I-OpenCV ilayibrari yokwamkelwa kwento kwimifanekiso nakwiikhamera

I-OpenCV ilayibrari yasimahla yombono weqonga lomnqamlezo (iinguqulelo ezikhoyo ze-GNU / Linux, Mac OS X, Windows kunye ne-Android) ezazingumsuka iphuhliswe yi-Intel kwaye isetyenziswa kwizicelo ezingenakubalwaukusuka kwiinkqubo zokhuselo ezinokubhaqwa kokuhamba, ukuqhubekeka nokulawula usetyenziso apho kufuneka khona ukwamkelwa kwento. Kungenxa yokuba ukupapashwa kwayo kunikwa phantsi kwelayisensi ye-BSD, evumela ukuba isetyenziswe ngokukhululekileyo kwiinjongo zorhwebo nezophando kunye neemeko ezichaziweyo.

Vula iCV Inemisebenzi engaphezu kwama-500 egubungela uluhlu olubanzi lweendawo kwinkqubo yombono, njengokubonwa kwento (ukubonwa kobuso), ukulinganiswa kwekhamera, umbono we stereo, umbono werobhothi, ukwahlula amanyathelo kwividiyo, ukuguqula imifanekiso, ukukhupha iimodeli ze-3D, ukwenza indawo ye-3D ukusuka kumfanekiso wekhamera yestereo ukwenza imifanekiso ekumgangatho ophezulu ngokudibanisa imifanekiso ekumgangatho ophantsi.

Tambien inikeza amandla okukhangela imifanekiso yezinto ezifanayo kuseto lwezinto ezithiwe thaca ngokusebenzisa iindlela zokufunda ngomatshini, ukumakisha, ukumisela izinto eziqhelekileyo kwimifanekiso eyahlukeneyo, ukuphelisa ngokuzenzekelayo iziphene ezinje ngamehlo abomvu.

I-OpenCV ibonelela ngaphezulu kwe-2500 algorithms, zozibini zakudala kwaye zibonisa impumelelo yakutshanje kwicandelo lombono wekhompyuter kunye neenkqubo zokufunda ngomatshini. Ikhowudi yelayibrari ibhaliwe kwi-C ++ kwaye ihanjiswa phantsi kwelayisensi ye-BSD.

Malunga nohlobo olutsha lwe-OpenCV 4.2

Okwangoku ilayibrari ikwinguqulelo yayo ye-OpenCV 4.2, apho ku kwimodyuli ye-DNN (Inethiwekhi enzulu ye-neural) kunye nokumiliselwa kwe-algorithms yokufunda komatshini esekwe kwinethiwekhi ye-neural, yongeze umva wokusebenzisa i-CUDA kunye nenkxaso yokulinga ye-nGraph OpenVINO API yaphunyezwa.

Ukongeza ekusebenziseni imiyalelo ye-SIMD, songeza ukusebenza kwekhowudi kwimveliso yestereo (StereoBM / StereoSGBM), ukuphinda wenze ubungakanani kwakhona, imaski, ukujikeleza, ukubala izinto zombala ezingekhoyo, kunye neminye imisebenzi emininzi.

Kwimodyuli ye-G-API (evulekile_gapi), esebenza njengenjini yokuqhubekeka Ukusebenza ngokukuko ngokukuko usebenzisa iigraphics ezisekwe kwimizobo, ixhasa ubuchwephesha obuntsonkothe ​​ngakumbi kumbono wekhompyuter kunye nokufunda komatshini ngokunzulu. Unika inkxaso kwi-Injini ye-Intel Inference. Inkxaso eyongeziweyo yokulungiswa komjelo wevidiyo kwimodeli yokuphunyezwa.

Ukuba sesichengeni (i-CVE-2019-5063, i-CVE-2019-5064) enokuthi ikhokelele ekuphunyezweni kwekhowudi yokuhlaselwa ngokuqhubekeka kwedatha engaqinisekiswanga kwiifomathi zeXML, YAML kunye neJSON. Ukuba umlinganiswa onekhowudi engafumanekiyo afunyenwe ngexesha lokuhluzwa kweJSON, ixabiso liphela likhutshelwa kwisikhuseli, kodwa ngaphandle kokuqinisekiswa okufanelekileyo kwemida yendawo yenkumbulo eyabelweyo.

Olunye utshintsho thaca kule nguqulo intsha:

• Kongezwe ukumiliselwa kwemisebenzi emininzi yomsebenzi we-pyrDown.
• Yongeze amandla okukhupha imijelo yevidiyo kwizikhongozeli seendaba (demuxing) usebenzisa i-backend yevidiyo esekwe kwi-FFmpeg.
• Yongeze ialgorithm yokuphinda ukhethe ngokukhawuleza ukwakhiwa kwakhona kwemifanekiso eyonakalisiweyo yeFSR (Frequency Selective Reconstruction).
• Yongeze indlela ye-RIC yokudibanisa iindawo ezingenanto.
• Yongezwe indlela yokuchasana neLOGOS.

