增强现实的简单实现（立方体、茶壶和老鼠的动态实现）

增强现实的简单实现（立方体、茶壶和老鼠的动态实现）

目录

• 环境搭建
• 静态-立方体
• 静态-茶壶
• 动态-老鼠

环境搭建：

1. OpenGL+OpenGL.accelerate
   去下载合适自己python版本的OpenGL和OpenGL.accelerate的.whl文件，然后使用pip install安装。
   
2. pygame（可以直接pip install安装）
   

立方体

效果图：

实现代码（来自《计算机视觉》）：

from pylab import *
from PIL import Image
from OpenGL.GLUT import *
# 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.
"""

def draw_teapot(size):
    glEnable(GL_LIGHTING)
    glEnable(GL_LIGHT0)
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('D:/pycharmfile/ar_cup/chapter4/book_frontal.JPG', 'im0.sift')
l0, d0 = sift.read_features_from_file('im0.sift')

sift.process_image('D:/pycharmfile/ar_cup/chapter4/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)

# 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('D:/pycharmfile/ar_cup/chapter4/book_frontal.JPG'))
im1 = array(Image.open('D:/pycharmfile/ar_cup/chapter4/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()

茶壶

效果图：

代码（来自《计算机视觉》）：

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('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()

运行上面代码可能会出现这样的问题：

这里的主要原因是，freeglut把原来glut库中的很多函数都重写了，比如glut中的glutInit函数和freeglut中的不一致。而在依赖项中如果还有glut32.lib，则在编译时可能会把glutInit认为是原来的那个。
按这样的道理应该吧glut64.vc15.dll删掉，但是可能因为版本的原因，删掉这个依旧还是会报同样的错误。所以只能把freeglut64.vc15.dll删掉了，也是可以正常运行的。

动态增强现实

参考该文章可以实现 https://blog.csdn.net/titansm/article/details/89057184?tdsourcetag=s_pcqq_aiomsg

上述链接要注意原文代码中很多需要修改的参数，例如相机参数和地址等等。多次修改无果，无法跑动这套代码。
然后找到了下面这套代码，其实现原理和上述代码基本相似，只是减去了把视频拆成图片处理，再把处理完的图片合成的过程。所以就可以完成在摄像机镜头上直接显示增强现实的物体。且要修改的参数极少，调试起来还是容易很多。
Win10的录屏好像无法录制弹窗，所以用手机拍的，效果如下，还是很不错的。

代码：https://download.csdn.net/download/betrapped/11093090

其中代码要修改的部分为：

• 代码文件夹的存放路径
• reference文件夹中要放一张你选择的背景图片，例如上面动图中我拿的书。并且在相应位置修改路径。
  
  总的来说就是只要修改以上两行，把它们换成你自己的地址和图片即可。

测试运行时只要把你背景图片的物品放在摄像机面前即可。其中model中的wolf和cow模型效果很差，应该是模型太大导致无法在书上显示出来。