【计算机视觉】照相机标定与增强现实
目录
（一）运行环境及使用工具说明
（二）照相机标定与增强现实
1、以平面和标记物进行姿态估计
2、增强现实——在图像上放置虚拟物体
（三）实验中遇到的问题
（一）运行环境及使用工具说明
运行环境：windows10，64位，python3.5
使用的工具包：PyGame，PyOpenGL
编译工具：PyCharm
下载安装PyGame和PyOpenGL工具包
点击PyGame下载地址，和PyOpenGL下载地址到网站上去下载相应的PyGame和PyOpenGL的.whl文件
根据自己系统的环境以及python的版本，我下载的是第4个。下载后的.whl文件不能够直接点开安装，需要到命令行窗口进行安装。
在命令行窗口转到你保存的这个.whl文件的文件夹下面，然后输入pip install +.whl的文件名（提示一下，可以输入pip install 后再输pygame或者pyopengl然后使用键盘上的tab键，就会帮你查询到这个文件了），如果没有报错，就说明安装成功了。
（二）照相机标定与增强现实
标定照相机是指计算出该照相机的内参数。
1、以平面和标记物进行姿态估计
相关代码：
from pylab import *
from PIL import Image
from PCV.geometry import homography, camera
from PCV.localdescriptors import sift
def cube_points(c, wid):
""" Creates a list of points for plotting
a cube with plot. (the first 5 points are
the bottom square, some sides repeated). """
p = []
# bottom
p.append([c[0]-wid, c[1]-wid, c[2]-wid])
p.append([c[0]-wid, c[1]+wid, c[2]-wid])
p.append([c[0]+wid, c[1]+wid, c[2]-wid])
p.append([c[0]+wid, c[1]-wid, c[2]-wid])
p.append([c[0]-wid, c[1]-wid, c[2]-wid]) #same as first to close plot
# top
p.append([c[0]-wid, c[1]-wid, c[2]+wid])
p.append([c[0]-wid, c[1]+wid, c[2]+wid])
p.append([c[0]+wid, c[1]+wid, c[2]+wid])
p.append([c[0]+wid, c[1]-wid, c[2]+wid])
p.append([c[0]-wid, c[1]-wid, c[2]+wid]) #same as first to close plot
# vertical sides
p.append([c[0]-wid, c[1]-wid, c[2]+wid])
p.append([c[0]-wid, c[1]+wid, c[2]+wid])
p.append([c[0]-wid, c[1]+wid, c[2]-wid])
p.append([c[0]+wid, c[1]+wid, c[2]-wid])
p.append([c[0]+wid, c[1]+wid, c[2]+wid])
p.append([c[0]+wid, c[1]-wid, c[2]+wid])
p.append([c[0]+wid, c[1]-wid, c[2]-wid])
return array(p).T
def my_calibration(sz):
"""
Calibration function for the camera (iPhone4) used in this example.
"""
row, col = sz
fx = 2555*col/2592
fy = 2586*row/1936
K = diag([fx, fy, 1])
K[0, 2] = 0.5*col
K[1, 2] = 0.5*row
return K
# compute features
sift.process_image('book_frontal.JPG', 'im0.sift')
l0, d0 = sift.read_features_from_file('im0.sift')
sift.process_image('book_perspective.JPG', 'im1.sift')
l1, d1 = sift.read_features_from_file('im1.sift')
matches = sift.match_twosided(d0, d1)
ndx = matches.nonzero()[0]
fp = homography.make_homog(l0[ndx, :2].T)
ndx2 = [int(matches[i]) for i in ndx]
tp = homography.make_homog(l1[ndx2, :2].T)
model = homography.RansacModel()
H, inliers = homography.H_from_ransac(fp, tp, model)
# camera calibration
K = my_calibration((747, 1000))
# 3D points at plane z=0 with sides of length 0.2
box = cube_points([0, 0, 0.1], 0.1)
# project bottom square in first image
cam1 = camera.Camera(hstack((K, dot(K, array([[0], [0], [-1]])))))
# first points are the bottom square
box_cam1 = cam1.project(homography.make_homog(box[:, :5]))
# use H to transfer points to the second image
box_trans = homography.normalize(dot(H,box_cam1))
# compute second camera matrix from cam1 and H
cam2 = camera.Camera(dot(H, cam1.P))
A = dot(linalg.inv(K), cam2.P[:, :3])
