的各个字段。本文的程序即实现了上述的两个步骤。

整个程序位于simplest_h264_parser()函数中,如下所示

#include <stdio.h>

#include <stdlib.h>

#include <string.h>


typedef enum {

NALU_TYPE_SLICE = 1,

NALU_TYPE_DPA = 2,

NALU_TYPE_DPB = 3,

NALU_TYPE_DPC = 4,

NALU_TYPE_IDR = 5,

NALU_TYPE_SEI = 6,

NALU_TYPE_SPS = 7,

NALU_TYPE_PPS = 8,

NALU_TYPE_AUD = 9,

NALU_TYPE_EOSEQ = 10,

NALU_TYPE_EOSTREAM = 11,

NALU_TYPE_FILL = 12,

} NaluType;


typedef enum {

NALU_PRIORITY_DISPOSABLE = 0,

NALU_PRIRITY_LOW = 1,

NALU_PRIORITY_HIGH = 2,

NALU_PRIORITY_HIGHEST = 3

} NaluPriority;


typedef struct

{

int startcodeprefix_len; //! 4 for parameter sets and first slice in picture, 3 for everything else (suggested)

unsigned len; //! Length of the NAL unit (Excluding the start code, which does not belong to the NALU)

unsigned max_size; //! Nal Unit Buffer size

int forbidden_bit; //! should be always FALSE

int nal_reference_idc; //! NALU_PRIORITY_xxxx

int nal_unit_type; //! NALU_TYPE_xxxx

char *buf; //! contains the first byte followed by the EBSP

} NALU_t;


FILE *h264bitstream = NULL; //!< the bit stream file


int info2=0, info3=0;


static int FindStartCode2 (unsigned char *Buf){

if(Buf[0]!=0 || Buf[1]!=0 || Buf[2] !=1) return 0; //0x000001?

else return 1;

}


static int FindStartCode3 (unsigned char *Buf){

if(Buf[0]!=0 || Buf[1]!=0 || Buf[2] !=0 || Buf[3] !=1) return 0;//0x00000001?

else return 1;

}


int GetAnnexbNALU (NALU_t *nalu){

int pos = 0;

int StartCodeFound, rewind;

unsigned char *Buf;


if ((Buf = (unsigned char*)calloc (nalu->max_size , sizeof(char))) == NULL)

printf ("GetAnnexbNALU: Could not allocate Buf memory\n");


nalu->startcodeprefix_len=3;


if (3 != fread (Buf, 1, 3, h264bitstream)){

free(Buf);

return 0;

}

info2 = FindStartCode2 (Buf);

if(info2 != 1) {

if(1 != fread(Buf+3, 1, 1, h264bitstream)){

free(Buf);

return 0;

}

info3 = FindStartCode3 (Buf);

if (info3 != 1){

free(Buf);

return -1;

}

else {

pos = 4;

nalu->startcodeprefix_len = 4;

}

}

else{

nalu->startcodeprefix_len = 3;

pos = 3;

}

StartCodeFound = 0;

info2 = 0;

info3 = 0;


while (!StartCodeFound){

if (feof (h264bitstream)){

nalu->len = (pos-1)-nalu->startcodeprefix_len;

memcpy (nalu->buf, &Buf[nalu->startcodeprefix_len], nalu->len);

nalu->forbidden_bit = nalu->buf[0] & 0x80; //1 bit

nalu->nal_reference_idc = nalu->buf[0] & 0x60; // 2 bit

nalu->nal_unit_type = (nalu->buf[0]) & 0x1f;// 5 bit

free(Buf);

return pos-1;

}

Buf[pos++] = fgetc (h264bitstream);

info3 = FindStartCode3(&Buf[pos-4]);

if(info3 != 1)

info2 = FindStartCode2(&Buf[pos-3]);

StartCodeFound = (info2 == 1 || info3 == 1);

}


// Here, we have found another start code (and read length of startcode bytes more than we should

// have. Hence, go back in the file

rewind = (info3 == 1)? -4 : -3;


if (0 != fseek (h264bitstream, rewind, SEEK_CUR)){

free(Buf);

printf("GetAnnexbNALU: Cannot fseek in the bit stream file");

}


// Here the Start code, the complete NALU, and the next start code is in the Buf.

