X-Git-Url: https://git.sesse.net/?a=blobdiff_plain;f=libavcodec%2Fpsymodel.h;h=1cc30668e40bb5fdc49fc30aff9bd3bc21797f12;hb=57ec83e4246b21c2f0c068b9151d806737d4497f;hp=5bcf556f0b22a5cf9b601b6d4bccb8ab7a8ba4d2;hpb=78e65cd7726942a1615ead039abe0bfa79341212;p=ffmpeg diff --git a/libavcodec/psymodel.h b/libavcodec/psymodel.h index 5bcf556f0b2..1cc30668e40 100644 --- a/libavcodec/psymodel.h +++ b/libavcodec/psymodel.h @@ -2,20 +2,20 @@ * audio encoder psychoacoustic model * Copyright (C) 2008 Konstantin Shishkov * - * This file is part of FFmpeg. + * This file is part of Libav. * - * FFmpeg is free software; you can redistribute it and/or + * Libav is free software; you can redistribute it and/or * modify it under the terms of the GNU Lesser General Public * License as published by the Free Software Foundation; either * version 2.1 of the License, or (at your option) any later version. * - * FFmpeg is distributed in the hope that it will be useful, + * Libav is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU * Lesser General Public License for more details. * * You should have received a copy of the GNU Lesser General Public - * License along with FFmpeg; if not, write to the Free Software + * License along with Libav; if not, write to the Free Software * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA */ @@ -26,44 +26,70 @@ /** maximum possible number of bands */ #define PSY_MAX_BANDS 128 +/** maximum number of channels */ +#define PSY_MAX_CHANS 20 /** * single band psychoacoustic information */ -typedef struct FFPsyBand{ +typedef struct FFPsyBand { int bits; float energy; float threshold; float distortion; float perceptual_weight; -}FFPsyBand; +} FFPsyBand; + +/** + * single channel psychoacoustic information + */ +typedef struct FFPsyChannel { + FFPsyBand psy_bands[PSY_MAX_BANDS]; ///< channel bands information + float entropy; ///< total PE for this channel +} FFPsyChannel; + +/** + * psychoacoustic information for an arbitrary group of channels + */ +typedef struct FFPsyChannelGroup { + FFPsyChannel *ch[PSY_MAX_CHANS]; ///< pointers to the individual channels in the group + uint8_t num_ch; ///< number of channels in this group + uint8_t coupling[PSY_MAX_BANDS]; ///< allow coupling for this band in the group +} FFPsyChannelGroup; /** * windowing related information */ -typedef struct FFPsyWindowInfo{ +typedef struct FFPsyWindowInfo { int window_type[3]; ///< window type (short/long/transitional, etc.) - current, previous and next int window_shape; ///< window shape (sine/KBD/whatever) int num_windows; ///< number of windows in a frame int grouping[8]; ///< window grouping (for e.g. AAC) int *window_sizes; ///< sequence of window sizes inside one frame (for eg. WMA) -}FFPsyWindowInfo; +} FFPsyWindowInfo; /** * context used by psychoacoustic model */ -typedef struct FFPsyContext{ +typedef struct FFPsyContext { AVCodecContext *avctx; ///< encoder context const struct FFPsyModel *model; ///< encoder-specific model functions - FFPsyBand *psy_bands; ///< frame bands information + FFPsyChannel *ch; ///< single channel information + FFPsyChannelGroup *group; ///< channel group information + int num_groups; ///< number of channel groups uint8_t **bands; ///< scalefactor band sizes for possible frame sizes int *num_bands; ///< number of scalefactor bands for possible frame sizes int num_lens; ///< number of scalefactor band sets + struct { + int size; ///< size of the bitresevoir in bits + int bits; ///< number of bits used in the bitresevoir + } bitres; + void* model_priv_data; ///< psychoacoustic model implementation private data -}FFPsyContext; +} FFPsyContext; /** * codec-specific psychoacoustic model implementation @@ -71,10 +97,32 @@ typedef struct FFPsyContext{ typedef struct FFPsyModel { const char *name; int (*init) (FFPsyContext *apc); - FFPsyWindowInfo (*window)(FFPsyContext *ctx, const int16_t *audio, const int16_t *la, int channel, int prev_type); - void (*analyze)(FFPsyContext *ctx, int channel, const float *coeffs, FFPsyWindowInfo *wi); + + /** + * Suggest window sequence for channel. + * + * @param ctx model context + * @param audio