virtualenv/FFmpeg
1
0
Fork 0
mirror of https://github.com/FFmpeg/FFmpeg.git synced 2025-08-04 22:03:09 +02:00
Code Issues Releases Activity

avfilter/vf_thumbnail: support more planar formats

Browse Source 
This adds support for high bit depth formats, as well as formats with fewer
than 3 planes. The implementation for HBD is the same as for 8 bit formats,
just right shifted to 8 bits.

It's worth pointing out that this also works for HDR formats (and even DV),
because the underlying implementation is just trying to minimize the histogram
difference. If anything, using a HDR format will result in a *more* accurate
detection, because HDR formats tend to be more perceptually uniform.
This commit is contained in:
Niklas Haas
2025-06-12 16:43:24 +02:00
parent 3ce348063c
commit cf18b280f0
1 changed files with 20 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
libavfilter/vf_thumbnail.c
View File

@ -53,6 +53,8 @@ typedef struct ThumbContext {
int planewidth[4]; int planewidth[4];
int planeheight[4]; int planeheight[4];
int planes;
int bitdepth;
} ThumbContext; } ThumbContext;
#define OFFSET(x) offsetof(ThumbContext, x) #define OFFSET(x) offsetof(ThumbContext, x)
@ -194,7 +196,7 @@ static int do_slice(AVFilterContext *ctx, void *arg, int jobnr, int nb_jobs)
} }
break; break;
default: default:
for (int plane = 0; plane < 3; plane++) { for (int plane = 0; plane < s->planes; plane++) {
const int slice_start = (s->planeheight[plane] * jobnr) / nb_jobs; const int slice_start = (s->planeheight[plane] * jobnr) / nb_jobs;
const int slice_end = (s->planeheight[plane] * (jobnr+1)) / nb_jobs; const int slice_end = (s->planeheight[plane] * (jobnr+1)) / nb_jobs;
const uint8_t *p = frame->data[plane] + slice_start * frame->linesize[plane]; const uint8_t *p = frame->data[plane] + slice_start * frame->linesize[plane];
@ -202,12 +204,23 @@ static int do_slice(AVFilterContext *ctx, void *arg, int jobnr, int nb_jobs)
const int planewidth = s->planewidth[plane]; const int planewidth = s->planewidth[plane];
int *hhist = hist + 256 * plane; int *hhist = hist + 256 * plane;
if (s->bitdepth > 8) {
const uint16_t *p16 = (const uint16_t *) p;
const int shift = s->bitdepth - 8;
for (int j = slice_start; j < slice_end; j++) {
for (int i = 0; i < planewidth; i++)
hhist[(p16[i] >> shift) & 0xFF]++;
p16 += linesize >> 1;
}
} else {
for (int j = slice_start; j < slice_end; j++) { for (int j = slice_start; j < slice_end; j++) {
for (int i = 0; i < planewidth; i++) for (int i = 0; i < planewidth; i++)
hhist[p[i]]++; hhist[p[i]]++;
p += linesize; p += linesize;
} }
} }
}
break; break;
} }
@ -286,6 +299,8 @@ static int config_props(AVFilterLink *inlink)
s->planewidth[0] = s->planewidth[3] = inlink->w; s->planewidth[0] = s->planewidth[3] = inlink->w;
s->planeheight[1] = s->planeheight[2] = AV_CEIL_RSHIFT(inlink->h, desc->log2_chroma_h); s->planeheight[1] = s->planeheight[2] = AV_CEIL_RSHIFT(inlink->h, desc->log2_chroma_h);
s->planeheight[0] = s->planeheight[3] = inlink->h; s->planeheight[0] = s->planeheight[3] = inlink->h;
s->planes = av_pix_fmt_count_planes(inlink->format) - !!(desc->flags & AV_PIX_FMT_FLAG_ALPHA);
s->bitdepth = desc->comp[0].depth;
return 0; return 0;
} }