def find_lines_in_map_probabilistic(self, map_img):
#Finds lines in the image using the probabilistic hough transform
lines=cv.CreateMemStorage(0)
line_img=cv.CreateMat(map_img.height, map_img.width, cv.CV_8UC1)
cv.Set(line_img, 255)
lines = cv.HoughLines2(map_img,cv.CreateMemStorage(), cv.CV_HOUGH_PROBABILISTIC, self.hough_rho,np.pi/2,self.hough_threshold)
np_line=np.asarray(lines)
print "list of probabilistic lines: ", np_line
def DetectRedEyes(image, faceCascade, eyeCascade): min_size = (20,20) image_scale = 2 haar_scale = 1.2 min_neighbors = 2 haar_flags = 0 # Allocate the temporary images gray = cv.CreateImage((image.width, image.height), 8, 1) smallImage = cv.CreateImage((cv.Round(image.width / image_scale),cv.Round (image.height / image_scale)), 8 ,1) # Convert color input image to grayscale cv.CvtColor(image, gray, cv.CV_BGR2GRAY) # Scale input image for faster processing cv.Resize(gray, smallImage, cv.CV_INTER_LINEAR) # Equalize the histogram cv.EqualizeHist(smallImage, smallImage) # Detect the faces faces = cv.HaarDetectObjects(smallImage, faceCascade, cv.CreateMemStorage(0), haar_scale, min_neighbors, haar_flags, min_size) # If faces are found if faces: for ((x, y, w, h), n) in faces: # the input to cv.HaarDetectObjects was resized, so scale the # bounding box of each face and convert it to two CvPoints pt1 = (int(x * image_scale), int(y * image_scale)) pt2 = (int((x + w) * image_scale), int((y + h) * image_scale)) cv.Rectangle(image, pt1, pt2, cv.RGB(255, 0, 0), 3, 8, 0) face_region = cv.GetSubRect(image,(x,int(y + (h/4)),w,int(h/2))) cv.SetImageROI(image, (pt1[0], pt1[1], pt2[0] - pt1[0], int((pt2[1] - pt1[1]) * 0.7))) eyes = cv.HaarDetectObjects(image, eyeCascade, cv.CreateMemStorage(0), haar_scale, min_neighbors, haar_flags, (15,15)) if eyes: # For each eye found for eye in eyes: # Draw a rectangle around the eye cv.Rectangle(image, (eye[0][0], eye[0][1]), (eye[0][0] + eye[0][2], eye[0][1] + eye[0][3]), cv.RGB(255, 0, 0), 1, 8, 0) cv.ResetImageROI(image) return image
def detect_and_draw(img, front_cascade, profile_cascade):
# allocate temporary images
gray = cv.CreateImage((img.width,img.height), 8, 1)
small_img = cv.CreateImage((cv.Round(img.width / image_scale),
cv.Round (img.height / image_scale)), 8, 1)
# convert color input image to grayscale
cv.CvtColor(img, gray, cv.CV_BGR2GRAY)
# scale input image for faster processing
cv.Resize(gray, small_img, cv.CV_INTER_LINEAR)
cv.EqualizeHist(small_img, small_img)
if(front_cascade):
# Test for frontal face
faces = cv.HaarDetectObjects(small_img, front_cascade, cv.CreateMemStorage(0),
haar_scale, min_neighbors, haar_flags, min_size)
if faces: # we've detected a face
return [faces, FRONTAL]
# Test for profile face
faces = cv.HaarDetectObjects(small_img, profile_cascade, cv.CreateMemStorage(0),
haar_scale, min_neighbors, haar_flags, min_size)
if faces: # we've detected a face
return [faces, PROFILE]
#t = cv.GetTickCount() - t
#print "detection time = %gms" % (t/(cv.GetTickFrequency()*1000.))
#if faces:
#for ((x, y, w, h), n) in faces:
## the input to cv.HaarDetectObjects was resized, so scale the
## bounding box of each face and convert it to two CvPoints
#pt1 = (int(x * image_scale), int(y * image_scale))
#pt2 = (int((x + w) * image_scale), int((y + h) * image_scale))
#imgWidth, imgHeight = cv.GetSize(img)
#croppedX = max(0, x*image_scale-w*image_scale/2)
#croppedY = max(0, y*image_scale-h*image_scale/2)
#croppedW = min(imgWidth, (2*w)*image_scale)
#croppedH = min(imgHeight, (2*h)*image_scale)
#imgCropped = cv.CreateImage((croppedW, croppedH), img.depth, img.nChannels)
#srcRegion = cv.GetSubRect(img, (croppedX, croppedY, croppedW, croppedH))
#cv.Copy(srcRegion, imgCropped)
#cv.ShowImage("cropped", imgCropped)
#cv.Rectangle(img, pt1, pt2, cv.RGB(255, 0, 0), 3, 8, 0)
return []
def ifFace(img,size):
gray=cv.CreateImage(size,8,1)
cv.CvtColor(img,gray,cv.CV_BGR2GRAY)
newMem1=cv.CreateMemStorage(0)
newMem2=cv.CreateMemStorage(0)
newMem3=cv.CreateMemStorage(0)
cv.EqualizeHist(gray,gray)
face=cv.HaarDetectObjects(gray,c_f,newMem1,1.2,3,cv.CV_HAAR_DO_CANNY_PRUNING,(50,50))
mouth=cv.HaarDetectObjects(gray,c_m,newMem2,1.2,2,cv.CV_HAAR_DO_CANNY_PRUNING,(10,10))
body=cv.HaarDetectObjects(gray,c_m,newMem3,1.2,2,cv.CV_HAAR_DO_CANNY_PRUNING,(100,100))
if face and mouth or body:
cv.SaveImage("img/out.jpg",img)
return 1
else:
return 0
def detectRightEye(self, img, rightEyeArea, centerX, centerY, pt1, cascade2):
rightEye = cv.HaarDetectObjects(rightEyeArea, cascade2, cv.CreateMemStorage(0),
haar_scale, min_neighbors, haar_flags, min_size)
# in case of multiple find the maximum box
minArea = 0
pt3 = (0, 0)
pt4 = (0, 0)
if rightEye:
for ((x, y, w, h), n) in rightEye:
# the input to cv.HaarDetectObjects was resized, so scale the
# bounding box of each face and convert it to two CvPoints
if(w * h > minArea):
minArea = w * h
pt3 = (x, y)
pt4 = (x + w, y + h)
# pt3 = (int(x * image_scale), int(y * image_scale))
# pt4 = (int((x + w) * image_scale), int((y + h) * image_scale))
# print "point 3 " + str(pt3)
# print "point 4 " + str(pt4)
#
# cv.Rectangle(img, (centerX + pt3[0], pt1[1] + pt3[1]),(centerX + pt4[0], pt1[1] + pt4[1]), cv.RGB(0, 255, 255))
# cv.Rectangle(img, pt3, pt4, cv.RGB(0, 0, 255))
if(minArea > 0):
cv.Rectangle(img, (centerX + pt3[0], pt1[1] + pt3[1]), (centerX + pt4[0], pt1[1] + pt4[1]), cv.RGB(0, 255, 255))
pointX = centerX + pt3[0] + 10
pointY = pt1[1] + pt3[1] + 10
distanceX = pt4[0] - pt3[0] - 10
distanceY = pt4[1] - pt3[1] - 10
eyePart = cv.GetSubRect(img, (pointX, pointY, distanceX, distanceY))
def detect_face(img):
haarFace = cv.Load('./haarcascade_frontalface_default.xml')
#RGB_img = cv.fromarray(np.array(rgb[:,:,::-1]))
allFaces = cv.HaarDetectObjects(cv.fromarray(img),
haarFace,
cv.CreateMemStorage(),
scale_factor=1.1,
min_neighbors=3,
flags=0,
min_size=(50, 50))
# Get confidences
if (allFaces != []):
count_no_face = 0
#print(allFaces)
face_confid = [c for ((x, y, w, h), c) in allFaces]
max_ind = np.argmax(face_confid)
FINAL_FACE = allFaces[max_ind]
return FINAL_FACE[0]
else:
return []
def getContours(im, approx_value=1): #Return contours approximated
storage = cv.CreateMemStorage(0)
contours = cv.FindContours(cv.CloneImage(im), storage, cv.CV_RETR_CCOMP,
cv.CV_CHAIN_APPROX_SIMPLE)
contourLow = cv.ApproxPoly(contours, storage, cv.CV_POLY_APPROX_DP,
approx_value, approx_value)
return contourLow
def findImageContour(img, frame):
storage = cv.CreateMemStorage()
cont = cv.FindContours(img, storage, cv.CV_RETR_EXTERNAL,
cv.CV_CHAIN_APPROX_NONE, (0, 0))
max_center = [None, 0]
for c in contour_iterator(cont):
# Number of points must be more than or equal to 6 for cv.FitEllipse2
# Use to set minimum size of object to be tracked.
if len(c) >= 60:
# Copy the contour into an array of (x,y)s
PointArray2D32f = cv.CreateMat(1, len(c), cv.CV_32FC2)
for (i, (x, y)) in enumerate(c):
PointArray2D32f[0, i] = (x, y)
# Fits ellipse to current contour.
(center, size, angle) = cv.FitEllipse2(PointArray2D32f)
# Only consider location of biggest contour -- adapt for multiple object tracking
if size > max_center[1]:
max_center[0] = center
max_center[1] = size
angle = angle
if True:
# Draw the current contour in gray
gray = cv.CV_RGB(255, 255, 255)
cv.DrawContours(img, c, gray, gray, 0, 1, 8, (0, 0))
if max_center[1] > 0:
# Convert ellipse data from float to integer representation.
center = (cv.Round(max_center[0][0]), cv.Round(max_center[0][1]))
size = (cv.Round(max_center[1][0] * 0.5),
cv.Round(max_center[1][1] * 0.5))
color = cv.CV_RGB(255, 0, 0)
cv.Ellipse(frame, center, size, angle, 0, 360, color, 3, cv.CV_AA, 0)
def detectFace(img, cascade):
# allocate temporary images
gray = cv.CreateImage((img.width, img.height), 8, 1)
small_img = cv.CreateImage(
(cv.Round(img.width / imageScale), cv.Round(img.height / imageScale)),
8, 1)
# convert color input image to grayscale
cv.CvtColor(img, gray, cv.CV_BGR2GRAY)
# scale input image for faster processing
cv.Resize(gray, small_img, cv.CV_INTER_LINEAR)
cv.EqualizeHist(small_img, small_img)
faces = cv.HaarDetectObjects(small_img, cascade, cv.CreateMemStorage(0),
haarScale, minNeighbors, haarFlags, minSize)
if faces:
print "\tDetected ", len(faces), " object(s)"
for ((x, y, w, h), n) in faces:
#the input to cv.HaarDetectObjects was resized, scale the
#bounding box of each face and convert it to two CvPoints
pt1 = (int(x * imageScale), int(y * imageScale))
pt2 = (int((x + w) * imageScale), int((y + h) * imageScale))
cv.Rectangle(img, pt1, pt2, cv.RGB(255, 0, 0), 3, 8, 0)
return img
else:
return False
def capture():
"""
Using the intel training set to capture the face in the video.
