FFmpeg的硬件编解码例子

本文介绍了一个基于FFmpeg的硬件加速视频解码示例,该示例演示了如何利用硬件加速进行视频解码并将解码后的帧输出到文件。代码详细展示了初始化硬件设备、选择合适的像素格式、读取和解码视频包的过程。

摘要生成于 C知道 ,由 DeepSeek-R1 满血版支持, 前往体验 >

FFmpeg 自带的硬件解码的例子

hw_decode.c

/*
 * Copyright (c) 2017 Jun Zhao
 * Copyright (c) 2017 Kaixuan Liu
 *
 * HW Acceleration API (video decoding) decode sample
 *
 * Permission is hereby granted, free of charge, to any person obtaining a copy
 * of this software and associated documentation files (the "Software"), to deal
 * in the Software without restriction, including without limitation the rights
 * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
 * copies of the Software, and to permit persons to whom the Software is
 * furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice shall be included in
 * all copies or substantial portions of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
 * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
 * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
 * THE SOFTWARE.
 */

/**
 * @file
 * HW-Accelerated decoding example.
 *
 * @example hw_decode.c
 * This example shows how to do HW-accelerated decoding with output
 * frames from the HW video surfaces.
 */

#include <stdio.h>

#include <libavcodec/avcodec.h>
#include <libavformat/avformat.h>
#include <libavutil/pixdesc.h>
#include <libavutil/hwcontext.h>
#include <libavutil/opt.h>
#include <libavutil/avassert.h>
#include <libavutil/imgutils.h>

static AVBufferRef *hw_device_ctx = NULL;
static enum AVPixelFormat hw_pix_fmt;
static FILE *output_file = NULL;

static int hw_decoder_init(AVCodecContext *ctx, const enum AVHWDeviceType type)
{
    int err = 0;

    if ((err = av_hwdevice_ctx_create(&hw_device_ctx, type,
                                      NULL, NULL, 0)) < 0) {
        fprintf(stderr, "Failed to create specified HW device.\n");
        return err;
    }
    ctx->hw_device_ctx = av_buffer_ref(hw_device_ctx);

    return err;
}

static enum AVPixelFormat get_hw_format(AVCodecContext *ctx,
                                        const enum AVPixelFormat *pix_fmts)
{
    const enum AVPixelFormat *p;

    for (p = pix_fmts; *p != -1; p++) {
        if (*p == hw_pix_fmt)
            return *p;
    }

    fprintf(stderr, "Failed to get HW surface format.\n");
    return AV_PIX_FMT_NONE;
}

static int decode_write(AVCodecContext *avctx, AVPacket *packet)
{
    AVFrame *frame = NULL, *sw_frame = NULL;
    AVFrame *tmp_frame = NULL;
    uint8_t *buffer = NULL;
    int size;
    int ret = 0;

    ret = avcodec_send_packet(avctx, packet);
    if (ret < 0) {
        fprintf(stderr, "Error during decoding\n");
        return ret;
    }

    while (1) {
        if (!(frame = av_frame_alloc()) || !(sw_frame = av_frame_alloc())) {
            fprintf(stderr, "Can not alloc frame\n");
            ret = AVERROR(ENOMEM);
            goto fail;
        }

        ret = avcodec_receive_frame(avctx, frame);
        if (ret == AVERROR(EAGAIN) || ret == AVERROR_EOF) {
            av_frame_free(&frame);
            av_frame_free(&sw_frame);
            return 0;
        } else if (ret < 0) {
            fprintf(stderr, "Error while decoding\n");
            goto fail;
        }

        // 在通用解码流程之后 转换 解码格式,转换成常用格式,FFmpeg 解码H264一般都是解码成 YUV420,AVFrame 的视频格式转换可以使用 libyuv 或者 SwsContext。
        if (frame->format == hw_pix_fmt) {
            /* retrieve data from GPU to CPU */
            if ((ret = av_hwframe_transfer_data(sw_frame, frame, 0)) < 0) {
                fprintf(stderr, "Error transferring the data to system memory\n");
                goto fail;
            }
            tmp_frame = sw_frame;
        } else
            tmp_frame = frame;

        size = av_image_get_buffer_size(tmp_frame->format, tmp_frame->width,
                                        tmp_frame->height, 1);
        buffer = av_malloc(size);
        if (!buffer) {
            fprintf(stderr, "Can not alloc buffer\n");
            ret = AVERROR(ENOMEM);
            goto fail;
        }
        ret = av_image_copy_to_buffer(buffer, size,
                                      (const uint8_t * const *)tmp_frame->data,
                                      (const int *)tmp_frame->linesize, tmp_frame->format,
                                      tmp_frame->width, tmp_frame->height, 1);
        if (ret < 0) {
            fprintf(stderr, "Can not copy image to buffer\n");
            goto fail;
        }

