33.FFmpeg+OpenGLES+OpenSLES播放器实现
2018-10-17 本文已影响92人
任振铭
像素格式转换
像素格式描述了像素数据存储所用的格式。定义了像素在内存中的编码方式。FFmpeg支持的像素格式主要是rbg和yuv两种，具体可以在结构体AVPixelFormat中看到
/**
* Pixel format.
*
* @note
* AV_PIX_FMT_RGB32 is handled in an endian-specific manner. An RGBA
* color is put together as:
* (A << 24) | (R << 16) | (G << 8) | B
* This is stored as BGRA on little-endian CPU architectures and ARGB on
* big-endian CPUs.
*
* @par
* When the pixel format is palettized RGB32 (AV_PIX_FMT_PAL8), the palettized
* image data is stored in AVFrame.data[0]. The palette is transported in
* AVFrame.data[1], is 1024 bytes long (256 4-byte entries) and is
* formatted the same as in AV_PIX_FMT_RGB32 described above (i.e., it is
* also endian-specific). Note also that the individual RGB32 palette
* components stored in AVFrame.data[1] should be in the range 0..255.
* This is important as many custom PAL8 video codecs that were designed
* to run on the IBM VGA graphics adapter use 6-bit palette components.
*
* @par
* For all the 8 bits per pixel formats, an RGB32 palette is in data[1] like
* for pal8. This palette is filled in automatically by the function
* allocating the picture.
*/
enum AVPixelFormat {
AV_PIX_FMT_NONE = -1,
AV_PIX_FMT_YUV420P, ///< planar YUV 4:2:0, 12bpp, (1 Cr & Cb sample per 2x2 Y samples)
AV_PIX_FMT_YUYV422, ///< packed YUV 4:2:2, 16bpp, Y0 Cb Y1 Cr
AV_PIX_FMT_RGB24, ///< packed RGB 8:8:8, 24bpp, RGBRGB...
AV_PIX_FMT_BGR24, ///< packed RGB 8:8:8, 24bpp, BGRBGR...
AV_PIX_FMT_YUV422P, ///< planar YUV 4:2:2, 16bpp, (1 Cr & Cb sample per 2x1 Y samples)
AV_PIX_FMT_YUV444P, ///< planar YUV 4:4:4, 24bpp, (1 Cr & Cb sample per 1x1 Y samples)
AV_PIX_FMT_YUV410P, ///< planar YUV 4:1:0, 9bpp, (1 Cr & Cb sample per 4x4 Y samples)
AV_PIX_FMT_YUV411P, ///< planar YUV 4:1:1, 12bpp, (1 Cr & Cb sample per 4x1 Y samples)
AV_PIX_FMT_GRAY8, ///< Y , 8bpp
AV_PIX_FMT_MONOWHITE, ///< Y , 1bpp, 0 is white, 1 is black, in each byte pixels are ordered from the msb to the lsb
AV_PIX_FMT_MONOBLACK, ///< Y , 1bpp, 0 is black, 1 is white, in each byte pixels are ordered from the msb to the lsb
AV_PIX_FMT_PAL8, ///< 8 bits with AV_PIX_FMT_RGB32 palette
AV_PIX_FMT_YUVJ420P, ///< planar YUV 4:2:0, 12bpp, full scale (JPEG), deprecated in favor of AV_PIX_FMT_YUV420P and setting color_range
AV_PIX_FMT_YUVJ422P, ///< planar YUV 4:2:2, 16bpp, full scale (JPEG), deprecated in favor of AV_PIX_FMT_YUV422P and setting color_range
AV_PIX_FMT_YUVJ444P, ///< planar YUV 4:4:4, 24bpp, full scale (JPEG), deprecated in favor of AV_PIX_FMT_YUV444P and setting color_range
#if FF_API_XVMC
AV_PIX_FMT_XVMC_MPEG2_MC,///< XVideo Motion Acceleration via common packet passing
AV_PIX_FMT_XVMC_MPEG2_IDCT,
AV_PIX_FMT_XVMC = AV_PIX_FMT_XVMC_MPEG2_IDCT,
#endif /* FF_API_XVMC */
AV_PIX_FMT_UYVY422, ///< packed YUV 4:2:2, 16bpp, Cb Y0 Cr Y1
AV_PIX_FMT_UYYVYY411, ///< packed YUV 4:1:1, 12bpp, Cb Y0 Y1 Cr Y2 Y3
AV_PIX_FMT_BGR8, ///< packed RGB 3:3:2, 8bpp, (msb)2B 3G 3R(lsb)
AV_PIX_FMT_BGR4, ///< packed RGB 1:2:1 bitstream, 4bpp, (msb)1B 2G 1R(lsb), a byte contains two pixels, the first pixel in the byte is the one composed by the 4 msb bits
AV_PIX_FMT_BGR4_BYTE, ///< packed RGB 1:2:1, 8bpp, (msb)1B 2G 1R(lsb)
AV_PIX_FMT_RGB8, ///< packed RGB 3:3:2, 8bpp, (msb)2R 3G 3B(lsb)
AV_PIX_FMT_RGB4, ///< packed RGB 1:2:1 bitstream, 4bpp, (msb)1R 2G 1B(lsb), a byte contains two pixels, the first pixel in the byte is the one composed by the 4 msb bits
AV_PIX_FMT_RGB4_BYTE, ///< packed RGB 1:2:1, 8bpp, (msb)1R 2G 1B(lsb)
AV_PIX_FMT_NV12, ///< planar YUV 4:2:0, 12bpp, 1 plane for Y and 1 plane for the UV components, which are interleaved (first byte U and the following byte V)
AV_PIX_FMT_NV21, ///< as above, but U and V bytes are swapped
AV_PIX_FMT_ARGB, ///< packed ARGB 8:8:8:8, 32bpp, ARGBARGB...
