def Get_gradient_img(self):
'''
calculate the intensity gradient of the image
:return: the gradient image
'''
print('calculating gradient image')
new_img_x = np.zeros([self.y, self.x], dtype=np.float)
new_img_y = np.zeros([self.y, self.x], dtype=np.float)
for i in range(0, self.x):
for j in range(0, self.y):
if j == 0:
new_img_y[j][i] = 1
else:
new_img_y[j][i] = np.sum(
np.array([[self.img[j - 1][i]], [self.img[j][i]]]) *
self.y_kernel)
if i == 0:
new_img_x[j][i] = 1
else:
new_img_x[j][i] = np.sum(
np.array([self.img[j][i - 1], self.img[j][i]]) *
self.x_kernel)
gradient_img, self.angle = cv2.cartToPolar(new_img_x, new_img_y)
self.angle = np.tan(self.angle)
self.img = gradient_img.astype(np.uint8)
return self.img
def performFourier(self):
#to gray
grayImg = cv2.cvtColor(self.img, cv2.COLOR_BGR2GRAY)
self.grayImg = grayImg
#give freq transform and shift (cuz zero freq is in the cornern - we want it in the middle)
f = np.fft.fft2(grayImg)
fshift = np.fft.fftshift(f)
self.fshift = fshift
#give magnitude and phase
mag, ang = cv2.cartToPolar(fshift.real, fshift.imag)
self.mag = mag
self.ang = ang
#display it
plt.subplot(221), plt.imshow(grayImg, cmap='gray')
plt.title('Original Grayscale Image'), plt.xticks([]), plt.yticks([])
plt.subplot(223), plt.imshow(20 * np.log(np.abs(mag)), cmap='gray')
plt.title('Magnitude of Fourier Transform'), plt.xticks(
[]), plt.yticks([])
plt.subplot(224), plt.imshow(20 * np.log(ang), cmap='gray')
plt.title('Phase of Fourier Transform'), plt.xticks([]), plt.yticks([])
plt.show()
def describe(self, pattern_img, eps=1e-7):
# Calculate Sobel gradient
grad_x = cv2.Sobel(pattern_img, cv2.CV_32F, 1, 0, ksize=3)
grad_y = cv2.Sobel(pattern_img, cv2.CV_32F, 0, 1, ksize=3)
grad_mag, grad_ang = cv2.cartToPolar(grad_x,
grad_y,
angleInDegrees=True)
hist = self.get_grad_features(grad_mag, grad_ang).astype(np.float32)
return hist
def roughlyBlur(src, dsc, allflow, fps=30):
# print("roughly blur drawing")
scale = 1.0
if fps > 30:
scale = float(fps) / 30.0
rows, cols, _ = src.shape
test_width = int(cols / test_round_x)
test_height = int(rows / test_round_y)
test_x = 0
# round_x_progress.reset(total=test_round_x)
# load all roi's mag and ang
arr = []
while test_x < cols: #round_x_progress:
# round_x_progress.set_description('roughly blur drawing')
startx = test_x
endx = startx + test_width if startx + test_width < cols else cols
test_x = endx
if startx == endx:
break
test_y = 0
while test_y < rows:
starty = test_y
endy = starty + test_height if starty + test_height < rows else rows
test_y = endy
if starty == endy:
break
flow_roi = allflow[starty:endy, startx:endx]
flow_avg_0 = np.array((np.average(flow_roi[..., 0])))
flow_avg_1 = np.array((np.average(flow_roi[..., 1])))
mag, ang = cv2.cartToPolar(flow_avg_0, flow_avg_1)
mag = (mag * scale) #/ 2.0
ang = -ang * 180.0 / math.pi # 这原本是弧度！
mag_using = mag[0, 0]
ang_using = ang[0, 0]
region = (starty, endy, startx, endx)