        if ((ret = fwrite(buffer, 1, size, output_file)) < 0) {
            fprintf(stderr, "Failed to dump raw data.\n");
            goto fail;
        }

    fail:
        av_frame_free(&frame);
        av_frame_free(&sw_frame);
        av_freep(&buffer);
        if (ret < 0)
            return ret;
    }
}

int main(int argc, char *argv[])
{
    AVFormatContext *input_ctx = NULL;
    int video_stream, ret;
    AVStream *video = NULL;
    AVCodecContext *decoder_ctx = NULL;
    AVCodec *decoder = NULL;
    AVPacket packet;
    enum AVHWDeviceType type;
    int i;

    if (argc < 4) {
        fprintf(stderr, "Usage: %s <device type> <input file> <output file>\n", argv[0]);
        return -1;
    }
    // 要求输入硬件类型名称
    type = av_hwdevice_find_type_by_name(argv[1]);
    if (type == AV_HWDEVICE_TYPE_NONE) {
        fprintf(stderr, "Device type %s is not supported.\n", argv[1]);
        fprintf(stderr, "Available device types:");
        while((type = av_hwdevice_iterate_types(type)) != AV_HWDEVICE_TYPE_NONE)
            fprintf(stderr, " %s", av_hwdevice_get_type_name(type));
        fprintf(stderr, "\n");
        return -1;
    }

    /* open the input file */
    if (avformat_open_input(&input_ctx, argv[2], NULL, NULL) != 0) {
        fprintf(stderr, "Cannot open input file '%s'\n", argv[2]);
        return -1;
    }

    if (avformat_find_stream_info(input_ctx, NULL) < 0) {
        fprintf(stderr, "Cannot find input stream information.\n");
        return -1;
    }

    //从文件中猜测解码器 ,主要是获取 codec_id 视频的编码类型, 比如 H264,H265等
    /* find the video stream information */
    ret = av_find_best_stream(input_ctx, AVMEDIA_TYPE_VIDEO, -1, -1, &decoder, 0);
    if (ret < 0) {
        fprintf(stderr, "Cannot find a video stream in the input file\n");
        return -1;
    }
    video_stream = ret;
    // 查询硬件是否支持解码,并设置硬件的解码结构体
    for (i = 0;; i++) {
        const AVCodecHWConfig *config = avcodec_get_hw_config(decoder, i);
        if (!config) {
            fprintf(stderr, "Decoder %s does not support device type %s.\n",
                    decoder->name, av_hwdevice_get_type_name(type));
            return -1;
        }
        if (config->methods & AV_CODEC_HW_CONFIG_METHOD_HW_DEVICE_CTX &&
            config->device_type == type) {
            hw_pix_fmt = config->pix_fmt;
            break;
        }
    }
    
    // 接下来通用的解码流程,从源文件读取 packet 解码成 frame
    // AVPacket 保存未解码数据, AVFrame 中保存解码后的数据,视频是一帧RGB或者YUV,音频是 多个采样的PCM
    if (!(decoder_ctx = avcodec_alloc_context3(decoder)))
        return AVERROR(ENOMEM);

    video = input_ctx->streams[video_stream];
    if (avcodec_parameters_to_context(decoder_ctx, video->codecpar) < 0)
        return -1;

    decoder_ctx->get_format  = get_hw_format;

    if (hw_decoder_init(decoder_ctx, type) < 0)
        return -1;

    if ((ret = avcodec_open2(decoder_ctx, decoder, NULL)) < 0) {
        fprintf(stderr, "Failed to open codec for stream #%u\n", video_stream);
        return -1;
    }

    /* open the file to dump raw data */
    output_file = fopen(argv[3], "w+");

    /* actual decoding and dump the raw data */
    while (ret >= 0) {
        if ((ret = av_read_frame(input_ctx, &packet)) < 0)
            break;

        if (video_stream == packet.stream_index)
            ret = decode_write(decoder_ctx, &packet);

        av_packet_unref(&packet);
    }

    /* flush the decoder */
    packet.data = NULL;
    packet.size = 0;
    ret = decode_write(decoder_ctx, &packet);
    av_packet_unref(&packet);

    if (output_file)
        fclose(output_file);
    avcodec_free_context(&decoder_ctx);
    avformat_close_input(&input_ctx);
    av_buffer_unref(&hw_device_ctx);

    return 0;
}

通过查看源码,发现硬件的类型名称有:

