opencv计算机视觉学习笔记三

第四章 深度估计和分割

1 捕获深度摄像头的帧

深度图 灰度 每个像素都是摄像头到物体表面的距离 毫米

点云图 彩色 每种颜色对应一个维度空间 米

视差图 灰度 每个像素代表物体表面的立体视差 近大远小

有效深度掩模一个给定像素的深度信息是否有效

2 从视差图中得到掩模

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time    : 2016/12/1 10:16
# @Author  : Retacn
# @Site    : 深度摄像头数据的处理
# @File    : depth.py
# @Software: PyCharm
__author__ = "retacn"
__copyright__ = "property of mankind."
__license__ = "CN"
__version__ = "0.0.1"
__maintainer__ = "retacn"
__email__ = "zhenhuayue@sina.com"
__status__ = "Development"

import numpy as np

#设备
CAP_OPENNI=900
CAP_OPENNI_ASUS=910

#通道(基于浮点数的距离)
CAP_OPENNI_DEPTH_MAP=0

#会得到bgr图像
CAP_OPENNI_POINT_CLOUD_MAP=1

#XYZ
CAP_OPENNI_DISPARITY_MAP=2

#
CAP_OPENNI_DISPARITY_MAP_32F=3
CAP_OPENNI_VALID_DEPTH_MASK=4

CAP_OPENNI_BGR_IMAGE=5
CAP_OPENNI_GRAY_IMAGE=6

#生成掩模
def createMedianMask(disparityMap,#视差图
validDepthMask,#有效深度掩模
rect=None):#矩形
if  rect is not None:
x,y,w,h=rect
disparityMap=disparityMap[y:y+h,x:x+w]
validDepthMask=validDepthMask[y:y+h,x:x+w]
#得到中值
median=np.median(disparityMap)
#生成掩模,逐像素进行布尔操作
return np.where((validDepthMask==0) | (abs(disparityMap-median)<12),#值为真假的数组,当有效视差与平均视差>=12,看作噪声
1.0,#为真时，数组相应元素为该值
0.0)#为假时，为该值

3 对复制操作进行掩模

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time    : 2016/12/1 10:22
# @Author  : Retacn
# @Site    : 矩形区域复制
# @File    : rects.py
# @Software: PyCharm
__author__ = "retacn"
__copyright__ = "property of mankind."
__license__ = "CN"
__version__ = "0.0.1"
__maintainer__ = "retacn"
__email__ = "zhenhuayue@sina.com"
__status__ = "Development"

import cv2
import numpy as np
from Three import utils

#对复制操作执行掩模
def copyRect(src,
dst,
srcRect,
dstRect,
mask=None,#掩模参数,掩模要和图像有相同的通道数
interpolation=cv2.INTER_LINEAR):#插值方法为线性插值
x0,y0,w0,h0=srcRect
x1,y1,w1,h1=dstRect

#如果掩模为空,则执行复制操作
if mask is None:
dst[y1:y1+h1,x1:x1+w1]=cv2.resize(src[y0:y0+h0,y0:y0+h0],#源图像
(w1,h1),#目标图像
interpolation=interpolation)#插值方法
else:
#如果掩模为单通道,则复制通道
if not utils.isGray(src):
mask=mask.repeat(3).reshape(h0,w0,3)
dst[y1:y1+h1,x1:x1+w1]=np.where(cv2.resize(mask,(w1,h1),interpolation=cv2.INTER_NEAREST),
cv2.resize(src[y0:y0+h0,x0:x0+w0],(w1,h1),interpolation=interpolation),
dst[y1:y1 + h1, x1:x1 + w1]
)

#一组矩形的循环交换
def swqpRects(src,dst,rects,masks=None,interpolation=cv2.INTER_LINEAR):
if dst is not src:
dst[:]=src

numRects=len(rects)
if numRects<2:
return

if masks is None:
masks=[None]*numRects

x,y,w,h=rects[numRects-1]
temp=src[y:y+h,x:x+w].copy()

i=numRects-2
while i>=0:
copyRect(src,dst,rects[i],rects[i+1],masks[i],interpolation)
i-=1
copyRect(temp,dst,(0,0,w,h),rects[0],masks[numRects-1],interpolation)

