def detect(image):
image_size = cv.GetSize(image)
# create grayscale version
grayscale = cv.CreateImage(image_size, 8, 1)
cv.CvtColor(image, grayscale, cv.BGR2GRAY)
# create storage
storage = cv.CreateMemStorage(0)
cv.ClearMemStorage(storage)
# equalize histogram
cv.EqualizeHist(grayscale, grayscale)
# detect objects
cascade = cv.LoadHaarClassifierCascade('haarcascade_frontalface_alt.xml',
cv.Size(1, 1))
faces = cv.HaarDetectObjects(grayscale, cascade, storage, 1.2, 2,
cv.HAAR_DO_CANNY_PRUNING, cv.Size(50, 50))
if faces:
print 'face detected!'
for i in faces:
cv.Rectangle(image, cv.Point(int(i.x), int(i.y)),
cv.Point(int(i.x + i.width), int(i.y + i.height)),
cv.RGB(0, 255, 0), 3, 8, 0)
# create windows
cv.NamedWindow('Camera', cv.WINDOW_AUTOSIZE)
# create capture device
device = 0 # assume we want first device
capture = cv.CreateCameraCapture(0)
cv.SetCaptureProperty(capture, cv.CAP_PROP_FRAME_WIDTH, 640)
cv.SetCaptureProperty(capture, cv.CAP_PROP_FRAME_HEIGHT, 480)
def detectObject(image):
grayscale = cv.CreateImage(cv.CvSize(640, 480), 8, 1)
cv.CvtColor(image, grayscale, CV_BGR2GRAY)
storage = cv.CreateMemStorage(0)
cv.ClearMemStorage(storage)
cv.EqualizeHist(grayscale, grayscale)
cascade = cv.LoadHaarClassifierCascade('haarcascade_frontalface_alt.xml',
cv.CvSize(1, 1))
faces = cv.HaarDetectObjects(grayscale, cascade, storage, 1.2, 2,
CV_HAAR_DO_CANNY_PRUNING, cv.Size(100, 100))
if faces:
for i in faces:
cv.Rectangle(image, cv.Point(int(i.x), int(i.y)),
cv.Point(int(i.x + i.width), int(i.y + i.height)),
CV_RGB(0, 255, 0), 3, 8, 0)
def detect(image):
image_size = cv.GetSize(image)
# create grayscale version
grayscale = cv.CreateImage(image_size, 8, 1)
cv.CvtColor(image, grayscale, cv.BGR2GRAY)
# create storage
storage = cv.CreateMemStorage(0)
cv.ClearMemStorage(storage)
# equalize histogram
cv.EqualizeHist(grayscale, grayscale)
# detect objects
cascade = cv.LoadHaarClassifierCascade('haarcascade_frontalface_alt.xml', cv.Size(1,1))
faces = cv.HaarDetectObjects(grayscale, cascade, storage, 1.2, 2, cv.HAAR_DO_CANNY_PRUNING, cv.Size(50, 50))
if faces:
print 'face detected!'
for i in faces:
cv.Rectangle(image, cv.Point( int(i.x), int(i.y)),
cv.Point(int(i.x + i.width), int(i.y + i.height)),
cv.RGB(0, 255, 0), 3, 8, 0)
def findSquares4(img, storage):
N = 11
sz = cv.Size(img.width & -2, img.height & -2)
timg = CloneImage(img)
# make a copy of input image
gray = CreateImage(sz, 8, 1)
pyr = CreateImage(cv.Size(sz.width / 2, sz.height / 2), 8, 3)
# create empty sequence that will contain points -
# 4 points per square (the square's vertices)
squares = CreateSeq(0, sizeof_CvSeq, sizeof_CvPoint, storage)
squares = CvSeq_CvPoint.cast(squares)
# select the maximum ROI in the image
# with the width and height divisible by 2
subimage = GetSubRect(timg, Rect(0, 0, sz.width, sz.height))
# down-scale and upscale the image to filter out the noise
PyrDown(subimage, pyr, 7)
PyrUp(pyr, subimage, 7)
tgray = CreateImage(sz, 8, 1)
# find squares in every color plane of the image
for c in range(3):
# extract the c-th color plane
channels = [None, None, None]
channels[c] = tgray
Split(subimage, channels[0], channels[1], channels[2], None)
for l in range(N):
