vault backup: 2025-03-04 11:17:00

2025-03-04 11:17:00 +08:00
parent d1e51bfd2f
commit ff12c4f4ca
161 changed files with 1 additions and 2 deletions
--- a/Programming/FFMPEG/FFMpeg.md
+++ b/Programming/FFMPEG/FFMpeg.md
@@ -0,0 +1,303 @@
+## Initialization
+```cpp
+av_register_all();
+avformat_network_init();
+```
+
+## Command line
+利用FFMpeg來轉檔
+```
+ffmpeg -i <SOURCE.mp4> -t 10 -s <W>x<H> -pix_fmt <OUTPUT_FORMAT> <OUTPUT_FILENAME>
+```
+- `-i`：來源檔名
+- `-t`：影片長度（秒）
+- `-s`：影片大小，長x寬
+- `-pix_fmt`：輸出的影像格式
+
+example:
+```
+ffmpeg -i test.mp4 -t 10 -s 240x128 -pix_fmt yuv420p out240x128.yuv
+```
+
+## Open file
+使用`avformat_open_input()`來打開檔案。
+```cpp
+AVFormatContext* pFormatContext = NULL;
+char* path = "E:\\download\\Incredible Patagonia_1920x1080.mp4";
+AVDictionary* pDict = NULL;
+
+int result = avformat_open_input(&pFormatContext, path, NULL, &pDict);
+```
+若是開啟失敗`result`會是一個非0的值。可以用`av_strerror()`來印出詳細的錯誤訊息。例：
+```cpp
+char errorMsg[1024] = { 0 };
+av_strerror(result, errorMsg, sizeof(errorMsg) - 1);
+printf("Open file %s error, code = %d, message = %s\n", path, result, errorMsg);
+```
+
+### Get file information
+用`avformat_find_stream_info()`來把檔案的video/audio相關訊息放到`AVFormatContext`裡面。例：
+```cpp
+result = avformat_find_stream_info(pFormatContext, NULL);
+```
+也可以用
+```cpp
+av_dump_format(pFormatContext, 0, path, 0);
+```
+來直接印出相關訊息，不過這方法是Ffmpeg內定的，如果要印出自己想要的內容，就必須將`AVFormatContext`裡面的`AVStream`一一撈出來：
+```cpp
+for (int i = 0; i < pFormatContext->nb_streams; i++) {
+    AVStream* avStream = pFormatContext->streams[i];
+
+    if (avStream->codecpar->codec_type == AVMEDIA_TYPE_AUDIO) {
+        printf("Stream[%d] is a audio stream.\n", i);
+        printf("    Sample rate: %d\n", avStream->codecpar->sample_rate);
+        printf("    Format     : %d\n", avStream->codecpar->format);
+        printf("    Channels   : %d\n", avStream->codecpar->channels);
+        printf("    FPS        : %d/%d\n", avStream->avg_frame_rate.num, avStream->avg_frame_rate.den);
+        printf("    Frame Size : %d\n", avStream->codecpar->frame_size);
+        printf("    Codec ID   : %d\n", avStream->codecpar->codec_id);
+    } else if (avStream->codecpar->codec_type == AVMEDIA_TYPE_VIDEO) {
+        printf("Stream[%d] is a video stream.\n", i);
+        printf("    Width : %d\n", avStream->codecpar->width);
+        printf("    Height: %d\n", avStream->codecpar->height);
+        printf("    FPS   : %d/%d\n", avStream->avg_frame_rate.num, avStream->avg_frame_rate.den);
+        printf("    Codec ID: %d\n", avStream->codecpar->codec_id);
+    }
+}
+```
+這個for-loop可以找出檔案裡面的video stream index與audio stream index。
+
+另一個找出video stream index與audio stream index的方法：
+```cpp
+int videoStream = av_find_best_stream(pFormatContext, AVMEDIA_TYPE_VIDEO, -1, -1, NULL, 0);
+int audioStream = av_find_best_stream(pFormatContext, AVMEDIA_TYPE_AUDIO, -1, -1, NULL, 0);
+printf("Found best video stream index: %d\n", videoStream);
+printf("Found best audio stream index: %d\n", audioStream);
+```
+
+## Demux
+### 重要結構
+#### AVPackt
+##### 重要的member：
+- `AVBufferRef *buf`：buffer的reference count，基本上不會用到。
+- `int64_t pts`：顯示順序
+- `int64_t dts`：decode順序
+- `uint8_t *data`：實際存data的buffer
+- `int size`：上面那個buffer的大小
+
+##### 操作function
+- `AVPacket* av_packet_alloc()`：產生一個兂的AVPacket