4 使用普通摄像头进行深试评估

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time    : 2016/12/1 11:40
# @Author  : Retacn
# @Site    : 使用普通摄像头进行深试估计
# @File    : commonCamera2Depth.py
# @Software: PyCharm
__author__ = "retacn"
__copyright__ = "property of mankind."
__license__ = "CN"
__version__ = "0.0.1"
__maintainer__ = "retacn"
__email__ = "zhenhuayue@sina.com"
__status__ = "Development"

import cv2
import numpy as np

def update(val=0):
stereo.setBlockSize(cv2.getTrackbarPos('window_size','disparity'))
stereo.setUniquenessRatio(cv2.getTrackbarPos('uniquenessRatio','disparity'))
stereo.setSpeckleWindowSize(cv2.getTrackbarPos('speckleWindowSize','disparity'))
stereo.setSpeckleRange(cv2.getTrackbarPos('speckleRange','disparity'))
stereo.setDisp12MaxDiff(cv2.getTrackbarPos('disp12MaxDiff','disparity'))
print('computing disparity...')
disp = stereo.compute(imgL, imgR).astype(np.float32) / 16.0
cv2.imshow('left', imgL)
cv2.imshow('disparity', (disp - min_disp) / num_disp)

if __name__=='__main__':
windows_size=5 #一个匹配块的大小,大于1的奇数
min_disp=16 #最小视差值
num_disp=192-min_disp #最大视差值和最小视差值的差
blockSize=windows_size
uniquenessRatio=1
speckleRange=3 #每个已连接部分的最大视差变化
speckleWindowSize=3 #平滑视差区域的最大窗口尺寸
disp12MaxDiff=200
P1=600 #控制视差图平滑度有第一个参数
P2=2400#第二个参数,值越大视差图越平滑

#读入图像
imgL=cv2.imread('../imgl.jpg')
imgR=cv2.imread('../imgr.jpg')

cv2.namedWindow('disparity')
cv2.createTrackbar('speckleRange','disparity',speckleRange,50,update)
cv2.createTrackbar('window_size','disparity',windows_size,21,update)
cv2.createTrackbar('speckleWindowSize','disparity',speckleWindowSize,200,update)
cv2.createTrackbar('uniquenessRatio','disparity',uniquenessRatio,50,update)
cv2.createTrackbar('disp12MaxDiff','disparity',disp12MaxDiff,250,update)

stereo=cv2.StereoSGBM_create(minDisparity=min_disp,
numDisparities=num_disp,
blockSize=blockSize,
uniquenessRatio=uniquenessRatio,
speckleRange=speckleRange,
speckleWindowSize=speckleWindowSize,
disp12MaxDiff=disp12MaxDiff,
P1=P1,
P2=P2)

update()
cv2.waitKey()

5 使用分水岭和grabcut算法进行物体分割

A 使用brabcut进行前景检测

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time    : 2016/12/2 11:17
# @Author  : Retacn
# @Site    : 使用grubCut进行前景检测
# @File    : grabcutNew.py
# @Software: PyCharm
__author__ = "retacn"
__copyright__ = "property of mankind."
__license__ = "CN"
__version__ = "0.0.1"
__maintainer__ = "retacn"
__email__ = "zhenhuayue@sina.com"
__status__ = "Development"

import cv2
import numpy as np
import sys

# 定义颜色
BLUE = [255, 0, 0]  # rectangle color
RED = [0, 0, 255]  # PR BG
GREEN = [0, 255, 0]  # PR FG
BLACK = [0, 0, 0]  # sure BG
WHITE = [255, 255, 255]  # sure FG

DRAW_BG = {'color': BLACK, 'val': 0}
DRAW_FG = {'color': WHITE, 'val': 1}
DRAW_PR_FG = {'color': GREEN, 'val': 3}
DRAW_PR_BG = {'color': RED, 'val': 2}

# 设置标志位
rect = (0, 0, 1, 1)  # 隔离对像矩形
drawing = False  # 绘制标志位
rectangle = False  # 矩形绘制标志
rect_over = False  # 检查隔离矩形是否绘制
rect_or_mask = 100  # 掩模模式
value = DRAW_FG  #
thickness = 3  # 画笔宽度

# 自定义鼠标回调函数
def onmouse(event, x, y, flags, param):
# 定义全局变量
global img, img2, drawing, value, mask, rectangle, rect, rect_or_mask, ix, iy, rect_over

# 绘制隔离矩形
if event == cv2.EVENT_RBUTTONDOWN:  # 鼠标右健按下,开始绘制矩形
rectangle = True
ix, iy = x, y

elif event == cv2.EVENT_MOUSEMOVE:  # 鼠标移动事件
if rectangle == True:  # 绘制矩形
img = img2.copy()
cv2.rectangle(img,  # 源图像
(ix, iy),  # 开始点
(x, y),  # 结束点
BLUE,  # 画笔颜色
2)  # 画笔宽度
rect = (min(ix, x), min(iy, y), abs(ix - x), abs(iy - y))
rect_or_mask = 0

elif event == cv2.EVENT_RBUTTONUP:  # 右键抬起
rectangle = False  # 设置标志位,矩形绘制完成
rect_over = True
cv2.rectangle(img, (ix, iy), (x, y), BLUE, 2)
rect = (min(ix, x), min(iy, y), abs(ix - x), abs(iy - y))
rect_or_mask=0
print('按下 n , 开始绘制')

