BPI-M2 Berry - Python + OpenCV

출처 : BPI-M2 Ultra use OpenCV and face recognition - Banana Pi BPI-M2 Ultra / BPI-M2 Berry
Compile and Run OpenCV2 on Banana Pi - Banana Pi BPI-M2 - banana pi single board computer official forum SinoVoip BPI team
Raspberry Pi 3에 opencv_contrib 포함하여 OpenCV 3.2 설치 - 멈춤보단 천천히라도
Install guide: Raspberry Pi 3 + Raspbian Jessie + OpenCV 3
OpenCV 설치 - MechaWiki

Use bpi-update command to update kernel image

Update bpi-tools

$ git clone https://github.com/BPI-SINOVOIP/bpi-tools.git
Cloning into 'bpi-tools'...
remote: Counting objects: 89, done.
remote: Total 89 (delta 0), reused 0 (delta 0), pack-reused 89
Unpacking objects: 100% (89/89), done.
Checking connectivity... done.
$ cd bpi-tools
$ sudo ./bpi-tools -u -U
F_UPDATE=yes
F_UPGRADE=yes
BPIFILE=/home/pi/.bpi-tools.lst
Wait for download index file ...
OK!!\n
BPIFILE=/home/pi/.bpi-tools.lst
Wait for download index file ...
OK!!\n
 
bpi files:
bpi-tools       v1.2.0(github)
bpi-bootsel     v1.0.6a
bpi-copy        v1.0.11a
bpi-get         v1.0.3(github)
bpi-migrate     v1.3.2a(github)
bpi-hw          v1.2.8
bpi-update      v1.3.2a
 
download bpi files:
bpi-tools
bpi-tools: v1.2.1(github)
bpi-bootsel
bpi-bootsel: v1.2.1(github)
bpi-copy
bpi-copy: v1.2.1(github)
bpi-get
bpi-get: v1.0.3(github)
bpi-migrate
bpi-migrate: v1.3.5(github)
bpi-hw
bpi-hw: v1.2.8
bpi-update
bpi-update: v1.3.4(github)
 
upgrade bpi files:
/usr/bin/bpi-tools
/usr/bin/bpi-bootsel
/usr/bin/bpi-copy
/usr/bin/bpi-get
/usr/bin/bpi-migrate
/usr/bin/bpi-hw
/usr/bin/bpi-update
 
bpi files:
/usr/bin/bpi-tools      v1.2.1(github)
/usr/bin/bpi-bootsel    v1.2.1(github)
/usr/bin/bpi-copy       v1.2.1(github)
/usr/bin/bpi-get        v1.0.3(github)
/usr/bin/bpi-migrate    v1.3.5(github)
/usr/bin/bpi-hw v1.2.8
/usr/bin/bpi-update     v1.3.4(github)

Check bpi-tools version

$ bpi-tools -v
F_VERSION=yes
 
bpi files:
/usr/bin/bpi-tools      v1.2.1(github)
/usr/bin/bpi-bootsel    v1.2.1(github)
/usr/bin/bpi-copy       v1.2.1(github)
/usr/bin/bpi-get        v1.0.3(github)
/usr/bin/bpi-migrate    v1.3.5(github)
/usr/bin/bpi-hw v1.2.8
/usr/bin/bpi-update     v1.3.4(github)

Use bpi-update to update kerenl

$ mkdir update_file
$ cd update_file
$ sudo bpi-update -c bpi-m2u.conf
CONFFILE=bpi-m2u.conf
Wait for download bpi-m2u.conf ...
https://github.com/BPI-SINOVOIP/BPI-files/raw/master/others/for-bpi-tools/conf/board/bpi-m2u.conf
OK!!\n
BPIFILE=/home/pi/.bpi-update.lst
Wait for download index file ...
OK!!\n
INFO: /dev/mmcblk0 : SD/eMMC !!
umount device: /dev/mmcblk0
umount /dev/mmcblk0p1
 
######################
update /dev/mmcblk0p1(vfat) with BPI-BOOT-bpi-m2u.tgz
######################
 
