FFMPEG-PTS和dts对视频没有适当增加，但对音频有增加

Question

Application provided invalid, non monotonically increasing dts to muxer in stream 0

非单调递增的dts是什么意思？

如何使用libavformat以相同的编解码器连接2个视频文件？

流中dts到muxer的非单调递增

typedef struct Video {
    char* filename;
    AVFormatContext* inputContext;
    AVFormatContext* outputContext;
    AVCodec* videoCodec;
    AVCodec* audioCodec;
    AVStream* inputStream;
    AVStream* outputStream;
    AVCodecContext* videoCodecContext_I; // Input
    AVCodecContext* audioCodecContext_I; // Input
    AVCodecContext* videoCodecContext_O; // Output
    AVCodecContext* audioCodecContext_O; // Output
    int videoStream;
    int audioStream;
    SwrContext* swrContext;
} Video;

typedef struct ClipSequence {
    VideoList* videos;
    AVFormatContext* outputContext;
    AVStream* outputStream;
    int64_t lastpts, lastdts;
    int64_t currentpts, currentdts;
} ClipSequence;

int decodeVideoSequence(ClipSequence* sequence, Video* video, AVPacket* packet, AVFrame* frame) {
    int response = avcodec_send_packet(video->videoCodecContext_I, packet);
    if (response < 0) {
        printf("[ERROR] Failed to send video packet to decoder\n");
        return response;
    }
    while (response >= 0) {
        response = avcodec_receive_frame(video->videoCodecContext_I, frame);
        if (response == AVERROR(EAGAIN) || response == AVERROR_EOF) {
            break;
        } else if (response < 0) {
            printf("[ERROR] Failed to receive video frame from decoder\n");
            return response;
        }
        if (response >= 0) {
            // Do stuff and encode
            sequence->currentpts = packet->pts; // Store decoded packet's pts and dts
            sequence->currentdts = packet->dts;
            if (encodeVideoSequence(sequence, video, frame) < 0) {
                printf("[ERROR] Failed to encode new video\n");
                return -1;
            }
        }
        av_frame_unref(frame);
    }
    return 0;
}

int encodeVideoSequence(ClipSequence* sequence, Video* video, AVFrame* frame) {
    AVPacket* packet = av_packet_alloc();
    if (!packet) {
        printf("[ERROR] Could not allocate memory for video output packet\n");
        return -1;
    }
    int response = avcodec_send_frame(video->videoCodecContext_O, frame);
    if (response < 0) {
        printf("[ERROR] Failed to send video frame for encoding\n");
        return response;
    }
    while (response >= 0) {
        response = avcodec_receive_packet(video->videoCodecContext_O, packet);
        if (response == AVERROR(EAGAIN) || response == AVERROR_EOF) {
            break;
        } else if (response < 0) {
            printf("[ERROR] Failed to receive video packet from encoder\n");
            return response;
        }
        // Set packet to have pts and dts based on the previous video's pts and dts
        packet->flags |= AV_PKT_FLAG_KEY;
        packet->pts = sequence->currentpts + sequence->lastpts;
        packet->dts = sequence->currentdts + sequence->lastdts;
        packet->stream_index = video->videoStream;
        packet->duration = 1000; // 60 fps
        response = av_interleaved_write_frame(sequence->outputContext, packet);
        if (response < 0) {
            printf("[ERROR] Failed to write video packet\n");
            break;
        }
    }
    av_packet_unref(packet);
    av_packet_free(&packet);
    return 0;
}

int readSequenceFrames(ClipSequence* sequence, Video* video, AVPacket* packet, AVFrame* frame) {
    if (!packet) {
        printf("[ERROR] Packet not allocated to be read\n");
        return -1;
    }
    if (!frame) {
        printf("[ERROR] Frame not allocated to be read\n");
        return -1;
    }
    // Sets video and audio codec context parameters
    if (prepareVideoOutStream(video) < 0) {
        printf("[ERROR] Failed to prepare output video stream\n");
        return -1;
    }
    if (prepareAudioOutStream(video) < 0) {
        printf("[ERROR] Failed to prepare output audio stream\n");
        return -1;
    }
    // Prepares audio resampling
    if (initResampler(video->audioCodecContext_I, video->audioCodecContext_O, &(video->swrContext)) < 0) {
        printf("[ERROR] Failed to init audio resampler\n");
        return -1;
    }
    // Read packets
    int frameNum = 0;
    while (av_read_frame(video->inputContext, packet) >= 0) {
        printf("[READ] Reading frame %i\n", frameNum);
        if (packet->stream_index == video->videoStream) {
            if (decodeVideoSequence(sequence, video, packet, frame) < 0) {
                printf("[ERROR] Failed to decode and encode video\n");
                return -1;
            }
        } else if (packet->stream_index == video->audioStream) {
            if (decodeAudioSequence(sequence, video, packet, frame) < 0) {
                printf("[ERROR] Failed to decode and encode audio\n");
                return -1;
            }
        }
        av_packet_unref(packet);
        frameNum++;
    }
    // Increment pts and dts by the last pts and dts in the current video
    sequence->lastpts += sequence->currentpts;
    sequence->lastdts += sequence->currentdts;
    return 0;
}

我相信当我增加pts和DTS时，我有正确的逻辑。我不知道我到底错过了什么。

谢了。

Answer 1

   // Increment pts and dts by the last pts and dts in the current video
    sequence->lastpts += sequence->currentpts;
    sequence->lastdts += sequence->currentdts;

这是不对的。首先，现在忽略PTS，只处理DTS。

DTS不是一个相对数，它是一个绝对数。将递增的数字加在一起会创建一个指数序列。例如：如果这是一个30 fps的视频，时基是1/30，每帧DTS将前进一个。例如0、1、2、3、4、5、6、7、9

如果你继续把它们加在一起，你会得到:0，1，3，6，10，15，21，28，36，45

否则，当需要增加1帧时，此帧将具有与前一帧相同的DTS

下一个临时秘书处：

PTS不是单调的，可以在时间上倒退。您不能以这种方式跟踪它，因为下一个PTS可能是一个较低的时间戳。要解决这个问题，您需要将PTS转换为CTS，然后返回：

auto cts = packet->pts - packet->dts
packet->dts = // Whatever you are updating the dts to
packet->pts = packet->dts + cts