# hack: use Canny instead of zero threshold level.
# Canny helps to catch squares with gradient shading
if (l == 0):
# apply Canny. Take the upper threshold from slider
# and set the lower to 0 (which forces edges merging)
Canny(tgray, gray, 0, thresh, 5)
# dilate canny output to remove potential
# holes between edge segments
Dilate(gray, gray, None, 1)
else:
# apply threshold if l!=0:
# tgray(x,y) = gray(x,y) < (l+1)*255/N ? 255 : 0
Threshold(tgray, gray, (l + 1) * 255 / N, 255,
CV_THRESH_BINARY)
# find contours and store them all as a list
count, contours = FindContours(gray, storage, sizeof_CvContour,
CV_RETR_LIST,
CV_CHAIN_APPROX_SIMPLE, Point(0, 0))
if not contours:
continue
# test each contour
for contour in contours.hrange():
# approximate contour with accuracy proportional
# to the contour perimeter
result = ApproxPoly(contour, sizeof_CvContour, storage,
CV_POLY_APPROX_DP,
ContourPerimeter(contours) * 0.02, 0)
# square contours should have 4 vertices after approximation
# relatively large area (to filter out noisy contours)
# and be convex.
# Note: absolute value of an area is used because
# area may be positive or negative - in accordance with the
# contour orientation
if (result.total == 4 and abs(ContourArea(result)) > 1000
and CheckContourConvexity(result)):
s = 0
for i in range(5):
# find minimum angle between joint
# edges (maximum of cosine)
if (i >= 2):
t = abs(
angle(result[i], result[i - 2], result[i - 1]))
if s < t:
s = t
# if cosines of all angles are small
# (all angles are ~90 degree) then write quandrange
# vertices to resultant sequence
if (s < 0.3):
for i in range(4):
squares.append(result[i])
return squares
class RobotVision:
#size = None
#cvImage hsv_frame, thresholded, thresholded2
#cvScalar hsv_min, hsv_max, hsv_min2, hsv_max2
#cvCapture capture;
if __name__ == '__main__':
#globals size, hsv_frame, thresholded, thresholded2, hsv_min, hsv_max, hsv_min2, hsv_max2, capture
print "Initializing ball Tracking"
size = cv.Size(640, 480)
hsv_frame = cv.CreateImage(size, cv.IPL_DEPTH_8U, 3)
thresholded = cv.CreateImage(size, cv.IPL_DEPTH_8U, 1)
thresholded2 = cv.CreateImage(size, cv.IPL_DEPTH_8U, 1)
hsv_min = cv.Scalar(0, 50, 170, 0)
hsv_max = cv.Scalar(10, 180, 256, 0)
hsv_min2 = cv.Scalar(170, 50, 170, 0)
hsv_max2 = cv.Scalar(256, 180, 256, 0)
storage = cv.CreateMemStorage(0)
# start capturing form webcam
capture = cv.CreateCameraCapture(0)
if not capture:
print "Could not open webcam"
sys.exit(1)
#CV windows
cv.NamedWindow("Camera", cv.CV_WINDOW_AUTOSIZE)
#globals size, hsv_frame, thresholded, thresholded2, hsv_min, hsv_max, hsv_min2, hsv_max2, capture
while True:
# get a frame from the webcam
frame = cv.QueryFrame(capture)
if frame is not None:
# convert to HSV for color matching
# as hue wraps around, we need to match it in 2 parts and OR together
cv.CvtColor(frame, hsv_frame, cv.CV_BGR2HSV)
cv.InRangeS(hsv_frame, hsv_min, hsv_max, thresholded)
cv.InRangeS(hsv_frame, hsv_min2, hsv_max2, thresholded2)
cv.Or(thresholded, thresholded2, thresholded)
# pre-smoothing improves Hough detector
cv.Smooth(thresholded, thresholded, cv.CV_GAUSSIAN, 9, 9)
circles = cv.HoughCircles(thresholded, storage,
cv.CV_HOUGH_GRADIENT, 2,
thresholded.height / 4, 100, 40, 20,
200)
# find largest circle
maxRadius = 0
x = 0
y = 0
found = False
for i in range(circles.total):
circle = circles[i]
if circle[2] > maxRadius:
found = True
maxRadius = circle[2]
x = circle[0]
y = circle[1]
cv.ShowImage("Camera", frame)
if found:
print "ball detected at position:", x, ",", y, " with radius:", maxRadius
else:
print "no ball"