#绘制隔离圆形
if event==cv2.EVENT_LBUTTONDOWN: #左键按下
if rect_over==False:
print("请先绘制圆形")
else:
drawing=True
cv2.circle(img,(x,y),thickness,value['color'],-1)
cv2.circle(mask,(x,y),thickness,value['color'],-1)

elif event==cv2.EVENT_MOUSEMOVE:
if drawing==True:
cv2.circle(img, (x, y), thickness, value['color'], -1)
cv2.circle(mask, (x, y), thickness, value['color'], -1)

elif event==cv2.EVENT_LBUTTONUP:
if drawing==True:
drawing=False
cv2.circle(img, (x, y), thickness, value['color'], -1)
cv2.circle(mask, (x, y), thickness, value['color'], -1)

if __name__ == '__main__':
fileName = '../test1.jpg'

img = cv2.imread(fileName)
img2 = img.copy()
mask = np.zeros(img.shape[:2], dtype=np.uint8)
output = np.zeros(img.shape, np.uint8)

# 定义输入输出窗口
cv2.namedWindow("output")
cv2.namedWindow('input')
#输出窗口注册鼠标事件
cv2.setMouseCallback('input', onmouse)
cv2.moveWindow('input',img.shape[1]+10,90)

print("操作指南:\n")
print('使用鼠标右健在源图像中绘制矩形\n')

while(1):
#显示图像
cv2.imshow('output',output)
cv2.imshow('input',img)
k=0xFF&cv2.waitKey(1)

if k==27: #ESC键退出
break
elif k==ord('0'):#绘制背景
print("左键绘制background标识区域 \n")
value=DRAW_BG
elif k==ord('1'):#绘制前景
print('左键绘制foreground标识区域 \n')
value=DRAW_FG
elif k==ord('2'):
value=DRAW_PR_BG
elif k == ord('3'):
value = DRAW_PR_FG
elif k==ord('s'):# 保存图像
bar=np.zeros((img.shape[0],5,3),np.uint8)
res=np.hstack((img2.bar,img,bar,output))
cv2.imwrite('grabcut_output.png',res)
print('保存图像')
elif k==ord('r'):#重置
print('开始重置 \n')
rect = (0, 0, 1, 1)
drawing = False
rectangle = False
rect_or_mask = 100
rect_over = False
value = DRAW_FG
img = img2.copy()
mask = np.zeros(img.shape[:2], dtype=np.uint8)
output = np.zeros(img.shape, np.uint8)
elif k == ord('n'):  # 图像截取
print(""" For finer touchups, mark foreground and background after pressing keys 0-3
and again press 'n' \n""")
if (rect_or_mask == 0):  # 设置掩模
bgdmodel = np.zeros((1, 65), np.float64)
fgdmodel = np.zeros((1, 65), np.float64)
cv2.grabCut(img2, mask, rect, bgdmodel, fgdmodel, 1, cv2.GC_INIT_WITH_RECT)
rect_or_mask = 1
elif rect_or_mask == 1:  # 设置掩模
bgdmodel = np.zeros((1, 65), np.float64)
fgdmodel = np.zeros((1, 65), np.float64)
cv2.grabCut(img2, mask, rect, bgdmodel, fgdmodel, 1, cv2.GC_INIT_WITH_MASK)

mask2 = np.where((mask == 1) + (mask == 3), 255, 0).astype('uint8')
output = cv2.bitwise_and(img2, img2, mask=mask2)

cv2.destroyAllWindows()

B 使用分水岭算法进行图像分割

示例代码如下:

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time    : 2016/12/2 12:21
# @Author  : Retacn
# @Site    : 使用分水岭算法进行图像分割
# @File    : watershed.py
# @Software: PyCharm
__author__ = "retacn"
__copyright__ = "property of mankind."
__license__ = "CN"
__version__ = "0.0.1"
__maintainer__ = "retacn"
__email__ = "zhenhuayue@sina.com"
__status__ = "Development"

import cv2
import numpy as np
from matplotlib import pyplot as plt

img =cv2.imread('../test1.jpg')
gray=cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)

#转换为灰度图,设置阈值
ret,thresh=cv2.threshold(gray,0,255,cv2.THRESH_BINARY_INV+cv2.THRESH_OTSU)

kernel=np.ones((3,3),np.uint8)
opening=cv2.morphologyEx(thresh,#源图像
cv2.MORPH_OPEN, #开运算
kernel, #核
iterations=2)#迭代次数

#取得确定的前景区域
sure_bg=cv2.dilate(opening,kernel,iterations=3)
dist_transform=cv2.distanceTransform(opening,cv2.DIST_L2,5)
ret,sure_fg=cv2.threshold(dist_transform,0.7*dist_transform.max(),255,0)

sure_fg=np.uint8(sure_fg)
unknown=cv2.subtract(sure_bg,sure_fg)

ret,markers=cv2.connectedComponents(sure_fg)
markers=markers+1
markers[unknown==255]=0

markers=cv2.watershed(img,markers)
img[markers==-1]=[255,0,0]
plt.imshow(img)
plt.show()