Python中使用金字塔的快速模板匹配 我试图在Python中实现以下C++代码： 如果你检查C++代码，你会看到这个循环： for (int i = 0; i < contours.size(); i++) { cv::Rect r = cv::boundingRect(contours[i]); cv::matchTemplate( ref(r + (tpl.size() - cv::Size(1,1))), tpl, res(r), CV_TM_CCORR_NORMED ); }
当我不断得到以下信息时，出现了一些问题：ValueError:无法将输入数组从shape（53,51）广播到shape（52,52） 这个数字（53，51）（52，52）可能会改变，因为我只是稍微修改了结果或当前图像中的坐标，但这不是正确的答案 这是我当前的代码：Python中使用金字塔的快速模板匹配 我试图在Python中实现以下C++代码： 如果你检查C++代码，你会看到这个循环： for (int i = 0; i < contours.size(); i++) { cv::Rect r = cv::boundingRect(contours[i]); cv::matchTemplate( ref(r + (tpl.size() - cv::Size(1,1))), tpl, res(r), CV_TM_CCORR_NORMED ); },python,opencv,template-matching,Python,Opencv,Template Matching,当我不断得到以下信息时，出现了一些问题：ValueError:无法将输入数组从shape（53,51）广播到shape（52,52） 这个数字（53，51）（52，52）可能会改变，因为我只是稍微修改了结果或当前图像中的坐标，但这不是正确的答案 这是我当前的代码： import cv2 as cv import numpy as np import argparse import os """ This script performs a fast template matching algo
import cv2 as cv
import numpy as np
import argparse
import os
"""
This script performs a fast template matching algorithm using the OpenCV
function matchTemplate plus an approximation through pyramid construction to
improve it's performance on large images.
"""
def buildPyramid(image, max_level):
results = [image]
aux = image
for i in range(0,max_level):
aux = cv.pyrDown(aux)
results = [aux] + results
return results
def temp_match(input, template, max_level):
results = []
source_pyr = buildPyramid(input, max_level)
template_pyr = buildPyramid(template, max_level)
for lvl in range(0, int(max_level), 1):
curr_image = source_pyr[lvl]
curr_template = template_pyr[lvl]
dX = curr_image.shape[1] + 1 - curr_template.shape[1]
dY = curr_image.shape[0] + 1 - curr_template.shape[0]
result = np.zeros([dX, dY])
#On the first level performs regular template matching.
if lvl == 0:
result = cv.matchTemplate(curr_image, curr_template,
cv.TM_CCORR_NORMED)
#On every other level, perform pyramid transformation and template
#matching on the predefined ROI areas, obtained using the result of the
#previous level.
else:
mask = cv.pyrUp(r)
mask8u = cv.inRange(mask, 0, 255)
contours = cv.findContours(mask8u, cv.RETR_EXTERNAL,
cv.CHAIN_APPROX_NONE)
#Uses contours to define the region of interest and perform TM on
#the areas.
for i in range(0, np.size(contours)-1):
x, y, w, h = cv.boundingRect(contours[i][0])
tpl_X = curr_template.shape[1]
tpl_Y = curr_template.shape[0]
#result = cv.matchTemplate(curr_image, curr_template,
# cv.TM_CCORR_NORMED)
result[y:y+h, x:x+w] = cv.matchTemplate(
curr_image[y:y+h+tpl_Y, x:x+w+tpl_X],
curr_template, cv.TM_CCORR_NORMED)
T, r = cv.threshold(result, 0.94, 1., cv.THRESH_TOZERO)
cv.imshow("test", r)
cv.waitKey()
results.append(r)
return results
def ftm_pyramid(input_file, template_file, max_level = 5):
if file_exists(input_file) == False:
raise IOError("Input file not found.")
if file_exists(template_file) == False:
raise IOError("Input file not found.")
img = cv.imread(input_file)
tpl = cv.imread(template_file)
image = cv.cvtColor(img, cv.COLOR_BGR2GRAY)
template = cv.cvtColor(tpl, cv.COLOR_BGR2GRAY)
tm_results = temp_match(image, template, max_level)
c = 0
flag = False
while flag == False and c < np.size(tm_results):
current = tm_results[c]
min_val, max_val, min_loc, max_loc = cv.minMaxLoc(current)
if max_val > 0.9:
cv.rectangle(img,
max_loc,
(max_loc[0] + template.shape[1],
max_loc[1] + template.shape[0]),
(0,0,255), 2)
else:
flag = True
c = c+1
cv.imshow("Result", img)
cv.waitKey()
return 0
# Auxiliary methods
def file_exists(input_file):
"""
:param input_file: path to the input file
:return: true or false wether the file exists or not.