Most of them are frameworks in OpenCV.
"""
j = 0
g = os.walk("origin")
for path, d, filelist in g:
for filename in filelist:
img = cv.LoadImage(os.path.join(path, filename))
image_size = cv.GetSize(img)
greyscale = cv.CreateImage(image_size, 8, 1)
cv.CvtColor(img, greyscale, cv.CV_BGR2GRAY)
storage = cv.CreateMemStorage(0)
cv.EqualizeHist(greyscale, greyscale)
cascade = cv.Load('haarcascade_frontalface_alt2.xml')
faces = cv.HaarDetectObjects(greyscale, cascade, storage, 1.2, 2,
cv.CV_HAAR_DO_CANNY_PRUNING, (50, 50))
for (x, y, w, h), n in faces:
j += 1
cv.SetImageROI(img, (x, y, w, h))
cv.SaveImage("captured/face" + str(j) + ".png", img)
def handel_camera_image(img, hc):
#resize it
img2 = cv.CreateMat(
cv.GetSize(img)[1] / 2,
cv.GetSize(img)[0] / 2, cv.CV_8UC3)
cv.Resize(img, img2)
#convert to grayscale
img_gray = cv.CreateImage(cv.GetSize(img2), 8, 1)
cv.CvtColor(img2, img_gray, cv.CV_RGB2GRAY)
#set the final image
img_f = img_gray
#detect faces from it
objects = cv.HaarDetectObjects(img_f, hc, cv.CreateMemStorage())
number_of_faces = len(objects)
if number_of_faces != 1:
if debug:
print "Error! Number of detected faces: " + str(number_of_faces)
return None
else:
for (x, y, w, h), n in objects:
#annotate the image
cv.Rectangle(img_f, (x, y), (x + w, y + h), 255)
if debug:
print "FACE -> h: " + str(h) + ", w: " + str(
w) + ", r(w/h): " + str(float(w) / float(h))
#resize to 64 to 64
img_r = resize_crop_img(img_f, x, y, w, h)
return (img_f, img_r)
def detect_and_draw(self, img, cascade, camera_position=0):
min_size = (20, 20)
image_scale = self.horizontalSlider_3.value()
haar_scale = 1.2
min_neighbors = 2
haar_flags = 0
# allocate temporary images
gray = cv.CreateImage((img.width, img.height), 8, 1)
small_img_height = cv.Round(img.height / image_scale)
small_img = cv.CreateImage(
(cv.Round(img.width / image_scale), small_img_height), 8, 1)
# convert color input image to grayscale
cv.CvtColor(img, gray, cv.CV_BGR2GRAY)
# scale input image for faster processing
cv.Resize(gray, small_img, cv.CV_INTER_LINEAR)
cv.EqualizeHist(small_img, small_img)
faces = cv.HaarDetectObjects(small_img, cascade,
cv.CreateMemStorage(0), haar_scale,
min_neighbors, haar_flags, min_size)
if faces:
for ((x, y, w, h), n) in faces:
if self.face_cert < n:
x2, y2, w2, h2 = self.make_the_rectangle_bigger(
x, y, w, h, 1.22, small_img_height, image_scale)
self.create_person_and_add_to_room(img, (x2, y2, w2, h2),
camera_position)
if self.mark_detected_objects[camera_position]:
pt2 = (int(x2 + w2), int(y2 + h2))
cv.Rectangle(img, (x2, y2), pt2, cv.RGB(255, 0, 0), 3,
8, 0)
if self.show_main_view[camera_position]:
cv.ShowImage("result" + str(camera_position), img)
def DetectFace(image, faceCascade, returnImage=False):
# This function takes a grey scale cv image and finds
# the patterns defined in the haarcascade function
# modified from: http://www.lucaamore.com/?p=638
#variables
min_size = (30, 30)
#image_scale = 2
haar_scale = 1.1
min_neighbors = 2
haar_flags = 0
# Equalize the histogram
cv.EqualizeHist(image, image)
# Detect the faces
faces = cv.HaarDetectObjects(image, faceCascade, cv.CreateMemStorage(0),
haar_scale, min_neighbors, haar_flags,
min_size)
# If faces are found
if faces and returnImage:
for ((x, y, w, h), n) in faces:
# Convert bounding box to two CvPoints
pt1 = (int(x), int(y))
pt2 = (int(x + w), int(y + h))
cv.Rectangle(image, pt1, pt2, cv.RGB(255, 0, 0), 5, 8, 0)
if returnImage:
return image
else:
return faces
def detect_and_draw(img, cascade):
# allocate temporary images
gray = cv.CreateImage((img.width, img.height), 8, 1)
small_img = cv.CreateImage((cv.Round(img.width / image_scale),
cv.Round(img.height / image_scale)), 8, 1)
# convert color input image to grayscale
cv.CvtColor(img, gray, cv.CV_BGR2GRAY)
# scale input image for faster processing
cv.Resize(gray, small_img, cv.CV_INTER_LINEAR)
cv.EqualizeHist(small_img, small_img)
if(cascade):
t = cv.GetTickCount()
faces = cv.HaarDetectObjects(small_img, cascade, cv.CreateMemStorage(0),
haar_scale, min_neighbors, haar_flags, min_size)
t = cv.GetTickCount() - t
print "detection time = %gms" % (t / (cv.GetTickFrequency() * 1000.))
