Ubuntu安装不同版本的opencv，并任意切换使用

参考：

参考官方：

主要参考：

在WSL-Ubuntu20.04下，安装OpenCV-3过程以及遇到的问题和相应的解决办法 - LesPlumes - 博客园

我是wsl2-ubuntu18.04，安装ros后已有opencv3.2.0，现在要再装opencv3.3.1

一.下载和安装依赖包

1、首先更新 apt-get，在安装前最好先更新一下系统，不然有可能会安装失败。在终端输入：

sudo apt-get update
sudo apt-get upgrade

2、接着安装官方给的opencv依赖包，在终端输入：

sudo apt-get install build-essential
sudo apt-get install cmake git libgtk2.0-dev pkg-config libavcodec-dev libavformat-dev libswscale-dev
sudo apt-get install python-dev python-numpy libtbb2 libtbb-dev libjpeg-dev libpng-dev libtiff-dev libjasper-dev libdc1394-22-dev

下面的步骤我做了：

错误：E: 无法定位软件包 libjasper-dev
sudo add-apt-repository "deb http://security.ubuntu.com/ubuntu xenial-security main"
sudo apt update
sudo apt install libjasper1 libjasper-dev

二.下载源文件

下载opencv-3.3.1，以及opencv_contrib-3.3.1。

opencv-3.3.1可以到官网或者github上去下载源文件（官网版本选择在下方翻页，github上通过tag选择）。

wget -q https://github.com/opencv/opencv/archive/3.3.1.zip

解压源文件并进入

unzip opencv-3.3.1.zip
cd opencv-3.3.1/

（opencv_contrib下载连接：GitHub - opencv/opencv_contrib: Repository for OpenCV's extra modules）

将opencv_contrib-3.3.1文件夹放入opencv-3.3.1文件夹内(我这里的opencv_contrib-3.3.1改名为opencv_contrib)。

三.安装

1.编译前的准备工作

①在进行cmake之前，将“Opencv3缺失文件”这个文件夹中的所有.i文件都复制到

opencv3_contrib\modules\xfeatures2d\src\这个目录下。

(百度网盘：https://pan.baidu.com/s/15QlHwu5ur2vc6ncyVS4e_Q 提取码：sysu)

②在进行make之前，将以下路径：

opencv-3.3.1\opencv_contrib\modules\xfeatures2d\include\opencv2\

的xfeatures2d文件夹和xfeatures2d.hpp都copy到

opencv-3.3.1\build\opencv2\路径下。

（opencv_contrib下载连接：https://github.com/opencv/opencv_contrib）

sudo mv opencv_contrib/modules/xfeatures2d/include/opencv2/xfeatures2d  build/opencv2
sudo mv opencv_contrib/modules/xfeatures2d/include/opencv2/xfeatures2d.hpp  build/opencv2

③在进行make之前，下载nvida_sdk（链接：https://pan.baidu.com/s/1IykEbf7SZgf2IE0T52_bqA 提取码：sysu）

然后把下载下来的Video_Codec_Interface_12.1.14\Video_Codec_Interface_12.1.14\Interface\目录下的三个文件，

都复制到opencv-3.3.1/modules/cudacodec/src/下；

再依次打开以下文件：

precomp.hpp、video_decoder.hpp、cuvid_video_source.hpp、

frame_queue.hpp、video_parser.hpp

将 #if CUDA_VERSION >= 9000 修改为 #if CUDA_VERSION >= 9000 && CUDA_VERSION < 10000

sudo mv /home/leaf1804/Video_Codec_Interface_12.1.14/Interface/cuviddec.h /home/leaf1804/opencv-3.3.1/modules/cudacodec/src

sudo mv /home/leaf1804/Video_Codec_Interface_12.1.14/Interface/nvcuvid.h /home/leaf1804/opencv-3.3.1/modules/cudacodec/src

sudo mv /home/leaf1804/Video_Codec_Interface_12.1.14/Interface/nvEncodeAPI.h /home/leaf1804/opencv-3.3.1/modules/cudacodec/src

④在进行make之前，打开opencv-3.3.1\modules\videoio\src\ cap_ffmpeg_impl.hpp，添加以下宏定义：

#define AV_CODEC_FLAG_GLOBAL_HEADER (1 << 22)

#define CODEC_FLAG_GLOBAL_HEADER AV_CODEC_FLAG_GLOBAL_HEADER

#define AVFMT_RAWPICTURE 0x0020

2.编译opencv

cd opencv-3.3.1
mkdir build && cd build
sudo cmake -D CMAKE_BUILD_TYPE=Release -D CMAKE_INSTALL_PREFIX=/home/leaf1804/software/opencv3.3.1 -D CUDA_NVCC_FLAGS="-D_FORCE_INLINES" -D BUILD_opencv_cudacodec=OFF -D OPENCV_EXTRA_MODULES_PATH=../opencv_contrib/modules ..

