测量一张图片中对象的尺寸需要我们首先定义一个比率来衡量每个给定指标的像素数。
The “pixels per metric” ratio
为了确定图片中一个物体的尺寸，我们首先需要使用一个参考对象进行“校准”。我们的参考对象需要有两个重要的属性：
1.我们应该以可测量的单位（例如毫米，英寸等）知道此对象的尺寸（以宽度或高度为单位）。
2.我们应该能够根据对象的位置（例如，始终将对象放置在图像的左上角）或通过外观（例如独特的颜色）轻松地在图像中找到该参考对象 或形状，与图片中的所有其他对象唯一且不同）。 无论哪种情况，我们的参考对象都应该以某种方式唯一地标识。
用计算机视觉测量物体尺寸
在我们理解“pixels per metric”ratio后，我们用python脚本来测量图片中物体的尺寸。
打开一个新的文件，命名为 object_size.py，插入下面的代码：
# import the necessary packages
from scipy.spatial import distance as dist
from imutils import perspective
from imutils import contours
import numpy as np
import argparse
import imutils
import cv2
def midpoint(ptA, ptB):
return ((ptA[0] + ptB[0]) * 0.5, (ptA[1] + ptB[1]) * 0.5)
# construct the argument parse and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-i", "--image", required=True,
help="path to the input image")
ap.add_argument("-w", "--width", type=float, required=True,
help="width of the left-most object in the image (in inches)")
args = vars(ap.parse_args())先import所有需要用到的python库。我们会着重用到imutils库，所以如果没安装的一定先安装好。已经安装过的，确保将其更新到最新版本。
接下来，我们可以导入我们的图片并且对其进行预处理过程：
# load the image, convert it to grayscale, and blur it slightly
image = cv2.imread(args["image"])
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
gray = cv2.GaussianBlur(gray, (7, 7), 0)
# perform edge detection, then perform a dilation + erosion to
# close gaps in between object edges
edged = cv2.Canny(gray, 50, 100)
edged = cv2.dilate(edged, None, iterations=1)
edged = cv2.erode(edged, None, iterations=1)
# find contours in the edge map
cnts = cv2.findContours(edged.copy(), cv2.RETR_EXTERNAL,
cv2.CHAIN_APPROX_SIMPLE)
cnts = imutils.grab_contours(cnts)
# sort the contours from left-to-right and initialize the
# 'pixels per metric' calibration variable
(cnts, _) = contours.sort_contours(cnts)
pixelsPerMetric = None以上最后两行是将图片中的轮廓按照从左到右的顺序进行排序（使我们能够提取参考对象），并且初始化pixelPerMetric值。
下一步是检测每个轮廓：
# loop over the contours individually
for c in cnts:
# if the contour is not sufficiently large, ignore it
if cv2.contourArea(c) < 100:
continue
# compute the rotated bounding box of the contour
orig = image.copy()
box = cv2.minAreaRect(c)
box = cv2.cv.BoxPoints(box) if imutils.is_cv2() else cv2.boxPoints(box)
box = np.array(box, dtype="int")
# order the points in the contour such that they appear
# in top-left, top-right, bottom-right, and bottom-left
# order, then draw the outline of the rotated bounding
# box
box = perspective.order_points(box)
cv2.drawContours(orig, [box.astype("int")], -1, (0, 255, 0), 2)
# loop over the original points and draw them
for (x, y) in box:
cv2.circle(orig, (int(x), int(y)), 5, (0, 0, 255), -1)以上代码不理解的可以参考另一篇博客图像处理–用python和OpenCV顺时针排列边框坐标。
接下来计算一系列中点坐标：
# unpack the ordered bounding box, then compute the midpoint
# between the top-left and top-right coordinates, followed by
# the midpoint between bottom-left and bottom-right coordinates
(tl, tr, br, bl) = box
(tltrX, tltrY) = midpoint(tl, tr)
(blbrX, blbrY) = midpoint(bl, br)
# compute the midpoint between the top-left and top-right points,
# followed by the midpoint between the top-righ and bottom-right
(tlblX, tlblY) = midpoint(tl, bl)
(trbrX, trbrY) = midpoint(tr, br)
# draw the midpoints on the image
cv2.circle(orig, (int(tltrX), int(tltrY)), 5, (255, 0, 0), -1)
cv2.circle(orig, (int(blbrX), int(blbrY)), 5, (255, 0, 0), -1)
cv2.circle(orig, (int(tlblX), int(tlblY)), 5, (255, 0, 0), -1)
cv2.circle(orig, (int(trbrX), int(trbrY)), 5, (255, 0, 0), -1)
# draw lines between the midpoints
cv2.line(orig, (int(tltrX), int(tltrY)), (int(blbrX), int(blbrY)),
(255, 0, 255), 2)
cv2.line(orig, (int(tlblX), int(tlblY)), (int(trbrX), int(trbrY)),
(255, 0, 255), 2)下一步，我们需要通过我们的参考对象初始化pixelsPerMetric变量：
# compute the Euclidean distance between the midpoints
dA = dist.euclidean((tltrX, tltrY), (blbrX, blbrY))
dB = dist.euclidean((tlblX, tlblY), (trbrX, trbrY))
# if the pixels per metric has not been initialized, then
# compute it as the ratio of pixels to supplied metric
# (in this case, inches)
if pixelsPerMetric is None:
pixelsPerMetric = dB / args["width"]最后，我们就可以测量一张图片中对象的尺寸：
# compute the size of the object
dimA = dA / pixelsPerMetric
dimB = dB / pixelsPerMetric