if faces:
for ((x, y, w, h), n) in faces:
# the input to cv.HaarDetectObjects was resized, so scale the
# bounding box of each face and convert it to two CvPoints
pt1 = (int(x * image_scale), int(y * image_scale))
pt2 = (int((x + w) * image_scale), int((y + h) * image_scale))
cv.Rectangle(img, pt1, pt2, cv.RGB(255, 0, 0), 3, 8, 0)
cv.ShowImage("result", img)
def __init__(self, parent=None):
QWidget.__init__(self)
self.setMinimumSize(640, 480)
self.setMaximumSize(self.minimumSize())
# register this callbacks to interact with the faces and the camera
# image before the widget will view the frame
self.image_callback = None
self.face_callback = None
# init view with correct size, depth, channels
self.frame = cv.CreateImage((640, 480), cv.IPL_DEPTH_8U, 3)
self.storage = cv.CreateMemStorage()
self.capture = cv.CaptureFromCAM(0)
self.face_cascade = cv.Load(CSC_PATH +
"haarcascade_frontalface_alt.xml")
self.fd_wait_frames = 1
self._fd_wait = self.fd_wait_frames
# get first frame
self._query_frame()
# set refresh rate
self.timer = QTimer(self)
self.timer.timeout.connect(self._query_frame)
self.timer.start(75)
def detect_face(self, image):
min_size = (20, 20)
image_scale = 2
haar_scale = 1.1
min_neighbors = 2
haar_flags = 0
# Allocate the temporary images
gray = cv.CreateImage((image.width, image.height), 8, 1)
smallImage = cv.CreateImage((cv.Round(
image.width / image_scale), cv.Round(image.height / image_scale)),
8, 1)
# Convert color input image to grayscale
cv.CvtColor(image, gray, cv.CV_BGR2GRAY)
# Scale input image for faster processing
cv.Resize(gray, smallImage, cv.CV_INTER_LINEAR)
# Equalize the histogram
cv.EqualizeHist(smallImage, smallImage)
# Detect the faces
faces = cv.HaarDetectObjects(smallImage, self.cascade,
cv.CreateMemStorage(0), haar_scale,
min_neighbors, haar_flags, min_size)
return faces
def HandDetection(file):
img=cv2.imread(file,0)
#get size of input image
w,h=img.shape[:2]
#create grayscale version
gray=np.zeros((h,w,3),np.uint8)
#cv2.cvtColor(img, gray)
gray=img
# cv2.imshow('winname', gray)
# cv2.waitKey(0)
#create storage
storage=cv.CreateMemStorage(0)
#equalize histogram
# cv.EqualizeHist(gray, gray)
cascade_hand= cv2.CascadeClassifier('mycascade.xml')
hands=cascade_hand.detectMultiScale(img, scaleFactor=1.3,
minNeighbors=2, minSize=(24,24),
flags=cv.CV_HAAR_DO_CANNY_PRUNING)
for (x,y,w,h) in hands:
cv2.rectangle(img, (x,y), (x+w,y+h), 255)
cv2.imshow('winname', img)
cv2.waitKey(0)
def findEyes(self):
""" Detects eyes in a photo and initializes relevant attributes
Uses opencv libarary methods to detect a face and then detect the
eyes in that face. If there are exactly two eye regions found it
populates the region attributes. If not exactly two
eye regions are found the method returns false.
Args:
None
Return:
bool - True if there were no issues. False for any error
"""
#imcolor = cv.LoadImage(self.path)
imcolor = self.facePhoto
#Path setups
cwd = os.path.dirname(os.path.abspath(sys.argv[0]))
cwd += "/opencv/haarcascades/"
frontalface = cwd + "haarcascade_frontalface_default.xml"
eye = cwd + "haarcascade_eye.xml"
faceCascade = cv.Load(frontalface)
eyeCascade = cv.Load(eye)
haarEyes = cv.Load(eye)
storage = cv.CreateMemStorage()
detectedEyes = cv.HaarDetectObjects(imcolor,haarEyes,storage)
if DEBUG:
print "detectedEyes = " + str(detectedEyes)
if len(detectedEyes) == 2:
if DEBUG:
# Draw the rectangle
cv.Rectangle(imcolor,(detectedEyes[0][0][0], detectedEyes[0][0][1]),
(detectedEyes[0][0][0] + detectedEyes[0][0][2],
detectedEyes[0][0][1] + detectedEyes[0][0][3]),cv.RGB(155,155,200),2)
cv.Rectangle(imcolor,(detectedEyes[1][0][0], detectedEyes[1][0][1]),
(detectedEyes[1][0][0] + detectedEyes[1][0][2],
detectedEyes[1][0][1] + detectedEyes[1][0][3]),cv.RGB(155,155,200),2)
