本次实验我们要实现的是以平面和标记物进行姿态估计和增强现实。
在实现代码之前,我们需要安装两个工具包
1.PyGame,下载网址为 https://www.lfd.uci.edu/~gohlke/pythonlibs/#pygame ;
2.OpenGL,下载网址为 https://www.lfd.uci.edu/~gohlke/pythonlibs/#pyopengl 。
from pylab import *
from PIL import Image
# If you have PCV installed, these imports should work
from PCV.geometry import homography, camera
from PCV.localdescriptors import sift
"""
This is the augmented reality and pose estimation cube example from Section 4.3.
"""
#创建用于绘制立方体的一个点列表(前5个点是底部的正方形,一些边重合了)
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 = []
# 底部
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
# 顶部
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
# 竖直边
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
# 计算特征
sift.process_image('book1.jpg', 'im0.sift')
l0, d0 = sift.read_features_from_file('im0.sift')
sift.process_image('book2.jpg', 'im1.sift')
l1, d1 = sift.read_features_from_file('im1.sift')
# 匹配特征并计算单应性矩阵
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)
# 计算照相机标定矩阵
K = my_calibration((747, 1000))
# 位于边长为0.2 z=0平面的三维点
box = cube_points([0, 0, 0.1], 0.1)
# 投影第一幅图像上底部的正方形
cam1 = camera.Camera(hstack((K, dot(K, array([[0], [0], [-1]])))))
# 底部正方形上的点
box_cam1 = cam1.project(homography.make_homog(box[:, :5]))
# 使用H将点变换到第二幅图像中
box_trans = homography.normalize(dot(H,box_cam1))
# 从cam1和H中计算第二个照相机矩阵
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)
# 使用第二个照相机矩阵投影
box_cam2 = cam2.project(homography.make_homog(box))
# plotting
im0 = array(Image.open('book1.jpg'))
im1 = array(Image.open('book2.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()
运行结果如下:
二、增强现实
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。代码实现了放置一个三维计算机图形学模型,使其看起来属于该场景。以下实验我们在书本的平面上叠加了者茶壶。
代码实现如下:
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):
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):
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):
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):
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('book1.jpg', 'im0.sift')
l0, d0 = sift.read_features_from_file('im0.sift')
sift.process_image('book2.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("book2.jpg")
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()