nvidia tk1基于gpu加速的opencv人体检测

默认在使用Jetpack安装系统时，已选择安装Opencv和CUDA，如安装系统时并未选择安装，可通过以下链接:

CUDA： http://blog.csdn.net/frd2009041510/article/details/42042807

Opencv： http://blog.csdn.net/frd2009041510/article/details/42930113

1. 安装一些函数库

sudo apt-add-repository universe  
sudo apt-get update  
sudo apt-get install build-essential make cmake cmake-curses-gui g++  
sudo apt-get install libavformat-dev libavutil-dev libswscale-dev  
sudo apt-get install libv4l-dev    
sudo apt-get install libeigen3-dev  
sudo apt-get install libglew1.6-dev  
sudo apt-get install libgtk2.0-dev

2.下载并配置opencv源码

下载源码

wget http://downloads.sourceforge.net/project/opencvlibrary/opencv-unix/2.4.9/opencv-2.4.9.zip

将压缩包解压后的文件夹opencv-2.4.9放置到home下后，进行如图操作

cd ~/opencv-2.4.9  
mkdir build  
cmake -DWITH_CUDA=ON -DCUDA_ARCH_BIN="3.2" -DCUDA_ARCH_PTX="" -DBUILD_TESTS=OFF -DBUILD_PERF_TESTS=OFF

sudo make -j4 install

最后确保系统可以找到/usr/local/lib

echo "# Use OpenCV and other custom-built libraries." >> ~/.bashrc  
echo "export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/lib/" >> ~/.bashrc  
source ~/.bashrc

3. 测试Opencv并运行几个例子

sudo apt-get install build-essential g++

cd ~/opencv-2.4.9/samples/gpu
g++ houghlines.cpp -lopencv_core -lopencv_imgproc -lopencv_highgui -lopencv_calib3d -lopencv_contrib -lopencv_features2d -lopencv_flann -lopencv_gpu -lopencv_legacy -lopencv_ml -lopencv_objdetect -lopencv_photo -lopencv_stitching -lopencv_superres -lopencv_video -lopencv_videostab -o houghlines  
./houghlines ../cpp/logo_in_clutter.png

4. 编译opencv中自带的HOG算法程序

cd opencv-2.4.9/samples/gpu
g++ hog.cpp -lopencv_core -lopencv_imgproc -lopencv_highgui -lopencv_calib3d -lopencv_contrib -lopencv_features2d -lopencv_flann -lopencv_gpu -lopencv_legacy -lopencv_ml -lopencv_nonfree -lopencv_objdetect -lopencv_photo -lopencv_stitching -lopencv_superres -lopencv_video -lopencv_videostab -o hog

5. 运行以监测行人

./hog --video 768x576.avi

如有摄像头，可通过执行下面命令来完成

./hog --camera 0

nvidia tk1基于gpu加速的opencv人体检测

猜你喜欢