AV_PIX_FMT_RGBA, ///< packed RGBA 8:8:8:8, 32bpp, RGBARGBA...
AV_PIX_FMT_ABGR, ///< packed ABGR 8:8:8:8, 32bpp, ABGRABGR...
AV_PIX_FMT_BGRA, ///< packed BGRA 8:8:8:8, 32bpp, BGRABGRA...
AV_PIX_FMT_GRAY16BE, ///< Y , 16bpp, big-endian
AV_PIX_FMT_GRAY16LE, ///< Y , 16bpp, little-endian
AV_PIX_FMT_YUV440P, ///< planar YUV 4:4:0 (1 Cr & Cb sample per 1x2 Y samples)
AV_PIX_FMT_YUVJ440P, ///< planar YUV 4:4:0 full scale (JPEG), deprecated in favor of AV_PIX_FMT_YUV440P and setting color_range
AV_PIX_FMT_YUVA420P, ///< planar YUV 4:2:0, 20bpp, (1 Cr & Cb sample per 2x2 Y & A samples)
#if FF_API_VDPAU
AV_PIX_FMT_VDPAU_H264,///< H.264 HW decoding with VDPAU, data[0] contains a vdpau_render_state struct which contains the bitstream of the slices as well as various fields extracted from headers
AV_PIX_FMT_VDPAU_MPEG1,///< MPEG-1 HW decoding with VDPAU, data[0] contains a vdpau_render_state struct which contains the bitstream of the slices as well as various fields extracted from headers
AV_PIX_FMT_VDPAU_MPEG2,///< MPEG-2 HW decoding with VDPAU, data[0] contains a vdpau_render_state struct which contains the bitstream of the slices as well as various fields extracted from headers
AV_PIX_FMT_VDPAU_WMV3,///< WMV3 HW decoding with VDPAU, data[0] contains a vdpau_render_state struct which contains the bitstream of the slices as well as various fields extracted from headers
AV_PIX_FMT_VDPAU_VC1, ///< VC-1 HW decoding with VDPAU, data[0] contains a vdpau_render_state struct which contains the bitstream of the slices as well as various fields extracted from headers
#endif
AV_PIX_FMT_RGB48BE, ///< packed RGB 16:16:16, 48bpp, 16R, 16G, 16B, the 2-byte value for each R/G/B component is stored as big-endian
AV_PIX_FMT_RGB48LE, ///< packed RGB 16:16:16, 48bpp, 16R, 16G, 16B, the 2-byte value for each R/G/B component is stored as little-endian
AV_PIX_FMT_RGB565BE, ///< packed RGB 5:6:5, 16bpp, (msb) 5R 6G 5B(lsb), big-endian
AV_PIX_FMT_RGB565LE, ///< packed RGB 5:6:5, 16bpp, (msb) 5R 6G 5B(lsb), little-endian
AV_PIX_FMT_RGB555BE, ///< packed RGB 5:5:5, 16bpp, (msb)1X 5R 5G 5B(lsb), big-endian , X=unused/undefined
AV_PIX_FMT_RGB555LE, ///< packed RGB 5:5:5, 16bpp, (msb)1X 5R 5G 5B(lsb), little-endian, X=unused/undefined
AV_PIX_FMT_BGR565BE, ///< packed BGR 5:6:5, 16bpp, (msb) 5B 6G 5R(lsb), big-endian
AV_PIX_FMT_BGR565LE, ///< packed BGR 5:6:5, 16bpp, (msb) 5B 6G 5R(lsb), little-endian
AV_PIX_FMT_BGR555BE, ///< packed BGR 5:5:5, 16bpp, (msb)1X 5B 5G 5R(lsb), big-endian , X=unused/undefined
AV_PIX_FMT_BGR555LE, ///< packed BGR 5:5:5, 16bpp, (msb)1X 5B 5G 5R(lsb), little-endian, X=unused/undefined
#if FF_API_VAAPI
/** @name Deprecated pixel formats */
/**@{*/
AV_PIX_FMT_VAAPI_MOCO, ///< HW acceleration through VA API at motion compensation entry-point, Picture.data[3] contains a vaapi_render_state struct which contains macroblocks as well as various fields extracted from headers
AV_PIX_FMT_VAAPI_IDCT, ///< HW acceleration through VA API at IDCT entry-point, Picture.data[3] contains a vaapi_render_state struct which contains fields extracted from headers
AV_PIX_FMT_VAAPI_VLD, ///< HW decoding through VA API, Picture.data[3] contains a VASurfaceID
/**@}*/
AV_PIX_FMT_VAAPI = AV_PIX_FMT_VAAPI_VLD,
#else
/**
* Hardware acceleration through VA-API, data[3] contains a
* VASurfaceID.
