OpenCV

Description

OpenCV (Open Source Computer Vision Library) is an open-source computer vision and machine learning software library. It was built to provide a common infrastructure for computer vision applications and to accelerate the use of machine perception in commercial products.

The library has more than 2,500 optimized algorithms, covering a comprehensive set of both classic and state-of-the-art computer vision and machine learning algorithms.

How to Build with SCALE

git clone https://github.com/opencv/opencv.git
git clone https://github.com/opencv/opencv_contrib.git
cd opencv
cmake \
    -DCMAKE_BUILD_TYPE=Release \
    -DWITH_CUDA=ON \
    -DCUDA_TOOLKIT_ROOT_DIR=/opt/scale \
    -DOPENCV_EXTRA_MODULES_PATH=../opencv_contrib/modules \
    -Bbuild .
make -C build -j$(nproc) install

Notes

• GPU-accelerated modules include: cudaarithm, cudabgsegm, cudafeatures2d, cudafilters, cudaimgproc, cudaobjdetect, cudaoptflow, cudastereo, cudawarping
• DNN module supports CUDA backend for inference acceleration
• cuFFT, cuBLAS, and cuDNN integrations are disabled in the current validation configuration