ffmpeg 加码cook 噪音大? 400 报错
if(codecCtx->codec_type == AVMEDIA_TYPE_AUDIO)
{
// Set audio settings from codec info
wanted_spec.freq = codecCtx->sample_rate;
wanted_spec.format = AUDIO_S16SYS;
wanted_spec.channels = codecCtx->channels;
wanted_spec.silence = 0;
wanted_spec.samples = SDL_AUDIO_BUFFER_SIZE;
wanted_spec.callback = audio_callback;
wanted_spec.userdata = is;
不知道这段代码出错没
我用ffmpeg类库开发了一个软件 音频用的自动解码 解码其他的音频没有问题 唯独cook音频出问题出现很大噪音
你发的这些东西看不出问题, 这只不过是设置SDL音频播放参数和回调接口而已.
得看看你是如何解码的, 有没有把解码出来的数据弄丢, 不然是不会有噪音的...
#include "libavformat/avformat.h" #include "libswscale/swscale.h" #include <SDL/SDL.h> #include <SDL/SDL_thread.h> #ifdef main #undef main #endif #include <stdio.h> #include <math.h> #define SDL_AUDIO_BUFFER_SIZE 1024 #define MAX_AUDIOQ_SIZE (5 * 16 * 1024) #define MAX_VIDEOQ_SIZE (5 * 256 * 1024) #define AV_SYNC_THRESHOLD 0.01 #define AV_NOSYNC_THRESHOLD 10.0 #define FF_ALLOC_EVENT (SDL_USEREVENT) #define FF_REFRESH_EVENT (SDL_USEREVENT + 1) #define FF_QUIT_EVENT (SDL_USEREVENT + 2) #define VIDEO_PICTURE_QUEUE_SIZE 1 typedef struct PacketQueue { AVPacketList *first_pkt, *last_pkt; int nb_packets; int size; SDL_mutex *mutex; SDL_cond *cond; } PacketQueue; typedef struct VideoPicture { SDL_Overlay *bmp; int width, height; int allocated; double pts; } VideoPicture; typedef struct VideoState { AVFormatContext *pFormatCtx; int videoStream, audioStream; double audio_clock; AVStream *audio_st; PacketQueue audioq; uint8_t audio_buf[(AVCODEC_MAX_AUDIO_FRAME_SIZE * 3) / 2]; unsigned int audio_buf_size; unsigned int audio_buf_index; AVPacket audio_pkt; uint8_t *audio_pkt_data; int audio_pkt_size; int audio_hw_buf_size; double frame_timer; double frame_last_pts; double frame_last_delay; double video_clock; ///<pts of last decoded frame / predicted pts of next decoded frame AVStream *video_st; PacketQueue videoq; VideoPicture pictq[VIDEO_PICTURE_QUEUE_SIZE]; int pictq_size, pictq_rindex, pictq_windex; SDL_mutex *pictq_mutex; SDL_cond *pictq_cond; SDL_Thread *parse_tid; SDL_Thread *video_tid; char filename[1024]; int quit; } VideoState; SDL_Surface *screen; VideoState *global_video_state; void packet_queue_init(PacketQueue *q) { memset(q, 0, sizeof(PacketQueue)); q->mutex = SDL_CreateMutex(); q->cond = SDL_CreateCond(); } int packet_queue_put(PacketQueue *q, AVPacket *pkt) { AVPacketList *pkt1; if(av_dup_packet(pkt) < 0) { return -1; } pkt1 = (AVPacketList *)av_malloc(sizeof(AVPacketList)); if (!pkt1) return -1; pkt1->pkt = *pkt; pkt1->next = NULL; SDL_LockMutex(q->mutex); if (!q->last_pkt) q->first_pkt = pkt1; else q->last_pkt->next = pkt1; q->last_pkt = pkt1; q->nb_packets++; q->size += pkt1->pkt.size; SDL_CondSignal(q->cond); SDL_UnlockMutex(q->mutex); return 0; } static int packet_queue_get(PacketQueue *q, AVPacket *pkt, int block) { AVPacketList *pkt1; int ret; SDL_LockMutex(q->mutex); for(;;) { if(global_video_state->quit) { ret = -1; break; } pkt1 = q->first_pkt; if (pkt1) { q->first_pkt = pkt1->next; if (!q->first_pkt) q->last_pkt = NULL; q->nb_packets--; q->size -= pkt1->pkt.size; *pkt = pkt1->pkt; av_free(pkt1); ret = 1; break; } else if (!block) { ret = 0; break; } else { SDL_CondWait(q->cond, q->mutex); } } SDL_UnlockMutex(q->mutex); return ret; } double get_audio_clock(VideoState *is) { double pts; int hw_buf_size, bytes_per_sec, n; pts = is->audio_clock; hw_buf_size = is->audio_buf_size - is->audio_buf_index; bytes_per_sec = 0; n = is->audio_st->codec->channels * 