# draw the object sizes on the image
cv2.putText(orig, "{:.1f}in".format(dimA),
(int(tltrX - 15), int(tltrY - 10)), cv2.FONT_HERSHEY_SIMPLEX,
0.65, (255, 255, 255), 2)
cv2.putText(orig, "{:.1f}in".format(dimB),
(int(trbrX + 10), int(trbrY)), cv2.FONT_HERSHEY_SIMPLEX,
0.65, (255, 255, 255), 2)
# show the output image
cv2.imshow("Image", orig)
cv2.waitKey(0)实施效果图如下：
由图可知，测量存在一定的误差，误差产生的两个主要原因：
1.摄像头不是垂直（完全成90度）拍摄硬币的，细小的角度偏差导致了误差的产生。
2.摄像头参数的设置。
修改代码，实时检测视频中硬币的尺寸：
# import the necessary packages
from scipy.spatial import distance as dist
from imutils import perspective
from imutils import contours
import numpy as np
import argparse
import imutils
import cv2
def midpoint(ptA, ptB):
return ((ptA[0] + ptB[0]) * 0.5, (ptA[1] + ptB[1]) * 0.5)
cap = cv2.VideoCapture("http://192.168.1.1:8080/?action=stream")
while(True):
# Capture frame-by-frame
ret, frame = cap.read()
# Our operations on the frame come here
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
gray = cv2.GaussianBlur(gray, (7, 7), 0)
# perform edge detection, then perform a dilation + erosion to
# close gaps in between object edges
edged = cv2.Canny(gray, 50, 100)
edged = cv2.dilate(edged, None, iterations=1)
edged = cv2.erode(edged, None, iterations=1)
# find contours in the edge map
cnts = cv2.findContours(edged.copy(), cv2.RETR_EXTERNAL,
cv2.CHAIN_APPROX_SIMPLE)
cnts = imutils.grab_contours(cnts)
# sort the contours from left-to-right and initialize the
# 'pixels per metric' calibration variable
(cnts, _) = contours.sort_contours(cnts)
pixelsPerMetric = None
# loop over the contours individually
for c in cnts:
# if the contour is not sufficiently large, ignore it
if cv2.contourArea(c) < 100:
continue
# compute the rotated bounding box of the contour
orig = frame.copy()
box = cv2.minAreaRect(c)
box = cv2.cv.BoxPoints(box) if imutils.is_cv2() else cv2.boxPoints(box)
box = np.array(box, dtype="int")
# order the points in the contour such that they appear
# in top-left, top-right, bottom-right, and bottom-left
# order, then draw the outline of the rotated bounding
# box
box = perspective.order_points(box)
cv2.drawContours(orig, [box.astype("int")], -1, (0, 255, 0), 2)
# loop over the original points and draw them
for (x, y) in box:
cv2.circle(orig, (int(x), int(y)), 5, (0, 0, 255), -1)
# unpack the ordered bounding box, then compute the midpoint
# between the top-left and top-right coordinates, followed by
# the midpoint between bottom-left and bottom-right coordinates
(tl, tr, br, bl) = box
(tltrX, tltrY) = midpoint(tl, tr)
(blbrX, blbrY) = midpoint(bl, br)
# compute the midpoint between the top-left and top-right points,
# followed by the midpoint between the top-righ and bottom-right
(tlblX, tlblY) = midpoint(tl, bl)
(trbrX, trbrY) = midpoint(tr, br)
# draw the midpoints on the image
cv2.circle(orig, (int(tltrX), int(tltrY)), 5, (255, 0, 0), -1)
cv2.circle(orig, (int(blbrX), int(blbrY)), 5, (255, 0, 0), -1)
cv2.circle(orig, (int(tlblX), int(tlblY)), 5, (255, 0, 0), -1)
cv2.circle(orig, (int(trbrX), int(trbrY)), 5, (255, 0, 0), -1)
# draw lines between the midpoints
cv2.line(orig, (int(tltrX), int(tltrY)), (int(blbrX), int(blbrY)),
(255, 0, 255), 2)
cv2.line(orig, (int(tlblX), int(tlblY)), (int(trbrX), int(trbrY)),
(255, 0, 255), 2)
# compute the Euclidean distance between the midpoints
dA = dist.euclidean((tltrX, tltrY), (blbrX, blbrY))
dB = dist.euclidean((tlblX, tlblY), (trbrX, trbrY))
# if the pixels per metric has not been initialized, then
# compute it as the ratio of pixels to supplied metric
# (in this case, inches)
if pixelsPerMetric is None:
# pixelsPerMetric = dB / args["width"]
pixelsPerMetric = dB / 20.5
# compute the size of the object
dimA = dA / pixelsPerMetric
dimB = dB / pixelsPerMetric
# draw the object sizes on the image
cv2.putText(orig, "{:.1f}mm".format(dimA),
(int(tltrX - 15), int(tltrY - 10)), cv2.FONT_HERSHEY_SIMPLEX,
0.65, (255, 255, 255), 2)
cv2.putText(orig, "{:.1f}mm".format(dimB),
(int(trbrX + 10), int(trbrY)), cv2.FONT_HERSHEY_SIMPLEX,
0.65, (255, 255, 255), 2)
# show the output image
cv2.imshow("Image", orig)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
cap.release()
cv2.destroyAllWindows()
本文章为转载内容，我们尊重原作者对文章享有的著作权。如有内容错误或侵权问题，欢迎原作者联系我们进行内容更正或删除文章。