 
Wait for download BPI-BOOT-bpi-m2u.tgz ...
https://github.com/BPI-SINOVOIP/BPI-files/raw/master/SD/BPI-BOOT/BPI-BOOT-bpi-m2u.tgz
OK!!\n
tar xf BPI-BOOT-bpi-m2u.tgz --keep-directory-symlink -C /mnt
total 28
drwxr-xr-x  4 root root 16384 Aug 24 08:04 .
drwxr-xr-x 22 root root  4096 Sep 13 10:24 ..
drwxr-xr-x  3 root root  4096 Aug 24 08:04 bananapi
drwxr-xr-x  2 root root  4096 Sep 13 04:35 System Volume Information
 
######################
update /dev/mmcblk0p2(root) with bpi-tools.tgz BOOTLOADER-bpi-m2u.tgz 3.10.107-BPI-M2U-Kernel.tgz libvdpau_sunxi.tgz bpi-service.tgz addons.tgz bt.tgz camera.tgz camera-apps.tgz brcm.tgz
######################
 
 
Wait for download bpi-tools.tgz ...
https://github.com/BPI-SINOVOIP/BPI-files/raw/master/SD/BPI-ROOT/bpi-tools.tgz
OK!!\n
tar xf bpi-tools.tgz --keep-directory-symlink -C /
Wait for download BOOTLOADER-bpi-m2u.tgz ...
https://github.com/BPI-SINOVOIP/BPI-files/raw/master/SD/BPI-ROOT/BOOTLOADER-bpi-m2u.tgz
OK!!\n
tar xf BOOTLOADER-bpi-m2u.tgz --keep-directory-symlink -C /
Wait for download 3.10.107-BPI-M2U-Kernel.tgz ...
https://github.com/BPI-SINOVOIP/BPI-files/raw/master/SD/BPI-ROOT/3.10.107-BPI-M2U-Kernel.tgz
OK!!\n
tar xf 3.10.107-BPI-M2U-Kernel.tgz --keep-directory-symlink -C /
Wait for download libvdpau_sunxi.tgz ...
https://github.com/BPI-SINOVOIP/BPI-files/raw/master/SD/BPI-ROOT/libvdpau_sunxi.tgz
OK!!\n
tar xf libvdpau_sunxi.tgz --keep-directory-symlink -C /
Wait for download bpi-service.tgz ...
https://github.com/BPI-SINOVOIP/BPI-files/raw/master/SD/BPI-ROOT/bpi-service.tgz
OK!!\n
tar xf bpi-service.tgz --keep-directory-symlink -C /
Wait for download addons.tgz ...
https://github.com/BPI-SINOVOIP/BPI-files/raw/master/SD/BPI-ROOT/addons.tgz
OK!!\n
tar xf addons.tgz --keep-directory-symlink -C /
Wait for download bt.tgz ...
https://github.com/BPI-SINOVOIP/BPI-files/raw/master/SD/BPI-ROOT/bt.tgz
OK!!\n
tar xf bt.tgz --keep-directory-symlink -C /
Wait for download camera.tgz ...
https://github.com/BPI-SINOVOIP/BPI-files/raw/master/SD/BPI-ROOT/camera.tgz
OK!!\n
tar xf camera.tgz --keep-directory-symlink -C /
Wait for download camera-apps.tgz ...
https://github.com/BPI-SINOVOIP/BPI-files/raw/master/SD/BPI-ROOT/camera-apps.tgz
OK!!\n
tar xf camera-apps.tgz --keep-directory-symlink -C /
Wait for download brcm.tgz ...
https://github.com/BPI-SINOVOIP/BPI-files/raw/master/SD/BPI-ROOT/brcm.tgz
OK!!\n
tar xf brcm.tgz --keep-directory-symlink -C /
total 92
drwxr-xr-x  22 root root  4096 Nov  8  2016 .
drwxr-xr-x  22 root root  4096 Nov  8  2016 ..
drwxr-xr-x   2 root root  4096 Nov 21  2016 bin
drwxr-xr-x   2 root root  4096 Apr 22  2016 boot
drwxr-xr-x  14 root root  4600 Sep 13 10:22 dev
drwxr-xr-x 150 root root 12288 Nov 22  2016 etc
drwxr-xr-x   3 root root  4096 Jul 13  2016 home
drwxr-xr-x  22 root root  4096 Nov 27  2015 lib
drwx------   2 root root 16384 Apr 22  2016 lost+found
drwxr-xr-x   3 root root  4096 Jul 21  2016 media
drwxr-xr-x   2 root root  4096 Apr 21  2016 mnt
drwxr-xr-x   3 root root  4096 Jul 20  2016 opt
dr-xr-xr-x 195 root root     0 Jan  1  1970 proc
drwx------   8 root root  4096 Aug 23 15:50 root
drwxr-xr-x  27 root root   880 Sep 13 10:24 run
drwxr-xr-x   2 root root  4096 Aug  1 10:54 sbin
drwxr-xr-x   2 root root  4096 Apr 21  2016 srv
dr-xr-xr-x  12 root root     0 Sep 13 10:21 sys
drwxr-xr-x   4 root root  4096 Nov 27  2015 system
drwxrwxrwt  10 root root  4096 Sep 13 15:47 tmp
drwxr-xr-x  12 root root  4096 Dec 21  2016 usr
drwxr-xr-x  13 root root  4096 Jul  4  2016 var
INFO: online system: skip umount /