A = array([A[:, 0], A[:, 1], cross(A[:, 0], A[:, 1])]).T
cam2.P[:, :3] = dot(K, A)
# project with the second camera
box_cam2 = cam2.project(homography.make_homog(box))
# plotting
im0 = array(Image.open('book_frontal.JPG'))
im1 = array(Image.open('book_perspective.JPG'))
figure()
imshow(im0)
plot(box_cam1[0, :], box_cam1[1, :], linewidth=3)
title('2D projection of bottom square')
axis('off')
figure()
imshow(im1)
plot(box_trans[0, :], box_trans[1, :], linewidth=3)
title('2D projection transfered with H')
axis('off')
figure()
imshow(im1)
plot(box_cam2[0, :], box_cam2[1, :], linewidth=3)
title('3D points projected in second image')
axis('off')
show()
运行结果：
使用平面物体作为标记物，来计算用于新视图投影矩阵的例子。将图像的特征和对齐后的标记匹配，计算出图像的单应性矩阵，然后用于计算照相机的姿态。（带有一个灰色正方形区域的模板图像）
从未知视角拍摄的一幅图像，该图像包含同一个正方形，该正方形已经经过估计的单应性矩阵进行了变换。
使用计算出的照相机矩阵变换立方体。
2、增强现实——在图像上放置虚拟物体
增强现实是将物体和相应信息放置在图像数据上的一系列操作的总称。（此处用到了PyGame和PyOpenGL工具包）
在图像中放置虚拟物体指的是以一张二维图像为背景，然后把使用相应工具绘制出来的3D图像放置在背景图中的指定位置。
相关代码：
import math
import pickle
from pylab import *
from OpenGL.GL import *
from OpenGL.GLU import *
from OpenGL.GLUT import *
import pygame, pygame.image
from pygame.locals import *
from PCV.geometry import homography, camera
from PCV.localdescriptors import sift
def cube_points(c, wid):
""" Creates a list of points for plotting
a cube with plot. (the first 5 points are
the bottom square, some sides repeated). """
p = []
# bottom
p.append([c[0]-wid, c[1]-wid, c[2]-wid])
p.append([c[0]-wid, c[1]+wid, c[2]-wid])
p.append([c[0]+wid, c[1]+wid, c[2]-wid])
p.append([c[0]+wid, c[1]-wid, c[2]-wid])
p.append([c[0]-wid, c[1]-wid, c[2]-wid]) #same as first to close plot
# top
p.append([c[0]-wid, c[1]-wid, c[2]+wid])
p.append([c[0]-wid, c[1]+wid, c[2]+wid])
p.append([c[0]+wid, c[1]+wid, c[2]+wid])
p.append([c[0]+wid, c[1]-wid, c[2]+wid])
p.append([c[0]-wid, c[1]-wid, c[2]+wid]) #same as first to close plot
# vertical sides
p.append([c[0]-wid, c[1]-wid, c[2]+wid])
p.append([c[0]-wid, c[1]+wid, c[2]+wid])
p.append([c[0]-wid, c[1]+wid, c[2]-wid])
p.append([c[0]+wid, c[1]+wid, c[2]-wid])
p.append([c[0]+wid, c[1]+wid, c[2]+wid])
p.append([c[0]+wid, c[1]-wid, c[2]+wid])
p.append([c[0]+wid, c[1]-wid, c[2]-wid])
return array(p).T
def my_calibration(sz):
row, col = sz
fx = 2555*col/2592
fy = 2586*row/1936
K = diag([fx, fy, 1])
K[0, 2] = 0.5*col
K[1, 2] = 0.5*row
return K
def set_projection_from_camera(K):
"""从照相机标定矩阵中获得视图"""
glMatrixMode(GL_PROJECTION)
glLoadIdentity()
fx = K[0,0]
fy = K[1,1]
fovy = 2*math.atan(0.5*height/fy)*180/math.pi
aspect = (width*fy)/(height*fx)
near = 0.1
far = 100.0
gluPerspective(fovy,aspect,near,far)
glViewport(0,0,width,height)
def set_modelview_from_camera(Rt):
"""从照相机姿态中获得模拟视图矩阵"""
glMatrixMode(GL_MODELVIEW)
glLoadIdentity()
Rx = np.array([[1,0,0],[0,0,-1],[0,1,0]])
R = Rt[:,:3]
U,S,V = np.linalg.svd(R)
R = np.dot(U,V)
R[0,:] = -R[0,:]
t = Rt[:,3]
M = np.eye(4)
M[:3,:3] = np.dot(R,Rx)
M[:3,3] = t
M = M.T
m = M.flatten()
glLoadMatrixf(m)
