- 1. 配置并更新树莓派系统
sudo raspi-config // 进入后打开摄像头、SSHsudo apt-get updatesudo apt-get upgradesudo rpi-update
- 2. 安装OpenCV的相关工具
sudo apt-get install build-essential cmake git pkg-config
- 3. 安装OpenCV的图像工具包
sudo apt-get install libjpeg8-dev sudo apt-get install libtiff5-dev sudo apt-get install libjasper-dev sudo apt-get install libpng12-dev
- 4. 安装视频I/O包
sudo apt-get install libavcodec-dev libavformat-dev libswscale-dev libv4l-dev
- 5.安装gtk2.0和优化函数包
sudo apt-get install libgtk2.0-devsudo apt-get install libatlas-base-dev gfortran
- 6. 下载OpenCV源码
git clone https://github.com/opencv/opencv.git
- 7. 安装OpenCV
// 根据下载的版本而定cd opencv-3.2.0 // 创建release文件夹mkdir release// 进入release目录下cd release// cmake读入所有源文件之后，自动生成makefilecmake -D CMAKE_BUILD_TYPE=RELEASE \-D CMAKE_INSTALL_PREFIX=/usr/local ..// 编译sudo make// 安装sudo make install//更新动态链接库sudo ldconfig
- 8. 解决无法打开摄像头硬件问题
sudo nano /etc/modules// 进入编辑界面后，在末尾添加输入snd-bcm2835bcm2835-v4l2
- 9. 测试用例Python代码
# -*- coding: utf-8 -*-__author__ = "kyoRan"import cv2cap = cv2.VideoCapture(0) # 打开摄像头print("VideoCapture is opened?", cap.isOpened())while(True):ret, frame = cap.read() # 读取摄像头图像center = (frame.shape[1]//2, frame.shape[0]//2) # 图像中心点位置gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY) # 转灰度cv2.circle(gray, center=center, radius=100, color=(0,0,255)) # 画圆cv2.imshow("frame", gray) # 显示图片if cv2.waitKey(1) & 0xFF == ord('q'):breakcap.release() # 释放摄像头cv2.destroyAllWindows() # 关闭所有窗口 - 测试结果示例
ps:测试出现错误可能是摄像头默认未打开，需要去raspi-config使能它，enable它哦。
原文：https://blog.csdn.net/kyokozan/article/details/79192646