21 #define DEFAULT_RESULT_NAME "transforms.trf" 23 #include <vid.stab/libvidstab.h> 44 #define OFFSET(x) offsetof(StabData, x) 45 #define OFFSETC(x) (offsetof(StabData, conf)+offsetof(VSMotionDetectConfig, x)) 46 #define FLAGS AV_OPT_FLAG_FILTERING_PARAM|AV_OPT_FLAG_VIDEO_PARAM 50 {
"shakiness",
"how shaky is the video and how quick is the camera?" 53 {
"stepsize",
"region around minimum is scanned with 1 pixel resolution",
OFFSETC(stepSize),
AV_OPT_TYPE_INT, {.i64 = 6}, 1, 32,
FLAGS},
56 {
"tripod",
"virtual tripod mode (if >0): motion is compared to a reference" 67 s->
class = &vidstabdetect_class;
75 VSMotionDetect *
md = &(s->
md);
82 vsMotionDetectionCleanup(md);
107 VSMotionDetect*
md = &(s->
md);
112 vsFrameInfoInit(&fi, inlink->
w, inlink->
h,
115 av_log(ctx,
AV_LOG_ERROR,
"pixel-format error: wrong bits/per/pixel, please report a BUG");
130 s->
conf.modName =
"vidstabdetect";
131 if (vsMotionDetectInit(md, &s->
conf, &fi) != VS_OK) {
132 av_log(ctx,
AV_LOG_ERROR,
"initialization of Motion Detection failed, please report a BUG");
136 vsMotionDetectGetConfig(&s->
conf, md);
151 if (vsPrepareFile(md, s->
f) != VS_OK) {
163 VSMotionDetect *
md = &(s->
md);
164 LocalMotions localmotions;
173 for (plane = 0; plane < md->fi.planes; plane++) {
174 frame.data[plane] = in->
data[plane];
175 frame.linesize[plane] = in->
linesize[plane];
177 if (vsMotionDetection(md, &localmotions, &frame) != VS_OK) {
181 if (vsWriteToFile(md, s->
f, &localmotions) != VS_OK) {
186 vs_vector_del(&localmotions);
211 .
name =
"vidstabdetect",
213 "pass 1 of 2 for stabilization " 214 "(see vidstabtransform for pass 2)."),
219 .
inputs = avfilter_vf_vidstabdetect_inputs,
220 .
outputs = avfilter_vf_vidstabdetect_outputs,
221 .priv_class = &vidstabdetect_class,
static av_cold int init(AVFilterContext *ctx)
const AVPixFmtDescriptor * av_pix_fmt_desc_get(enum AVPixelFormat pix_fmt)
This structure describes decoded (raw) audio or video data.
planar YUV 4:4:4, 24bpp, (1 Cr & Cb sample per 1x1 Y samples)
Main libavfilter public API header.
packed RGB 8:8:8, 24bpp, RGBRGB...
int av_get_bits_per_pixel(const AVPixFmtDescriptor *pixdesc)
Return the number of bits per pixel used by the pixel format described by pixdesc.
int h
agreed upon image height
AVFILTER_DEFINE_CLASS(vidstabdetect)
static int query_formats(AVFilterContext *ctx)
uint8_t log2_chroma_w
Amount to shift the luma width right to find the chroma width.
const char * name
Pad name.
int ff_filter_frame(AVFilterLink *link, AVFrame *frame)
Send a frame of data to the next filter.
planar YUV 4:2:0, 20bpp, (1 Cr & Cb sample per 2x2 Y & A samples)
static const AVOption vidstabdetect_options[]
static int config_input(AVFilterLink *inlink)
AVFilter ff_vf_vidstabdetect
#define AV_LOG_VERBOSE
Detailed information.
static const AVFilterPad avfilter_vf_vidstabdetect_outputs[]
A filter pad used for either input or output.
A link between two filters.
#define AV_LOG_ERROR
Something went wrong and cannot losslessly be recovered.
uint8_t log2_chroma_h
Amount to shift the luma height right to find the chroma height.
