gpt4 book ai didi

ffmpeg - 使用ffmpeg解码h264 mpegts udp流时图片模糊

转载 作者:行者123 更新时间:2023-12-04 23:24:03 29 4
gpt4 key购买 nike

我使用 ffmpeg 确实读取了一个 udp 流(仅包含视频)并解码帧,然后我想再次编码,但是在解码或从解复用过程中,我得到模糊的图片图片,尤其是下部。

我有一个视频播放器,它也使用 ffmpeg 完美显示视频,我尝试查看该代码,但我没有看到任何差异。

在日志中,我看到了类似的东西

Invalid NAL unit 8, skipping.nal_unit_type: 1(Coded slice of a non-IDR picture), nal_ref_idc: 3Invalid NAL unit 7, skipping.bytestream overread tderror while decoding MB 109 49, bytestream td

The main things in the code looks like:

av_register_all();

AVFormatContext *fmt_ctx = 0;

AVDictionary *options = 0;
av_dict_set(&options, "analyzeduration", "500000", NULL);
av_dict_set(&options, "probesize", "500000", NULL);
char* url = "udp://239.0.0.3:8081";
avformat_open_input(&fmt_ctx, url, 0, &options);

avformat_find_stream_info(fmt_ctx, &options);

int nRet = 0;
av_dump_format(fmt_ctx, 0, url, 0);
AVStream *pStream = fmt_ctx->streams[0];
AVCodecID nCodecid = pStream->codec->codec_id;
AVCodec* pCodec = avcodec_find_decoder(nCodecid);
AVCodecContext* pCodecCtx = pStream->codec;

nRet = avcodec_open2(pCodecCtx, pCodec, NULL);
int nInH = pStream->codec->height;
int nInW = pStream->codec->width;
int nOutW = nInW / 4;
int nOutH = nInH / 4;

SwsContext* pSwsCtx = sws_getContext(nInW, nInH, AV_PIX_FMT_YUV420P,
nOutW, nOutH, AV_PIX_FMT_RGB24,
SWS_BICUBIC, NULL, NULL, NULL);


m_pFilmWdg->m_img = QImage(nOutW, nOutH, QImage::Format_RGB888);
int linesizes[4];
av_image_fill_linesizes(linesizes, AV_PIX_FMT_RGB24, nOutW);


for (;;)
{
av_init_packet(&pkt);
pkt.data = NULL;
pkt.size = 0;
nRet = av_read_frame(fmt_ctx, &pkt);

nRet = avcodec_send_packet(pCodecCtx, &pkt);

AVFrame* picture = av_frame_alloc();

nRet = avcodec_receive_frame(pCodecCtx, picture);

if (AVERROR(EAGAIN) == nRet)
continue;

uint8_t* p[] = { m_pFilmWdg->m_img.bits() };



nRet = sws_scale(pSwsCtx, picture->data, picture->linesize, 0, nInH, p, linesizes);

av_packet_unref(&pkt);
av_frame_free(&picture);
m_pFilmWdg->update();

}

最佳答案

经过大量调试,我发现了问题所在。问题是 udp 包在解码过程中丢失或损坏。我在不同的线程中将循环分成了两个。一
DemuxLoop 和一个 DecodeLoop 类似

void VideoDecode::DemuxLoop()
{
..
int nRet = av_read_frame(fmt_ctx, &pkt);
put in queue

}


void VideoDecode::DecodeLoop()
{
...
pick from queue
int nRet = avcodec_send_packet(pCodecCtx, &pkt);

AVFrame* picture = av_frame_alloc();

nRet = avcodec_receive_frame(pCodecCtx, picture);

...
}

关于ffmpeg - 使用ffmpeg解码h264 mpegts udp流时图片模糊,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/56130119/

29 4 0
Copyright 2021 - 2024 cfsdn All Rights Reserved 蜀ICP备2022000587号
广告合作:1813099741@qq.com 6ren.com