像素格式轉(zhuǎn)換
像素格式描述了像素?cái)?shù)據(jù)存儲所用的格式夕冲。定義了像素在內(nèi)存中的編碼方式妓柜。FFmpeg支持的像素格式主要是rbg和yuv兩種谦炒,具體可以在結(jié)構(gòu)體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
};
像素格式轉(zhuǎn)換涉及到兩個(gè)函數(shù)
sws_getCachedContext()(或sws_getContext()):獲取一個(gè)像素格式上下文對象
這個(gè)方法是相對于sws_getContext()的赂鲤,區(qū)別在于是否有重用SwsContext對象的機(jī)制, sws_getCachedContext在調(diào)用時(shí)會檢查當(dāng)前上下文對象是否可重用测僵,如果可以則使用逊躁,不可以再開辟新的,類似享元模式
struct SwsContext *context : 傳入的上下文盾舌,可以為NULL墓臭。如果為NULL,那么調(diào)用sws_getContext獲取新的上下文,如果不為NULL妖谴,會判斷參數(shù)是否和context中保存的相等窿锉,如果相等則直接使用當(dāng)前Context,否則就用這些參數(shù)構(gòu)建一個(gè)新的context
int srcW:輸入的一張像素圖片的寬度
int srcH :輸入的一張像素圖片的高度
enum AVPixelFormat srcFormat :像素圖片的格式
int dstW :輸出的像素圖片的寬度
int dstH :輸出的像素圖片的高度
enum AVPixelFormat dstFormat :輸出的像素圖片的格式
int flags :指定重新縮放視頻所采用的算法
SwsFilter *srcFilter :通常指定為0
SwsFilter *dstFilter:通常指定為0
const double *param:通常指定為0
sws_scale():進(jìn)行像素圖片縮放
struct SwsContext *c :通過sws_getCachedContext創(chuàng)建的上下文對象,這里要傳入進(jìn)去
const uint8_t *const srcSlice[] :包含視頻源數(shù)據(jù)的一個(gè)數(shù)組窖维,指的就是解碼后的AVFrame中的data數(shù)據(jù)
const int srcStride[] :輸入的stride榆综,可以把stride看做每一行的字節(jié)數(shù)妙痹,對于視頻铸史,指每個(gè)圖片行的字節(jié)大小,對于音頻怯伊,指每個(gè)平面的字節(jié)大小琳轿,在代碼中指的時(shí)AVFrame中的linesize
int srcSliceY:處理的起點(diǎn)位置,0表示從頭開始處理
int srcSliceH :stride(指一個(gè)像素切面)的高度,也就是他的行數(shù)
uint8_t *const dst[] :轉(zhuǎn)換之后輸出的緩沖區(qū)
const int dstStride[] :輸出的stride高度,和輸入對應(yīng)
代碼如下:
//*************************像素格式轉(zhuǎn)換******************************
//像素格式轉(zhuǎn)換的上下文
SwsContext *swsContext = NULL;
//像素格式轉(zhuǎn)換的輸出寬度和高度
int destWidth = 1280;
int destHeight = 720;
char *rgb = new char[1920*1080*4];
//*************************像素格式轉(zhuǎn)換******************************
//*************************像素格式轉(zhuǎn)換******************************
//sws_getContext() sws_freeContext()
swsContext = sws_getCachedContext(
swsContext,
avFrame->width,
avFrame->height,
(AVPixelFormat)avFrame->format,
destWidth,
destHeight,
AV_PIX_FMT_RGBA,
// flag 指定用于重新縮放的算法和選項(xiàng) SWS_FAST_BILINEAR雙線性的
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,
//輸入的源buffer
(const uint8_t **)avFrame->data,
//輸入的stride,可以把stride看做每一行的字節(jié)數(shù)
//對于視頻崭篡,指每個(gè)圖片行的字節(jié)大小挪哄。
//對于音頻,指每個(gè)平面的字節(jié)大小
avFrame->linesize,
//處理的起點(diǎn)位置,0表示從頭開始處理
0,
//源的高度
avFrame->height,
//輸出的緩沖區(qū)buffer
data,
//輸出的stride,和輸入對應(yīng)
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);
}