*/
AV_PIX_FMT_VAAPI,
#endif
AV_PIX_FMT_YUV420P16LE, ///< planar YUV 4:2:0, 24bpp, (1 Cr & Cb sample per 2x2 Y samples), little-endian
AV_PIX_FMT_YUV420P16BE, ///< planar YUV 4:2:0, 24bpp, (1 Cr & Cb sample per 2x2 Y samples), big-endian
AV_PIX_FMT_YUV422P16LE, ///< planar YUV 4:2:2, 32bpp, (1 Cr & Cb sample per 2x1 Y samples), little-endian
AV_PIX_FMT_YUV422P16BE, ///< planar YUV 4:2:2, 32bpp, (1 Cr & Cb sample per 2x1 Y samples), big-endian
AV_PIX_FMT_YUV444P16LE, ///< planar YUV 4:4:4, 48bpp, (1 Cr & Cb sample per 1x1 Y samples), little-endian
AV_PIX_FMT_YUV444P16BE, ///< planar YUV 4:4:4, 48bpp, (1 Cr & Cb sample per 1x1 Y samples), big-endian
#if FF_API_VDPAU
AV_PIX_FMT_VDPAU_MPEG4, ///< MPEG-4 HW decoding with VDPAU, data[0] contains a vdpau_render_state struct which contains the bitstream of the slices as well as various fields extracted from headers
#endif
AV_PIX_FMT_DXVA2_VLD, ///< HW decoding through DXVA2, Picture.data[3] contains a LPDIRECT3DSURFACE9 pointer
AV_PIX_FMT_RGB444LE, ///< packed RGB 4:4:4, 16bpp, (msb)4X 4R 4G 4B(lsb), little-endian, X=unused/undefined
AV_PIX_FMT_RGB444BE, ///< packed RGB 4:4:4, 16bpp, (msb)4X 4R 4G 4B(lsb), big-endian, X=unused/undefined
AV_PIX_FMT_BGR444LE, ///< packed BGR 4:4:4, 16bpp, (msb)4X 4B 4G 4R(lsb), little-endian, X=unused/undefined
AV_PIX_FMT_BGR444BE, ///< packed BGR 4:4:4, 16bpp, (msb)4X 4B 4G 4R(lsb), big-endian, X=unused/undefined
AV_PIX_FMT_YA8, ///< 8 bits gray, 8 bits alpha
AV_PIX_FMT_Y400A = AV_PIX_FMT_YA8, ///< alias for AV_PIX_FMT_YA8
AV_PIX_FMT_GRAY8A= AV_PIX_FMT_YA8, ///< alias for AV_PIX_FMT_YA8
AV_PIX_FMT_BGR48BE, ///< packed RGB 16:16:16, 48bpp, 16B, 16G, 16R, the 2-byte value for each R/G/B component is stored as big-endian
AV_PIX_FMT_BGR48LE, ///< packed RGB 16:16:16, 48bpp, 16B, 16G, 16R, the 2-byte value for each R/G/B component is stored as little-endian
/**
* The following 12 formats have the disadvantage of needing 1 format for each bit depth.
* Notice that each 9/10 bits sample is stored in 16 bits with extra padding.
* If you want to support multiple bit depths, then using AV_PIX_FMT_YUV420P16* with the bpp stored separately is better.
*/
AV_PIX_FMT_YUV420P9BE, ///< planar YUV 4:2:0, 13.5bpp, (1 Cr & Cb sample per 2x2 Y samples), big-endian
AV_PIX_FMT_YUV420P9LE, ///< planar YUV 4:2:0, 13.5bpp, (1 Cr & Cb sample per 2x2 Y samples), little-endian
AV_PIX_FMT_YUV420P10BE,///< planar YUV 4:2:0, 15bpp, (1 Cr & Cb sample per 2x2 Y samples), big-endian
AV_PIX_FMT_YUV420P10LE,///< planar YUV 4:2:0, 15bpp, (1 Cr & Cb sample per 2x2 Y samples), little-endian
AV_PIX_FMT_YUV422P10BE,///< planar YUV 4:2:2, 20bpp, (1 Cr & Cb sample per 2x1 Y samples), big-endian
AV_PIX_FMT_YUV422P10LE,///< planar YUV 4:2:2, 20bpp, (1 Cr & Cb sample per 2x1 Y samples), little-endian
AV_PIX_FMT_YUV444P9BE, ///< planar YUV 4:4:4, 27bpp, (1 Cr & Cb sample per 1x1 Y samples), big-endian
AV_PIX_FMT_YUV444P9LE, ///< planar YUV 4:4:4, 27bpp, (1 Cr & Cb sample per 1x1 Y samples), little-endian
AV_PIX_FMT_YUV444P10BE,///< planar YUV 4:4:4, 30bpp, (1 Cr & Cb sample per 1x1 Y samples), big-endian
AV_PIX_FMT_YUV444P10LE,///< planar YUV 4:4:4, 30bpp, (1 Cr & Cb sample per 1x1 Y samples), little-endian
AV_PIX_FMT_YUV422P9BE, ///< planar YUV 4:2:2, 18bpp, (1 Cr & Cb sample per 2x1 Y samples), big-endian