기존에 설치된 OpenCV 제거

OpenCV 설치 여부 확인 - 설치가 안 된경우

$ pkg-config --modversion opencv
Package opencv was not found in the pkg-config search path.
Perhaps you should add the directory containing `opencv.pc'
to the PKG_CONFIG_PATH environment variable
No package 'opencv' found

OpenCV 설치 여부 확인 - 설치 되어 있는 경우

$  pkg-config --modversion opencv
2.4.9.1

설치되어 있는 OpenCV 삭제

$ sudo apt-get purge libopencv* python-opencv
$ sudo apt-get autoremove

OS 업그레이드

$ sudo apt-get update
$ sudo apt-get upgrade

개발 도구와 관련 패키지 설치

$ sudo apt-get install build-essential cmake pkg-config

이미지(JPEG, PNG, TIFF, 기타 등등...) 처리 관련 패키지 설치

$ sudo apt-get install libjpeg-dev libtiff5-dev libjasper-dev libpng12-dev

비디오 처리 관련 패키지 설치

$ sudo apt-get install libavcodec-dev libavformat-dev libswscale-dev libv4l-dev
$ sudo apt-get install libxvidcore-dev libx264-dev

Video4Linux 패키지 설치

$ sudo apt-get install libv4l-dev v4l-utils

GTK 패키지 설치

$ sudo apt-get install libgtk2.0-dev

OpenCV 관련 패키지 설치

$ sudo apt-get install libatlas-base-dev gfortran libeigen3-dev

Python 설치

$ sudo apt-get install python2.7-dev python3-dev

NumPy 설치

출처 : 예제로 배우는 파이썬 프로그래밍 - numpy 사용하기

$ sudo apt-get install python-numpy python3-numpy

OpenCV 소스 다운로드 및 압축해제

$ cd ~
$ wget -O opencv.zip https://github.com/Itseez/opencv/archive/3.2.0.zip
$ unzip opencv.zip

OpenCV Extra Modules 소스 다운로드 및 압축해제

$ wget -O opencv_contrib.zip https://github.com/Itseez/opencv_contrib/archive/3.2.0.zip
$ unzip opencv_contrib.zip

cmake

$ cd ~/opencv-3.2.0/
$ mkdir build
$ cd build
$ cmake -D CMAKE_BUILD_TYPE=RELEASE \
-D CMAKE_INSTALL_PREFIX=/usr/local \
-D BUILD_ZLIB=ON \
-D BUILD_PNG=ON \
-D WITH_TBB=OFF \
-D WITH_IPP=OFF \
-D WITH_1394=OFF \
-D BUILD_WITH_DEBUG_INFO=OFF \
-D BUILD_DOCS=OFF \
-D INSTALL_C_EXAMPLES=ON \
-D INSTALL_PYTHON_EXAMPLES=ON \
-D BUILD_EXAMPLES=OFF \
-D BUILD_TESTS=OFF \
-D BUILD_PERF_TESTS=OFF \
-D ENABLE_NEON=ON \
-D OPENCV_EXTRA_MODULES_PATH=~/opencv_contrib-3.2.0/modules \
-D WITH_V4L=ON  \
-D WITH_FFMPEG=ON \
-D WITH_XINE=ON \
-D BUILD_NEW_PYTHON_SUPPORT=ON \
../
 