cv.ShowImage("Face with eyes",imcolor)
cv.WaitKey(0)
cv.DestroyWindow("Face with eyes")
left = (detectedEyes[0][0][0], detectedEyes[0][0][1],
detectedEyes[0][0][0] + detectedEyes[0][0][2],
detectedEyes[0][0][1] + detectedEyes[0][0][3])
right = (detectedEyes[1][0][0], detectedEyes[1][0][1],
detectedEyes[1][0][0] + detectedEyes[1][0][2],
detectedEyes[1][0][1] + detectedEyes[1][0][3])
if DEBUG:
print "left: " + str(left)
print "right: " + str(right)
self.setEyes(left, right)
return True
if DEBUG:
print "Found more or less than 2 eyes, returning false"
return False
def detect_and_draw(img, face_cascade):
gray = cv.CreateImage((img.width, img.height), 8, 1)
image_scale = img.width / smallwidth
small_img = cv.CreateImage((cv.Round(
img.width / image_scale), cv.Round(img.height / image_scale)), 8, 1)
# gray = cv.CreateImage((img.width,img.height), 8, 1)
image_scale = img.width / smallwidth
# small_img = cv.CreateImage((cv.Round(img.width / image_scale), cv.Round (img.height / image_scale)), 8, 1)
# convert color input image to grayscale
cv.CvtColor(img, gray, cv.CV_BGR2GRAY)
# scale input image for faster processing
cv.Resize(gray, small_img, cv.CV_INTER_LINEAR)
cv.EqualizeHist(small_img, small_img)
faces = cv.HaarDetectObjects(small_img, face_cascade,
cv.CreateMemStorage(0), haar_scale,
min_neighbors, haar_flags, min_size)
if opencv_preview and faces:
for ((x, y, w, h), n) in faces:
# the input to cv.HaarDetectObjects was resized, so scale the
# bounding box of each face and convert it to two CvPoints
pt1 = (int(x * image_scale), int(y * image_scale))
pt2 = (int((x + w) * image_scale), int((y + h) * image_scale))
cv.Rectangle(img, pt1, pt2, cv.RGB(255, 0, 0), 3, 8, 0)
if verbose:
print "Face at: ", pt1[0], ",", pt2[0], "\t", pt1[1], ",", pt2[
1]
return True if faces else False
def detectLeftEye(self, originalImage, cascade2, pt1, centerX, centerY):
leftEyeArea = cv.GetSubRect(originalImage, (pt1[0], pt1[1], centerX - pt1[0], centerY - pt1[1]))
leftEye = cv.HaarDetectObjects(leftEyeArea, cascade2, cv.CreateMemStorage(0),
haar_scale, min_neighbors, haar_flags, min_size)
# in case of multiple find the maximum box
minArea = 0
pt3 = (0, 0)
pt4 = (0, 0)
if leftEye:
for ((x, y, w, h), n) in leftEye:
# the input to cv.HaarDetectObjects was resized, so scale the
# bounding box of each face and convert it to two CvPoints
if(w * h > minArea):
minArea = w * h
pt3 = (x, y)
pt4 = (x + w, y + h)
if(minArea > 0):
cv.Rectangle(originalImage, (pt1[0] + pt3[0], pt1[1] + pt3[1]), (pt1[0] + pt4[0], pt1[1] + pt4[1]), cv.RGB(255, 255, 0))
pointX = pt1[0] + pt3[0] + 10
pointY = pt1[1] + pt3[1] + 10
distanceX = pt4[0] - pt3[0] - 10
distanceY = pt4[1] - pt3[1] - 10
eyePart = cv.GetSubRect(originalImage, (pointX, pointY, distanceX, distanceY))
def detect_face(RGB_img):
# Image Properties
#print('Image Size: ({},{})'.format(cv.GetCaptureProperty(CAM_CAPT, cv.CV_CAP_PROP_FRAME_HEIGHT), cv.GetCaptureProperty(CAM_CAPT, cv.CV_CAP_PROP_FRAME_WIDTH)))
#print('FPS: {}'.format(cv.GetCaptureProperty(CAM_CAPT, cv.CV_CAP_PROP_FPS)))
RGB_img_mat = cv.fromarray(RGB_img)
haarFace = cv.Load('haarcascade_frontalface_default.xml')
#RGB_img = cv.fromarray(np.array(rgb[:,:,::-1]))
allFaces = cv.HaarDetectObjects(RGB_img_mat,
haarFace,
cv.CreateMemStorage(),
scale_factor=1.1,
min_neighbors=10,
flags=0,
min_size=(50, 50))
# Get confidences
if (allFaces != []):
#print(allFaces)
face_confid = [c for ((x, y, w, h), c) in allFaces]
area = [w * h for ((x, y, w, h), c) in allFaces]
#max_ind = np.argmax(face_confid)
max_ind = np.argmax(area)
FINAL_FACE = allFaces[max_ind]
x0 = FINAL_FACE[0][0]
y0 = FINAL_FACE[0][1]
w = FINAL_FACE[0][2]
h = FINAL_FACE[0][3]
# Show detected face
print('Face Detected!!')