AV_PIX_FMT_YUV422P9LE, ///< planar YUV 4:2:2, 18bpp, (1 Cr & Cb sample per 2x1 Y samples), little-endian
AV_PIX_FMT_VDA_VLD, ///< hardware decoding through VDA
AV_PIX_FMT_GBRP, ///< planar GBR 4:4:4 24bpp
AV_PIX_FMT_GBR24P = AV_PIX_FMT_GBRP, // alias for #AV_PIX_FMT_GBRP
AV_PIX_FMT_GBRP9BE, ///< planar GBR 4:4:4 27bpp, big-endian
AV_PIX_FMT_GBRP9LE, ///< planar GBR 4:4:4 27bpp, little-endian
AV_PIX_FMT_GBRP10BE, ///< planar GBR 4:4:4 30bpp, big-endian
AV_PIX_FMT_GBRP10LE, ///< planar GBR 4:4:4 30bpp, little-endian
AV_PIX_FMT_GBRP16BE, ///< planar GBR 4:4:4 48bpp, big-endian
AV_PIX_FMT_GBRP16LE, ///< planar GBR 4:4:4 48bpp, little-endian
AV_PIX_FMT_YUVA422P, ///< planar YUV 4:2:2 24bpp, (1 Cr & Cb sample per 2x1 Y & A samples)
AV_PIX_FMT_YUVA444P, ///< planar YUV 4:4:4 32bpp, (1 Cr & Cb sample per 1x1 Y & A samples)
AV_PIX_FMT_YUVA420P9BE, ///< planar YUV 4:2:0 22.5bpp, (1 Cr & Cb sample per 2x2 Y & A samples), big-endian
AV_PIX_FMT_YUVA420P9LE, ///< planar YUV 4:2:0 22.5bpp, (1 Cr & Cb sample per 2x2 Y & A samples), little-endian
AV_PIX_FMT_YUVA422P9BE, ///< planar YUV 4:2:2 27bpp, (1 Cr & Cb sample per 2x1 Y & A samples), big-endian
AV_PIX_FMT_YUVA422P9LE, ///< planar YUV 4:2:2 27bpp, (1 Cr & Cb sample per 2x1 Y & A samples), little-endian
AV_PIX_FMT_YUVA444P9BE, ///< planar YUV 4:4:4 36bpp, (1 Cr & Cb sample per 1x1 Y & A samples), big-endian
AV_PIX_FMT_YUVA444P9LE, ///< planar YUV 4:4:4 36bpp, (1 Cr & Cb sample per 1x1 Y & A samples), little-endian
AV_PIX_FMT_YUVA420P10BE, ///< planar YUV 4:2:0 25bpp, (1 Cr & Cb sample per 2x2 Y & A samples, big-endian)
AV_PIX_FMT_YUVA420P10LE, ///< planar YUV 4:2:0 25bpp, (1 Cr & Cb sample per 2x2 Y & A samples, little-endian)
AV_PIX_FMT_YUVA422P10BE, ///< planar YUV 4:2:2 30bpp, (1 Cr & Cb sample per 2x1 Y & A samples, big-endian)
AV_PIX_FMT_YUVA422P10LE, ///< planar YUV 4:2:2 30bpp, (1 Cr & Cb sample per 2x1 Y & A samples, little-endian)
AV_PIX_FMT_YUVA444P10BE, ///< planar YUV 4:4:4 40bpp, (1 Cr & Cb sample per 1x1 Y & A samples, big-endian)
AV_PIX_FMT_YUVA444P10LE, ///< planar YUV 4:4:4 40bpp, (1 Cr & Cb sample per 1x1 Y & A samples, little-endian)
AV_PIX_FMT_YUVA420P16BE, ///< planar YUV 4:2:0 40bpp, (1 Cr & Cb sample per 2x2 Y & A samples, big-endian)
AV_PIX_FMT_YUVA420P16LE, ///< planar YUV 4:2:0 40bpp, (1 Cr & Cb sample per 2x2 Y & A samples, little-endian)
AV_PIX_FMT_YUVA422P16BE, ///< planar YUV 4:2:2 48bpp, (1 Cr & Cb sample per 2x1 Y & A samples, big-endian)
AV_PIX_FMT_YUVA422P16LE, ///< planar YUV 4:2:2 48bpp, (1 Cr & Cb sample per 2x1 Y & A samples, little-endian)
AV_PIX_FMT_YUVA444P16BE, ///< planar YUV 4:4:4 64bpp, (1 Cr & Cb sample per 1x1 Y & A samples, big-endian)
AV_PIX_FMT_YUVA444P16LE, ///< planar YUV 4:4:4 64bpp, (1 Cr & Cb sample per 1x1 Y & A samples, little-endian)
AV_PIX_FMT_VDPAU, ///< HW acceleration through VDPAU, Picture.data[3] contains a VdpVideoSurface
AV_PIX_FMT_XYZ12LE, ///< packed XYZ 4:4:4, 36 bpp, (msb) 12X, 12Y, 12Z (lsb), the 2-byte value for each X/Y/Z is stored as little-endian, the 4 lower bits are set to 0
AV_PIX_FMT_XYZ12BE, ///< packed XYZ 4:4:4, 36 bpp, (msb) 12X, 12Y, 12Z (lsb), the 2-byte value for each X/Y/Z is stored as big-endian, the 4 lower bits are set to 0
AV_PIX_FMT_NV16, ///< interleaved chroma YUV 4:2:2, 16bpp, (1 Cr & Cb sample per 2x1 Y samples)
AV_PIX_FMT_NV20LE, ///< interleaved chroma YUV 4:2:2, 20bpp, (1 Cr & Cb sample per 2x1 Y samples), little-endian