-- 
-- General configuration for OpenCV 3.2.0 =====================================
--   Version control:               unknown
-- 
--   Extra modules:
--     Location (extra):            /home/pi/opencv_contrib-3.2.0/modules
--     Version control (extra):     unknown
-- 
--   Platform:
--     Timestamp:                   2017-09-12T15:12:16Z
--     Host:                        Linux 3.10.107-BPI-M2U-Kernel armv7l
--     CMake:                       3.5.1
--     CMake generator:             Unix Makefiles
--     CMake build tool:            /usr/bin/make
--     Configuration:               RELEASE
-- 
--   C/C++:
--     Built as dynamic libs?:      YES
--     C++ Compiler:                /usr/bin/c++  (ver 5.4.0)
--     C++ flags (Release):         -fsigned-char -W -Wall -Werror=return-type -Werror=non-virtual-dtor -Werror=address -Werror=sequence-point -Wformat -Werror=format-security -Wmissing-declarations -Wundef -Winit-self -Wpointer-arith -Wshadow -Wsign-promo -Wno-narrowing -Wno-delete-non-virtual-dtor -Wno-comment -fdiagnostics-show-option -pthread -fomit-frame-pointer -mfp16-format=ieee -mfpu=neon -ffunction-sections -fvisibility=hidden -fvisibility-inlines-hidden -O3 -DNDEBUG  -DNDEBUG
--     C++ flags (Debug):           -fsigned-char -W -Wall -Werror=return-type -Werror=non-virtual-dtor -Werror=address -Werror=sequence-point -Wformat -Werror=format-security -Wmissing-declarations -Wundef -Winit-self -Wpointer-arith -Wshadow -Wsign-promo -Wno-narrowing -Wno-delete-non-virtual-dtor -Wno-comment -fdiagnostics-show-option -pthread -fomit-frame-pointer -mfp16-format=ieee -mfpu=neon -ffunction-sections -fvisibility=hidden -fvisibility-inlines-hidden -g  -O0 -DDEBUG -D_DEBUG
--     C Compiler:                  /usr/bin/cc
--     C flags (Release):           -fsigned-char -W -Wall -Werror=return-type -Werror=non-virtual-dtor -Werror=address -Werror=sequence-point -Wformat -Werror=format-security -Wmissing-declarations -Wmissing-prototypes -Wstrict-prototypes -Wundef -Winit-self -Wpointer-arith -Wshadow -Wno-narrowing -Wno-comment -fdiagnostics-show-option -pthread -fomit-frame-pointer -mfp16-format=ieee -mfpu=neon -ffunction-sections -fvisibility=hidden -O3 -DNDEBUG  -DNDEBUG
--     C flags (Debug):             -fsigned-char -W -Wall -Werror=return-type -Werror=non-virtual-dtor -Werror=address -Werror=sequence-point -Wformat -Werror=format-security -Wmissing-declarations -Wmissing-prototypes -Wstrict-prototypes -Wundef -Winit-self -Wpointer-arith -Wshadow -Wno-narrowing -Wno-comment -fdiagnostics-show-option -pthread -fomit-frame-pointer -mfp16-format=ieee -mfpu=neon -ffunction-sections -fvisibility=hidden -g  -O0 -DDEBUG -D_DEBUG
--     Linker flags (Release):
--     Linker flags (Debug):
--     ccache:                      NO
--     Precompiled headers:         YES
--     Extra dependencies:          /usr/lib/arm-linux-gnueabihf/libtiff.so /usr/lib/arm-linux-gnueabihf/libjasper.so /usr/lib/arm-linux-gnueabihf/libjpeg.so gtk-3 gdk-3 pangocairo-1.0 pango-1.0 atk-1.0 cairo-gobject cairo gdk_pixbuf-2.0 gio-2.0 gobject-2.0 glib-2.0 gthread-2.0 avcodec-ffmpeg avformat-ffmpeg avutil-ffmpeg swscale-ffmpeg dl m pthread rt
--     3rdparty dependencies:       zlib libwebp libpng IlmImf libprotobuf tegra_hal
-- 
--   OpenCV modules:
--     To be built:                 core flann imgproc ml photo reg surface_matching video dnn freetype fuzzy imgcodecs shape videoio highgui objdetect plot superres xobjdetect xphoto bgsegm bioinspired dpm face features2d line_descriptor saliency text calib3d ccalib datasets rgbd stereo tracking videostab xfeatures2d ximgproc aruco optflow phase_unwrapping stitching structured_light python2 python3
--     Disabled:                    world contrib_world
--     Disabled by dependency:      -
--     Unavailable:                 cudaarithm cudabgsegm cudacodec cudafeatures2d cudafilters cudaimgproc cudalegacy cudaobjdetect cudaoptflow cudastereo cudawarping cudev java ts viz cnn_3dobj cvv hdf matlab sfm
