aboutsummaryrefslogtreecommitdiffstats
path: root/libavcodec/aacenc_utils.h
blob: 40e174663908352963f035ff35dfad4b33691721 (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
/*
 * AAC encoder utilities
 * Copyright (C) 2015 Rostislav Pehlivanov
 *
 * This file is part of FFmpeg.
 *
 * FFmpeg 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,
 * 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
 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
 */

/**
 * @file
 * AAC encoder utilities
 * @author Rostislav Pehlivanov ( atomnuker gmail com )
 */

#ifndef AVCODEC_AACENC_UTILS_H
#define AVCODEC_AACENC_UTILS_H

#include "aac.h"
#include "aacenctab.h"
#include "aactab.h"

#define ROUND_STANDARD 0.4054f
#define ROUND_TO_ZERO 0.1054f
#define C_QUANT 0.4054f

static inline void abs_pow34_v(float *out, const float *in, const int size)
{
    int i;
    for (i = 0; i < size; i++) {
        float a = fabsf(in[i]);
        out[i] = sqrtf(a * sqrtf(a));
    }
}

/**
 * Quantize one coefficient.
 * @return absolute value of the quantized coefficient
 * @see 3GPP TS26.403 5.6.2 "Scalefactor determination"
 */
static inline int quant(float coef, const float Q, const float rounding)
{
    float a = coef * Q;
    return sqrtf(a * sqrtf(a)) + rounding;
}

static inline void quantize_bands(int *out, const float *in, const float *scaled,
                                  int size, float Q34, int is_signed, int maxval,
                                  const float rounding)
{
    int i;
    double qc;
    for (i = 0; i < size; i++) {
        qc = scaled[i] * Q34;
        out[i] = (int)FFMIN(qc + rounding, (double)maxval);
        if (is_signed && in[i] < 0.0f) {
            out[i] = -out[i];
        }
    }
}

static inline float find_max_val(int group_len, int swb_size, const float *scaled)
{
    float maxval = 0.0f;
    int w2, i;
    for (w2 = 0; w2 < group_len; w2++) {
        for (i = 0; i < swb_size; i++) {
            maxval = FFMAX(maxval, scaled[w2*128+i]);
        }
    }
    return maxval;
}

static inline int find_min_book(float maxval, int sf)
{
    float Q = ff_aac_pow2sf_tab[POW_SF2_ZERO - sf + SCALE_ONE_POS - SCALE_DIV_512];
    float Q34 = sqrtf(Q * sqrtf(Q));
    int qmaxval, cb;
    qmaxval = maxval * Q34 + C_QUANT;
    if (qmaxval >= (FF_ARRAY_ELEMS(aac_maxval_cb)))
        cb = 11;
    else
        cb = aac_maxval_cb[qmaxval];
    return cb;
}

static inline float find_form_factor(int group_len, int swb_size, float thresh,
                                     const float *scaled, float nzslope) {
    const float iswb_size = 1.0f / swb_size;
    const float iswb_sizem1 = 1.0f / (swb_size - 1);
    const float ethresh = thresh;
    float form = 0.0f, weight = 0.0f;
    int w2, i;
    for (w2 = 0; w2 < group_len; w2++) {
        float e = 0.0f, e2 = 0.0f, var = 0.0f, maxval = 0.0f;
        float nzl = 0;
        for (i = 0; i < swb_size; i++) {
            float s = fabsf(scaled[w2*128+i]);
            maxval = FFMAX(maxval, s);
            e += s;
            e2 += s *= s;
            /* We really don't want a hard non-zero-line count, since
             * even below-threshold lines do add up towards band spectral power.
             * So, fall steeply towards zero, but smoothly
             */
            if (s >= ethresh) {
                nzl += 1.0f;
            } else {
                nzl += powf(s / ethresh, nzslope);
            }
        }
        if (e2 > thresh) {
            float frm;
            e *= iswb_size;

            /** compute variance */
            for (i = 0; i < swb_size; i++) {
                float d = fabsf(scaled[w2*128+i]) - e;
                var += d*d;
            }
            var = sqrtf(var * iswb_sizem1);

            e2 *= iswb_size;
            frm = e / FFMIN(e+4*var,maxval);
            form += e2 * sqrtf(frm) / FFMAX(0.5f,nzl);
            weight += e2;
        }
    }
    if (weight > 0) {
        return form / weight;
    } else {
        return 1.0f;
    }
}

/** Return the minimum scalefactor where the quantized coef does not clip. */
static inline uint8_t coef2minsf(float coef)
{
    return av_clip_uint8(log2f(coef)*4 - 69 + SCALE_ONE_POS - SCALE_DIV_512);
}

/** Return the maximum scalefactor where the quantized coef is not zero. */
static inline uint8_t coef2maxsf(float coef)
{
    return av_clip_uint8(log2f(coef)*4 +  6 + SCALE_ONE_POS - SCALE_DIV_512);
}

/*
 * Returns the closest possible index to an array of float values, given a value.
 */
static inline int quant_array_idx(const float val, const float *arr, const int num)
{
    int i, index = 0;
    float quant_min_err = INFINITY;
    for (i = 0; i < num; i++) {
        float error = (val - arr[i])*(val - arr[i]);
        if (error < quant_min_err) {
            quant_min_err = error;
            index = i;
        }
    }
    return index;
}

/**
 * approximates exp10f(-3.0f*(0.5f + 0.5f * cosf(FFMIN(b,15.5f) / 15.5f)))
 */
static av_always_inline float bval2bmax(float b)
{
    return 0.001f + 0.0035f * (b*b*b) / (15.5f*15.5f*15.5f);
}

/*
 * linear congruential pseudorandom number generator, copied from the decoder
 */
static inline int lcg_random(unsigned previous_val)
{
    union { unsigned u; int s; } v = { previous_val * 1664525u + 1013904223 };
    return v.s;
}

#define ERROR_IF(cond, ...) \
    if (cond) { \
        av_log(avctx, AV_LOG_ERROR, __VA_ARGS__); \
        return AVERROR(EINVAL); \
    }

#define WARN_IF(cond, ...) \
    if (cond) { \
        av_log(avctx, AV_LOG_WARNING, __VA_ARGS__); \
    }

#endif /* AVCODEC_AACENC_UTILS_H */