AV_PIX_FMT_NV20BE, ///< interleaved chroma YUV 4:2:2, 20bpp, (1 Cr & Cb sample per 2x1 Y samples), big-endian
AV_PIX_FMT_RGBA64BE, ///< packed RGBA 16:16:16:16, 64bpp, 16R, 16G, 16B, 16A, the 2-byte value for each R/G/B/A component is stored as big-endian
AV_PIX_FMT_RGBA64LE, ///< packed RGBA 16:16:16:16, 64bpp, 16R, 16G, 16B, 16A, the 2-byte value for each R/G/B/A component is stored as little-endian
AV_PIX_FMT_BGRA64BE, ///< packed RGBA 16:16:16:16, 64bpp, 16B, 16G, 16R, 16A, the 2-byte value for each R/G/B/A component is stored as big-endian
AV_PIX_FMT_BGRA64LE, ///< packed RGBA 16:16:16:16, 64bpp, 16B, 16G, 16R, 16A, the 2-byte value for each R/G/B/A component is stored as little-endian
AV_PIX_FMT_YVYU422, ///< packed YUV 4:2:2, 16bpp, Y0 Cr Y1 Cb
AV_PIX_FMT_VDA, ///< HW acceleration through VDA, data[3] contains a CVPixelBufferRef
AV_PIX_FMT_YA16BE, ///< 16 bits gray, 16 bits alpha (big-endian)
AV_PIX_FMT_YA16LE, ///< 16 bits gray, 16 bits alpha (little-endian)
AV_PIX_FMT_GBRAP, ///< planar GBRA 4:4:4:4 32bpp
AV_PIX_FMT_GBRAP16BE, ///< planar GBRA 4:4:4:4 64bpp, big-endian
AV_PIX_FMT_GBRAP16LE, ///< planar GBRA 4:4:4:4 64bpp, little-endian
/**
* HW acceleration through QSV, data[3] contains a pointer to the
* mfxFrameSurface1 structure.
*/
AV_PIX_FMT_QSV,
/**
* HW acceleration though MMAL, data[3] contains a pointer to the
* MMAL_BUFFER_HEADER_T structure.
*/
AV_PIX_FMT_MMAL,
AV_PIX_FMT_D3D11VA_VLD, ///< HW decoding through Direct3D11 via old API, Picture.data[3] contains a ID3D11VideoDecoderOutputView pointer
/**
* HW acceleration through CUDA. data[i] contain CUdeviceptr pointers
* exactly as for system memory frames.
*/
AV_PIX_FMT_CUDA,
AV_PIX_FMT_0RGB=0x123+4,///< packed RGB 8:8:8, 32bpp, XRGBXRGB... X=unused/undefined
AV_PIX_FMT_RGB0, ///< packed RGB 8:8:8, 32bpp, RGBXRGBX... X=unused/undefined
AV_PIX_FMT_0BGR, ///< packed BGR 8:8:8, 32bpp, XBGRXBGR... X=unused/undefined
AV_PIX_FMT_BGR0, ///< packed BGR 8:8:8, 32bpp, BGRXBGRX... X=unused/undefined
AV_PIX_FMT_YUV420P12BE, ///< planar YUV 4:2:0,18bpp, (1 Cr & Cb sample per 2x2 Y samples), big-endian
AV_PIX_FMT_YUV420P12LE, ///< planar YUV 4:2:0,18bpp, (1 Cr & Cb sample per 2x2 Y samples), little-endian
AV_PIX_FMT_YUV420P14BE, ///< planar YUV 4:2:0,21bpp, (1 Cr & Cb sample per 2x2 Y samples), big-endian
AV_PIX_FMT_YUV420P14LE, ///< planar YUV 4:2:0,21bpp, (1 Cr & Cb sample per 2x2 Y samples), little-endian
AV_PIX_FMT_YUV422P12BE, ///< planar YUV 4:2:2,24bpp, (1 Cr & Cb sample per 2x1 Y samples), big-endian
AV_PIX_FMT_YUV422P12LE, ///< planar YUV 4:2:2,24bpp, (1 Cr & Cb sample per 2x1 Y samples), little-endian
AV_PIX_FMT_YUV422P14BE, ///< planar YUV 4:2:2,28bpp, (1 Cr & Cb sample per 2x1 Y samples), big-endian
AV_PIX_FMT_YUV422P14LE, ///< planar YUV 4:2:2,28bpp, (1 Cr & Cb sample per 2x1 Y samples), little-endian
AV_PIX_FMT_YUV444P12BE, ///< planar YUV 4:4:4,36bpp, (1 Cr & Cb sample per 1x1 Y samples), big-endian
AV_PIX_FMT_YUV444P12LE, ///< planar YUV 4:4:4,36bpp, (1 Cr & Cb sample per 1x1 Y samples), little-endian
AV_PIX_FMT_YUV444P14BE, ///< planar YUV 4:4:4,42bpp, (1 Cr & Cb sample per 1x1 Y samples), big-endian
AV_PIX_FMT_YUV444P14LE, ///< planar YUV 4:4:4,42bpp, (1 Cr & Cb sample per 1x1 Y samples), little-endian
AV_PIX_FMT_GBRP12BE, ///< planar GBR 4:4:4 36bpp, big-endian