-- 
--   GUI: 
--     QT:                          NO
--     GTK+ 3.x:                    YES (ver 3.18.9)
--     GThread :                    YES (ver 2.48.2)
--     GtkGlExt:                    NO
--     OpenGL support:              NO
--     VTK support:                 NO
-- 
--   Media I/O: 
--     ZLib:                        build (ver 1.2.8)
--     JPEG:                        /usr/lib/arm-linux-gnueabihf/libjpeg.so (ver )
--     WEBP:                        build (ver 0.3.1)
--     PNG:                         build (ver 1.6.24)
--     TIFF:                        /usr/lib/arm-linux-gnueabihf/libtiff.so (ver 42 - 4.0.6)
--     JPEG 2000:                   /usr/lib/arm-linux-gnueabihf/libjasper.so (ver 1.900.1)
--     OpenEXR:                     build (ver 1.7.1)
--     GDAL:                        NO
--     GDCM:                        NO
-- 
--   Video I/O:
--     DC1394 1.x:                  NO
--     DC1394 2.x:                  NO
--     FFMPEG:                      YES
--       avcodec:                   YES (ver 56.60.100)
--       avformat:                  YES (ver 56.40.101)
--       avutil:                    YES (ver 54.31.100)
--       swscale:                   YES (ver 3.1.101)
--       avresample:                NO
--     GStreamer:                   NO
--     OpenNI:                      NO
--     OpenNI PrimeSensor Modules:  NO
--     OpenNI2:                     NO
--     PvAPI:                       NO
--     GigEVisionSDK:               NO
--     Aravis SDK:                  NO
--     UniCap:                      NO
--     UniCap ucil:                 NO
--     V4L/V4L2:                    NO/YES
--     XIMEA:                       NO
--     Xine:                        NO
--     gPhoto2:                     NO
-- 
--   Parallel framework:            pthreads
-- 
--   Other third-party libraries:
--     Use IPP:                     NO
--     Use VA:                      NO
--     Use Intel VA-API/OpenCL:     NO
--     Use Lapack:                  NO
--     Use Eigen:                   YES (ver 3.2.92)
--     Use Cuda:                    NO
--     Use OpenCL:                  YES
--     Use OpenVX:                  NO
--     Use custom HAL:              YES (carotene (ver 0.0.1))
-- 
--   OpenCL:                        <Dynamic loading of OpenCL library>
--     Include path:                /home/pi/opencv-3.2.0/3rdparty/include/opencl/1.2
--     Use AMDFFT:                  NO
--     Use AMDBLAS:                 NO
-- 
--   Python 2:
--     Interpreter:                 /usr/bin/python2.7 (ver 2.7.12)
--     Libraries:                   /usr/lib/arm-linux-gnueabihf/libpython2.7.so (ver 2.7.12)
--     numpy:                       /usr/lib/python2.7/dist-packages/numpy/core/include (ver 1.11.0)
--     packages path:               lib/python2.7/dist-packages
-- 
--   Python 3:
--     Interpreter:                 /usr/bin/python3 (ver 3.5.2)
--     Libraries:                   /usr/lib/arm-linux-gnueabihf/libpython3.5m.so (ver 3.5.2)
--     numpy:                       /usr/lib/python3/dist-packages/numpy/core/include (ver 1.11.0)
--     packages path:               lib/python3.5/dist-packages
-- 
--   Python (for build):            /usr/bin/python2.7
-- 
--   Java:
--     ant:                         NO
--     JNI:                         NO
--     Java wrappers:               NO
--     Java tests:                  NO
-- 
--   Matlab:                        Matlab not found or implicitly disabled
-- 
--   Tests and samples:
--     Tests:                       NO
--     Performance tests:           NO
--     C/C++ Examples:              NO
-- 
--   Install path:                  /usr/local
-- 
--   cvconfig.h is in:              /home/pi/opencv-3.2.0/build
-- -----------------------------------------------------------------
-- 
-- Configuring done
-- Generating done
-- Build files have been written to: /home/pi/opencv-3.2.0/build

