Windows搭建opencv cuda开发环境并验证是否成功

编译opencv cuda源码

   电脑安装cuda 12.0或者11.8，根据你的电脑配置自行选择

  下载opencv 源码

git clone https://github.com/opencv/opencv.git
git clone https://github.com/opencv/opencv_contrib.git

在opencv目录里新建 build 文件夹

cd  build后   

cmake选项

cmake -D CMAKE_BUILD_TYPE=RELEASE \-D CMAKE_INSTALL_PREFIX=/usr/local \-D WITH_TBB=ON \-D WITH_V4L=ON \-D WITH_QT=ON \-D WITH_OPENGL=ON \-D WITH_CUDA=ON \-D CUDA_ARCH_BIN=7.5 \-D OPENCV_EXTRA_MODULES_PATH=~/opencv_contrib/modules \-D VTK_DIR=/usr/lib/x86_64-linux-gnu/cmake/vtk-8.2 \  # 根据实际路径修改-D JAVA_INCLUDE_PATH=/usr/lib/jvm/java-8-openjdk-amd64/include \-D JAVA_INCLUDE_PATH2=/usr/lib/jvm/java-8-openjdk-amd64/include/linux \-D BUILD_opencv_python2=ON \-D BUILD_opencv_python3=ON \-D INSTALL_PYTHON_EXAMPLES=ON \-D INSTALL_C_EXAMPLES=OFF \-D OPENCV_GENERATE_PKGCONFIG=ON \-D BUILD_EXAMPLES=ON ..

使用多线程编译

msbuild /m:%NUMBER_OF_PROCESSORS% /p:Configuration=Release /p:Platform=x64 OpenCV.sln

编译运行测试程序，验证opencv 是否正常使用cuda

#include <opencv2/opencv.hpp>
#include <iostream>int main() {// 检查CUDA设备int count = cv::cuda::getCudaEnabledDeviceCount();std::cout << "CUDA设备数量: " << count << std::endl;if (count > 0) {cv::cuda::setDevice(0);  // 选择第一个CUDA设备cv::cuda::DeviceInfo info(0);std::cout << "当前CUDA设备: " << info.name() << std::endl;}return 0;
}

打印信息输出如下，说明opencv cuda 开发环境搭建成功

CUDA设备数量: 1
当前CUDA设备: NVIDIA GeForce RTX 4060