AV_PIX_FMT_GBRP12LE, ///< planar GBR 4:4:4 36bpp, little-endian
AV_PIX_FMT_GBRP14BE, ///< planar GBR 4:4:4 42bpp, big-endian
AV_PIX_FMT_GBRP14LE, ///< planar GBR 4:4:4 42bpp, little-endian
AV_PIX_FMT_YUVJ411P, ///< planar YUV 4:1:1, 12bpp, (1 Cr & Cb sample per 4x1 Y samples) full scale (JPEG), deprecated in favor of AV_PIX_FMT_YUV411P and setting color_range
AV_PIX_FMT_BAYER_BGGR8, ///< bayer, BGBG..(odd line), GRGR..(even line), 8-bit samples */
AV_PIX_FMT_BAYER_RGGB8, ///< bayer, RGRG..(odd line), GBGB..(even line), 8-bit samples */
AV_PIX_FMT_BAYER_GBRG8, ///< bayer, GBGB..(odd line), RGRG..(even line), 8-bit samples */
AV_PIX_FMT_BAYER_GRBG8, ///< bayer, GRGR..(odd line), BGBG..(even line), 8-bit samples */
AV_PIX_FMT_BAYER_BGGR16LE, ///< bayer, BGBG..(odd line), GRGR..(even line), 16-bit samples, little-endian */
AV_PIX_FMT_BAYER_BGGR16BE, ///< bayer, BGBG..(odd line), GRGR..(even line), 16-bit samples, big-endian */
AV_PIX_FMT_BAYER_RGGB16LE, ///< bayer, RGRG..(odd line), GBGB..(even line), 16-bit samples, little-endian */
AV_PIX_FMT_BAYER_RGGB16BE, ///< bayer, RGRG..(odd line), GBGB..(even line), 16-bit samples, big-endian */
AV_PIX_FMT_BAYER_GBRG16LE, ///< bayer, GBGB..(odd line), RGRG..(even line), 16-bit samples, little-endian */
AV_PIX_FMT_BAYER_GBRG16BE, ///< bayer, GBGB..(odd line), RGRG..(even line), 16-bit samples, big-endian */
AV_PIX_FMT_BAYER_GRBG16LE, ///< bayer, GRGR..(odd line), BGBG..(even line), 16-bit samples, little-endian */
AV_PIX_FMT_BAYER_GRBG16BE, ///< bayer, GRGR..(odd line), BGBG..(even line), 16-bit samples, big-endian */
#if !FF_API_XVMC
AV_PIX_FMT_XVMC,///< XVideo Motion Acceleration via common packet passing
#endif /* !FF_API_XVMC */
AV_PIX_FMT_YUV440P10LE, ///< planar YUV 4:4:0,20bpp, (1 Cr & Cb sample per 1x2 Y samples), little-endian
AV_PIX_FMT_YUV440P10BE, ///< planar YUV 4:4:0,20bpp, (1 Cr & Cb sample per 1x2 Y samples), big-endian
AV_PIX_FMT_YUV440P12LE, ///< planar YUV 4:4:0,24bpp, (1 Cr & Cb sample per 1x2 Y samples), little-endian
AV_PIX_FMT_YUV440P12BE, ///< planar YUV 4:4:0,24bpp, (1 Cr & Cb sample per 1x2 Y samples), big-endian
AV_PIX_FMT_AYUV64LE, ///< packed AYUV 4:4:4,64bpp (1 Cr & Cb sample per 1x1 Y & A samples), little-endian
AV_PIX_FMT_AYUV64BE, ///< packed AYUV 4:4:4,64bpp (1 Cr & Cb sample per 1x1 Y & A samples), big-endian
AV_PIX_FMT_VIDEOTOOLBOX, ///< hardware decoding through Videotoolbox
AV_PIX_FMT_P010LE, ///< like NV12, with 10bpp per component, data in the high bits, zeros in the low bits, little-endian
AV_PIX_FMT_P010BE, ///< like NV12, with 10bpp per component, data in the high bits, zeros in the low bits, big-endian
AV_PIX_FMT_GBRAP12BE, ///< planar GBR 4:4:4:4 48bpp, big-endian
AV_PIX_FMT_GBRAP12LE, ///< planar GBR 4:4:4:4 48bpp, little-endian
AV_PIX_FMT_GBRAP10BE, ///< planar GBR 4:4:4:4 40bpp, big-endian
AV_PIX_FMT_GBRAP10LE, ///< planar GBR 4:4:4:4 40bpp, little-endian
AV_PIX_FMT_MEDIACODEC, ///< hardware decoding through MediaCodec
AV_PIX_FMT_GRAY12BE, ///< Y , 12bpp, big-endian
AV_PIX_FMT_GRAY12LE, ///< Y , 12bpp, little-endian
AV_PIX_FMT_GRAY10BE, ///< Y , 10bpp, big-endian
AV_PIX_FMT_GRAY10LE, ///< Y , 10bpp, little-endian
AV_PIX_FMT_P016LE, ///< like NV12, with 16bpp per component, little-endian
AV_PIX_FMT_P016BE, ///< like NV12, with 16bpp per component, big-endian
/**
* Hardware surfaces for Direct3D11.