def draw_background(imname):
"""使用四边形绘制背景图像"""
bg_image = pygame.image.load(imname).convert()
bg_data = pygame.image.tostring(bg_image,"RGBX",1)
glMatrixMode(GL_MODELVIEW)
glLoadIdentity()
glClear(GL_COLOR_BUFFER_BIT | GL_DEPTH_BUFFER_BIT)
glEnable(GL_TEXTURE_2D)
glBindTexture(GL_TEXTURE_2D,glGenTextures(1))
glTexImage2D(GL_TEXTURE_2D,0,GL_RGBA,width,height,0,GL_RGBA,GL_UNSIGNED_BYTE,bg_data)
glTexParameterf(GL_TEXTURE_2D,GL_TEXTURE_MAG_FILTER,GL_NEAREST)
glTexParameterf(GL_TEXTURE_2D,GL_TEXTURE_MIN_FILTER,GL_NEAREST)
glBegin(GL_QUADS)
glTexCoord2f(0.0,0.0); glVertex3f(-1.0,-1.0,-1.0)
glTexCoord2f(1.0,0.0); glVertex3f( 1.0,-1.0,-1.0)
glTexCoord2f(1.0,1.0); glVertex3f( 1.0, 1.0,-1.0)
glTexCoord2f(0.0,1.0); glVertex3f(-1.0, 1.0,-1.0)
glEnd()
glDeleteTextures(1)
def draw_teapot(size):
"""在原点处绘制红色茶壶"""
glEnable(GL_LIGHTING)
glEnable(GL_LIGHT0)
glEnable(GL_DEPTH_TEST)
glClear(GL_DEPTH_BUFFER_BIT)
glMaterialfv(GL_FRONT,GL_AMBIENT,[0,0,0,0])
glMaterialfv(GL_FRONT,GL_DIFFUSE,[0.5,0.0,0.0,0.0])
glMaterialfv(GL_FRONT,GL_SPECULAR,[0.7,0.6,0.6,0.0])
glMaterialf(GL_FRONT,GL_SHININESS,0.25*128.0)
glutSolidTeapot(size)
width,height = 1000,747
def setup():
pygame.init()
pygame.display.set_mode((width,height),OPENGL | DOUBLEBUF)
pygame.display.set_caption("OpenGL AR demo")
# compute features
sift.process_image('book_frontal.JPG', 'im0.sift')
l0, d0 = sift.read_features_from_file('im0.sift')
sift.process_image('book_perspective.JPG', 'im1.sift')
l1, d1 = sift.read_features_from_file('im1.sift')
# match features and estimate homography
matches = sift.match_twosided(d0, d1)
ndx = matches.nonzero()[0]
fp = homography.make_homog(l0[ndx, :2].T)
ndx2 = [int(matches[i]) for i in ndx]
tp = homography.make_homog(l1[ndx2, :2].T)
model = homography.RansacModel()
H, inliers = homography.H_from_ransac(fp, tp, model)
K = my_calibration((747, 1000))
cam1 = camera.Camera(hstack((K, dot(K, array([[0], [0], [-1]])))))
box = cube_points([0, 0, 0.1], 0.1)
box_cam1 = cam1.project(homography.make_homog(box[:, :5]))
box_trans = homography.normalize(dot(H,box_cam1))
cam2 = camera.Camera(dot(H, cam1.P))
A = dot(linalg.inv(K), cam2.P[:, :3])
A = array([A[:, 0], A[:, 1], cross(A[:, 0], A[:, 1])]).T
cam2.P[:, :3] = dot(K, A)
Rt=dot(linalg.inv(K),cam2.P)
setup()
draw_background("book_perspective.bmp")
set_projection_from_camera(K)
set_modelview_from_camera(Rt)
draw_teapot(0.05)
pygame.display.flip()
while True:
for event in pygame.event.get():
if event.type==pygame.QUIT:
sys.exit()
运行结果：
增强现实。使用由特征匹配计算出的照相机参数，将一个计算机图形学模型放置在场景中的书本上，将茶壶按照和坐标轴对齐的方式显示。
（三）实验中遇到的问题
1、因为实验设计到了SIFT特征匹配，所以应该将代码和图片同sift.exe和vl.dll文件放在同一个文件夹下并且修改sift.exe路径。
2、因为编译的工具是PyCharm，所以有的人会直接从软件中的Setting中安装PyOpenGL包，但是直接在软件里面安装的包，使用的时候会报错：
OpenGL.error.NullFunctionError: Attempt to call an undefined function glutSolidTeapot, check for bool(glutSolidTeapot) before calling
这个时候就需要去下载网站下载PyOpenGL的.whl文件进行安装，但是在安装之前需要将软件中下载的包给卸载掉，可能需要等一段时间，别着急。