빌드 (BPI-M2 Berry 에는 4 개의 코어가 있으므로 OpenCV를 더 빠르게 컴파일 할 수 있도록 -j4 옵션추가)

$ cat /proc/cpuinfo | grep processor | wc -l
4
$ make -j4

OpenCV 설치

$ sudo make install

/etc/ld.so.conf.d/ 디렉토리에 /usr/local/lib를 포함하는 설정파일이 있는지 확인

$ cat /etc/ld.so.conf.d/*
#/opt/vc/lib
/usr/lib/mali
## Multiarch support
/lib/arm-linux-gnueabihf
/usr/lib/arm-linux-gnueabihf
/usr/lib/arm-linux-gnueabihf/mesa-egl
/usr/lib/arm-linux-gnueabihf/mesa
## libc default configuration
/usr/local/lib
/opt/vc/lib

OpenCV 설치

$ sudo ldconfig

OpenCV 설치 확인 - 1

$ pkg-config --modversion opencv
3.2.0

OpenCV 설치 확인 - 2

$ pkg-config --libs --cflags opencv
-I/usr/local/include/opencv -I/usr/local/include -L/usr/local/lib -lopencv_stitching -lopencv_superres -lopencv_videostab -lopencv_aruco -lopencv_bgsegm -lopencv_bioinspired -lopencv_ccalib -lopencv_dpm -lopencv_freetype -lopencv_fuzzy -lopencv_line_descriptor -lopencv_optflow -lopencv_reg -lopencv_saliency -lopencv_stereo -lopencv_structured_light -lopencv_phase_unwrapping -lopencv_rgbd -lopencv_surface_matching -lopencv_tracking -lopencv_datasets -lopencv_text -lopencv_face -lopencv_plot -lopencv_dnn -lopencv_xfeatures2d -lopencv_shape -lopencv_video -lopencv_ximgproc -lopencv_calib3d -lopencv_features2d -lopencv_flann -lopencv_xobjdetect -lopencv_objdetect -lopencv_ml -lopencv_xphoto -lopencv_highgui -lopencv_videoio -lopencv_imgcodecs -lopencv_photo -lopencv_imgproc -lopencv_core

용량 확보를 위해서 다운로드 받은 소스 파일 삭제

$ cd ~
$ rm -rf opencv-3.2.0 opencv_contrib-3.2.0

python3에서 OpenCV 버전확인

$ python3
Python 3.4.2 (default, Oct 19 2014, 13:31:11) 
[GCC 4.9.1] on linux
Type "help", "copyright", "credits" or "license" for more information.
>>> import cv2
>>> cv2.__version__
'3.2.0'

python3에서 얼굴인식 예제 실행 (Camera 인식 실패로 Camera 직접 제어는 포기)

$ python3 /usr/local/share/OpenCV/samples/python/facedetect.py --cascade "/usr/local/share/OpenCV/haarcascades/haarcascade_frontalface_alt.xml" --nested-cascade "/usr/local/share/OpenCV/haarcascades/haarcascade_eye_tree_eyeglasses.xml" /dev/video0
 
 
face detection using haar cascades
 
USAGE:
    facedetect.py [--cascade <cascade_fn>] [--nested-cascade <cascade_fn>] [<video_source>]
 
Warning: unable to open video source:  /dev/video0
Warning: unable to open video source:  synth
Traceback (most recent call last):
  File "/usr/local/share/OpenCV/samples/python/facedetect.py", line 52, in <module>
    ret, img = cam.read()
AttributeError: 'NoneType' object has no attribute 'read'

python3에서 얼굴인식 예제 작성 (mjpg-streamer에서 Camera 영상을 받아 오도록 수정)

#!/usr/bin/env python

'''
face detection using haar cascades

USAGE:
    facedetect.py [--cascade <cascade_fn>] [--nested-cascade <cascade_fn>] [<video_source>]
'''

