C/C++实现H264文件解析
作者:静止了 所有的花开
这篇文章主要为大家详细介绍了如何通过C++实现H264文件以及一段H264码流解析,文中的示例代码讲解详细,感兴趣的小伙伴可以跟随小编一起学习一下
H264视频编码格式简介
H264是视频压缩编码标准。视频⽂件的传输是⼀个极⼤的问题:⼀段分辨率为19201080的视频,每个像素点为RGB占⽤3个字节,帧率是25的视频,对于传输带宽的要求是:192010803*25/1024/1024=148.315MB/s,换成bps则意味着视频每秒带宽为1186.523Mbps,这样的速率对于⽹络存储是不可接受的。因此视频压缩和编码技术应运⽽⽣。
H264码流分析
通常我们使用H264码流分析工具时,我们会发现H264码流是由连续的帧组成的,一组连续的帧成为1个GOP即1组,对于1个GOP来说,通常包括SPS(序列参数集,编码视频序列的全局参数)PPS(图像参数集,⼀个序列中某⼀幅图像或者某⼏幅图像的参数),IDR帧(第一个出现的I帧成为IDR帧,1个GOP中通常只包含1个IDR帧),P帧(GOP中剩余帧基本都是P帧);GOP描述如下:
H264码流结构如图:
C/C++ H264文件解析
C++实现H264文件以及一段H264码流解析,源码如下:
h264Parse.h:
#ifndef _H264PARSE_H_ #define _H264PARSE_H_ #include <fstream> class H264Parse { public: int open_file(const std::string &filename); /** * @brief 从文件中读取一个nalu,包含起始码 * @param buf 存放nalu的缓冲区 * @param size 缓冲区大小 * @param len nalu的长度 * @param n 每次读取多少个字节 * @return -1 失败 0 已到文件末尾 1 成功获取到一个nalu */ int read_nalu(uint8_t *buf, uint32_t size, uint32_t &len, uint32_t n); void close_file(); // 获取起始码长度 static int get_startCode_len(const uint8_t *ptr); static const uint8_t *find_startCode_pos(const uint8_t *buf, uint32_t len); /** * @brief 从一段h264码流中分割nalu,包含起始码 * @param stream h264码流 * @param streamLen 码流大小 * @param nalu Pointer to the extracted nalu * @param naluLen nalu的长度 * @param record Pointer用于记录状态,第一次分割时把 *record 赋值为NULL * @return -1 失败 0 已分割完 1 成功获取到一个nalu */ static int nalu_tok(const uint8_t *stream, uint32_t streamLen, const uint8_t **nalu, uint32_t &naluLen, const uint8_t **record); private: std::fstream h264File; int read_start_code(uint8_t *buf); int adjust_filePointer_pos(uint32_t totalRead, uint32_t naluLen); }; #endif // _H264PARSE_H_
h264Parse.cpp:
#include "h264Parse.h" #include <iostream> #include <cstring> int H264Parse::open_file(const std::string &filename) { h264File.open(filename, std::ios::in | std::ios::binary); if (!h264File.is_open()) { std::cout << "Failed to open the H.264 file." << std::endl; return -1; } return 0; } int H264Parse::get_startCode_len(const uint8_t *ptr) { if (ptr[0] == 0x00 && ptr[1] == 0x00) { if (ptr[2] == 0x01) return 3; else if (ptr[2] == 0x00 && ptr[3] == 0x01) return 4; } return -1; // 无效的起始码 } // 读取起始码,并返回其长度 int H264Parse::read_start_code(uint8_t *buf) { // 读取前4个字节来判断起始码长度 h264File.read(reinterpret_cast<char *>(buf), 4); if (h264File.gcount() < 4) { return -1; } return get_startCode_len(buf); } // 寻找NALU的起始码位置 const uint8_t *H264Parse::find_startCode_pos(const uint8_t *buf, uint32_t len) { const uint8_t *p = buf; if (len < 3) return NULL; for (uint32_t i = 0; i < len - 3; ++i) { if ((p[0] == 0x00 && p[1] == 0x00 && p[2] == 0x01) || (p[0] == 0x00 && p[1] == 0x00 && p[2] == 0x00 && p[3] == 0x01)) { return p; } p++; } // 检查最后3字节是不是起始码 if (p[0] == 0x00 && p[1] == 0x00 && p[2] == 0x01) return p; return NULL; } // 调整文件指针位置 int H264Parse::adjust_filePointer_pos(uint32_t totalRead, uint32_t naluLen) { int offset = -(totalRead - naluLen); if (!h264File.eof()) { h264File.seekg(offset, std::ios::cur); } else { h264File.clear(); // 达到文件末尾了要先清除 eof 标志 h264File.seekg(offset, std::ios::end); } if (h264File.fail()) { std::cout << "seekg failed!" << std::endl; return -1; } return 0; } int H264Parse::read_nalu(uint8_t *buf, uint32_t size, uint32_t &len, uint32_t n) { uint32_t totalRead = 0; int startCodeLength = read_start_code(buf); if (startCodeLength == -1) { printf("read_start_code failed.\n"); return -1; } totalRead += 4; // 已经读取了4字节的长度 while (true) { if (size < totalRead + n) { std::cout << "Buffer size is too small: size=" << size << ", needed=" << totalRead + n << std::endl; return -1; } h264File.read(reinterpret_cast<char *>(buf + totalRead), n); std::streamsize bytesRead = h264File.gcount(); if (bytesRead <= 0) { std::cout << "Failed to read from file!" << std::endl; return -1; } uint32_t searchStart = (totalRead > 4) ? totalRead - 3 : startCodeLength; const uint8_t *naluEnd = find_startCode_pos(buf + searchStart, bytesRead + (totalRead > 4 ? 