"""
if input_file == '':
raise ValueError("The input file can't be ''.")
if input_file == None:
raise ValueError("The input file can't be a None object")
return os.path.isfile(input_file)
if __name__ == '__main__':
#CLI arguments
ap = argparse.ArgumentParser()
ap.add_argument("-i", "--input", required="True",
help="Path to the input image.")
ap.add_argument("-t", "--template", required="True",
help="Path to the template image.")
ap.add_argument("-l", "--levels", help="Number of levels of the pyramid.")
args = vars(ap.parse_args())
#Loading values
input_file = args["input"]
template = args["template"]
max_lvl = args["levels"]
if max_lvl == None:
max_lvl = 5
ftm_pyramid(input_file, template, max_lvl)
将cv2作为cv导入
将numpy作为np导入
导入argparse
导入操作系统
"""
此脚本使用OpenCV执行快速模板匹配算法
函数matchTemplate加上通过金字塔构造的近似值
提高它在大图像上的性能。
"""
def buildPyramid（图像，最高级别）：
结果=[图像]
aux=图像
对于范围内的i（0，最大水平）：
aux=cv.pyrDown（aux）
结果=[aux]+结果
返回结果
def温度匹配（输入、模板、最高液位）：
结果=[]
source\u pyr=buildPyramid（输入，最大级别）
模板\u pyr=buildPyramid（模板，最大级别）
对于范围内的lvl（0，整数（最大值），1）：
curr\u image=source\u pyr[lvl]
curr\u template=template\u pyr[lvl]
dX=当前图像.shape[1]+1-当前模板.shape[1]
dY=当前图像.shape[0]+1-当前模板.shape[0]
结果=np.零（[dX，dY]）
#在第一级执行常规模板匹配。
如果lvl==0：
结果=cv.matchTemplate（当前图像、当前模板、，
cv.TM\U CCORR\U标准）
#在每一层上，执行金字塔变换和模板转换
#在预定义的ROI区域上进行匹配，使用
#上一级。
其他：
遮罩=cv.pyrUp（r）
mask8u=cv.inRange（mask，0255）
等高线=等高线（mask8u、等高线外部、，
等速链条（约无）
#使用等高线定义感兴趣的区域并对其执行TM
#这些地区。
对于范围内的i（0，np.尺寸（轮廓）-1）：
x、 y，w，h=cv.boundingRect（等高线[i][0]）
tpl_X=当前模板形状[1]
tpl_Y=当前模板形状[0]
#结果=cv.matchTemplate（当前图像、当前模板、，
#cv.TM\U CCORR\U标准）
结果[y:y+h，x:x+w]=cv.matchTemplate(
当前图像[y:y+h+tpl\U y，x:x+w+tpl\U x]，
当前模板，cv.TM（标准）
T、 r=cv.阈值（结果，0.94，1，cv.阈值为零）
简历：imshow（“测试”，r）
cv.waitKey（）
结果。追加（r）
返回结果
def ftm_金字塔（输入文件、模板文件、最大级别=5）：
如果文件存在（输入文件）=False：
raise IOError（“未找到输入文件”）
如果文件_存在（模板_文件）==False：
raise IOError（“未找到输入文件”）
img=cv.imread（输入文件）
tpl=cv.imread（模板文件）
图像=cv.CVT颜色（img，cv.COLOR\u bgr2灰色）
模板=cv.CVT颜色（tpl、cv.COLOR\u BGR2GRAY）
tm_结果=临时匹配（图像、模板、最大级别）
c=0
flag=False
而flag==False和c0.9：
等速矩形（img，
马克斯·卢克，
（最大位置[0]+模板形状[1]，
最大位置[1]+模板形状[0]，
(0,0,255), 2)
其他：
flag=True
c=c+1
简历imshow（“结果”，img）
cv.waitKey（）
返回0
#辅助方法
def文件_存在（输入文件）：
"""
：param input_file：输入文件的路径
：return:true或false，无论文件是否存在。
"""
如果输入文件==''：
raise VALUERROR（“输入文件不能为“”））
如果输入文件==无：
raise VALUERROR（“输入文件不能是无对象”）
返回os.path.isfile（输入文件）
如果uuuu name uuuuuu='\uuuuuuu main\uuuuuuu'：
#CLI参数
ap=argparse.ArgumentParser（）
ap.add_参数（“-i”，“--input”，required=“True”，
help=“输入图像的路径。”）
ap.add_参数（“-t”，“--template”，required=“True”，
help=“模板图像的路径。”）
ap.add_参数（“-l”，“--levels”，help=“金字塔的层数”）
args=vars（ap.parse_args（））
#加载值
输入文件=args[“输入”]
模板=参数[“模板”]
最大值=args[“级别”]
如果最大值=无：
最大值=5
ftm_金字塔（输入文件、模板、最大层）
任何帮助都将不胜感激 在图像金字塔中进行图像模板匹配，从粗到精，这是许多领域的基本思想 您的代码有问题，我在参考原始CPP代码和Python代码的同时重写了代码
这是
参考图像模板图像结果我不明白这是怎么回事，当在等高线上循环时，你用一个小补丁的TM覆盖结果，而不是更新结果中的相同补丁。你有没有把代码和非金字塔TM放在一起？
import cv2 as cv
import numpy as np
import argparse
import os
"""
This script performs a fast template matching algorithm using the OpenCV
function matchTemplate plus an approximation through pyramid construction to
improve it's performance on large images.