# Python 2/3 compatibility
from __future__ import print_function

import numpy as np
import cv2
import requests

# local modules
# from video import create_capture
from common import clock, draw_str

BYTES_NONE = b'';

def detect(img, cascade):
    rects = cascade.detectMultiScale(img, scaleFactor=1.3, minNeighbors=4, minSize=(30, 30),
                                     flags=cv2.CASCADE_SCALE_IMAGE)
    if len(rects) == 0:
        return []
    rects[:,2:] += rects[:,:2]
    return rects

def draw_rects(img, rects, color):
    for x1, y1, x2, y2 in rects:
        cv2.rectangle(img, (x1, y1), (x2, y2), color, 2)

if __name__ == '__main__':
    import sys, getopt
    print(__doc__)

    args, video_src = getopt.getopt(sys.argv[1:], '', ['cascade=', 'nested-cascade='])
    try:
        video_src = video_src[0]
    except:
        video_src = 0
    args = dict(args)
    cascade_fn = args.get('--cascade', "../../data/haarcascades/haarcascade_frontalface_alt.xml")
    nested_fn  = args.get('--nested-cascade', "../../data/haarcascades/haarcascade_eye.xml")

    cascade = cv2.CascadeClassifier(cascade_fn)
    nested = cv2.CascadeClassifier(nested_fn)

    #cam = create_capture(video_src, fallback='synth:bg=../data/lena.jpg:noise=0.05')

    while True:
        r = requests.get('http://127.0.0.1:8080/?action=snapshot"', auth=('user', 'password'), stream=True)
        if (r.status_code == 200):
            bytes = BYTES_NONE
            for chunk in r.iter_content(chunk_size=1024):
                bytes += chunk
                a = bytes.find(b'\xff\xd8')
                b = bytes.find(b'\xff\xd9')
                if a != -1 and b != -1:
                    jpg = bytes[a:b + 2]
                    bytes = bytes[b + 2:]

                    # ret, img = cam.read()
                    # ret, \
                    img = cv2.imdecode(np.fromstring(jpg, dtype=np.uint8), cv2.IMREAD_COLOR)
                    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
                    gray = cv2.equalizeHist(gray)

                    t = clock()
                    rects = detect(gray, cascade)
                    vis = img.copy()
                    draw_rects(vis, rects, (0, 255, 0))
                    if not nested.empty():
                        for x1, y1, x2, y2 in rects:
                            roi = gray[y1:y2, x1:x2]
                            vis_roi = vis[y1:y2, x1:x2]
                            subrects = detect(roi.copy(), nested)
                            draw_rects(vis_roi, subrects, (255, 0, 0))
                    dt = clock() - t

                    draw_str(vis, (20, 20), 'time: %.1f ms' % (dt*1000))
                    cv2.imshow('facedetect', vis)

        if cv2.waitKey(5) == 27:
            break
    cv2.destroyAllWindows()

$ python3 /usr/local/share/OpenCV/samples/python/facedetect.py --cascade "/usr/local/share/OpenCV/haarcascades/haarcascade_frontalface_alt.xml" --nested-cascade "/usr/local/share/OpenCV/haarcascades/haarcascade_eye_tree_eyeglasses.xml" /dev/video0

python3에서 얼굴인식 예제 실행

얼굴인식 예제 컴파일, 실행 (컴파일 실패로 CPP 예제는 포기)

$ cp /usr/local/share/OpenCV/samples/cpp/facedetect.cpp ./
$ g++ -o facedetect facedetect.cpp $(pkg-config --libs --cflags opencv) 
/usr/bin/ld: /tmp/ccWuwUjB.o: undefined reference to symbol 'fopen@@GLIBC_2.4'
//lib/arm-linux-gnueabihf/libc.so.6: error adding symbols: DSO missing from command line
collect2: error: ld returned 1 exit status

cmake 다른 옵션

$ cmake -D CMAKE_BUILD_TYPE=RELEASE \
-D CMAKE_INSTALL_PREFIX=/usr/local \
-D BUILD_SHARED_LIBS=OFF \
-D BUILD_ZLIB=ON \
-D BUILD_PNG=ON \
-D WITH_TBB=OFF \
-D WITH_IPP=OFF \
-D WITH_1394=OFF \
-D BUILD_WITH_DEBUG_INFO=OFF \
-D BUILD_DOCS=OFF \
-D INSTALL_C_EXAMPLES=ON \
-D INSTALL_PYTHON_EXAMPLES=ON \
-D BUILD_EXAMPLES=OFF \
-D BUILD_TESTS=OFF \
-D BUILD_PERF_TESTS=OFF \
-D ENABLE_NEON=ON \
-D OPENCV_EXTRA_MODULES_PATH=~/opencv_contrib-3.2.0/modules \
-D WITH_V4L=ON  \
-D WITH_FFMPEG=ON \
-D WITH_XINE=ON \
-D BUILD_NEW_PYTHON_SUPPORT=ON \
../