// The size of Buf is pos, pos+rewind are the number of bytes excluding the next

// start code, and (pos+rewind)-startcodeprefix_len is the size of the NALU excluding the start code


nalu->len = (pos+rewind)-nalu->startcodeprefix_len;

memcpy (nalu->buf, &Buf[nalu->startcodeprefix_len], nalu->len);//

nalu->forbidden_bit = nalu->buf[0] & 0x80; //1 bit

nalu->nal_reference_idc = nalu->buf[0] & 0x60; // 2 bit

nalu->nal_unit_type = (nalu->buf[0]) & 0x1f;// 5 bit

free(Buf);


return (pos+rewind);

}


/**

* Analysis H.264 Bitstream

* @param url Location of input H.264 bitstream file.

*/

int simplest_h264_parser(char *url){


NALU_t *n;

int buffersize=100000;


//FILE *myout=fopen("output_log.txt","wb+");

FILE *myout=stdout;


h264bitstream=fopen(url, "rb+");

if (h264bitstream==NULL){

printf("Open file error\n");

return 0;

}


n = (NALU_t*)calloc (1, sizeof (NALU_t));

if (n == NULL){

printf("Alloc NALU Error\n");

return 0;

}


n->max_size=buffersize;

n->buf = (char*)calloc (buffersize, sizeof (char));

if (n->buf == NULL){

free (n);

printf ("AllocNALU: n->buf");

return 0;

}


int data_offset=0;

int nal_num=0;

printf("-----+-------- NALU Table ------+---------+\n");

printf(" NUM | POS | IDC | TYPE | LEN |\n");

printf("-----+---------+--------+-------+---------+\n");


while(!feof(h264bitstream))

{

int data_lenth;

data_lenth=GetAnnexbNALU(n);


char type_str[20]={0};

switch(n->nal_unit_type){

case NALU_TYPE_SLICE:sprintf(type_str,"SLICE");break;

case NALU_TYPE_DPA:sprintf(type_str,"DPA");break;

case NALU_TYPE_DPB:sprintf(type_str,"DPB");break;

case NALU_TYPE_DPC:sprintf(type_str,"DPC");break;

case NALU_TYPE_IDR:sprintf(type_str,"IDR");break;

case NALU_TYPE_SEI:sprintf(type_str,"SEI");break;

case NALU_TYPE_SPS:sprintf(type_str,"SPS");break;

case NALU_TYPE_PPS:sprintf(type_str,"PPS");break;

case NALU_TYPE_AUD:sprintf(type_str,"AUD");break;

case NALU_TYPE_EOSEQ:sprintf(type_str,"EOSEQ");break;

case NALU_TYPE_EOSTREAM:sprintf(type_str,"EOSTREAM");break;

case NALU_TYPE_FILL:sprintf(type_str,"FILL");break;

}

char idc_str[20]={0};

switch(n->nal_reference_idc>>5){

case NALU_PRIORITY_DISPOSABLE:sprintf(idc_str,"DISPOS");break;

case NALU_PRIRITY_LOW:sprintf(idc_str,"LOW");break;

case NALU_PRIORITY_HIGH:sprintf(idc_str,"HIGH");break;

case NALU_PRIORITY_HIGHEST:sprintf(idc_str,"HIGHEST");break;

}


fprintf(myout,"%5d| %8d| %7s| %6s| %8d|\n",nal_num,data_offset,idc_str,type_str,n->len);


data_offset=data_offset+data_lenth;


nal_num++;

}


//Free

if (n){

if (n->buf){

free(n->buf);

n->buf=NULL;

}

free (n);

}

return 0;

}

————————————————

本文为「雷霄骅」博士文章,向博士致敬!

Tags:

本文暂时没有评论,来添加一个吧(●'◡'●)

欢迎 发表评论:

最近发表
标签列表