#define NULL_IF_CONFIG_SMALL(x)
Return NULL if CONFIG_SMALL is true, otherwise the argument without modification. ...
void * priv
private data for use by the filter
packed RGBA 8:8:8:8, 32bpp, RGBARGBA...
planar YUV 4:2:2, 16bpp, (1 Cr & Cb sample per 2x1 Y samples)
int w
agreed upon image width
uint64_t flags
Combination of AV_PIX_FMT_FLAG_...
these buffered frames must be flushed immediately if a new input produces new the filter must not call request_frame to get more It must just process the frame or queue it The task of requesting more frames is left to the filter s request_frame method or the application If a filter has several the filter must be ready for frames arriving randomly on any input any filter with several inputs will most likely require some kind of queuing mechanism It is perfectly acceptable to have a limited queue and to drop frames when the inputs are too unbalanced request_frame For filters that do not use the this method is called when a frame is wanted on an output For a it should directly call filter_frame on the corresponding output For a if there are queued frames already one of these frames should be pushed If the filter should request a frame on one of its repeatedly until at least one frame has been pushed Return or at least make progress towards producing a frame
packed RGB 8:8:8, 24bpp, BGRBGR...
static const AVFilterPad outputs[]
int format
agreed upon media format
#define AV_LOG_INFO
Standard information.
static const AVFilterPad avfilter_vf_vidstabdetect_inputs[]
int av_frame_is_writable(AVFrame *frame)
Check if the frame data is writable.
int linesize[AV_NUM_DATA_POINTERS]
For video, size in bytes of each picture line.
Descriptor that unambiguously describes how the bits of a pixel are stored in the up to 4 data planes...
#define DEFAULT_RESULT_NAME
these buffered frames must be flushed immediately if a new input produces new the filter must not call request_frame to get more It must just process the frame or queue it The task of requesting more frames is left to the filter s request_frame method or the application If a filter has several inputs
uint8_t pi<< 24) CONV_FUNC_GROUP(AV_SAMPLE_FMT_FLT, float, AV_SAMPLE_FMT_U8, uint8_t,(*(const uint8_t *) pi-0x80)*(1.0f/(1<< 7))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_DBL, double, AV_SAMPLE_FMT_U8, uint8_t,(*(const uint8_t *) pi-0x80)*(1.0/(1<< 7))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_S16, int16_t,(*(const int16_t *) pi >> 8)+0x80) CONV_FUNC_GROUP(AV_SAMPLE_FMT_FLT, float, AV_SAMPLE_FMT_S16, int16_t,*(const int16_t *) pi *(1.0f/(1<< 15))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_DBL, double, AV_SAMPLE_FMT_S16, int16_t,*(const int16_t *) pi *(1.0/(1<< 15))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_S32, int32_t,(*(const int32_t *) pi >> 24)+0x80) CONV_FUNC_GROUP(AV_SAMPLE_FMT_FLT, float, AV_SAMPLE_FMT_S32, int32_t,*(const int32_t *) pi *(1.0f/(1U<< 31))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_DBL, double, AV_SAMPLE_FMT_S32, int32_t,*(const int32_t *) pi *(1.0/(1U<< 31))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_FLT, float, av_clip_uint8(lrintf(*(const float *) pi *(1<< 7))+0x80)) CONV_FUNC_GROUP(AV_SAMPLE_FMT_S16, int16_t, AV_SAMPLE_FMT_FLT, float, av_clip_int16(lrintf(*(const float *) pi *(1<< 15)))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_S32, int32_t, AV_SAMPLE_FMT_FLT, float, av_clipl_int32(llrintf(*(const float *) pi *(1U<< 31)))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_DBL, double, av_clip_uint8(lrint(*(const double *) pi *(1<< 7))+0x80)) CONV_FUNC_GROUP(AV_SAMPLE_FMT_S16, int16_t, AV_SAMPLE_FMT_DBL, double, av_clip_int16(lrint(*(const double *) pi *(1<< 15)))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_S32, int32_t, AV_SAMPLE_FMT_DBL, double, av_clipl_int32(llrint(*(const double *) pi *(1U<< 31))))#define SET_CONV_FUNC_GROUP(ofmt, ifmt) static void set_generic_function(AudioConvert *ac){}void ff_audio_convert_free(AudioConvert **ac){if(!