item = (region, mag_using, ang_using)
arr.append(item)
sortedarr = sorted(arr, key=lambda iii: iii[1], reverse=True)
count = len(sortedarr)
for index in range(count):
if shouldprintblurprogress and (random.randint(1, 50) % 10) == 0:
print("test", index, count)
region, mag, ang = sortedarr[index]
if math.isinf(mag):
continue
drawRegionBlur(src=src,
dsc=dsc,
region=region,
mag=mag,
ang=ang,
maskvalue=1.5)
return dsc
def hog(img):
gx = cv2.Sobel(img, cv2.CV_32F, 1, 0)
gy = cv2.Sobel(img, cv2.CV_32F, 0, 1)
mag, ang = cv2.cartToPolar(gx, gy)
bins = np.int32(bin_n*ang/(2*np.pi)) # quantizing binvalues in (0...16)
bin_cells = bins[:10,:10], bins[10:,:10], bins[:10,10:], bins[10:,10:]
mag_cells = mag[:10,:10], mag[10:,:10], mag[:10,10:], mag[10:,10:]
hists = [np.bincount(b.ravel(), m.ravel(), bin_n) for b, m in zip(bin_cells, mag_cells)]
hist = np.hstack(hists) # hist is a 64 bit vector
# cv2.imshow('hog',hist)
return hist
def main():
drone = tellopy.Tello()
try:
drone.connect()
drone.wait_for_connection(60.0)
pygame.init()
pygame.joystick.init()
container = av.open(drone.get_video_stream())
frameCount = 0 # Stores the current frame being processed
frame1 = None # Store variables for first frame
frame2 = None # Store variables for second frame
prvs = None
hsv = None
while True:
for frame in container.decode(video=0):
checkController()
frameCount += 1
if frameCount == 1: # If first frame
frame1 = cv2.cvtColor(np.array(frame.to_image()),
cv2.COLOR_RGB2BGR)
prvs = cv2.cvtColor(frame1, cv2.COLOR_BGR2GRAY)
hsv = np.zeros_like(frame1)
hsv[..., 1] = 255
else: # If not first frame
frame2 = cv2.cvtColor(np.array(frame.to_image()),
cv2.COLOR_RGB2BGR)
next = cv2.cvtColor(frame2, cv2.COLOR_BGR2GRAY)
flow = cv2.calcOpticalFlowFarneback(
prvs, next, None, 0.5, 3, 15, 3, 5, 1.2, 0)
mag, ang = cv2.cartToPolar(flow[..., 0], flow[..., 1])
hsv[..., 0] = ang * 180 / np.pi / 2
hsv[..., 2] = cv2.normalize(mag, None, 0, 255,
cv2.NORM_MINMAX)
bgr = cv2.cvtColor(hsv, cv2.COLOR_HSV2BGR)
cv2.imshow('frame2', bgr)
k = cv2.waitKey(30) & 0xff
if k == 27:
break
elif k == ord('s'):
cv2.imwrite('opticalfb.png', frame2)
cv2.imwrite('opticalhsv.png', bgr)
prvs = next
print(frameCount)
except Exception as ex:
exc_type, exc_value, exc_traceback = sys.exc_info()
traceback.print_exception(exc_type, exc_value, exc_traceback)
print(ex)
finally:
drone.quit()
cv2.destroyAllWindows()
def optical_flow(img: np.ndarray, previous: np.ndarray) -> np.ndarray:
mask = np.zeros(shape=img.shape, dtype=np.uint8)
mask[..., 1] = 255
gray = to_gray(img)
previous = to_gray(previous)
flow = cv2.calcOpticalFlowFarneback(previous, gray, None, 0.5, 3, 15, 3, 5,
1.2, 0)
magnitude, polar_angle = cv2.cartToPolar(flow[..., 0], flow[..., 1])
mask[..., 0] = polar_angle * 180 / np.pi / 2
mask[..., 2] = cv2.normalize(magnitude, None, 0, 255, cv2.NORM_MINMAX)
rgb = cv2.cvtColor(mask, cv2.COLOR_HSV2BGR)
return rgb
def optical_flow(previous_, current_):
"""
光流