2; if(is->audio_st) { bytes_per_sec = is->audio_st->codec->sample_rate * n; } if(bytes_per_sec) { pts -= (double)hw_buf_size / bytes_per_sec; } return pts; } int audio_decode_frame(VideoState *is, uint8_t *audio_buf, int buf_size, double *pts_ptr) { int len1, data_size, n; AVPacket *pkt = &is->audio_pkt; double pts; for(;;) { while(is->audio_pkt_size > 0) { data_size = buf_size; len1 = avcodec_decode_audio2(is->audio_st->codec, (int16_t *)audio_buf, &data_size, is->audio_pkt_data, is->audio_pkt_size); if(len1 < 0) { is->audio_pkt_size = 0; break; } is->audio_pkt_data += len1; is->audio_pkt_size -= len1; if(data_size <= 0) { continue; } pts = is->audio_clock; *pts_ptr = pts; n = 2 * is->audio_st->codec->channels; is->audio_clock += (double)data_size / (double)(n * is->audio_st->codec->sample_rate); return data_size; } if(pkt->data) av_free_packet(pkt); if(is->quit) { return -1; } if(packet_queue_get(&is->audioq, pkt, 1) < 0) { return -1; } is->audio_pkt_data = pkt->data; is->audio_pkt_size = pkt->size; if(pkt->pts != AV_NOPTS_VALUE) { is->audio_clock = av_q2d(is->audio_st->time_base)*pkt->pts; } } } void audio_callback(void *userdata, Uint8 *stream, int len) { VideoState *is = (VideoState *)userdata; int len1, audio_size; double pts; while(len > 0) { if(is->audio_buf_index >= is->audio_buf_size) { audio_size = audio_decode_frame(is, is->audio_buf, sizeof(is->audio_buf), &pts); if(audio_size < 0) { is->audio_buf_size = 1024; memset(is->audio_buf, 0, is->audio_buf_size); } else { is->audio_buf_size = audio_size; } is->audio_buf_index = 0; } len1 = is->audio_buf_size - is->audio_buf_index; if(len1 > len) len1 = len; memcpy(stream, (uint8_t *)is->audio_buf + is->audio_buf_index, len1); len -= len1; stream += len1; is->audio_buf_index += len1; } } static Uint32 sdl_refresh_timer_cb(Uint32 interval, void *opaque) { SDL_Event event; event.type = FF_REFRESH_EVENT; event.user.data1 = opaque; SDL_PushEvent(&event); return 0; } static void schedule_refresh(VideoState *is, int delay) { SDL_AddTimer(delay, sdl_refresh_timer_cb, is); } void video_display(VideoState *is) { SDL_Rect rect; VideoPicture *vp; AVPicture pict; float aspect_ratio; int w, h, x, y; int i; vp = &is->pictq[is->pictq_rindex]; if(vp->bmp) { if(is->video_st->codec->sample_aspect_ratio.num == 0) { aspect_ratio = 0; } else { aspect_ratio = av_q2d(is->video_st->codec->sample_aspect_ratio) * is->video_st->codec->width / is->video_st->codec->height; } if(aspect_ratio <= 0.0) { aspect_ratio = (float)is->video_st->codec->width / (float)is->video_st->codec->height; } h = screen->h; w = ((int)(h * aspect_ratio)) & -3; if(w > screen->w) { w = screen->w; h = ((int)(w / aspect_ratio)) & -3; } x = (screen->w - w) / 2; y = (screen->h - h) / 2; rect.x = x; rect.y = y; rect.w = w; rect.h = h; SDL_DisplayYUVOverlay(vp->bmp, &rect); } } void video_refresh_timer(void *userdata) { VideoState *is = (VideoState *)userdata; VideoPicture *vp; double actual_delay, delay, sync_threshold, ref_clock, diff; if(is->video_st) { if(is->pictq_size == 0) { schedule_refresh(is, 1); } else { vp = &is->pictq[is->pictq_rindex]; delay = vp->pts - is->frame_last_pts; if(delay <= 0 || delay >= 1.0) { delay = is->frame_last_delay; } is->frame_last_delay = delay; is->frame_last_pts = vp->pts; ref_clock = get_audio_clock(is); diff = vp->pts - ref_clock; sync_threshold = (delay > AV_SYNC_THRESHOLD) ? delay : AV_SYNC_THRESHOLD; if(fabs(diff) < AV_NOSYNC_THRESHOLD) { if(diff <= -sync_threshold) { delay = 0; } else if(diff >= sync_threshold) { delay = 2 * delay; } } is->frame_timer += delay; actual_delay = is->frame_timer - (av_gettime() / 1000000.0); if(actual_delay < 0.010) { actual_delay = 0.010; } schedule_refresh(is, (int)(actual_delay * 1000 + 0.5)); video_display(is); if(++is->pictq_rindex == VIDEO_PICTURE_QUEUE_SIZE) { is->pictq_rindex = 0; } SDL_LockMutex(is->pictq_mutex); is->pictq_size--; SDL_CondSignal(is->pictq_cond); SDL_UnlockMutex(is->pictq_mutex); } } else { schedule_refresh(is, 100); } } void alloc_picture(void *userdata) { VideoState *is = (VideoState *)userdata; VideoPicture *vp; vp = &is->pictq[is->pictq_windex]; if(vp->bmp) { // we already have one make another, bigger/smaller SDL_FreeYUVOverlay(vp->bmp); } // Allocate a place to put our YUV image on that screen vp->bmp = SDL_CreateYUVOverlay(is->video_st->codec->width, is->video_st->codec->height, SDL_YV12_OVERLAY, screen); vp->width = is->video_st->codec->width; vp->height = is->video_st->codec->height; SDL_LockMutex(is->pictq_mutex); vp->allocated = 1; SDL_CondSignal(is->pictq_cond); SDL_UnlockMutex(is->pictq_mutex); } int queue_picture(VideoState *is, AVFrame *pFrame, double pts) { VideoPicture *vp; //int dst_pix_fmt; AVPicture pict; SDL_LockMutex(is->pictq_mutex); while(is->pictq_size >= VIDEO_PICTURE_QUEUE_SIZE && !is->quit) { SDL_CondWait(is->pictq_cond, is->pictq_mutex); } SDL_UnlockMutex(is->pictq_mutex); if(is->quit) return -1; // windex is set to 0 initially vp = &is->pictq[is->pictq_windex]; if(!vp->bmp || vp->width != is->video_st->codec->width || vp->height != is->video_st->codec->height) { SDL_Event event; vp->allocated = 0; event.type = FF_ALLOC_EVENT; event.user.data1 = is; SDL_PushEvent(&event); SDL_LockMutex(is->pictq_mutex); while(!vp->allocated && !is->quit) { SDL_CondWait(is->pictq_cond, is->pictq_mutex); } SDL_UnlockMutex(is->pictq_mutex); if(is->quit) { return -1; } } static struct SwsContext *img_convert_ctx; if (img_convert_ctx == NULL) { img_convert_ctx = sws_getContext(is->video_st->codec->width, is->video_st->codec->height, is->video_st->codec->pix_fmt, is->video_st->codec->width, is->video_st->codec->height, PIX_FMT_YUV420P, SWS_BICUBIC, NULL, NULL, NULL); if (img_convert_ctx == NULL) { fprintf(stderr, "Cannot initialize the conversion context\n"); exit(1); } } if(vp->bmp) { SDL_LockYUVOverlay(vp->bmp); //dst_pix_fmt = PIX_FMT_YUV420P; pict.data[0] = vp->bmp->pixels[0]; pict.data[1] = vp->bmp->pixels[2]; pict.data[2] = vp->bmp->pixels[1]; pict.linesize[0] = vp->bmp->pitches[0]; pict.linesize[1] = vp->bmp->pitches[2]; pict.linesize[2] = vp->bmp->pitches[1]; // Convert the image into YUV format that SDL uses sws_scale(img_convert_ctx, pFrame->data, pFrame->linesize, 0, is->video_st->codec->height, pict.data, pict.linesize); SDL_UnlockYUVOverlay(vp->bmp); vp->pts = pts; if(++is->pictq_windex == VIDEO_PICTURE_QUEUE_SIZE) { is->pictq_windex = 0; } SDL_LockMutex(is->pictq_mutex); is->pictq_size++; SDL_UnlockMutex(is->pictq_mutex); } return 0; } double synchronize_video(VideoState *is, AVFrame *src_frame, double pts) { double frame_delay; if(pts != 0) { is->video_clock = pts; } else { pts = is->video_clock; } frame_delay = av_q2d(is->video_st->codec->time_base); frame_delay += src_frame->repeat_pict * (frame_delay * 0.5); is->video_clock += frame_delay; return pts; } uint64_t global_video_pkt_pts = AV_NOPTS_VALUE; int our_get_buffer(struct AVCodecContext *c, AVFrame *pic) { int ret = avcodec_default_get_buffer(c, pic); uint64_t *pts = (uint64_t *)av_malloc(sizeof(uint64_t)); *pts = global_video_pkt_pts; pic->opaque = pts; return ret; } void our_release_buffer(struct AVCodecContext *c, AVFrame *pic) { if(pic) av_freep(&pic->opaque); avcodec_default_release_buffer(c, pic); } int video_thread(void *arg) { VideoState *is = (VideoState *)arg; AVPacket pkt1, *packet = &pkt1; int len1, frameFinished; AVFrame *pFrame; double pts; pFrame = avcodec_alloc_frame(); for(;;) { if(packet_queue_get(&is->videoq, packet, 1) < 0) { // means we quit getting packets break; } pts = 0; // Save global pts to be stored in pFrame in first call global_video_pkt_pts = packet->pts; // Decode video frame len1 = avcodec_decode_video(is->video_st->codec, pFrame, &frameFinished, packet->data, packet->size); if(packet->dts == AV_NOPTS_VALUE && pFrame->opaque && *(uint64_t*)pFrame->opaque != AV_NOPTS_VALUE) { pts = *(uint64_t *)pFrame->opaque; } else if(packet->dts != AV_NOPTS_VALUE) { pts = packet->dts; } else { pts = 0; } pts *= av_q2d(is->video_st->time_base); // Did we get a video frame? if(frameFinished) { pts = synchronize_video(is, pFrame, pts); if(queue_picture(is, pFrame, pts) < 0) { break; } } av_free_packet(packet); } av_free(pFrame); return 0; } int stream_component_open(VideoState *is, int stream_index) { AVFormatContext *pFormatCtx = is->pFormatCtx; AVCodecContext *codecCtx; AVCodec *codec; SDL_AudioSpec wanted_spec, spec; if(stream_index < 0 || stream_index >= pFormatCtx->nb_streams) { return -1; } // Get a pointer to the codec context for the video stream codecCtx = pFormatCtx->streams[stream_index]->codec; if(codecCtx->codec_type == CODEC_TYPE_AUDIO) { // Set audio settings from codec info wanted_spec.freq = codecCtx->sample_rate; wanted_spec.format = AUDIO_S16SYS; wanted_spec.channels = codecCtx->channels; wanted_spec.silence = 0; wanted_spec.samples = SDL_AUDIO_BUFFER_SIZE; wanted_spec.callback = audio_callback; wanted_spec.userdata = is; if(SDL_OpenAudio(&wanted_spec, &spec) < 0) { fprintf(stderr, "SDL_OpenAudio: %s\n", SDL_GetError()); return -1; } is->audio_hw_buf_size = spec.size; } codec = avcodec_find_decoder(codecCtx->codec_id); if(!codec || (avcodec_open(codecCtx, codec) < 0)) { fprintf(stderr, "Unsupported codec!\n"); return -1; } switch(codecCtx->codec_type) { case CODEC_TYPE_AUDIO: is->audioStream = stream_index; is->audio_st = pFormatCtx->streams[stream_index]; is->audio_buf_size = 0; is->audio_buf_index = 0; memset(&is->audio_pkt, 0, sizeof(is->audio_pkt)); packet_queue_init(&is->audioq); SDL_PauseAudio(0); break; case CODEC_TYPE_VIDEO: is->videoStream = stream_index; is->video_st = pFormatCtx->streams[stream_index]; is->frame_timer = (double)av_gettime() / 1000000.0; is->frame_last_delay = 40e-3; packet_queue_init(&is->videoq); is->video_tid = SDL_CreateThread(video_thread, is); codecCtx->get_buffer = our_get_buffer; codecCtx->release_buffer = our_release_buffer; break; default: break; } return 0; } int decode_interrupt_cb(void) { return (global_video_state && global_video_state->quit); } int decode_thread(void *arg) { VideoState *is = (VideoState *)arg; AVFormatContext *pFormatCtx; AVPacket pkt1, *packet = &pkt1; int video_index = -1; int audio_index = -1; int i; is->videoStream=-1; is->audioStream=-1; global_video_state = is; // will interrupt blocking functions if we quit! url_set_interrupt_cb(decode_interrupt_cb); // Open video file if(av_open_input_file(&pFormatCtx, is->filename, NULL, 0, NULL)!