*
* This is preferred over the legacy AV_PIX_FMT_D3D11VA_VLD. The new D3D11
* hwaccel API and filtering support AV_PIX_FMT_D3D11 only.
*
* data[0] contains a ID3D11Texture2D pointer, and data[1] contains the
* texture array index of the frame as intptr_t if the ID3D11Texture2D is
* an array texture (or always 0 if it's a normal texture).
*/
AV_PIX_FMT_D3D11,
AV_PIX_FMT_GRAY9BE, ///< Y , 9bpp, big-endian
AV_PIX_FMT_GRAY9LE, ///< Y , 9bpp, little-endian
AV_PIX_FMT_GBRPF32BE, ///< IEEE-754 single precision planar GBR 4:4:4, 96bpp, big-endian
AV_PIX_FMT_GBRPF32LE, ///< IEEE-754 single precision planar GBR 4:4:4, 96bpp, little-endian
AV_PIX_FMT_GBRAPF32BE, ///< IEEE-754 single precision planar GBRA 4:4:4:4, 128bpp, big-endian
AV_PIX_FMT_GBRAPF32LE, ///< IEEE-754 single precision planar GBRA 4:4:4:4, 128bpp, little-endian
/**
* DRM-managed buffers exposed through PRIME buffer sharing.
*
* data[0] points to an AVDRMFrameDescriptor.
*/
AV_PIX_FMT_DRM_PRIME,
AV_PIX_FMT_NB ///< number of pixel formats, DO NOT USE THIS if you want to link with shared libav* because the number of formats might differ between versions
};
像素格式转换涉及到两个函数
sws_getCachedContext()（或sws_getContext()）:获取一个像素格式上下文对象
这个方法是相对于sws_getContext()的，区别在于是否有重用SwsContext对象的机制， sws_getCachedContext在调用时会检查当前上下文对象是否可重用，如果可以则使用，不可以再开辟新的，类似享元模式
struct SwsContext *context : 传入的上下文，可以为NULL。如果为NULL,那么调用sws_getContext获取新的上下文，如果不为NULL，会判断参数是否和context中保存的相等，如果相等则直接使用当前Context,否则就用这些参数构建一个新的context
int srcW：输入的一张像素图片的宽度
int srcH ：输入的一张像素图片的高度
enum AVPixelFormat srcFormat ：像素图片的格式
int dstW ：输出的像素图片的宽度
int dstH ：输出的像素图片的高度
enum AVPixelFormat dstFormat ：输出的像素图片的格式
int flags ：指定重新缩放视频所采用的算法
SwsFilter *srcFilter ：通常指定为0
SwsFilter *dstFilter：通常指定为0
const double *param：通常指定为0
sws_scale()：进行像素图片缩放
struct SwsContext *c ：通过sws_getCachedContext创建的上下文对象，这里要传入进去
const uint8_t *const srcSlice[] ：包含视频源数据的一个数组，指的就是解码后的AVFrame中的data数据
const int srcStride[] ：输入的stride，可以把stride看做每一行的字节数，对于视频，指每个图片行的字节大小，对于音频，指每个平面的字节大小，在代码中指的时AVFrame中的linesize
int srcSliceY：处理的起点位置,0表示从头开始处理
int srcSliceH ：stride（指一个像素切面）的高度，也就是他的行数
uint8_t *const dst[] ：转换之后输出的缓冲区
const int dstStride[] ：输出的stride高度,和输入对应
代码如下：
//*************************像素格式转换******************************
//像素格式转换的上下文
SwsContext *swsContext = NULL;
//像素格式转换的输出宽度和高度
int destWidth = 1280;
int destHeight = 720;
char *rgb = new char[1920*1080*4];
//*************************像素格式转换******************************
//*************************像素格式转换******************************
//sws_getContext() sws_freeContext()
swsContext = sws_getCachedContext(
swsContext,
avFrame->width,
avFrame->height,
(AVPixelFormat)avFrame->format,
destWidth,
destHeight,
AV_PIX_FMT_RGBA,
// flag 指定用于重新缩放的算法和选项 SWS_FAST_BILINEAR双线性的
SWS_FAST_BILINEAR,
0,0,0
);
if (swsContext == NULL){
LOGE("sws_getCachedContext failed!");
}
uint8_t *data[AV_NUM_DATA_POINTERS] = {0};
data[0] =(uint8_t *)rgb;
int lines[AV_NUM_DATA_POINTERS] = {0};
lines[0] = destWidth * 4;
int h = sws_scale(
swsContext,
//输入的源buffer
(const uint8_t **)avFrame->data,
//输入的stride，可以把stride看做每一行的字节数