#cv.Rectangle(RGB_img_mat, (x0, y0), (x0+w, y0+h), cv.RGB(0,0,255), 2)
# Detect eyes only in given face region
print('Face: ' + str(FINAL_FACE))
cropped_img = RGB_img[y0:y0 + h, x0:x0 + w]
#cv.Smooth(cropped_img, cropped_img, cv.CV_GAUSSIAN, 15, 15)
#print(cv.GetSize(cropped_img))
#cv.ShowImage('crop', cropped_img)
#cv.SaveImage('IMAGE.png', cropped_img)
#allEyes = detect_eyes(cropped_img)
#print('Eyes: '+str(allEyes))
#for eye in allEyes:
# eye = eye[0]
# eye=(eye[0]+x0, eye[1]+y0, eye[2], eye[3])
# cv.Rectangle(RGB_img, (eye[0], eye[1]), (eye[0]+eye[2], eye[1]+eye[3]), cv.RGB(255,0,0), 2)
return np.asarray(cropped_img[:, :])
else:
print('No Face!!')
return RGB_img
def detect_and_draw(img, cascade, jpg_cnt):
# allocate temporary images
gray = cv.CreateImage((img.width, img.height), 8, 1)
small_img = cv.CreateImage((cv.Round(
img.width / image_scale), cv.Round(img.height / image_scale)), 8, 1)
# convert color input image to grayscale
cv.CvtColor(img, gray, cv.CV_BGR2GRAY)
# scale input image for faster processing
cv.Resize(gray, small_img, cv.CV_INTER_LINEAR)
cv.EqualizeHist(small_img, small_img)
if (cascade):
t = cv.GetTickCount()
faces = cv.HaarDetectObjects(small_img, cascade,
cv.CreateMemStorage(0), haar_scale,
min_neighbors, haar_flags, min_size)
t = cv.GetTickCount() - t
print "detection time = %gms" % (t / (cv.GetTickFrequency() * 10000))
if faces:
for ((x, y, w, h), n) in faces:
# the input to cv.HaarDetectObjects was resized, so scale the
# bounding box of each face and convert it to two CvPoints
pt1 = (int(x * image_scale), int(y * image_scale))
pt2 = (int((x + w) * image_scale), int((y + h) * image_scale))
cv.Rectangle(img, pt1, pt2, cv.RGB(255, 0, 0), 3, 8, 0)
if jpg_cnt % 50 == 1:
print('capture completed')
cv.SaveImage('test_' + str(jpg_cnt) + '.jpg', img)
print("aaa1")
url = 'http://210.94.185.52:8080/upload.php'
#files={ 'upfiles' : open('/home/lee/test_'+str(jpg_cnt)+'.jpg','rb')}
files = {
'upfiles':
open('/home/lee/test_' + str(jpg_cnt) + '.jpg', 'rb')
}
print("aaa2")
r = requests.post(url, files=files)
print("aaa3")
print(r.text)
for i in r.text.split():
try:
op = float(i)
break
except:
continue
print(op)
#LED
if op >= 0.9:
lock_on()
else:
print('no')
cv.ShowImage("result", img)
def update_mhi(img, dst, diff_threshold):
global last
global mhi
global storage
global mask
global orient
global segmask
timestamp = time.clock() / CLOCKS_PER_SEC # get current time in seconds
size = cv.GetSize(img) # get current frame size
idx1 = last
if not mhi or cv.GetSize(mhi) != size:
for i in range(N):
buf[i] = cv.CreateImage(size, cv.IPL_DEPTH_8U, 1)
cv.Zero(buf[i])
mhi = cv.CreateImage(size,cv. IPL_DEPTH_32F, 1)
cv.Zero(mhi) # clear MHI at the beginning
orient = cv.CreateImage(size,cv. IPL_DEPTH_32F, 1)
segmask = cv.CreateImage(size,cv. IPL_DEPTH_32F, 1)
mask = cv.CreateImage(size,cv. IPL_DEPTH_8U, 1)
cv.CvtColor(img, buf[last], cv.CV_BGR2GRAY) # convert frame to grayscale
idx2 = (last + 1) % N # index of (last - (N-1))th frame
last = idx2
silh = buf[idx2]
cv.AbsDiff(buf[idx1], buf[idx2], silh) # get difference between frames
cv.Threshold(silh, silh, diff_threshold, 1, cv.CV_THRESH_BINARY) # and threshold it
cv.UpdateMotionHistory(silh, mhi, timestamp, MHI_DURATION) # update MHI
cv.CvtScale(mhi, mask, 255./MHI_DURATION,
(MHI_DURATION - timestamp)*255./MHI_DURATION)
cv.Zero(dst)
cv.Merge(mask, None, None, None, dst)
cv.CalcMotionGradient(mhi, mask, orient, MAX_TIME_DELTA, MIN_TIME_DELTA, 3)
if not storage:
storage = cv.CreateMemStorage(0)
seq = cv.SegmentMotion(mhi, segmask, storage, timestamp, MAX_TIME_DELTA)
for (area, value, comp_rect) in seq:
if comp_rect[2] + comp_rect[3] > 100: # reject very small components
color = cv.CV_RGB(255, 0,0)
silh_roi = cv.GetSubRect(silh, comp_rect)
mhi_roi = cv.GetSubRect(mhi, comp_rect)
orient_roi = cv.GetSubRect(orient, comp_rect)
mask_roi = cv.GetSubRect(mask, comp_rect)
angle = 360 - cv.CalcGlobalOrientation(orient_roi, mask_roi, mhi_roi, timestamp, MHI_DURATION)
count = cv.Norm(silh_roi, None, cv.CV_L1, None) # calculate number of points within silhouette ROI
if count < (comp_rect[2] * comp_rect[3] * 0.05):
continue
magnitude = 30.
center = ((comp_rect[0] + comp_rect[2] / 2), (comp_rect[1] + comp_rect[3] / 2))
cv.Circle(dst, center, cv.Round(magnitude*1.2), color, 3, cv.CV_AA, 0)
cv.Line(dst,
center,
(cv.Round(center[0] + magnitude * cos(angle * cv.CV_PI / 180)),
cv.Round(center[1] - magnitude * sin(angle * cv.CV_PI / 180))),
color,
3,
cv.CV_AA,
0)
def find_Lines(im):
out = cv.CreateImage(cv.GetSize(im), 8, 1)
tmp = cv.CreateImage(cv.GetSize(im), 8, 3)
storage = cv.CreateMemStorage(0)
cv.Canny(im, out, 50, 200, 3)
cv.CvtColor(out, tmp, cv.CV_GRAY2BGR)
return cv.HoughLines2(out, storage, cv.CV_HOUGH_STANDARD, 1, pi / 180, 100,
0, 0)
def track(img, threshold=100):
'''Accepts BGR image and optional object threshold between 0 and 255 (default = 100).