"""
def buildPyramid(image, max_level):
results = [image]
aux = image
for i in range(0,max_level):
aux = cv.pyrDown(aux)
results = [aux] + results
return results
def temp_match(input, template, max_level):
results = []
source_pyr = buildPyramid(input, max_level)
template_pyr = buildPyramid(template, max_level)
for lvl in range(0, int(max_level), 1):
curr_image = source_pyr[lvl]
curr_template = template_pyr[lvl]
dX = curr_image.shape[1] + 1 - curr_template.shape[1]
dY = curr_image.shape[0] + 1 - curr_template.shape[0]
result = np.zeros([dX, dY])
#On the first level performs regular template matching.
if lvl == 0:
result = cv.matchTemplate(curr_image, curr_template,
cv.TM_CCORR_NORMED)
#On every other level, perform pyramid transformation and template
#matching on the predefined ROI areas, obtained using the result of the
#previous level.
else:
mask = cv.pyrUp(r)
mask8u = cv.inRange(mask, 0, 255)
contours = cv.findContours(mask8u, cv.RETR_EXTERNAL,
cv.CHAIN_APPROX_NONE)
#Uses contours to define the region of interest and perform TM on
#the areas.
for i in range(0, np.size(contours)-1):
x, y, w, h = cv.boundingRect(contours[i][0])
tpl_X = curr_template.shape[1]
tpl_Y = curr_template.shape[0]
#result = cv.matchTemplate(curr_image, curr_template,
# cv.TM_CCORR_NORMED)
result[y:y+h, x:x+w] = cv.matchTemplate(
curr_image[y:y+h+tpl_Y, x:x+w+tpl_X],
curr_template, cv.TM_CCORR_NORMED)
T, r = cv.threshold(result, 0.94, 1., cv.THRESH_TOZERO)
cv.imshow("test", r)
cv.waitKey()
results.append(r)
return results
def ftm_pyramid(input_file, template_file, max_level = 5):
if file_exists(input_file) == False:
raise IOError("Input file not found.")
if file_exists(template_file) == False:
raise IOError("Input file not found.")
img = cv.imread(input_file)
tpl = cv.imread(template_file)
image = cv.cvtColor(img, cv.COLOR_BGR2GRAY)
template = cv.cvtColor(tpl, cv.COLOR_BGR2GRAY)
tm_results = temp_match(image, template, max_level)
c = 0
flag = False
while flag == False and c < np.size(tm_results):
current = tm_results[c]
min_val, max_val, min_loc, max_loc = cv.minMaxLoc(current)
if max_val > 0.9:
cv.rectangle(img,
max_loc,
(max_loc[0] + template.shape[1],
max_loc[1] + template.shape[0]),
(0,0,255), 2)
else:
flag = True
c = c+1
cv.imshow("Result", img)
cv.waitKey()
return 0
# Auxiliary methods
def file_exists(input_file):
"""
:param input_file: path to the input file
:return: true or false wether the file exists or not.