:param previous_:
:param current_:
:return:
"""
previous = cv2.cvtColor(previous_, cv2.COLOR_BGR2GRAY)
current = cv2.cvtColor(current_, cv2.COLOR_BGR2GRAY)
flow = cv2.calcOpticalFlowFarneback(previous, current, None, 0.5, 3, 15, 3, 5, 1.2, 0)
hsv = np.zeros_like(previous_)
mag, ang = cv2.cartToPolar(flow[..., 0], flow[..., 1])
hsv[..., 0] = ang * 180 / np.pi / 2
hsv[..., 1] = 255
hsv[..., 2] = cv2.normalize(mag, None, 0, 255, cv2.NORM_MINMAX)
flow = cv2.cvtColor(hsv, cv2.COLOR_HSV2BGR)
return flow
def Dense_Optical_Flow(image):
image_old = image
frame1 = image
next = image
hsv = np.zeros([frame1.shape[0], frame1.shape[1], 3], dtype=np.uint8)
hsv[..., 1] = 255
while (1):
flow = cv2.calcOpticalFlowFarneback(image_old, next, None, 0.5, 3, 50,
3, 5, 1.2, 0)
mag, ang = cv2.cartToPolar(flow[..., 0], flow[..., 1])
hsv[..., 0] = ang * 180 / np.pi / 2
hsv[..., 2] = cv2.normalize(mag, None, 0, 255, cv2.NORM_MINMAX)
bgr = cv2.cvtColor(hsv, cv2.COLOR_HSV2BGR)
image_old = next
k = cv2.waitKey(30) & 0xff
if k == 27:
break
next = (yield bgr)
def gradient(img: np.ndarray, kernel_size: int = 3) -> np.ndarray:
"""
calculates the magnitude and polar_angle of 2D vectors using Sobel operator on both axis.
Args:
img: image as numpy array
kernel_size: kernel size of Sobel operator (NxN)
Returns:
magnitude of gradients in image shape
"""
img = np.float32(img) / 255.0
sy = sobel_y(img, kernel_size=kernel_size)
sx = sobel_x(img, kernel_size=kernel_size)
mag, polar_angle = cv2.cartToPolar(sx, sy, angleInDegrees=True)
mag = np.ndarray.astype(mag, dtype=np.float32)
mag = to_bgr(mag)
return mag
def read_data(self):
print("Hello")
prvs = None
hsv = None
num_img = 0
while (cap.isOpened()):
ret, frame = cap.read()
if frame is not None:
if (num_img == 0):
num_img += 1
prvs = frame.copy()
prvs_gray = cv2.cvtColor(prvs, cv2.COLOR_RGB2GRAY)
continue
curr = frame.copy()
curr_gray = cv2.cvtColor(curr, cv2.COLOR_RGB2GRAY)
flow = cv2.calcOpticalFlowFarneback(prvs_gray, curr_gray, None,
0.5, 3, 15, 3, 5, 1.2, 0)
hsv = np.zeros_like(prvs)
mag, ang = cv2.cartToPolar(flow[..., 0], flow[..., 1])
hsv[..., 0] = ang * 180 / np.pi / 2
hsv[..., 1] = 255
hsv[..., 2] = cv2.normalize(mag, None, 0, 255, cv2.NORM_MINMAX)
rgb = cv2.cvtColor(hsv, cv2.COLOR_HSV2BGR)
number_str = str(num_img)
print("Saving file number: {}".format(number_str), end='\r')
zero_filled_number = number_str.zfill(5)
cv2.imwrite(
PATH_TO_SAVE_DIRECTORY + zero_filled_number + '.jpg', rgb)
num_img += 1
prvs = curr
cv2.imshow('frame2', rgb)
k = cv2.waitKey(30) & 0xff
if k == 27:
break
else:
break
ret, frame1 = cap.read()
prvs = cv2.cvtColor(frame1, cv2.COLOR_BGR2GRAY)
hsv = np.zeros(frame1.shape, np.uint8) # simular with np.zeros_like
hsv[..., 1] = 255
while (1):
ret, frame2 = cap.read()
if ret == False:
break
next = cv2.cvtColor(frame2, cv2.COLOR_BGR2GRAY)
flow = cv2.calcOpticalFlowFarneback(prvs, next, None, 0.5, 3, 15, 3, 5,
1.2, 0)
