跟雷神学音视频-8.H264视频码流解析

H.264结构基本介绍

H264比特流 = Start_Code_Prefix + NALU + Start_Code_Prefix + NALU + …

由此可见，H264由一个起始码将各个NALU（ Network Abstract Layer，即网络抽象层 U单元），其中，起始码分为3Byte和4Byte的0x000001和0x00000001。如果以Slice为一帧开始就用0x00000001，否则用0x000001。在起始码后面的第一个字节，就是NALU的类型。详细

类型值	解释
1	非IDR图像的编码条带，为P或B帧。P帧，前向预测编码帧，表示该帧与前一帧的差别（I或P），在I中找出P某点的预测值和运动矢量，一起传送。接收端根据运动矢量从I中找出P某点的预测值并与差值相加得到样值。 1P帧在I帧后面1~2帧的位置 2压缩率比较高 3采用运动补偿传送差值和运动矢量 4可造成解码错误扩散 B帧，双向预测编码帧，通过前后帧与本帧数据叠加取得最终画面。先找出B帧中某点的预测值和两个运动矢量，传送预测值和运动矢量。接收端根据运动矢量在两个帧中找出预测值并求和。 1B帧由前面的I或者P和后面的P帧来计算 2压缩率最高，只反映帧间运动主体的变化 3不会造成解码错误扩散
2	编码条带数据分割块A
3	编码条带数据分割块B
4	编码条带数据分割块C
5	I帧，IDR图像的编码条带，俗称关键帧，也叫帧内编码帧。1全帧JPEG压缩编码 2描述了图像背景和运动主体的详情 3是P和B帧的参考帧 4一组只有一个
6	辅助增强信息 (SEI)
7	SPS（Sequence Parameter Set）序列参数集。包括编码所用的profile，level，图像的宽和高，deblock滤波器等
8	PPS（Picture Parameter Set）图像参数集。包括编码所用的profile，level，图像的宽和高，deblock滤波器等
9	访问单元分隔符
10	序列结尾
11	流结尾
12	填充数据
13	序列参数集扩展
19	未分割的辅助编码图像的编码条带

源码解析

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;      //slice表示4位 否则3位
	unsigned len;                 //NALU的长度 不包括起始码
	unsigned max_size;            //NALU缓冲区大小
	int forbidden_bit;            //FALSE
	int nal_reference_idc;        //NALU_PRIORITY_xxxx
	int nal_unit_type;            //NALU_TYPE_xxxx    
	char *buf;                    //包含EBSP后面的第一个字节
} NALU_t;

FILE *h264bitstream;

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;//假设是0x000001
 
	if (3 != fread (Buf, 1, 3, h264bitstream)){
		free(Buf);
		return 0;
	}
	info2 = FindStartCode2 (Buf);
	if(info2 != 1) {//不是0x000001
		if(1 != fread(Buf+3, 1, 1, h264bitstream)){//多读取一个
			free(Buf);
			return 0;
		}
		info3 = FindStartCode3 (Buf);//是不是0x00000001
		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)){//读到文件尾
			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 10000000
			nalu->nal_reference_idc = nalu->buf[0] & 0x60; // 2 bit 01100000
			nalu->nal_unit_type = (nalu->buf[0]) & 0x1f;// 5 bit 00011111
			free(Buf);
			return pos-1;
		}
		Buf[pos++] = fgetc (h264bitstream);
        
        //判断本段是否结束
		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);
}

int h264Parser(char *url){
    
    int data_offset=0;
	int nal_num=0;
    NALU_t *n=(NALU_t*)calloc(1,sizeof(NALU_t));
    n->max_size=100000;
	n->buf = (char*)calloc (buffersize, sizeof (char));
    
    h264bitstream=fopen(url, "rb+");
    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++;
	}
    if (n){
		if (n->buf){
			free(n->buf);
			n->buf=NULL;
		}
		free (n);
	}
	return 0;
}

跟雷神学音视频-8.H264视频码流解析

跟雷神学音视频-8.H264视频码流解析

H.264结构基本介绍

源码解析

相关阅读