第五章： pcDuino上面安装和测试SimpleCV以及OpenCV

pcDuino有计算能力来进行计算机视觉，这就让很多在Arduino 上不可能的项目可以在pcDuino上实现。 我们可以把计算机视觉这一非常强大的技术用在我们的项目中。 在这章，我们来看怎么安装和使用SimpleCV和OpenCV。 SimpleCV的安装和例子 在我们开始动手之前，我们要确保手头有一个 UVC 兼容的USB摄像头。 下面为安装SimpleCV的步骤： $sudo apt-get install ipython python-opencv python-scipy python-numpy python-setuptools python-pip $sudo pip install https://github.com/ingenuitas/SimpleCV/zipball/master $sudo apt-get install python-pygame $sudo apt-get install python-imaging 复制代码 在终端里面输入 “$simpleCV" 就可以启动simpleCV. simpleCV是一个交互的命令解释器。 我们可以输入命令来执行： ubuntu@ubuntu:~$ simplecv +-----------------------------------------------------------+ SimpleCV 1.3.0 [interactive shell] - http:// +-----------------------------------------------------------+ Commands: "exit()" or press "Ctrl+ D" to exit the shell "clear" to clear the shell screen "tutorial" to begin the SimpleCV interactive tutorial "example" gives a list of examples you can run "forums" will launch a web browser for the help forums "walkthrough" will launch a web browser with a walkthrough Usage: dot complete works to show library for example: Image().save("/tmp/test.jpg") will dot complete just by touching TAB after typing Image(). Documentation: help(Image), ?Image, Image?, or Image()? all do the same "docs" will launch webbrowser showing documentation SimpleCV:1> cam=Camera() VIDIOC_QUERYMENU: Invalid argument VIDIOC_QUERYMENU: Invalid argument VIDIOC_QUERYMENU: Invalid argument VIDIOC_QUERYMENU: Invalid argument VIDIOC_QUERYMENU: Invalid argument VIDIOC_QUERYMENU: Invalid argument VIDIOC_QUERYMENU: Invalid argument SimpleCV:2> img=cam.getImage() SimpleCV:3> img.show() SimpleCV:5: 复制代码 以下为命令执行的结果： OpenCV的安装和例子 OpenCV 是个开源的计算机视觉软件包。在这里我们详细的介绍如何安装OpenCV Python版本到pcDuino上面。 并且给出了两个例子，一个例子用来通过USB 摄像头来获取图形，另外一个例子通过OpenCV来做人脸识别。 安装步骤： $ sudo apt-get -y install build-essential cmake cmake-qt-gui pkg-config libpng12-0 libpng12-dev libpng++-dev libpng3 libpnglite-dev zlib1g-dbg zlib1g zlib1g-dev pngtools libtiff4-dev libtiff4 libtiffxx0c2 libtiff-tools $sudo apt-get -y install libjpeg8 libjpeg8-dev libjpeg8-dbg libjpeg-progs ffmpeg libavcodec-dev libavcodec53 libavformat53 libavformat-dev libgstreamer0.10-0-dbg libgstreamer0.10-0 libgstreamer0.10-dev libxine1-ffmpeg libxine-dev libxine1-bin libunicap2 libunicap2-dev libdc1394-22-dev libdc1394-22 libdc1394-utils swig libv4l-0 libv4l-dev python-numpy libpython2.6 python2.6-dev libgtk2.0-dev pkg-config $sudo apt-get install libopencv-dev python-opencv $sudo apt-get install python-dev $sudo ln -s /usr/lib/arm-linux-gnueabihf/libjpeg.so /usr/lib $sudo ln -s /usr/lib/arm-linux-gnueabihf/libfreetype.so /usr/lib $sudo ln -s /usr/lib/arm-linux-gnueabihf/libz.so /usr/lib $sudo easy_install PIL $sudo pip install -v PIL 复制代码 例子1： 用OpenCV通过USB摄像头来抓图像： #!/Users/brent/.virtualenvs/lumber/bin/python import cv cv.NamedWindow("w1", cv.CV_WINDOW_AUTOSIZE) camera_index = 0 capture = cv.CaptureFromCAM(camera_index) gx = gy = 1 grayscale = blur = canny = False def repeat():     global capture #declare as globals since we are assigning to them now     global camera_index     global gx, gy, grayscale, canny, blur     frame = cv.QueryFrame(capture)     # import pdb; pdb.set_trace()     if grayscale:         gray = cv.CreateImage(cv.GetSize(frame), frame.depth, 1)         cv.CvtColor(frame, gray, cv.CV_RGB2GRAY)         frame = gray     if blur:         g = cv.CreateImage(cv.GetSize(frame), cv.IPL_DEPTH_8U, frame.channels)         cv.Smooth(frame, g, cv.CV_GAUSSIAN, gx, gy)         frame = g     if grayscale and canny:         c = cv.CreateImage(cv.GetSize(frame), frame.depth, frame.channels)         cv.Canny(frame, c, 10, 100, 3)         frame = c     cv.ShowImage("w1", frame)     c = cv.WaitKey(10)     if c==ord('='): #in "n" key is pressed while the popup window is in focus         gx += 2         gy += 2     elif c == ord('-'):         gx = max(1, gx-2)         gy = max(1, gy-2)     elif c == ord('x'):         gx += 2     elif c == ord('X'):         gx = max(1, gx-2)     elif c == ord('q'):         exit(0)     elif c == ord('b'):         blur = not blur     elif c == ord('g'):         grayscale = not grayscale     elif c == ord('c'):         canny = not canny while True: repeat() 复制代码 例子二： 人脸识别 输入图像： 下载上面的图像，保存为 ”opencv_in.jpg"。 输出图像： #!/usr/bin/env python #coding=utf-8 import os from PIL import Image, ImageDraw import cv def detect_object(image):     grayscale = cv.CreateImage((image.width, image.height), 8, 1)     cv.CvtColor(image, grayscale, cv.CV_BGR2GRAY)     cascade = cv.Load("/usr/share/opencv/haarcascades/haarcascade_frontalface_alt_tree.xml")     rect = cv.HaarDetectObjects(grayscale, cascade, cv.CreateMemStorage(), 1.1, 2,         cv.CV_HAAR_DO_CANNY_PRUNING, (20,20))     result = []     for r in rect:         result.append((r[0][0], r[0][1], r[0][0]+r[0][2], r[0][1]+r[0][3]))     return result def process(infile):     image = cv.LoadImage(infile);     if image:         faces = detect_object(image)     im = Image.open(infile)     path = os.path.abspath(infile)     save_path = os.path.splitext(path)[0]+"_face"     try:         os.mkdir(save_path)     except:         pass     if faces:         draw = ImageDraw.Draw(im)         count = 0         for f in faces:             count += 1             draw.rectangle(f, outline=(255, 0, 0))             a = im.crop(f)             file_name = os.path.join(save_path,str(count)+".jpg")      #       print file_name             a.save(file_name)         drow_save_path = os.path.join(save_path,"out.jpg")         im.save(drow_save_path, "JPEG", quality=80)     else:         print "Error: cannot detect faces on %s" % infile if __name__ == "__main__": process("./opencv_in.jpg") 复制代码 保存上面的代码到文件名为" test_face.py"的文件中。 运行“$ python test_face.py" 来运行。

chapter5_2.png (340.02 KB, 下载次数: 5)