+- `AVPacket* av_packet_clone(const AVPacket*)`：複製一個AVPacket
+- `int av_packet_ref(AVPacket*, const AVPacket*)`：增加reference count
+- `av_packet_unref(AVPacket*)`：減少reference count
+- `void av_packet_free(AVPacket**)`：釋放AVPacket
+- `void av_init_packet(AVPacket*)`：初始化AVPacket
+- `int av_packet_from_data(AVPacket*, uint8_t*, int size)`：從自己的data 
+- `av_seek_frame`：
+    - `AVFormatContext*`
+    - `int stream_index`：要seek的stream
+    - `int64_t timestamp`：timestamp
+    - `int flag`：seek的方法
+        - `#define AVSEEK_FLAG_BACKWARD 1`：往後找
+        - `#define AVSEEK_FLAG_BYTE     2`：以byte為單位，跳到timestamp相對應的byte
+        - `#define AVSEEK_FLAG_ANY      4`：跳到任意frame，不一定要key frame
+        - `#define AVSEEK_FLAG_FRAME    8`：依照frame number來找
+
+## Decode
+### 重要結構
+#### AVCodecContext
+##### 重要的member
+- `int thread_count`：執行續的數量
+- `AVRational time_base`
+
+##### 操作function
+- `avcodec_register_all()`：註冊所有的decoder。
+- `AVCodec* avcodec_find_decoder(enum AVCodecID)`：用codec ID來找到相對應的codec instance
+- `AVCodec* avcodec_find_decoder_by_name(const char* name)`：用codec的名子來找到相對應的codec instance
+- `AVCodecContext* avcodec_alloc_context3(const AVCodec*)`：用codec來建立`AVCodecContext`，codec只是用來解碼，解碼之後的相關資料要放在`AVCodecContext`裡面。
+- `void avcodec_free_context(AVCodecContext**)`：釋放`AVCodecContext`。
+- `int avcodec_open2(AVCodecContext*, const AVCodec*, AVDictionary*)`
+    - 開始解碼
+    - `AVDictionary`的選項請看`libavcodec/options_table.h`
+
+#### AVFrame
+##### 重要的member
+- `uint8_t* data[AV_NUM_DATA_POINTERS]`：存放這個frame的資料
+- `int linesize[AV_NUM_DATA_POINTERS]`：存放指向各個plane的pointer
+    - Plane mode
+        - For video
+            - 0：Y
+            - 1：U
+            - 2：V
+            - 3：NULL
+        - For audio
+            - 0：Left channel
+            - 1：Right channel
+            - 2：NULL
+    - Non plane mode
+        - For video
+            - 0：RGB RGB RGB
+            - 1：NULL
+- `int width`：For video, frame width
+- `int height`：For video, frame height
+- `int nb_samples`：For audio
+- `int64_t pts`：這個frame的pts
+- `int64_t pkt_dts`：Packet的dts
+- `int sample_rate`：For audio，sampling rate
+- `uint64_t channel_layout`：For audio
+- `int channels`：For audio
+- `int format`：For video it's AVPixelFormat, for audio it's AVSampleFormat
+
+##### 操作function
+- `AVFrame* av_frame_alloc()`：
+- `void av_frame_free(AVFrame*)`：
+- `AVFrame* av_frame_clone(const AVFrame*)`：
+- `int av_frame_ref(AVFrame* dst, const AVFrame* src)`：
+- `void av_frame_unref(AVFrame*)`：
+- `int avcodec_send_packet(AVCodecContext*, const AVPacket*)`
+- `int avcodec_receive_frame(AVCodecContext*, AVFrame*)`
+
+## Frame scaling
+##### 操作function
+- `sws_getContext`
+- `sws_getCachedContext`
+    ```
+    SwsContext* sws_getCachedContext(
+        SwsContext*, 
+        int srcW, int srcH, enum AVPixelFormat srcFormat,
+        int dstW, int dstH, enum AVPixelFormat dstFormat,
+        int flags,
+        SwsFilter srcFilter,
+        SwsFilter dstFilter,
+        const double* param)
+    ```
+- `sws_scale`
+    ```
+    int sws_scale(
+        SwsContext*,
+        const uint8_t* const srcSlice[], // 來源buffer的pointer, 如果是plane mode，要丟srcSlice[3]
+        const int srcStride[],           // linesize
+        int srcSliceY,
+        int srcSliceH,                   // image height
+        uint8_t* const dst[],            // 目標buffer的pointer, 如果是plane mode，要丟dst[3]