mag, ang = cv2.cartToPolar(flow[..., 0], flow[..., 1])
hsv[..., 0] = ang * 180 / np.pi / 2
hsv[..., 2] = cv2.normalize(mag, None, 0, 255, cv2.NORM_MINMAX)
rgb = cv2.cvtColor(hsv, cv2.COLOR_HSV2BGR)
cv2.imshow('frame2', rgb)
k = cv2.waitKey(30) & 0xff
if k == 27:
break
elif k == ord('s'):
cv2.imwrite('opticalfb.png', frame2)
cv2.imwrite('opticalhsv.png', rgb)
prvs = next
cv2.waitKey(0)
cap.release()
cv2.destroyAllWindows()
def getVideo():
global tracks
global track_len
global detect_interval
global frame_idx
global VIDEO_SCALE
global videoLabel
global typeOfVideo
global connectingToDrone
global takePicture
frameCount = 0 # Stores the current frame being processed
frame1Optical = None # Store variables for first frame
frame2Optical = None # Store variables for second frame
prvs = None
hsv = None
try:
while connectingToDrone:
#time.sleep(0.03)
for frameRaw in container.decode(video=0):
checkController()
if takePicture:
frame1 = np.array(frameRaw.to_image())
#im = Image.fromarray(frame1, 'RGB')
cv.imwrite(
"pics/" + datetime.datetime.now().isoformat() + ".jpg",
frame1)
#imageTk = ImageTk.PhotoImage(image=im)
#videoLabel.configure(image=imageTk)
#videoLabel.image = imageTk
#videoLabel.update()
takePicture = False
if typeOfVideo.get() == "Canny Edge Detection":
frame1 = np.array(frameRaw.to_image())
frame1 = cv.resize(frame1, (0, 0),
fx=VIDEO_SCALE,
fy=VIDEO_SCALE)
frameCanny = cv.Canny(frame1, 50, 100)
im = Image.fromarray(frameCanny)
imageTk = ImageTk.PhotoImage(image=im)
videoLabel.configure(image=imageTk)
videoLabel.image = imageTk
videoLabel.update()
elif typeOfVideo.get() == "LK Optical Flow":
frame1 = np.array(frameRaw.to_image())
frame = frame1
frame = cv.resize(frame1, (0, 0),
fx=VIDEO_SCALE,
fy=VIDEO_SCALE)
frame_gray = cv.cvtColor(frame, cv.COLOR_BGR2GRAY)
vis = frame.copy()
if len(tracks) > 0:
img0, img1 = prev_gray, frame_gray
p0 = np.float32([tr[-1]
for tr in tracks]).reshape(-1, 1, 2)
p1, _st, _err = cv.calcOpticalFlowPyrLK(
img0, img1, p0, None, **lk_params)
p0r, _st, _err = cv.calcOpticalFlowPyrLK(
img1, img0, p1, None, **lk_params)
d = abs(p0 - p0r).reshape(-1, 2).max(-1)
good = d < 1
new_tracks = []
for tr, (x,
y), good_flag in zip(tracks,
p1.reshape(-1, 2), good):
if not good_flag:
continue
tr.append((x, y))
if len(tr) > track_len:
del tr[0]
new_tracks.append(tr)
cv.circle(vis, (x, y), 2, (0, 255, 0), -1)
tracks = new_tracks
cv.polylines(vis, [np.int32(tr) for tr in tracks],
False, (0, 255, 0))
draw_str(vis, (20, 20),
'track count: %d' % len(tracks))
if frame_idx % detect_interval == 0:
mask = np.zeros_like(frame_gray)
mask[:] = 255
for x, y in [np.int32(tr[-1]) for tr in tracks]:
cv.circle(mask, (x, y), 5, 0, -1)
p = cv.goodFeaturesToTrack(frame_gray,
mask=mask,
**feature_params)
if p is not None:
for x, y in np.float32(p).reshape(-1, 2):
tracks.append([(x, y)])
frame_idx += 1
prev_gray = frame_gray
#cv.imshow('Tello Dense Optical - Middlebury Research', vis)
im = Image.fromarray(vis, 'RGB')