"""
if input_file == '':
raise ValueError("The input file can't be ''.")
if input_file == None:
raise ValueError("The input file can't be a None object")
return os.path.isfile(input_file)
if __name__ == '__main__':
#CLI arguments
ap = argparse.ArgumentParser()
ap.add_argument("-i", "--input", required="True",
help="Path to the input image.")
ap.add_argument("-t", "--template", required="True",
help="Path to the template image.")
ap.add_argument("-l", "--levels", help="Number of levels of the pyramid.")
args = vars(ap.parse_args())
#Loading values
input_file = args["input"]
template = args["template"]
max_lvl = args["levels"]
if max_lvl == None:
max_lvl = 5
ftm_pyramid(input_file, template, max_lvl)
#!/usr/bin/python3
# 2017.10.04 14:50:50 CST START
# 2017.10.04 17:32:39 CST FINISH
import cv2
import numpy as np
import argparse
import os
def fileExists(filename):
"""Judge wether the file exists!
"""
if filename in ('', None):
raise ValueError("The input file can't be '' or None.")
return os.path.isfile(filename)
def buildPyramid(image, maxleval):
"""Build image pyramid for level [0,...,maxlevel]
"""
imgpyr = [image]
aux = image
for i in range(0,maxleval):
aux = cv2.pyrDown(aux)
imgpyr.append(aux)
imgpyr.reverse()
return imgpyr
def fastTemplateMatchPyramid(src_refimg, src_tplimg, maxleval):
"""Do fast template matching using matchTemplate plus an approximation
through pyramid construction to improve it's performance on large images.
"""
results = []
## Change BGR to Grayscale
gray_refimg = cv2.cvtColor(src_refimg, cv2.COLOR_BGR2GRAY)
gray_tplimg = cv2.cvtColor(src_tplimg, cv2.COLOR_BGR2GRAY)
## Build image pyramid
refimgs = buildPyramid(gray_refimg, maxleval)
tplimgs = buildPyramid(gray_tplimg, maxleval)
## Do template match
for idx in range(0, maxleval+1):
refimg = refimgs[idx]
tplimg = tplimgs[idx]
# On the first level performs regular template matching.
# On every other level, perform pyramid transformation and template matching
# on the predefined ROI areas, obtained using the result of the previous level.
# Uses contours to define the region of interest and perform TM on the areas.
if idx == 0:
result = cv2.matchTemplate(refimg, tplimg, cv2.TM_CCORR_NORMED)
else:
mask = cv2.pyrUp(threshed)
mask8u = cv2.inRange(mask, 0, 255)
contours = cv2.findContours(mask8u, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)[-2]
tH, tW = tplimg.shape[:2]
for cnt in contours:
x, y, w, h = cv2.boundingRect(cnt)
src = refimg[y:y+h+tH, x:x+w+tW]
result = cv2.matchTemplate(src, tplimg, cv2.TM_CCORR_NORMED)
T, threshed = cv2.threshold(result, 0.90, 1., cv2.THRESH_TOZERO)
results.append(threshed)
return threshed
#return results
def fastTemplateMatch(refname, tplname, maxleval = 5):
"""Fast template match.
"""
## Read the image pairs.
if fileExists(refname) == False:
raise IOError("Input file not found.")
if fileExists(tplname) == False:
raise IOError("Input file not found.")
refimg = cv2.imread(refname)
tplimg = cv2.imread(tplname)
cv2.imwrite("cat.png",refimg)
## Call fastTemplateMatchInPyramid()
result = fastTemplateMatchPyramid(refimg, tplimg, maxleval)
## Analysis the result
minval, maxval, minloc, maxloc = cv2.minMaxLoc(result)
if maxval > 0.9:
pt1 = maxloc
pt2 = (maxloc[0] + tplimg.shape[1], maxloc[1] + tplimg.shape[0])
print("Found the template region: {} => {}".format(pt1,pt2))
dst = refimg.copy()
cv2.rectangle(dst, pt1, pt2, (0,255,0), 2)
cv2.imshow("Result", dst)
cv2.imwrite("template_matching_result.png",dst)
cv2.waitKey()
else:
print("Cannot find the template in the origin image!")
if __name__ == '__main__':
## CLI arguments
"""
ap = argparse.ArgumentParser()
ap.add_argument("-r", "--referer", required="True",
help="Path to the referer image.")
ap.add_argument("-t", "--template", required="True",
help="Path to the template image.")
ap.add_argument("-l", "--levels", help="Number of levels of the pyramid.")
args = vars(ap.parse_args())
## Loading values
refname = args["referer"]
tplname = args["template"]
maxlevel = args["levels"]
"""
## Set parmeters
refname = "/home/auss/Pictures/cat.jpg"
tplname = "cat_face.png"
maxlevel = 5
## call the function
fastTemplateMatch(refname, tplname, maxlevel)