def redraw(self):
edge_img = cv.Mat()
# 边缘检测
cv.Canny(self.img_gray, edge_img, self.th1, self.th2)
3 ###
# 计算结果图
if self.show_canny:
show_img = cv.Mat()
cv.cvtColor(edge_img, show_img, cv.CV_GRAY2BGR)
else:
show_img = self.img.clone()
4 ###
# 线段检测
theta = self.theta / 180.0 * np.pi
lines = cv.HoughLinesP(edge_img, self.rho, theta, self.hough_th,
self.minlen, self.maxgap)
for line in lines:
cv.line(show_img, cv.asPoint(line[:2]), cv.asPoint(line[2:]),
cv.CV_RGB(255, 0, 0), 2)
5 ###
# 圆形检测
circles = cv.HoughCircles(self.img_smooth,
3,
self.dp,
self.mindist,
param1=self.param1,
param2=self.param2)
for circle in circles:
cv.circle(show_img, cv.Point(int(circle[0]), int(circle[1])),
int(circle[2]), cv.CV_RGB(0, 255, 0), 2)
cv.imshow("Hough Demo", show_img)
def redraw(self):
edge_img = cv.Mat()
# 边缘检测
cv.Canny(self.img_gray, edge_img, self.th1, self.th2)
3###
# 计算结果图
if self.show_canny:
show_img = cv.Mat()
cv.cvtColor(edge_img, show_img, cv.CV_GRAY2BGR)
else:
show_img = self.img.clone()
4###
# 线段检测
theta = self.theta / 180.0 * np.pi
lines = cv.HoughLinesP(edge_img,
self.rho, theta, self.hough_th, self.minlen, self.maxgap)
for line in lines:
cv.line(show_img,
cv.asPoint(line[:2]),
cv.asPoint(line[2:]),
cv.CV_RGB(255, 0, 0), 2)
5###
# 圆形检测
circles = cv.HoughCircles(self.img_smooth, 3,
self.dp, self.mindist, param1=self.param1, param2=self.param2)
for circle in circles:
cv.circle(show_img,
cv.Point(int(circle[0]), int(circle[1])), int(circle[2]),
cv.CV_RGB(0, 255, 0), 2)
cv.imshow("Hough Demo", show_img)
print("Extraction time = %gms\n" % (tt / (cv.getTickFrequency() * 1000.)))
# create a correspond Mat
correspond = cv.Mat(image.rows + object.rows, image.cols, cv.CV_8UC1,
cv.Scalar(0))
# copy the images to correspond -- numpy way
correspond[:object.rows, :object.cols] = object[:]
correspond[object.rows:, :image.cols] = image[:]
# find pairs
ptpairs = findPairs(surf, objectKeypoints, objectDescriptors,
imageKeypoints, imageDescriptors)
for pair in ptpairs:
cv.line(correspond, cv.asPoint(pair[0]),
cv.Point(int(pair[1].x), int(pair[1].y + object.rows)),
colors[8])
# locate planar object
if locatePlanarObject(ptpairs, src_corners, dst_corners):
for i in range(4):
r1 = dst_corners[i]
r2 = dst_corners[(i + 1) % 4]
cv.line(correspond, cv.Point(r1.x, r1.y + object.rows),
cv.Point(r2.x, r2.y + object.rows), colors[8])
# show the object correspondents
cv.imshow("Object Correspond", correspond)
# draw circles
print("Image Descriptors: %d\n" % len(imageKeypoints))
tt = float(cv.getTickCount()) - tt
print("Extraction time = %gms\n" % (tt/(cv.getTickFrequency()*1000.)))
# create a correspond Mat
correspond = cv.Mat(image.rows+object.rows, image.cols, cv.CV_8UC1, cv.Scalar(0))
# copy the images to correspond -- numpy way
correspond[:object.rows, :object.cols] = object[:]
correspond[object.rows:, :image.cols] = image[:]
# find pairs
ptpairs = findPairs(surf, objectKeypoints, objectDescriptors, imageKeypoints, imageDescriptors)
for pair in ptpairs:
cv.line( correspond, cv.asPoint(pair[0]), cv.Point(int(pair[1].x), int(pair[1].y+object.rows)), colors[8] )
# locate planar object
if locatePlanarObject( ptpairs, src_corners, dst_corners ):
for i in range(4):
r1 = dst_corners[i]
r2 = dst_corners[(i+1)%4]
cv.line( correspond, cv.Point(r1.x, r1.y+object.rows ), cv.Point(r2.x, r2.y+object.rows ), colors[8] )
# show the object correspondents
cv.imshow("Object Correspond", correspond)
# draw circles
for keypt in objectKeypoints:
cv.circle(object_color, cv.asPoint(keypt.pt), int(keypt.size*1.2/9.*2), colors[0], 1, 8, 0)
cv.imshow("Object", object_color)
