FFmpeg
spherical.c
Go to the documentation of this file.
1 /*
2  * Copyright (c) 2016 Vittorio Giovara <vittorio.giovara@gmail.com>
3  *
4  * This file is part of FFmpeg.
5  *
6  * FFmpeg is free software; you can redistribute it and/or
7  * modify it under the terms of the GNU Lesser General Public
8  * License as published by the Free Software Foundation; either
9  * version 2.1 of the License, or (at your option) any later version.
10  *
11  * FFmpeg is distributed in the hope that it will be useful,
12  * but WITHOUT ANY WARRANTY; without even the implied warranty of
13  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
14  * Lesser General Public License for more details.
15  *
16  * You should have received a copy of the GNU Lesser General Public
17  * License along with FFmpeg; if not, write to the Free Software
18  * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
19  */
20 
21 #include "avstring.h"
22 #include "mem.h"
23 #include "spherical.h"
24 
26 {
27  AVSphericalMapping *spherical = av_mallocz(sizeof(AVSphericalMapping));
28  if (!spherical)
29  return NULL;
30 
31  if (size)
32  *size = sizeof(*spherical);
33 
34  return spherical;
35 }
36 
38  size_t width, size_t height,
39  size_t *left, size_t *top,
40  size_t *right, size_t *bottom)
41 {
42  /* conversion from 0.32 coordinates to pixels */
43  uint64_t orig_width = (uint64_t) width * UINT32_MAX /
44  (UINT32_MAX - map->bound_right - map->bound_left);
45  uint64_t orig_height = (uint64_t) height * UINT32_MAX /
46  (UINT32_MAX - map->bound_bottom - map->bound_top);
47 
48  /* add a (UINT32_MAX - 1) to round up integer division */
49  *left = (orig_width * map->bound_left + UINT32_MAX - 1) / UINT32_MAX;
50  *top = (orig_height * map->bound_top + UINT32_MAX - 1) / UINT32_MAX;
51  *right = orig_width - width - *left;
52  *bottom = orig_height - height - *top;
53 }
54 
55 static const char *const spherical_projection_names[] = {
56  [AV_SPHERICAL_EQUIRECTANGULAR] = "equirectangular",
57  [AV_SPHERICAL_CUBEMAP] = "cubemap",
58  [AV_SPHERICAL_EQUIRECTANGULAR_TILE] = "tiled equirectangular",
59 };
60 
62 {
63  if ((unsigned)projection >= FF_ARRAY_ELEMS(spherical_projection_names))
64  return "unknown";
65 
66  return spherical_projection_names[projection];
67 }
68 
69 int av_spherical_from_name(const char *name)
70 {
71  int i;
72 
73  for (i = 0; i < FF_ARRAY_ELEMS(spherical_projection_names); i++) {
75  return i;
76  }
77 
78  return -1;
79 }
AVSphericalProjection
AVSphericalProjection
Projection of the video surface(s) on a sphere.
Definition: spherical.h:51
name
it s the only field you need to keep assuming you have a context There is some magic you don t need to care about around this just let it vf default minimum maximum flags name is the option name
Definition: writing_filters.txt:88
av_spherical_tile_bounds
void av_spherical_tile_bounds(const AVSphericalMapping *map, size_t width, size_t height, size_t *left, size_t *top, size_t *right, size_t *bottom)
Convert the bounding fields from an AVSphericalVideo from 0.32 fixed point to pixels.
Definition: spherical.c:37
spherical.h
AV_SPHERICAL_EQUIRECTANGULAR_TILE
@ AV_SPHERICAL_EQUIRECTANGULAR_TILE
Video represents a portion of a sphere mapped on a flat surface using equirectangular projection.
Definition: spherical.h:72
AV_SPHERICAL_EQUIRECTANGULAR
@ AV_SPHERICAL_EQUIRECTANGULAR
Video represents a sphere mapped on a flat surface using equirectangular projection.
Definition: spherical.h:56
spherical_projection_names
static const char *const spherical_projection_names[]
Definition: spherical.c:55
FF_ARRAY_ELEMS
#define FF_ARRAY_ELEMS(a)
Definition: sinewin_tablegen.c:29
width
#define width
NULL
#define NULL
Definition: coverity.c:32
av_spherical_projection_name
const char * av_spherical_projection_name(enum AVSphericalProjection projection)
Provide a human-readable name of a given AVSphericalProjection.
Definition: spherical.c:61
AV_SPHERICAL_CUBEMAP
@ AV_SPHERICAL_CUBEMAP
Video frame is split into 6 faces of a cube, and arranged on a 3x2 layout.
Definition: spherical.h:65
size
int size
Definition: twinvq_data.h:10344
height
#define height
av_strstart
int av_strstart(const char *str, const char *pfx, const char **ptr)
Return non-zero if pfx is a prefix of str.
Definition: avstring.c:37
i
#define i(width, name, range_min, range_max)
Definition: cbs_h2645.c:269
av_mallocz
void * av_mallocz(size_t size)
Allocate a memory block with alignment suitable for all memory accesses (including vectors if availab...
Definition: mem.c:264
av_spherical_from_name
int av_spherical_from_name(const char *name)
Get the AVSphericalProjection form a human-readable name.