=0) return -1; // Couldn't open file is->pFormatCtx = pFormatCtx; // Retrieve stream information if(av_find_stream_info(pFormatCtx)<0) return -1; // Couldn't find stream information // Dump information about file onto standard error dump_format(pFormatCtx, 0, is->filename, 0); // Find the first video stream for(i=0; i<pFormatCtx->nb_streams; i++) { if(pFormatCtx->streams[i]->codec->codec_type==CODEC_TYPE_VIDEO && video_index < 0) { video_index=i; } if(pFormatCtx->streams[i]->codec->codec_type==CODEC_TYPE_AUDIO && audio_index < 0) { audio_index=i; } } if(audio_index >= 0) { stream_component_open(is, audio_index); } if(video_index >= 0) { stream_component_open(is, video_index); } if(is->videoStream < 0 || is->audioStream < 0) { fprintf(stderr, "%s: could not open codecs\n", is->filename); goto fail; } // main decode loop for(;;) { if(is->quit) { break; } // seek stuff goes here if(is->audioq.size > MAX_AUDIOQ_SIZE || is->videoq.size > MAX_VIDEOQ_SIZE) { SDL_Delay(10); continue; } if(av_read_frame(is->pFormatCtx, packet) < 0) { if(url_ferror(pFormatCtx->pb) == 0) { SDL_Delay(100); continue; } else { break; } } // Is this a packet from the video stream? if(packet->stream_index == is->videoStream) { packet_queue_put(&is->videoq, packet); } else if(packet->stream_index == is->audioStream) { packet_queue_put(&is->audioq, packet); } else { av_free_packet(packet); } } while(!is->quit) { SDL_Delay(100); } fail: { SDL_Event event; event.type = FF_QUIT_EVENT; event.user.data1 = is; SDL_PushEvent(&event); } return 0; } int main(int argc, char *argv[]) { SDL_Event event; VideoState *is; is = (VideoState *)av_mallocz(sizeof(VideoState)); if(argc < 2) { fprintf(stderr, "Usage: test <file>\n"); exit(1); } // Register all formats and codecs av_register_all(); if(SDL_Init(SDL_INIT_VIDEO | SDL_INIT_AUDIO | SDL_INIT_TIMER)) { fprintf(stderr, "Could not initialize SDL - %s\n", SDL_GetError()); exit(1); } // Make a screen to put our video #ifndef __DARWIN__ screen = SDL_SetVideoMode(640, 480, 0, 0); #else screen = SDL_SetVideoMode(640, 480, 24, 0); #endif if(!screen) { fprintf(stderr, "SDL: could not set video mode - exiting\n"); exit(1); } //pstrcpy(is->filename, sizeof(is->filename), argv[1]); strcpy(is->filename,argv[1]); is->pictq_mutex = SDL_CreateMutex(); is->pictq_cond = SDL_CreateCond(); schedule_refresh(is, 40); is->parse_tid = SDL_CreateThread(decode_thread, is); if(!is->parse_tid) { av_free(is); return -1; } for(;;) { SDL_WaitEvent(&event); switch(event.type) { case FF_QUIT_EVENT: case SDL_QUIT: is->quit = 1; SDL_Quit(); exit(0); break; case FF_ALLOC_EVENT: alloc_picture(event.user.data1); break; case FF_REFRESH_EVENT: video_refresh_timer(event.user.data1); break; default: break; } } return 0; }
你帮我看一下
######你有没有最新的ffmpeg转码示范代码啊######回复 @Jack.arain : 给我一个示范代码好不,这上面的代码是一个示范代码,我把 avcodec_decode_audio3,######看了下代码, 不知道你用的是哪个版本的ffmpeg, 但你这个代码是非常老的了, 另外, 在ffmpeg后期的版本中, avcodec_decode_audio函数可能解码出来的数据要比实际的数据要长, 需要使用av_samples_get_buffer_size来获得实际大小.######C++我不懂,不过音视频解码的内核我写过不少。如果内核解别的不出错,那么噪音基本来源于输出的音频PCM的BUF不干净或者输入的频段信息有缺失,某个通道没有数据进入。前者你的输出BUF可能被别的代码(包括解码本身)写操作过。你查下有没有内存泄露的问题。后者,是你的输入不全的问题。更大概率是后者。前者要定期加入噪音的概率还是比较小。
这类问题的检测方法是外围做最简单的调用。验证调用方法和内核模块都没有问题。然后再堆叠其他系统模块上去。版权声明:本文内容由阿里云实名注册用户自发贡献,版权归原作者所有,阿里云开发者社区不拥有其著作权,亦不承担相应法律责任。具体规则请查看《阿里云开发者社区用户服务协议》和《阿里云开发者社区知识产权保护指引》。如果您发现本社区中有涉嫌抄袭的内容,填写侵权投诉表单进行举报,一经查实,本社区将立刻删除涉嫌侵权内容。