//对于视频，指每个图片行的字节大小。
//对于音频，指每个平面的字节大小
avFrame->linesize,
//处理的起点位置,0表示从头开始处理
0,
//源的高度
avFrame->height,
//输出的缓冲区buffer
data,
//输出的stride,和输入对应
lines
);
LOGI("sws_scale = %d",h);
if(h>0){
ANativeWindow_lock(nativeWindow,&nativeWindow_buffer,0);
uint8_t *dst = (uint8_t*)nativeWindow_buffer.bits;
memcpy(dst,rgb,destWidth*destHeight*4);
ANativeWindow_unlockAndPost(nativeWindow);
}
//*************************像素格式转换******************************
音频重采样
在声纹识别中，为了满足对不同采样率的要求，常需要对语音进行重采样。重采样即将原始的采样频率变换为新的采样频率以适应不同采样率的要求（人耳能够感觉到的最高频率为20kHz，因此要满足人耳的听觉要求，则需要至少每秒进行40k次采样，用40kHz表达，这个40kHz就是采样率。我们常见的CD，采样率为44.1kHz）
ffmpeg种处理音频采样涉及到的函数
swr_alloc ： 创建一个SwrContext上下文对象
swr_alloc_set_opts：创建SwrContext或者为SwrContext设置参数
这个方法不依赖swr_alloc来创建上下文对象，也就是说如果传入的SwrContext是null的话，他会创建出来并设置参数。这个方法就是设置输出的音频的一些相关参数，你当然可以设置为和输入相同，但这样做也就达不到重采样的目的了
struct SwrContext *s：如果已经存在了SwrContext 就传入，没有则传NULL
int64_t out_ch_layout : 音频输出的声道布局，av_get_default_channel_layout(2),输入指定的声道数，调用这个方法即可
enum AVSampleFormat out_sample_fmt ：输出的样本格式，有如下选择
enum AVSampleFormat {
AV_SAMPLE_FMT_NONE = -1,
AV_SAMPLE_FMT_U8, ///< unsigned 8 bits
AV_SAMPLE_FMT_S16, ///< signed 16 bits
AV_SAMPLE_FMT_S32, ///< signed 32 bits
AV_SAMPLE_FMT_FLT, ///< float
AV_SAMPLE_FMT_DBL, ///< double
AV_SAMPLE_FMT_U8P, ///< unsigned 8 bits, planar
AV_SAMPLE_FMT_S16P, ///< signed 16 bits, planar
AV_SAMPLE_FMT_S32P, ///< signed 32 bits, planar
AV_SAMPLE_FMT_FLTP, ///< float, planar
AV_SAMPLE_FMT_DBLP, ///< double, planar
AV_SAMPLE_FMT_S64, ///< signed 64 bits
AV_SAMPLE_FMT_S64P, ///< signed 64 bits, planar
AV_SAMPLE_FMT_NB ///< Number of sample formats. DO NOT USE if linking dynamically
};
int out_sample_rate :输出的采样率，可以和输入的一致，也可以指定
int64_t in_ch_layout：输入的声道布局
enum AVSampleFormat in_sample_fmt ：输入的样本格式
int in_sample_rate ：输入的采样率
int log_offset ：设置为0即可
void *log_ctx ：设置为0即可
swr_init 参数设置之后初始化SwrContext
swr_convert ：开始转换，得到采样后的音频存储在数组种准备播放
struct SwrContext *s：被初始化的函数参数的SwrContext ，这个参数规定了音频重采样的转换格式
uint8_t **out ：输出缓冲区
int out_count ：输出一帧音频含有的样本数avFrame->nb_samples
const uint8_t **in ：输人的数据源avFrame->data
int in_count：输入的每帧音频含有的样本数avFrame->nb_samples
音频重采样的关键代码为：
SwrContext *swrContext = swr_alloc();
//给重采样上下文填充参数
swrContext = swr_alloc_set_opts(
swrContext,
//输出的channel layout
av_get_default_channel_layout(2),
//输出的样本格式
AV_SAMPLE_FMT_S16,
//输出的采样率
audioCodecContext->sample_rate,
//输入的channel layout
av_get_default_channel_layout(audioCodecContext->channels),
//输入的样本格式
audioCodecContext->sample_fmt,
//输入的采样率
audioCodecContext->sample_rate,
0, 0
);
//swr_init(), swr_free()
//设置参数之后进行上下文初始化
result = swr_init(swrContext);
if (result != 0){
LOGW("swr_init failed!");
} else {
LOGW("swr_init success!");
}
//********************音频重采样*****************************
//********************音频重采样*****************************
uint8_t *out[2] = {0};
out[0] = (uint8_t*) pcm;
int len = swr_convert(
swrContext,
//输出缓冲区
out,
//输出一帧音频含有的样本数
avFrame->nb_samples,
//输入的源缓冲区
(const uint8_t**)avFrame->data,
//输入的每帧音频含有的样本数
avFrame->nb_samples
);
LOGI("swr_convert = %d",len);
//********************音频重采样*****************************
