1
0
mirror of https://github.com/FFmpeg/FFmpeg.git synced 2024-12-02 03:06:28 +02:00
FFmpeg/doc
Guo, Yejun 41ef57fdb2 lavfi/dnn_classify: add filter dnn_classify for classification based on detection bounding boxes
classification is done on every detection bounding box in frame's side data,
which are the results of object detection (filter dnn_detect).

Please refer to commit log of dnn_detect for the material for detection,
and see below for classification.

- download material for classifcation:
wget https://github.com/guoyejun/ffmpeg_dnn/raw/main/models/openvino/2021.1/emotions-recognition-retail-0003.bin
wget https://github.com/guoyejun/ffmpeg_dnn/raw/main/models/openvino/2021.1/emotions-recognition-retail-0003.xml
wget https://github.com/guoyejun/ffmpeg_dnn/raw/main/models/openvino/2021.1/emotions-recognition-retail-0003.label

- run command as:
./ffmpeg -i cici.jpg -vf dnn_detect=dnn_backend=openvino:model=face-detection-adas-0001.xml:input=data:output=detection_out:confidence=0.6:labels=face-detection-adas-0001.label,dnn_classify=dnn_backend=openvino:model=emotions-recognition-retail-0003.xml:input=data:output=prob_emotion:confidence=0.3:labels=emotions-recognition-retail-0003.label:target=face,showinfo -f null -

We'll see the detect&classify result as below:
[Parsed_showinfo_2 @ 0x55b7d25e77c0]   side data - detection bounding boxes:
[Parsed_showinfo_2 @ 0x55b7d25e77c0] source: face-detection-adas-0001.xml, emotions-recognition-retail-0003.xml
[Parsed_showinfo_2 @ 0x55b7d25e77c0] index: 0,  region: (1005, 813) -> (1086, 905), label: face, confidence: 10000/10000.
[Parsed_showinfo_2 @ 0x55b7d25e77c0]            classify:  label: happy, confidence: 6757/10000.
[Parsed_showinfo_2 @ 0x55b7d25e77c0] index: 1,  region: (888, 839) -> (967, 926), label: face, confidence: 6917/10000.
[Parsed_showinfo_2 @ 0x55b7d25e77c0]            classify:  label: anger, confidence: 4320/10000.

Signed-off-by: Guo, Yejun <yejun.guo@intel.com>
2021-05-06 10:50:44 +08:00
..
dev_community Doc: Tech Resolution Process 2021-03-11 10:03:38 +01:00
doxy
examples avformat/avformat, utils: Make av_find_best_stream const-correct 2021-04-27 10:43:14 -03:00
.gitignore
APIchanges doc/APIchanges: add hashes and version numbers for recent entries 2021-04-27 18:42:25 -03:00
authors.texi
bitstream_filters.texi avcodec/setts_bsf: add sample rate for expressions 2021-02-15 20:52:44 +01:00
bootstrap.min.css
build_system.txt tools: add a fuzzer tool for bitstream filters 2019-12-05 20:49:15 -03:00
codecs.texi avcodec: Remove private options from AVCodecContext 2021-04-27 10:43:02 -03:00
decoders.texi avcodec/dvbsubdec: Support computing clut only once 2021-03-29 22:19:39 +02:00
default.css
demuxers.texi doc/demuxers: note support for flv variant KUX 2021-03-31 15:16:12 +05:30
developer.texi fftools/ffmpeg: update text requesting samples 2020-06-01 14:39:52 -04:00
devices.texi
doxy-wrapper.sh
Doxyfile
encoders.texi doc/encoders: add entry for a64 encoders 2021-04-02 15:20:14 +05:30
errno.txt
faq.texi
fate_config.sh.template
fate.texi doc/fate: Document how to request samples upload access 2019-08-09 01:33:49 +02:00
ffmpeg-bitstream-filters.texi
ffmpeg-codecs.texi
ffmpeg-devices.texi
ffmpeg-filters.texi
ffmpeg-formats.texi
ffmpeg-protocols.texi
ffmpeg-resampler.texi
ffmpeg-scaler.texi
ffmpeg-utils.texi
ffmpeg.texi doc/ffmpeg: clarify what -hwaccels list indicates 2021-04-03 10:58:07 +05:30
ffmpeg.txt
ffplay.texi doc: include general in *-all pages. 2020-09-08 14:29:19 +02:00
ffprobe.texi ffprobe: add option to control optional fields display 2021-05-05 15:04:54 +05:30
ffprobe.xsd doc/ffprobe.xsd: Clean-up choice indicator definitions 2021-04-16 08:40:23 +02:00
fftools-common-opts.texi doc/fftools-common-opts: document max_alloc 2021-01-23 14:59:47 +05:30
filter_design.txt
filters.texi lavfi/dnn_classify: add filter dnn_classify for classification based on detection bounding boxes 2021-05-06 10:50:44 +08:00
formats.texi avformat: Remove deprecated AVFMT_FLAG_MP4A_LATM flag, latm option 2021-04-27 10:43:09 -03:00
general_contents.texi doc: update for adpcm_ima_ws encoder and wsaud muxer 2021-04-27 00:26:10 +10:00
general.texi doc/general: move contents into a separate file. 2020-09-08 14:29:19 +02:00
git-howto.texi
indevs.texi avdevice/xcbgrab: Add option for grabbing a window 2021-03-14 18:16:18 -04:00
issue_tracker.txt
lexicon
libav-merge.txt
libavcodec.texi
libavdevice.texi
libavfilter.texi
libavformat.texi
libavutil.texi
libswresample.texi
libswscale.texi
mailing-list-faq.texi Revert "doc/mailing-list-faq: Mention current problem with GMX" 2020-05-08 13:29:43 +02:00
Makefile
metadata.texi
mips.txt
multithreading.txt avcodec: deprecate thread_safe_callbacks 2020-11-27 15:46:50 +01:00
muxers.texi avformat/dashenc: Remove deprecated min_seg_duration option 2021-04-27 10:43:09 -03:00
nut.texi
optimization.txt
outdevs.texi lavdevice: Add AudioToolbox output device. 2020-06-15 15:09:33 +02:00
patchwork
platform.texi
print_options.c
protocols.texi avformat/rtsp: Remove deprecated old options, rename stimeout->timeout 2021-04-27 10:43:09 -03:00
rate_distortion.txt
resampler.texi
scaler.texi
snow.txt
style.min.css
swresample.txt
swscale.txt
t2h.init
t2h.pm
tablegen.txt
texi2pod.pl doc/texi2pod: support @float. 2020-09-08 14:29:19 +02:00
texidep.pl
transforms.md doc/transforms: add documentation for the FFT transforms 2021-04-24 17:19:17 +02:00
undefined.txt
utils.texi doc/utils: document the "s", "ms" and "us" suffixes for durations 2020-06-09 17:55:52 +05:30
writing_filters.txt