samples for the current frame + * @param la lookahead samples (NULL when unavailable) + * @param channel number of channel element to analyze + * @param prev_type previous window type + * + * @return suggested window information in a structure + */ + FFPsyWindowInfo (*window)(FFPsyContext *ctx, const float *audio, const float *la, int channel, int prev_type); + + /** + * Perform psychoacoustic analysis and set band info (threshold, energy) for a group of channels. + * + * @param ctx model context + * @param channel channel number of the first channel in the group to perform analysis on + * @param coeffs array of pointers to the transformed coefficients + * @param wi window information for the channels in the group + */ + void (*analyze)(FFPsyContext *ctx, int channel, const float **coeffs, const FFPsyWindowInfo *wi); + void (*end) (FFPsyContext *apc); -}FFPsyModel; +} FFPsyModel; /** * Initialize psychoacoustic model. @@ -84,46 +132,31 @@ typedef struct FFPsyModel { * @param num_lens number of possible frame lengths * @param bands scalefactor band lengths for all frame lengths * @param num_bands number of scalefactor bands for all frame lengths + * @param num_groups number of channel groups + * @param group_map array with # of channels in group - 1, for each group * * @return zero if successful, a negative value if not */ -av_cold int ff_psy_init(FFPsyContext *ctx, AVCodecContext *avctx, - int num_lens, - const uint8_t **bands, const int* num_bands); +int ff_psy_init(FFPsyContext *ctx, AVCodecContext *avctx, int num_lens, + const uint8_t **bands, const int *num_bands, + int num_groups, const uint8_t *group_map); /** - * Suggest window sequence for channel. + * Determine what group a channel belongs to. * - * @param ctx model context - * @param audio samples for the current frame - * @param la lookahead samples (NULL when unavailable) - * @param channel number of channel element to analyze - * @param prev_type previous window type - * - * @return suggested window information in a structure - */ -FFPsyWindowInfo ff_psy_suggest_window(FFPsyContext *ctx, - const int16_t *audio, const int16_t *la, - int channel, int prev_type); - - -/** - * Perform psychoacoustic analysis and set band info (threshold, energy). + * @param ctx psymodel context + * @param channel channel to locate the group for * - * @param ctx model context - * @param channel audio channel number - * @param coeffs pointer to the transformed coefficients - * @param wi window information + * @return pointer to the FFPsyChannelGroup this channel belongs to */ -void ff_psy_set_band_info(FFPsyContext *ctx, int channel, const float *coeffs, - FFPsyWindowInfo *wi); +FFPsyChannelGroup *ff_psy_find_group(FFPsyContext *ctx, int channel); /** * Cleanup model context at the end. * * @param ctx model context */ -av_cold void ff_psy_end(FFPsyContext *ctx); +void ff_psy_end(FFPsyContext *ctx); /************************************************************************** @@ -135,24 +168,20 @@ struct FFPsyPreprocessContext; /** * psychoacoustic model audio preprocessing initialization */ -av_cold struct FFPsyPreprocessContext* ff_psy_preprocess_init(AVCodecContext *avctx); +struct FFPsyPreprocessContext *ff_psy_preprocess_init(AVCodecContext *avctx); /** * Preprocess several channel in audio frame in order to compress it better. * * @param ctx preprocessing context - * @param audio samples to preprocess - * @param dest place to put filtered samples - * @param tag channel number - * @param channels number of channel to preprocess (some additional work may be done on stereo pair) + * @param audio samples to be filtered (in place) + * @param channels number of channel to preprocess */ -void ff_psy_preprocess(struct FFPsyPreprocessContext *ctx, - const int16_t *audio, int16_t *dest, - int tag, int channels); +void ff_psy_preprocess(struct FFPsyPreprocessContext *ctx, float **audio, int channels); /** * Cleanup audio preprocessing module. */ -av_cold void ff_psy_preprocess_end(struct FFPsyPreprocessContext *ctx); +void ff_psy_preprocess_end(struct FFPsyPreprocessContext *ctx); #endif /* AVCODEC_PSYMODEL_H */