3 : 0)); totalRead += bytesRead; if (naluEnd != nullptr) { len = naluEnd - buf; if (adjust_filePointer_pos(totalRead, len) < 0) return -1; break; } // 是否读取到文件末尾 if (h264File.peek() == std::char_traits<char>::eof()) { len = totalRead; return 0; // NALU完整读取 } } memset(buf + len, 0, size - len); // 清空剩余部分 return 1; // 成功读取 } void H264Parse::close_file() { h264File.close(); } int H264Parse::nalu_tok(const uint8_t *stream, uint32_t streamLen, const uint8_t **nalu, uint32_t &naluLen, const uint8_t **record) { const uint8_t *current = (record && *record) ? *record : stream; uint32_t offset = static_cast<uint32_t>(current - stream); if (offset >= streamLen) { return -1; // 当前记录位置超出缓冲区 } int scLen = get_startCode_len(current); if (scLen == -1 || (current + scLen) > (stream + streamLen)) { return -1; // 无效的起始码或起始码长度超出缓冲区 } // 查找下一个起始码的位置 const uint8_t *next_start = find_startCode_pos(current + scLen, streamLen - offset - scLen); if (next_start) { *nalu = current; naluLen = static_cast<uint32_t>(next_start - current); *record = next_start; return 1; // 成功获取到一个 NALU } else { // 最后一个 NALU *nalu = current; naluLen = streamLen - offset; *record = NULL; // 重置记录指针 return 0; // 分割完毕 } }
测试:
#include <iostream> #include <vector> #include "h264Parse.h" void test1() { int ret; int number = 0; H264Parse h264; uint8_t buf[1024 * 1024]; uint32_t len = 0; h264.open_file("/home/tl/work/app/res/output.h264"); while ((ret = h264.read_nalu(buf, sizeof(buf), len, 1024 * 2)) != -1) { printf("number: %d nalu len: %u\n", number, len - h264.get_startCode_len(buf)); number++; if (ret == 0) break; } if (ret == -1) { std::cout << "read_nalu failed." << std::endl; } h264.close_file(); } // 辅助函数:打印 NALU 信息 void print_nalu(const uint8_t *nalu, uint32_t len, int index) { std::cout << "NALU " << index << ": Length = " << len << " bytes, Data = "; for (uint32_t i = 0; i < len; ++i) { printf("%02X ", nalu[i]); } std::cout << std::endl; } void test2() { // 构造一个模拟的 H.264 码流缓冲区,包含多个 NALU // 起始码格式:0x000001 (3 字节) 和 0x00000001 (4 字节) // NALU 内容:随机填充的字节数据 std::vector<uint8_t> buffer; // NALU 1: 3 字节起始码 + 5 字节数据 std::vector<uint8_t> nalu1 = {0x00, 0x00, 0x01, 0x65, 0x88, 0x84, 0x21, 0xA0}; buffer.insert(buffer.end(), nalu1.begin(), nalu1.end()); // NALU 2: 4 字节起始码 + 6 字节数据 std::vector<uint8_t> nalu2 = {0x00, 0x00, 0x00, 0x01, 0x41, 0x9A, 0x5C, 0xD4, 0x00, 0x11}; buffer.insert(buffer.end(), nalu2.begin(), nalu2.end()); // NALU 3: 3 字节起始码 + 4 字节数据 std::vector<uint8_t> nalu3 = {0x00, 0x00, 0x01, 0x06, 0x05, 0xFF, 0xEE}; buffer.insert(buffer.end(), nalu3.begin(), nalu3.end()); // NALU 4: 3 字节起始码 + 3 字节数据 (测试末尾) std::vector<uint8_t> nalu4 = {0x00, 0x00, 0x01, 0x07, 0xAD, 0xBE}; buffer.insert(buffer.end(), nalu4.begin(), nalu4.end()); // 输出构建的缓冲区(可选) std::cout << "Constructed H.264 Buffer: "; for (size_t i = 0; i < buffer.size(); ++i) { printf("%02X ", buffer[i]); } std::cout << "\n\n"; const uint8_t *pnalu = nullptr; uint32_t nale_len = 0; const uint8_t *pRecord = NULL; // 初始时为 NULL int ret; int nalu_index = 1; // 循环分割并打印每个 NALU while ((ret = H264Parse::nalu_tok(buffer.data(), buffer.size(), &pnalu, nale_len, &pRecord)) != -1) { print_nalu(pnalu, nale_len, nalu_index); nalu_index++; if (ret == 0) break; } if (ret == -1) { std::cout << "Error occurred during NALU tokenization." << std::endl; } } // 主函数 int main() { test1(); // test2(); return 0; }
以上就是C/C++实现H264文件解析的详细内容,更多关于C++ H264文件解析的资料请关注脚本之家其它相关文章!