Definition: spherical.c:69
left
Tag MUST be and< 10hcoeff half pel interpolation filter coefficients, hcoeff[0] are the 2 middle coefficients[1] are the next outer ones and so on, resulting in a filter like:...eff[2], hcoeff[1], hcoeff[0], hcoeff[0], hcoeff[1], hcoeff[2] ... the sign of the coefficients is not explicitly stored but alternates after each coeff and coeff[0] is positive, so ...,+,-,+,-,+,+,-,+,-,+,... hcoeff[0] is not explicitly stored but found by subtracting the sum of all stored coefficients with signs from 32 hcoeff[0]=32 - hcoeff[1] - hcoeff[2] - ... a good choice for hcoeff and htaps is htaps=6 hcoeff={40,-10, 2} an alternative which requires more computations at both encoder and decoder side and may or may not be better is htaps=8 hcoeff={42,-14, 6,-2}ref_frames minimum of the number of available reference frames and max_ref_frames for example the first frame after a key frame always has ref_frames=1spatial_decomposition_type wavelet type 0 is a 9/7 symmetric compact integer wavelet 1 is a 5/3 symmetric compact integer wavelet others are reserved stored as delta from last, last is reset to 0 if always_reset||keyframeqlog quality(logarithmic quantizer scale) stored as delta from last, last is reset to 0 if always_reset||keyframemv_scale stored as delta from last, last is reset to 0 if always_reset||keyframe FIXME check that everything works fine if this changes between framesqbias dequantization bias stored as delta from last, last is reset to 0 if always_reset||keyframeblock_max_depth maximum depth of the block tree stored as delta from last, last is reset to 0 if always_reset||keyframequant_table quantization tableHighlevel bitstream structure:==============================--------------------------------------------|Header|--------------------------------------------|------------------------------------|||Block0||||split?||||yes no||||......... intra?||||:Block01 :yes no||||:Block02 :....... ..........||||:Block03 ::y DC ::ref index:||||:Block04 ::cb DC ::motion x :||||......... :cr DC ::motion y :||||....... ..........|||------------------------------------||------------------------------------|||Block1|||...|--------------------------------------------|------------ ------------ ------------|||Y subbands||Cb subbands||Cr subbands||||--- ---||--- ---||--- ---|||||LL0||HL0||||LL0||HL0||||LL0||HL0|||||--- ---||--- ---||--- ---||||--- ---||--- ---||--- ---|||||LH0||HH0||||LH0||HH0||||LH0||HH0|||||--- ---||--- ---||--- ---||||--- ---||--- ---||--- ---|||||HL1||LH1||||HL1||LH1||||HL1||LH1|||||--- ---||--- ---||--- ---||||--- ---||--- ---||--- ---|||||HH1||HL2||||HH1||HL2||||HH1||HL2|||||...||...||...|||------------ ------------ ------------|--------------------------------------------Decoding process:=================------------|||Subbands|------------||||------------|Intra DC||||LL0 subband prediction ------------|\ Dequantization ------------------- \||Reference frames|\ IDWT|------- -------|Motion \|||Frame 0||Frame 1||Compensation . OBMC v -------|------- -------|--------------. \------> Frame n output Frame Frame<----------------------------------/|...|------------------- Range Coder:============Binary Range Coder:------------------- The implemented range coder is an adapted version based upon "Range encoding: an algorithm for removing redundancy from a digitised message." by G. N. N. Martin. The symbols encoded by the Snow range coder are bits(0|1). The associated probabilities are not fix but change depending on the symbol mix seen so far. bit seen|new state ---------+----------------------------------------------- 0|256 - state_transition_table[256 - old_state];1|state_transition_table[old_state];state_transition_table={ 0, 0, 0, 0, 0, 0, 0, 0, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 114, 115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126, 127, 128, 129, 130, 131, 132, 133, 133, 134, 135, 136, 137, 138, 139, 140, 141, 142, 143, 144, 145, 146, 147, 148, 149, 150, 151, 152, 152, 153, 154, 155, 156, 157, 158, 159, 160, 161, 162, 163, 164, 165, 166, 167, 168, 169, 170, 171, 171, 172, 173, 174, 175, 176, 177, 178, 179, 180, 181, 182, 183, 184, 185, 186, 187, 188, 189, 190, 190, 191, 192, 194, 194, 195, 196, 197, 198, 199, 200, 201, 202, 202, 204, 205, 206, 207, 208, 209, 209, 210, 211, 212, 213, 215, 215, 216, 217, 218, 219, 220, 220, 222, 223, 224, 225, 226, 227, 227, 229, 229, 230, 231, 232, 234, 234, 235, 236, 237, 238, 239, 240, 241, 242, 243, 244, 245, 246, 247, 248, 248, 0, 0, 0, 0, 0, 0, 0};FIXME Range Coding of integers:------------------------- FIXME Neighboring Blocks:===================left and top are set to the respective blocks unless they are outside of the image in which case they are set to the Null block top-left is set to the top left block unless it is outside of the image in which case it is set to the left block if this block has no larger parent block or it is at the left side of its parent block and the top right block is not outside of the image then the top right block is used for top-right else the top-left block is used Null block y, cb, cr are 128 level, ref, mx and my are 0 Motion Vector Prediction:=========================1. the motion vectors of all the neighboring blocks are scaled to compensate for the difference of reference frames scaled_mv=(mv *(256 *(current_reference+1)/(mv.reference+1))+128)> the median of the scaled left
Definition: snow.txt:386
av_spherical_alloc
AVSphericalMapping * av_spherical_alloc(size_t *size)
Allocate a AVSphericalVideo structure and initialize its fields to default values.
Definition: spherical.c:25
mem.h
map
const VDPAUPixFmtMap * map
Definition: hwcontext_vdpau.c:71
avstring.h
AVSphericalMapping
This structure describes how to handle spherical videos, outlining information about projection,...
Definition: spherical.h:82