imageTk = ImageTk.PhotoImage(image=im)
videoLabel.configure(image=imageTk)
videoLabel.image = imageTk
videoLabel.update()
elif typeOfVideo.get() == "Optical Flow":
frameCount += 1
if frameCount == 1: # If first frame
frame1Optical = cv.cvtColor(
np.array(frameRaw.to_image()), cv.COLOR_RGB2BGR)
prvs = cv.cvtColor(frame1Optical, cv.COLOR_BGR2GRAY)
hsv = np.zeros_like(frame1Optical)
hsv[..., 1] = 255
else: # If not first frame
frame2Optical = cv.cvtColor(
np.array(frameRaw.to_image()), cv.COLOR_RGB2BGR)
next = cv.cvtColor(frame2Optical, cv.COLOR_BGR2GRAY)
flow = cv.calcOpticalFlowFarneback(
prvs, next, None, 0.5, 3, 15, 3, 5, 1.2, 0)
mag, ang = cv.cartToPolar(flow[..., 0], flow[..., 1])
hsv[..., 0] = ang * 180 / np.pi / 2
hsv[..., 2] = cv.normalize(mag, None, 0, 255,
cv.NORM_MINMAX)
bgr = cv.cvtColor(hsv, cv.COLOR_HSV2BGR)
im = Image.fromarray(
cv.resize(frame2Optical, (0, 0),
fx=VIDEO_SCALE,
fy=VIDEO_SCALE))
imageTk = ImageTk.PhotoImage(image=im)
videoLabel.configure(image=imageTk)
videoLabel.image = imageTk
videoLabel.update()
k = cv.waitKey(30) & 0xff
if k == 27:
break
prvs = next
elif typeOfVideo.get() == "Grayscale":
frame = cv.cvtColor(np.array(frameRaw.to_image()),
cv.COLOR_RGB2BGR)
frame1 = cv.resize(frame, (0, 0),
fx=VIDEO_SCALE,
fy=VIDEO_SCALE)
im = Image.fromarray(frame1, 'RGB')
gray = im.convert('L')
# Using numpy, convert pixels to pure black or white
bw = np.asarray(gray).copy()
im = Image.fromarray(bw)
imageTk = ImageTk.PhotoImage(image=im)
videoLabel.configure(image=imageTk)
videoLabel.image = imageTk
videoLabel.update()
elif typeOfVideo.get() == "BGR":
frame = cv.cvtColor(np.array(frameRaw.to_image()),
cv.COLOR_RGB2BGR)
frame1 = cv.resize(frame, (0, 0),
fx=VIDEO_SCALE,
fy=VIDEO_SCALE)
im = Image.fromarray(frame1)
imageTk = ImageTk.PhotoImage(image=im)
videoLabel.configure(image=imageTk)
videoLabel.image = imageTk
videoLabel.update()
elif typeOfVideo.get() == "Black & White":
frame = cv.cvtColor(np.array(frameRaw.to_image()),
cv.COLOR_RGB2BGR)
frame1 = cv.resize(frame, (0, 0),
fx=VIDEO_SCALE,
fy=VIDEO_SCALE)
im = Image.fromarray(frame1, 'RGB')
gray = im.convert('L')
# Using numpy, convert pixels to pure black or white
bw = np.asarray(gray).copy()
# Pixel range is 0...255, 256/2 = 128
bw[bw < 128] = 0 # Black
bw[bw >= 128] = 255 # White
im = Image.fromarray(bw)
imageTk = ImageTk.PhotoImage(image=im)
videoLabel.configure(image=imageTk)
videoLabel.image = imageTk
videoLabel.update()
else: # typeOfVideo.get() == "Normal":
frame1 = np.array(frameRaw.to_image())
frame1 = cv.resize(frame1, (0, 0),
fx=VIDEO_SCALE,
fy=VIDEO_SCALE)
im = Image.fromarray(frame1, 'RGB')
imageTk = ImageTk.PhotoImage(image=im)
videoLabel.configure(image=imageTk)
videoLabel.image = imageTk
videoLabel.update()
ch = cv.waitKey(1)
if ch == 27:
break
except Exception as ex:
exc_type, exc_value, exc_traceback = sys.exc_info()
traceback.print_exception(exc_type, exc_value, exc_traceback)
print(ex)