+        const int dstStride[])           // linesize
+    ```
+- `void sws_freeContext(SwsContext*)`
+
+## Audio resampling
+- `SwrContext* swr_alloc()`
+- `swr_alloc_set_opts`
+    ```cpp
+    SwrContext* swr_alloc_set_opts(
+        SwrContext*,
+        int64_t out_ch_layout,           // Output
+        AVSampleFormat outSampleFormat,  // Output
+        int outSampleRate,               // Output
+        int64_t in_ch_layout,            // Input
+        AVSampleFormat inSampleFormat,   // Input
+        int inSampleRate,                // Input
+        int log_offset,                  // 一般丟0
+        void* log_ctx)                   // 一般丟0
+    ```
+- `int swr_init(SwrContext*)`
+- `void swr_free(SwrContext**)`
+- `swr_convert`
+    ```cpp
+    int swt_convert(
+        SwrContext*,
+        uint8_t** outData,
+        int outCount,        // Sample count for one channel
+        uint8_t** inData,
+        int inCount)         // Sample count for one channel
+    ```
+    
+## Audio 播放
+### 會用到的class
+#### QAudioFormat 
+- `setSampleRate`
+- `setSampleSize`
+- `setChannelCount`
+- `setCodec("audio/pcm")`
+- `setByteOrder(QAudioFormat::LittleEndian)`
+- `setSampleType(QAudioFormat::UnSignedInt)`
+
+#### QAudioOutput
+- Constuctor參數就是一個`QAudioFormat`
+- `QIODevice* start()`
+- `suspend()`
+- `resume()`
+- `bufferSize()`
+- `byteFree()`
+- `periodSize()`
+
+#### QIODevice
+- `qint64 write(const char* data, qint64 len)`
+
+#### QBuffer
+```cpp
+QBuffer buffer;
+
+if (buffer.open(QIODevice::ReadWrite)) {
+    qInfo() << "Buffer Opened!";
+    QByteArray data("Hello World");
+
+    for (int i = 0; i < 5; i++) {
+        buffer.write(data);
+        buffer.write("\r\n");
+    }
+    //File and device access you may need to flush the data to the device
+    //buffer.flush()
+
+    //Move to the first position
+    buffer.seek(0);
+
+    qInfo() << buffer.readAll();     // retuen a QVariant
+    qInfo() << "closing the buffer";
+
+    //ALWAYS close your device!
+    buffer.close();
+}
+```
+
+### Example
+```cpp
+QAudioFormat audioFormat;
+audioFormat.setSampleRate(44100);
+audioFormat.setSampleSize(16);
+audioFormat.setChannelCount(2);
+audioFormat.setCodec("audio/pcm");
+audioFormat.setByteOrder(QAudioFormat::LittleEndian);
+audioFormat.setSampleType(QAudioFormat::UnSignedInt);
+
+QAudioOutput* audioOutput = new QAudioOutput(audioFormat);
+QIODevice* ioDevice = audioOutput->start();
+
+int size = audioOutput->periodSize();
+char* buffer = new char[size];
+FILE *pFile = fopen("E:\\download\\out.pcm", "rb");
+while (!feof(pFile)) {
+    if (audioOutput->bytesFree() < size) {
+        QThread::msleep(1);
+    }
+
+    qint64 len = fread(buffer, 1, size, pFile);
+    if (len <= 0) {
+        break;
+    }
+    ioDevice->write(buffer, len);
+}
+fclose(pFile);
+delete buffer;
+buffer = NULL;
+```
+
+### 使用FFmpeg decode audio
+- [音视频开发之旅（60) -调试分析FFmpeg (解封装部分的）常用结构体](https://zhuanlan.zhihu.com/p/441055685)
+
+## 參考資料
+- [mpv.io](https://mpv.io/)
+- [《FFmpeg基础知识》](https://opensourcelibs.com/lib/zhangfangtaozft-ffmpeg)
+- [ffmpeg - 专题 - 简书](https://www.jianshu.com/c/21a6fafc8ee3)
+- [FFmpeg打开输入文件 · FFmpeg原理](https://ffmpeg.xianwaizhiyin.net/api-ffmpeg/input.html)
+- [FFplay视频同步分析 - 掘金](https://juejin.cn/post/7156903872789741581)