sudo make -j6
sudo make install

报错1：

运行sudo make -j6的时候报错：

[ 46%] Building NVCC (Device) object modules/cudabgsegm/CMakeFiles/cuda_compile.dir/src/cuda/cuda_compile_generated_mog2.cu.o /home/leaf1804/opencv-3.3.1/modules/core/include/opencv2/core/cuda/vec_math.hpp(203): error: calling a constexpr __host__ function("abs") from a __device__ function("abs") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this. /home/leaf1804/opencv-3.3.1/modules/core/include/opencv2/core/cuda/vec_math.hpp(203): error: calling a constexpr __host__ function("abs") from a __device__ function("abs") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this. /home/leaf1804/opencv-3.3.1/modules/core/include/opencv2/core/cuda/vec_math.hpp(203): error: calling a constexpr __host__ function("abs") from a __device__ function("abs") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this. /home/leaf1804/opencv-3.3.1/modules/core/include/opencv2/core/cuda/vec_math.hpp(203): error: calling a constexpr __host__ function("abs") from a __device__ function("abs") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this. /home/leaf1804/opencv-3.3.1/modules/core/include/opencv2/core/cuda/vec_math.hpp(203): error: calling a constexpr __host__ function("abs") from a __device__ function("abs") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this. /home/leaf1804/opencv-3.3.1/modules/core/include/opencv2/core/cuda/vec_math.hpp(203): error: calling a constexpr __host__ function("abs") from a __device__ function("abs") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this. /home/leaf1804/opencv-3.3.1/modules/core/include/opencv2/core/cuda/vec_math.hpp(203): error: calling a constexpr __host__ function("abs") from a __device__ function("abs") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this. /home/leaf1804/opencv-3.3.1/modules/core/include/opencv2/core/cuda/vec_math.hpp(203): error: calling a constexpr __host__ function("abs") from a __device__ function("abs") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this. /home/leaf1804/opencv-3.3.1/modules/core/include/opencv2/core/cuda/vec_math.hpp(203): error: calling a constexpr __host__ function("abs") from a __device__ function("abs") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this. /home/leaf1804/opencv-3.3.1/modules/core/include/opencv2/core/cuda/vec_math.hpp(203): error: calling a constexpr __host__ function("abs") from a __device__ function("abs") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this. /home/leaf1804/opencv-3.3.1/modules/core/include/opencv2/core/cuda/vec_math.hpp(205): error: calling a constexpr __host__ function("abs") from a __device__ function("abs") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this. /home/leaf1804/opencv-3.3.1/modules/core/include/opencv2/core/cuda/vec_math.hpp(205): error: calling a constexpr __host__ function("abs") from a __device__ function("abs") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this. /home/leaf1804/opencv-3.3.1/modules/core/include/opencv2/core/cuda/vec_math.hpp(205): error: calling a constexpr __host__ function("abs") from a __device__ function("abs") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this. /home/leaf1804/opencv-3.3.1/modules/core/include/opencv2/core/cuda/vec_math.hpp(205): error: calling a constexpr __host__ function("abs") from a __device__ function("abs") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this. /home/leaf1804/opencv-3.3.1/modules/core/include/opencv2/core/cuda/vec_math.hpp(205): error: calling a constexpr __host__ function("abs") from a __device__ function("abs") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this. /home/leaf1804/opencv-3.3.1/modules/core/include/opencv2/core/cuda/vec_math.hpp(205): error: calling a constexpr __host__ function("abs") from a __device__ function("abs") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this. /home/leaf1804/opencv-3.3.1/modules/core/include/opencv2/core/cuda/vec_math.hpp(205): error: calling a constexpr __host__ function("abs") from a __device__ function("abs") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this. /home/leaf1804/opencv-3.3.1/modules/core/include/opencv2/core/cuda/vec_math.hpp(205): error: calling a constexpr __host__ function("abs") from a __device__ function("abs") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this. /home/leaf1804/opencv-3.3.1/modules/core/include/opencv2/core/cuda/vec_math.hpp(205): error: calling a constexpr __host__ function("abs") from a __device__ function("abs") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this. /home/leaf1804/opencv-3.3.1/modules/core/include/opencv2/core/cuda/vec_math.hpp(205): error: calling a constexpr __host__ function("abs") from a __device__ function("abs") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this. 20 errors detected in the compilation of "/tmp/tmpxft_00006fcc_00000000-13_mog2.compute_70.cpp1.ii". CMake Error at cuda_compile_generated_mog2.cu.o.cmake:264 (message): Error generating file /home/leaf1804/opencv-3.3.1/build/modules/cudabgsegm/CMakeFiles/cuda_compile.dir/src/cuda/./cuda_compile_generated_mog2.cu.o modules/cudabgsegm/CMakeFiles/opencv_cudabgsegm.dir/build.make:89: recipe for target 'modules/cudabgsegm/CMakeFiles/cuda_compile.dir/src/cuda/cuda_compile_generated_mog2.cu.o' failed make[2]: *** [modules/cudabgsegm/CMakeFiles/cuda_compile.dir/src/cuda/cuda_compile_generated_mog2.cu.o] Error 1 CMakeFiles/Makefile2:7100: recipe for target 'modules/cudabgsegm/CMakeFiles/opencv_cudabgsegm.dir/all' failed make[1]: *** [modules/cudabgsegm/CMakeFiles/opencv_cudabgsegm.dir/all] Error 2 make[1]: *** Waiting for unfinished jobs.... [ 46%] Building NVCC (Device) object modules/cudaarithm/CMakeFiles/cuda_compile.dir/src/cuda/cuda_compile_generated_sum.cu.o [ 46%] Building NVCC (Device) object modules/cudaarithm/CMakeFiles/cuda_compile.dir/src/cuda/cuda_compile_generated_threshold.cu.o /home/leaf1804/opencv-3.3.1/modules/cudaarithm/src/cuda/sub_mat.cu(78): warning: function "<unnamed>::SubOp2::operator()" was declared but never referenced /home/leaf1804/opencv-3.3.1/modules/cudaarithm/src/cuda/sub_mat.cu(97): warning: function "<unnamed>::SubOp4::operator()" was declared but never referenced Scanning dependencies of target opencv_cudaarithm [ 46%] Building CXX object modules/cudaarithm/CMakeFiles/opencv_cudaarithm.dir/src/arithm.cpp.o [ 46%] Building CXX object modules/cudaarithm/CMakeFiles/opencv_cudaarithm.dir/src/element_operations.cpp.o [ 47%] Building CXX object modules/cudaarithm/CMakeFiles/opencv_cudaarithm.dir/src/reductions.cpp.o [ 47%] Building CXX object modules/cudaarithm/CMakeFiles/opencv_cudaarithm.dir/src/core.cpp.o cc1plus: warning: /home/leaf1804/opencv-3.3.1/build/modules/cudaarithm/precomp.hpp.gch/opencv_cudaarithm_Release.gch: not used because OPENCV_TRAITS_ENABLE_DEPRECATED' is defined [-Winvalid-pch] cc1plus: warning: /home/leaf1804/opencv-3.3.1/build/modules/cudaarithm/precomp.hpp.gch/opencv_cudaarithm_Release.gch: not used because OPENCV_TRAITS_ENABLE_DEPRECATED' is defined [-Winvalid-pch] cc1plus: warning: /home/leaf1804/opencv-3.3.1/build/modules/cudaarithm/precomp.hpp.gch/opencv_cudaarithm_Release.gch: not used because OPENCV_TRAITS_ENABLE_DEPRECATED' is defined [-Winvalid-pch] cc1plus: warning: /home/leaf1804/opencv-3.3.1/build/modules/cudaarithm/precomp.hpp.gch/opencv_cudaarithm_Release.gch: not used because OPENCV_TRAITS_ENABLE_DEPRECATED' is defined [-Winvalid-pch] [ 47%] Linking CXX shared library ../../lib/libopencv_cudaarithm.so [ 47%] Built target opencv_cudaarithm Makefile:181: recipe for target 'all' failed make: *** [all] Error 2