Uyifaka njani i-OpenCV 4.2?

Kwabo banomdla wokukwazi ukufaka eli thala leencwadi, unokufumana ingxelo entsha kunye nokubonisana nolwazi olunxulumene nokusetyenziswa kunye nokufumana izifundo kwiwebhusayithi esemthethweni.

Ikhonkco yile.

Kule nqaku Siza kubonelela ngamanyathelo ukuze sikwazi ukuphumeza ithala leencwadi kwiRaspberry pi.

Ukufaka i-OpenCV kwi-Raspberry PKuya kufuneka ndibenenkqubo yakho, eyiRaspbian.

Ukusuka kwivSiza kuvula i-terminal kwaye siza kuchwetheza kuyo le miyalelo ilandelayo yokufaka ukuxhomekeka, izixhobo zokuphucula, iiphakheji zemifanekiso phakathi kwezinye iilayibrari ezongezelelweyo:

sudo apt-get install build-essential cmake pkg-config
sudo apt-get install libjpeg-dev libtiff5-dev libjasper-dev libpng-dev libavcodec-dev libavformat-dev libswscale-dev libv4l-dev libxvidcore-dev libx264-dev libfontconfig1-dev libcairo2-dev libgdk-pixbuf2.0-dev libpango1.0-dev libgtk2.0-dev libgtk-3-dev libatlas-base-dev gfortran libhdf5-dev libhdf5-serial-dev libhdf5-103 libqtgui4 libqtwebkit4 libqt4-test python3-pyqt5

Ekugqibeleni, Masifake i-python 3 iifayile zeentloko ukuze sikwazi ukwenza i-OpenCV:

sudo apt-get install python3-dev

Ngoku masenze imeko yePython ngale miyalelo ilandelayo, oku ukuze ubenendawo eyodwa:

wget https://bootstrap.pypa.io/get-pip.py
sudo python get-pip.py
sudo python3 get-pip.py
sudo rm -rf ~/.cache/pip

Siza kufaka ubuhle kunye nevalealenvwrapper:

sudo pip install virtualenv virtualenvwrapper
nano ~/.bashrc

# virtualenv and virtualenvwrapper
export WORKON_HOME=$HOME/.virtualenvs
export VIRTUALENVWRAPPER_PYTHON=/usr/bin/python3

source /usr/local/bin/virtualenvwrapper.sh
source ~/.bashrc
mkvirtualenv cv -p python3
pip install "picamera[array]"

Uyenzile ngoku siza kuqulunqa i-openCV nge:

cd ~
wget -O opencv.zip https://github.com/opencv/opencv/archive/4.2.0.zip
wget -O opencv_contrib.zip https://github.com/opencv/opencv_contrib/archive/4.2.0.zip
unzip opencv.zip
unzip opencv_contrib.zip
mv opencv-4.2.0 opencv
mv opencv_contrib-4.2.0 opencv_contrib

Ngoku sizokwandisa utshintsho kutshintsho lwenkqubo yethu kuba ukuba siyishiya njengoko injalo ngokungagqibekanga inkqubo inokuxhoma:

sudo nano /etc/dphys-swapfile

Kwaye siza kuhlelela umahluko we-CONF_SWAPSIZE:

CONF_SWAPSIZE=1024

Sigcina kwaye sivale nge-ctrl + o kunye ne-ctrl + x. Emva koko sichwetheza:

sudo /etc/init.d/dphys-swapfile stop
sudo /etc/init.d/dphys-swapfile start

Ngoku siza kuqhubeka nokudibanisa:

workon cv
pip install numpy
cd ~/opencv
mkdir build
cd build
cmake -D CMAKE_BUILD_TYPE=RELEASE \
-D CMAKE_INSTALL_PREFIX=/usr/local \
-D OPENCV_EXTRA_MODULES_PATH=~/opencv_contrib/modules \
-D ENABLE_NEON=ON \
-D ENABLE_VFPV3=ON \
-D BUILD_TESTS=OFF \
-D INSTALL_PYTHON_EXAMPLES=OFF \
-D OPENCV_ENABLE_NONFREE=ON \
-D CMAKE_SHARED_LINKER_FLAGS=-latomic \
-D BUILD_EXAMPLES=OFF ..
make -j4
sudo make install
sudo ldconfig
cd /usr/local/lib/python3.7/site-packages/cv2/python-3.7
sudo mv cv2.cpython-37m-arm-linux-gnueabihf.so cv2.so
cd ~/.virtualenvs/cv/lib/python3.7/site-packages/
ln -s /usr/local/lib/python3.7/site-packages/cv2/python-3.7/cv2.so cv2.so

Kwaye ukulungele.