Returns: (x,y) coordinates of centroid if found
(-1,-1) if no centroid was found
None if user hit ESC
'''
cascade = cv.Load("haarcascade_frontalface_default.xml")
gray = cv.CreateImage((img.width, img.height), 8, 1)
small_img = cv.CreateImage((cv.Round(
img.width / image_scale), cv.Round(img.height / image_scale)), 8, 1)
# convert color input image to grayscale
cv.CvtColor(img, gray, cv.CV_BGR2GRAY)
# scale input image for faster processing
cv.Resize(gray, small_img, cv.CV_INTER_LINEAR)
cv.EqualizeHist(small_img, small_img)
center = (-1, -1)
faces = []
original_size_faces = []
#import ipdb; ipdb.set_trace()
if (cascade):
t = cv.GetTickCount()
# HaarDetectObjects takes 0.02s
faces = cv.HaarDetectObjects(small_img, cascade,
cv.CreateMemStorage(0), haar_scale,
min_neighbors, haar_flags, min_size)
t = cv.GetTickCount() - t
if faces:
for ((x, y, w, h), n) in faces:
# the input to cv.HaarDetectObjects was resized, so scale the
# bounding box of each face and convert it to two CvPoints
pt1 = (int(x * image_scale), int(y * image_scale))
pt2 = (int((x + w) * image_scale), int((y + h) * image_scale))
# cv.Rectangle(img, pt1, pt2, cv.RGB(255, 0, 0), 3, 8, 0)
#cv.Rectangle(img, (x,y), (x+w,y+h), 255)
# get the xy corner co-ords, calc the center location
x1 = pt1[0]
x2 = pt2[0]
y1 = pt1[1]
y2 = pt2[1]
centerx = x1 + ((x2 - x1) / 2)
centery = y1 + ((y2 - y1) / 2)
center = (centerx, centery)
scaled = ((x1, y1, x2 - x1, y2 - y1), n)
original_size_faces.append(scaled)
# print scaled
# cv.NamedWindow(WINDOW_NAME, 1)
# cv.ShowImage(WINDOW_NAME, img)
# if cv.WaitKey(5) == 27:
# center = None
return (center, original_size_faces)
def find_squares_from_binary( gray ):
"""
use contour search to find squares in binary image
returns list of numpy arrays containing 4 points
"""
squares = []
storage = cv.CreateMemStorage(0)
contours = cv.FindContours(gray, storage, cv.CV_RETR_TREE, cv.CV_CHAIN_APPROX_SIMPLE, (0,0))
storage = cv.CreateMemStorage(0)
while contours:
#approximate contour with accuracy proportional to the contour perimeter
arclength = cv.ArcLength(contours)
polygon = cv.ApproxPoly( contours, storage, cv.CV_POLY_APPROX_DP, arclength * 0.02, 0)
if is_square(polygon):
squares.append(polygon[0:4])
contours = contours.h_next()
return squares
def initialize(self, frame):
# Initialize
# log_file_name = "tracker_output.log"
# log_file = file( log_file_name, 'a' )
print str(type(frame))
print "resize to ::: " + str(cv.GetSize(frame)) + " " + str(type(frame))
(w, h) = cv.GetSize(frame)
# gray = cv.CreateImage(cv.GetSize(frame), cv.IPL_DEPTH_8U, 1)
size = (w, h) #cv.GetSize(frame)#(300 , 300)
self.thumbnail = cv.CreateImage(size, cv.IPL_DEPTH_8U, 3)
self.grey_average_image = cv.CreateImage(size, cv.IPL_DEPTH_8U, 1)
self.grey_original_image = cv.CreateImage(size, cv.IPL_DEPTH_8U, 1)
# cv.CvtColor(display_image, gray, cv.CV_RGB2GRAY)
# prev_image = gray
# Greyscale image, thresholded to create the motion mask:
self.grey_image = cv.CreateImage(size, cv.IPL_DEPTH_8U, 1)