 

static const char *const hw_type_names[] = {
    [AV_HWDEVICE_TYPE_CUDA]   = "cuda",
    [AV_HWDEVICE_TYPE_DRM]    = "drm",
    [AV_HWDEVICE_TYPE_DXVA2]  = "dxva2",
    [AV_HWDEVICE_TYPE_D3D11VA] = "d3d11va",
    [AV_HWDEVICE_TYPE_OPENCL] = "opencl",
    [AV_HWDEVICE_TYPE_QSV]    = "qsv",                // Intel PC CPU 自带的
    [AV_HWDEVICE_TYPE_VAAPI]  = "vaapi",
    [AV_HWDEVICE_TYPE_VDPAU]  = "vdpau",
    [AV_HWDEVICE_TYPE_VIDEOTOOLBOX] = "videotoolbox", // ios 硬件
    [AV_HWDEVICE_TYPE_MEDIACODEC] = "mediacodec",     // 安卓硬件
    [AV_HWDEVICE_TYPE_VULKAN] = "vulkan",
};

 

<think>好的,用户想了如何使用V4L2编写一个视频编解码例子。我需要先理清V4L2的基本概念和用途。V4L2是Video4Linux2的缩写,主要用于Linux系统中的视频采集设备,比如摄像头。不过,用户提到的是视频编解码,这里可能需要明确V4L2是否直接支持编解码功能。 首先,V4L2本身主要处理视频设备的控制和数据流,而编解码通常需要硬件加速或者使用专门的库,比如FFmpeg。可能用户是想通过V4L2捕获视频数据,然后进行编解码处理。因此,我需要分步骤来答:先介绍V4L2的基本使用流程,再结合编解码部分。 接下来,我需要确保回答的结构清晰。用户可能需要一个例子,所以应该提供一个简化的代码框架,并释每个步骤。同时,注意用户可能对V4L2不太熟悉,所以需要释关键的系统调用和结构体,比如open、ioctl、VIDIOC_REQBUFS等。 需要注意的是,V4L2的编解码支持可能依赖于具体的驱动和硬件。比如,某些摄像头可能支持MJPEG或H.264的输出格式,这时候可以直接读取压缩后的数据流。如果用户需要软件编解码,可能需要集成如libx264或libavcodec等库。因此,在回答中要区分这两种情况,并给出相应的处理步骤。 另外,用户可能对实际的代码示例比较关注,所以需要确保代码的正确性,但也要注明这只是一个框架,实际开发中需要处理更多错误和细节。同时,提醒用户注意权限问题,比如访问设备节点可能需要root权限或相应的用户组。 最后,总结部分要强调V4L2与编解码库的结合使用,以及硬件加速的可能性,帮助用户理整个流程。可能还需要指出,复杂的编解码应用建议使用更高级的框架如GStreamer,但底层了V4L2仍有其价值。</think>以下是用V4L2实现视频编解码的基础开发框架及关键步骤说明: 1. V4L2基础架构 V4L2通过设备节点(如`/dev/video0`)操作视频设备,核心操作流程包含: ``` 打开设备 -> 设置格式 -> 请求缓冲区 -> 映射内存 -> 捕获帧 -> 处理数据 -> 释放资源 ``` 2. 设备初始化示例代码框架 ```c #include <linux/videodev2.h> int main() { int fd = open("/dev/video0", O_RDWR); struct v4l2_format fmt = { .type = V4L2_BUF_TYPE_VIDEO_CAPTURE, .fmt.pix = { .width = 640, .height = 480, .pixelformat = V4L2_PIX_FMT_MJPEG, // 选择设备支持的编码格式 .field = V4L2_FIELD_NONE } }; ioctl(fd, VIDIOC_S_FMT, &fmt); // 设置格式 } ``` 3. 编解码处理逻辑 根据选择的`pixelformat`不同,后续处理分为两种模式: ▨ 硬件编码模式(推荐) 当设备支持H264/MJPEG等压缩格式时: ```c // 通过VIDIOC_REQBUFS申请缓冲区 struct v4l2_requestbuffers req = {0}; req.type = V4L2_BUF_TYPE_VIDEO_CAPTURE; req.memory = V4L2_MEMORY_MMAP; req.count = 4; ioctl(fd, VIDIOC_REQBUFS, &req); // 读取压缩帧数据后可直接写入文件或网络流 unsigned char* buffer = mmap(...); write(output_fd, buffer, length); ``` ▨ 软件编码模式 当需要处理原始YUV数据时: ```c // 设置像素格式为V4L2_PIX_FMT_YUYV fmt.fmt.pix.pixelformat = V4L2_PIX_FMT_YUYV; // 获取YUV帧后使用编码库处理 AVFrame* frame = av_frame_alloc(); sws_scale(...); // 格式转换 avcodec_send_frame(codec_ctx, frame); // FFmpeg编码 ``` 4. 开发注意事项 - 权限管理:需`sudo
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值