然后修改cmake命令后重新从cmake那一步开始再运行一遍

成功了！！

然后运行sudo make install

成功！！

报错后，可以清理并重新配置

在尝试修复之前，可以确保清理 build 目录以避免遗留问题：

cd /home/leaf/opencv-3.3.1/build
rm -rf *

我还删除过一次opencv-3.3.1和opencv_contrib文件夹，从头开始再来过一次

四.切换不同版本opencv

打开bashrc文件(~/.bashrc)主目录下 gedit ~/.bashrc ，并加入

# # opencv-3.3.1
# export PKG_CONFIG_PATH=~/software/opencv3.3.1/lib/pkgconfig
# export LD_LIBRARY_PATH=~/software/opencv3.3.1/lib

#OpenCV 3.2.0
export PKG_CONFIG_PATH=/usr/local/lib/pkgconfig
export LD_LIBRARY_PATH=/usr/local/lib

用那个取消注释另一个，可以使用 pkg-config --modversion opencv 进行验证。

source ~/.bashrc
pkg-config --modversion opencv

# 查看详细的路径：
pkg-config --cflags --libs opencv

使用多版本opencv

在写CmakeList.txt，如果只有一个版本的opencv,我们一般直接使用

FIND_PACKAGE(OpenCV REQUIRED)

如果现在要使用的是默认安装的opencv3.2.0,则使用使用上面的指令就足够了。

如果现在要使用的是我们自己指定路径的opencv-3.3.1，则在上面指令前面加上如下指令：

set(OpenCV_DIR "/home/wh/opencv4/lib/cmake/opencv4")：引号里面的地址是OpencvConfig.cmake地址

OpenCVConfig.cmake 是 OpenCV 库的配置文件。它是用来告诉项目如何使用 OpenCV 库的。它包含了 OpenCV 库的路径信息、版本信息和链接信息等。当项目使用 find_package(OpenCV) 命令时，CMake 就会去寻找这个文件，并读取其中的信息，最终使项目可以使用 OpenCV 库。

比如我的就要在原来的cmakelist.txt里面加上一句

set(OpenCV_DIR "/home/leaf1804/software/opencv3.3.1/share/OpenCV")，因为我的OpencvConfig.cmake地址是这里