//*************************像素格式轉(zhuǎn)換******************************
音頻重采樣
在聲紋識別中琉闪,為了滿足對不同采樣率的要求迹炼,常需要對語音進(jìn)行重采樣。重采樣即將原始的采樣頻率變換為新的采樣頻率以適應(yīng)不同采樣率的要求(人耳能夠感覺到的最高頻率為20kHz颠毙,因此要滿足人耳的聽覺要求斯入,則需要至少每秒進(jìn)行40k次采樣,用40kHz表達(dá)蛀蜜,這個(gè)40kHz就是采樣率刻两。我們常見的CD,采樣率為44.1kHz)
ffmpeg種處理音頻采樣涉及到的函數(shù)
swr_alloc : 創(chuàng)建一個(gè)SwrContext上下文對象
swr_alloc_set_opts:創(chuàng)建SwrContext或者為SwrContext設(shè)置參數(shù)
這個(gè)方法不依賴swr_alloc來創(chuàng)建上下文對象滴某,也就是說如果傳入的SwrContext是null的話磅摹,他會創(chuàng)建出來并設(shè)置參數(shù)。這個(gè)方法就是設(shè)置輸出的音頻的一些相關(guān)參數(shù)霎奢,你當(dāng)然可以設(shè)置為和輸入相同户誓,但這樣做也就達(dá)不到重采樣的目的了
struct SwrContext *s:如果已經(jīng)存在了SwrContext 就傳入,沒有則傳NULL
int64_t out_ch_layout : 音頻輸出的聲道布局椰憋,av_get_default_channel_layout(2),輸入指定的聲道數(shù)厅克,調(diào)用這個(gè)方法即可
enum AVSampleFormat out_sample_fmt :輸出的樣本格式,有如下選擇
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 :輸出的采樣率橙依,可以和輸入的一致证舟,也可以指定
int64_t in_ch_layout:輸入的聲道布局
enum AVSampleFormat in_sample_fmt :輸入的樣本格式
int in_sample_rate :輸入的采樣率
int log_offset :設(shè)置為0即可
void *log_ctx :設(shè)置為0即可
swr_init 參數(shù)設(shè)置之后初始化SwrContext
swr_convert :開始轉(zhuǎn)換,得到采樣后的音頻存儲在數(shù)組種準(zhǔn)備播放
struct SwrContext *s:被初始化的函數(shù)參數(shù)的SwrContext 窗骑,這個(gè)參數(shù)規(guī)定了音頻重采樣的轉(zhuǎn)換格式
uint8_t **out :輸出緩沖區(qū)
int out_count :輸出一幀音頻含有的樣本數(shù)avFrame->nb_samples
const uint8_t **in :輸人的數(shù)據(jù)源avFrame->data
int in_count:輸入的每幀音頻含有的樣本數(shù)avFrame->nb_samples
音頻重采樣的關(guān)鍵代碼為:
SwrContext *swrContext = swr_alloc();
//給重采樣上下文填充參數(shù)
swrContext = swr_alloc_set_opts(
swrContext,
//輸出的channel layout
av_get_default_channel_layout(2),
//輸出的樣本格式
AV_SAMPLE_FMT_S16,
//輸出的采樣率
audioCodecContext->sample_rate,
//輸入的channel layout
av_get_default_channel_layout(audioCodecContext->channels),
//輸入的樣本格式
audioCodecContext->sample_fmt,
//輸入的采樣率
audioCodecContext->sample_rate,
0, 0
);
//swr_init(), swr_free()
//設(shè)置參數(shù)之后進(jìn)行上下文初始化
result = swr_init(swrContext);
if (result != 0){
LOGW("swr_init failed!");
} else {
LOGW("swr_init success!");
}
//********************音頻重采樣*****************************
//********************音頻重采樣*****************************
uint8_t *out[2] = {0};
out[0] = (uint8_t*) pcm;
int len = swr_convert(
swrContext,
//輸出緩沖區(qū)
out,
//輸出一幀音頻含有的樣本數(shù)
avFrame->nb_samples,
//輸入的源緩沖區(qū)
(const uint8_t**)avFrame->data,
//輸入的每幀音頻含有的樣本數(shù)
avFrame->nb_samples
);
LOGI("swr_convert = %d",len);
//********************音頻重采樣*****************************