# The RunningAvg() function requires a 32-bit or 64-bit image...
self.running_average_image = cv.CreateImage(size, cv.IPL_DEPTH_32F, 3)
# ...but the AbsDiff() function requires matching image depths:
self.running_average_in_display_color_depth = cv.CloneImage(self.thumbnail)
# RAM used by FindContours():
self.mem_storage = cv.CreateMemStorage(0)
# The difference between the running average and the current frame:
self.difference = cv.CloneImage(self.thumbnail)
self.target_count = 1
self.last_target_count = 1
self.last_target_change_t = 0.0
self.k_or_guess = 1
self.codebook = []
self.last_frame_entity_list = []
self.frame_count = 0
# For toggling display:
image_list = [ "camera", "difference", "threshold", "display", "faces" ]
image_index = 3 # Index into image_list
# Prep for text drawing:
text_font = cv.InitFont(cv.CV_FONT_HERSHEY_COMPLEX, .5, .5, 0.0, 1, cv.CV_AA)
text_coord = (5, 15)
text_color = cv.CV_RGB(255, 255, 255)
# Set this to the max number of targets to look for (passed to k-means):
self.max_targets = 5
def lines2():
im = cv.LoadImage('roi_edges.jpg', cv.CV_LOAD_IMAGE_GRAYSCALE)
pi = math.pi
x = 0
dst = cv.CreateImage(cv.GetSize(im), 8, 1)
cv.Canny(im, dst, 200, 200)
cv.Threshold(dst, dst, 100, 255, cv.CV_THRESH_BINARY)
color_dst_standard = cv.CreateImage(cv.GetSize(im), 8, 3)
cv.CvtColor(im, color_dst_standard,
cv.CV_GRAY2BGR) #Create output image in RGB to put red lines
lines = cv.HoughLines2(dst, cv.CreateMemStorage(0), cv.CV_HOUGH_STANDARD,
1, pi / 100, 71, 0, 0)
klsum = 0
klaver = 0
krsum = 0
kraver = 0
#global k
#k=0
for (rho, theta) in lines[:100]:
kl = []
kr = []
a = math.cos(theta)
b = math.sin(theta)
x0 = a * rho
y0 = b * rho
pt1 = (cv.Round(x0 + 1000 * (-b)), cv.Round(y0 + 1000 * (a)))
pt2 = (cv.Round(x0 - 1000 * (-b)), cv.Round(y0 - 1000 * (a)))
k = ((y0 - 1000 * (a)) - (y0 + 1000 * (a))) / ((x0 - 1000 * (-b)) -
(x0 + 1000 * (-b)))
if abs(k) < 0.4:
pass
elif k > 0:
kr.append(k)
len_kr = len(kr)
for i in kr:
krsum = krsum + i
kraver = krsum / len_kr
cv.Line(color_dst_standard, pt1, pt2, cv.CV_RGB(255, 0, 0), 2,
4)
elif k < 0:
kr.append(k)
kl.append(k)
len_kl = len(kl)
for i in kl:
klsum = klsum + i
klaver = klsum / len_kl
cv.Line(color_dst_standard, pt1, pt2, cv.CV_RGB(255, 0, 0), 2,
4)
#print k
# cv.Line(color_dst_standard, pt1, pt2, cv.CV_RGB(255, 0, 0), 2, 4)
cv.SaveImage('lane.jpg', color_dst_standard)
print '左车道平均斜率:', klaver, ' 右车道平均斜率:', kraver
cv.ShowImage("Hough Standard", color_dst_standard)
cv.WaitKey(0)
def find_rectangles(self,input_img):
""" Find contours in the input image.
input_img: Is a binary image
"""
contours_img=cv.CreateMat(input_img.height, input_img.width, cv.CV_8UC1) # Image to draw the contours
copied_img=cv.CreateMat(input_img.height, input_img.width, input_img.type) # Image to draw the contours
cv.Copy(input_img, copied_img)
contours = cv.FindContours(copied_img,cv.CreateMemStorage(),cv.CV_RETR_TREE,cv.CV_CHAIN_APPROX_SIMPLE)
cv.DrawContours(contours_img,contours,255,0,10)
return contours_img
def OnPaint(self, evt):
if not self.timer.IsRunning() :
dc = wx.BufferedDC(wx.ClientDC(self), wx.NullBitmap, wx.BUFFER_VIRTUAL_AREA)
dc.SetBackground(wx.Brush(wx.Colour(0, 0, 0)))
return
# Capture de l'image
frame = cv.QueryFrame(CAMERA)
cv.CvtColor(frame, frame, cv.CV_BGR2RGB)
Img = wx.EmptyImage(frame.width, frame.height)
Img.SetData(frame.tostring())
self.bmp = wx.BitmapFromImage(Img)
width, height = frame.width, frame.height
# Détection des visages
min_size = (20, 20)
image_scale = 2
haar_scale = 1.2
min_neighbors = 2
haar_flags = 0
gray = cv.CreateImage((frame.width, frame.height), 8, 1)
small_img = cv.CreateImage((cv.Round(frame.width / image_scale), cv.Round (frame.height / image_scale)), 8, 1)
cv.CvtColor(frame, gray, cv.CV_BGR2GRAY)
cv.Resize(gray, small_img, cv.CV_INTER_LINEAR)
cv.EqualizeHist(small_img, small_img)
listeVisages = cv.HaarDetectObjects(small_img, CASCADE, cv.CreateMemStorage(0), haar_scale, min_neighbors, haar_flags, min_size)
# Affichage de l'image
x, y = (0, 0)
try:
dc = wx.BufferedDC(wx.ClientDC(self), wx.NullBitmap, wx.BUFFER_VIRTUAL_AREA)
try :
dc.SetBackground(wx.Brush(wx.Colour(0, 0, 0)))
except :
pass
dc.Clear()
dc.DrawBitmap(self.bmp, x, y)
# Dessin des rectangles des visages
if listeVisages :
for ((x, y, w, h), n) in listeVisages :
dc.SetBrush(wx.TRANSPARENT_BRUSH)
dc.SetPen(wx.Pen(wx.Colour(255, 0, 0), 2))
dc.DrawRectangle(x* image_scale, y* image_scale, w* image_scale, h* image_scale)
self.listeVisages = listeVisages
del dc
del Img
except TypeError:
pass
except wx.PyDeadObjectError:
pass