I-OpenCV umtapo wezincwadi wamahhala wombono womshini wesiphambano (izinhlobo ezikhona ze-GNU / Linux, Mac OS X, Windows ne-Android) okwakungukuqala ithuthukiswe yi-Intel futhi isetshenziswe ezinhlelweni eziningi, kusuka kuzinhlelo zokuphepha ezinokutholwa kokunyakaza, ukucubungula izinhlelo zokusebenza zokulawula lapho kudingeka khona ukuqashelwa kwento. Lokhu kungenxa yokuthi ukushicilelwa kwayo kunikezwa ngaphansi kwelayisense le-BSD, eliyivumela ukuthi lisetshenziselwe ngokukhululekile ukufeza kanye nenjongo yocwaningo ngezimo ezivezwe lapho.
Vula i-CV iqukethe imisebenzi engaphezu kuka-500 ehlanganisa izindawo ezahlukahlukene enqubweni yombono, njengokuqashelwa kwento (ukuqashelwa kobuso), ukulinganiswa kwekhamera, umbono wesitiriyo, umbono we-robotic, ukuhlukanisa izenzo kuvidiyo, ukuguqula izithombe, ukukhipha amamodeli we-3D, ukudala isikhala se-3D esithombeni sekhamera ye-stereo okwenza izithombe zekhwalithi ephezulu ngokuhlanganisa izithombe ezisezingeni eliphansi.
Tambien inikeza amandla okusesha izithombe zezinto ezifanayo kusethi yezakhi ezethulwe ngokusebenzisa izindlela zokufunda ngomshini, ukuhlela omaka, ukukhomba izinto ezivamile ezithombeni ezahlukahlukene, kususe ngokuzenzakalela ukukhubazeka njengamehlo abomvu.
I-OpenCV inikeza ama-algorithms angaphezu kwama-2500, Kokubili okudala futhi okukhombisa impumelelo yakamuva emkhakheni wokubuka kwamakhompyutha nezinhlelo zokufunda ngomshini. Ikhodi yelabhulali ibhalwe ku-C ++ futhi isatshalaliswa ngaphansi kwelayisense le-BSD.
Mayelana nenguqulo entsha i-OpenCV 4.2
Okwamanje umtapo wezincwadi ukuhlobo lwawo lwe-OpenCV 4.2, lapho kumodyuli ye-DNN (Inethiwekhi ejulile ye-neural) ngokusetshenziswa kwama-algorithms wokufunda ngomshini ngokususelwa kumanethiwekhi we-neural, ungeze i-backend ukusebenzisa i-CUDA nokwesekwa kokuhlola kwe-nGraph OpenVINO API kwaqaliswa.
Ngaphezu kokusebenzisa imiyalelo ye-SIMD, sisebenzisa ukusebenza kwekhodi ngokukhipha isitiriyo (StereoBM / StereoSGBM), ukukhulisa usayizi, imaski, ukushintshanisa, ukubala izingxenye zombala ezingekho, neminye imisebenzi eminingi.
Kumodyuli ye-G-API (i-opencv_gapi), esebenza njengenjini yokucubungula Ukusebenza kahle kwesithombe usebenzisa ama-algorithms asuselwa kugrafu, kusekela ubuchule be-hybrid obuyinkimbinkimbi ngokubona kwekhompyutha nokufunda komshini okujulile. Inikeza ukusekelwa kwe-Intel Inference Engine. Kungezwe ukusekelwa kokucubungula ukusakazwa kwevidiyo kumodeli yokwenza.
Ukuhlukunyezwa (i-CVE-2019-5063, i-CVE-2019-5064) engaholela ekusetshenzisweni kwekhodi yokuhlasela ngokucubungula idatha engaqinisekisiwe kumafomethi weXML, YAML, neJSON nawo alungiswa. Uma umlingiswa onekhodi engasebenzi etholakala ngesikhathi sokuhlukaniswa kwe-JSON, lonke inani likopishelwa kubhafa, kepha ngaphandle kokuqinisekiswa okufanele kwemikhawulo yendawo yememori eyabiwe.
Kwezinye izinguquko okwethulwe kule nguqulo entsha:
- Kungezwe ukuqaliswa okufundwa okuningi komsebenzi we-pyrDown.
- Kungezwe ikhono lokukhipha ukusakazwa kwevidiyo ezitsheni zemidiya (ukukhipha) usebenzisa i-backend yevidiyo esekwe ku-FFmpeg.
- Kungezwe i-algorithm yokwakhiwa kabusha okukhethiwe kokuvama kwezithombe ze-FSR ezilimele (Frequency Selective Reconstruction).
- Kungezwe indlela ye-RIC yokuhumusha izindawo ezijwayelekile ezingenalutho.
- Kungezwe indlela ejwayelekile yokuphambuka kwe-LOGOS.
Uyifaka kanjani i-OpenCV 4.2?
Okwalabo abanentshisekelo yokukwazi ukufaka le library, ingathola inguqulo entsha futhi uthinte imininingwane ehlobene nokusetshenziswa futhi uthole nokufundiswa okuvela kuwebhusayithi yayo esemthethweni.
Kule ndatshana Sizohlinzeka ngezinyathelo ezizokwazi ukusebenzisa umtapo wezincwadi ku-Raspberry pi.
Ukufaka i-OpenCV ku-Raspberry Pkumele ngibe nesistimu yakho, eyiRaspbian.
Kusuka ku-vSizovula i-terminal futhi kuyo sizothayipha imiyalo elandelayo ukufaka ukuncika, amathuluzi wonjiniyela, amaphakheji wesithombe phakathi kweminye imitapo yolwazi eyengeziwe:
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
Ekugcineni, ake sifake amafayela unhlokweni we-python 3 ukuze sikwazi ukuhlanganisa i-OpenCV:
sudo apt-get install python3-dev
Manje ake sakhe imvelo yePython ngemiyalo elandelayo, lokhu ukuze ube nesiza esikude:
wget https://bootstrap.pypa.io/get-pip.py
sudo python get-pip.py
sudo python3 get-pip.py
sudo rm -rf ~/.cache/pip
Sizofaka i-virtualenv ne-virtualenvwrapper:
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]"
Kwenziwe lokhu manje sizohlanganisa 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
Manje sizokwengeza ukushintshana kusistimu yethu ngoba uma siyishiya njengoba injalo ngokuzenzakalela uhlelo lungaxhoma:
sudo nano /etc/dphys-swapfile
Futhi sizohlela ukuguquguquka kwe-CONF_SWAPSIZE:
CONF_SWAPSIZE=1024
Songa futhi sivale nge-ctrl + o ne-ctrl + x. Ngemuva kwalokho siyathayipha:
sudo /etc/init.d/dphys-swapfile stop
sudo /etc/init.d/dphys-swapfile start
Manje sizoqhubeka nokuhlanganisa:
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
Futhi ngomumo.