*ac) return;ff_dither_free(&(*ac) ->dc);av_freep(ac);}AudioConvert *ff_audio_convert_alloc(AVAudioResampleContext *avr, enum AVSampleFormat out_fmt, enum AVSampleFormat in_fmt, int channels, int sample_rate, int apply_map){AudioConvert *ac;int in_planar, out_planar;ac=av_mallocz(sizeof(*ac));if(!ac) return NULL;ac->avr=avr;ac->out_fmt=out_fmt;ac->in_fmt=in_fmt;ac->channels=channels;ac->apply_map=apply_map;if(avr->dither_method!=AV_RESAMPLE_DITHER_NONE &&av_get_packed_sample_fmt(out_fmt)==AV_SAMPLE_FMT_S16 &&av_get_bytes_per_sample(in_fmt) > 2){ac->dc=ff_dither_alloc(avr, out_fmt, in_fmt, channels, sample_rate, apply_map);if(!ac->dc){av_free(ac);return NULL;}return ac;}in_planar=ff_sample_fmt_is_planar(in_fmt, channels);out_planar=ff_sample_fmt_is_planar(out_fmt, channels);if(in_planar==out_planar){ac->func_type=CONV_FUNC_TYPE_FLAT;ac->planes=in_planar?ac->channels:1;}else if(in_planar) ac->func_type=CONV_FUNC_TYPE_INTERLEAVE;else ac->func_type=CONV_FUNC_TYPE_DEINTERLEAVE;set_generic_function(ac);if(ARCH_AARCH64) ff_audio_convert_init_aarch64(ac);if(ARCH_ARM) ff_audio_convert_init_arm(ac);if(ARCH_X86) ff_audio_convert_init_x86(ac);return ac;}int ff_audio_convert(AudioConvert *ac, AudioData *out, AudioData *in){int use_generic=1;int len=in->nb_samples;int p;if(ac->dc){av_log(ac->avr, AV_LOG_TRACE,"%d samples - audio_convert: %s to %s (dithered)\n", len, av_get_sample_fmt_name(ac->in_fmt), av_get_sample_fmt_name(ac->out_fmt));return ff_convert_dither(ac-> in
planar YUV 4:1:0, 9bpp, (1 Cr & Cb sample per 4x4 Y samples)
Describe the class of an AVClass context structure.
const char * name
Filter name.
AVFilterLink ** outputs
array of pointers to output links
VSMotionDetectConfig conf
static enum AVPixelFormat pix_fmts[]
static int filter_frame(AVFilterLink *inlink, AVFrame *in)
int av_frame_make_writable(AVFrame *frame)
Ensure that the frame data is writable, avoiding data copy if possible.
uint8_t * data[AV_NUM_DATA_POINTERS]
pointer to the picture/channel planes.
The exact code depends on how similar the blocks are and how related they are to the and needs to apply these operations to the correct inlink or outlink if there are several Macros are available to factor that when no extra processing is inlink
planar YUV 4:2:0, 12bpp, (1 Cr & Cb sample per 2x2 Y samples)
VSPixelFormat ff_av2vs_pixfmt(AVFilterContext *ctx, enum AVPixelFormat pf)
convert AV's pixelformat to vid.stab pixelformat
common internal and external API header
planar YUV 4:1:1, 12bpp, (1 Cr & Cb sample per 4x1 Y samples)
static av_cold void uninit(AVFilterContext *ctx)
AVFilterContext * dst
dest filter
void ff_vs_init(void)
sets the memory allocation function and logging constants to av versions
planar YUV 4:4:0 (1 Cr & Cb sample per 1x2 Y samples)
Filter the word “frame” indicates either a video frame or a group of audio as stored in an AVFrame structure Format for each input and each output the list of supported formats For video that means pixel format For audio that means channel sample they are references to shared objects When the negotiation mechanism computes the intersection of the formats supported at each end of a all references to both lists are replaced with a reference to the intersection And when a single format is eventually chosen for a link amongst the remaining all references to the list are updated That means that if a filter requires that its input and output have the same format amongst a supported all it has to do is use a reference to the same list of formats query_formats can leave some formats unset and return AVERROR(EAGAIN) to cause the negotiation mechanism toagain later.That can be used by filters with complex requirements to use the format negotiated on one link to set the formats supported on another.Frame references ownership and permissions
#define AVERROR_EXTERNAL
Generic error in an external library.
AVPixelFormat
Pixel format.
#define AV_PIX_FMT_FLAG_PLANAR
At least one pixel component is not in the first data plane.