NVIDIA Jetson TK1学习与开发(九):基于GPU加速的OpenCV人体检测(Full Body Detection)

基于GPU加速的OpenCV人体检测(Full Body Detection)

1、CUDA和OpenCV的安装

首先,确定一下自己的平台是否安装好了CUDA和OpenCV。

CUDA的安装可以参考:http://blog.csdn.net/frd2009041510/article/details/42042807http://blog.csdn.net/frd2009041510/article/details/42925205

OpenCV的安装可以参考:http://blog.csdn.net/frd2009041510/article/details/42930113

2、Simply build the OpenCV HOG (Hough Of Gradients) sample person detector program

[cpp]  view plain  copy
 print ?
  1. cd opencv-2.4.9/samples/gpu  
  2. 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  

进入目录:


编译:


3、run the HOG demo

[cpp]  view plain  copy
 print ?
  1. ./hog --video 768x576.avi  

注意:You can run the HOG demo such as on a pre-recorded video of people walking around. The HOG demo displays a graphical output, hence you should plug a HDMI monitor in or use a remote viewer such as X Tunneling or VNC or TeamViewer on your desktop in order to see the output.

结果截图如下:



如果有摄像头,可以执行下面的命令来完成演示:

[html]  view plain  copy
 print ?
  1. ./hog --camera 0  


注意:Note: This looks for whole bodies and assumes they are small, so you need to stand atleast 5m away from the camera if you want it to detect you!

结果截图如下:


4、HOG demo中的一些控制命令

You can toggle between CPU vs GPU by pressing 'm', where you will see that the GPU is typically 5x faster at HOG than the CPU!

©️2020 CSDN 皮肤主题: 精致技术 设计师:CSDN官方博客 返回首页