def find_limbus_edge_pts(self, eye_roi, debug=False):
blurred_eye_roi_img = cv2.GaussianBlur(eye_roi.img, (5, 5), 5)
pupil_x0, pupil_y0 = eye_roi.img.shape[1] / 2, eye_roi.img.shape[0] / 2
min_limb_r = int(eye_roi.img.shape[0] * self.limb_r_ratios[0])
max_limb_r = int(eye_roi.img.shape[0] * self.limb_r_ratios[1])
pts_found = set()
pts_found = pts_found.union(
self.cast_rays_spread(bgr_img=blurred_eye_roi_img,
start_pos=(pupil_x0, pupil_y0),
angle_mean=0,
spread=120,
limb_r_range=(min_limb_r, max_limb_r)))
pts_found = pts_found.union(
self.cast_rays_spread(bgr_img=blurred_eye_roi_img,
start_pos=(pupil_x0, pupil_y0),
angle_mean=180,
spread=120,
limb_r_range=(min_limb_r, max_limb_r)))
if debug:
debug_img = blurred_eye_roi_img.copy()
cv2.circle(blurred_eye_roi_img,
(eye_roi.img.shape[1] / 2, eye_roi.img.shape[0] / 2),
min_limb_r, (255, 255, 0))
cv2.circle(blurred_eye_roi_img,
(eye_roi.img.shape[1] / 2, eye_roi.img.shape[0] / 2),
max_limb_r, (255, 255, 0))
draw_cross(debug_img, (pupil_x0, pupil_y0),
color=(255, 255, 0),
width=6)
draw_points(debug_img,
pts_found, (0, 0, 255),
width=1,
thickness=2)
stacked_imgs = np.concatenate(
[eye_roi.img, blurred_eye_roi_img, debug_img], axis=1)
if debug == 1:
self.full_debug_img = stacked_imgs
elif debug == 2:
self.full_debug_img = stack_imgs_vertical(
[self.full_debug_img, stacked_imgs])
cv2.imshow(winname, self.full_debug_img)
elif debug == 3:
cv2.imshow(winname, stacked_imgs)
return pts_found
def find_limbus_edge_pts(self, eye_roi, debug=False):
blurred_eye_roi_img = cv2.GaussianBlur(eye_roi.img, (5, 5), 5)
pupil_x0, pupil_y0 = eye_roi.img.shape[1] / 2, eye_roi.img.shape[0] / 2
min_limb_r = int(eye_roi.img.shape[0] * self.limb_r_ratios[0])
max_limb_r = int(eye_roi.img.shape[0] * self.limb_r_ratios[1])
pts_found = set()
pts_found = pts_found.union(self.cast_rays_spread(bgr_img=blurred_eye_roi_img,
start_pos=(pupil_x0, pupil_y0),
angle_mean=0, spread=120,
limb_r_range=(min_limb_r, max_limb_r)))
pts_found = pts_found.union(self.cast_rays_spread(bgr_img=blurred_eye_roi_img,
start_pos=(pupil_x0, pupil_y0),
angle_mean=180, spread=120,
limb_r_range=(min_limb_r, max_limb_r)))
if debug:
debug_img = blurred_eye_roi_img.copy()
cv2.circle(blurred_eye_roi_img, (eye_roi.img.shape[1] / 2, eye_roi.img.shape[0] / 2), min_limb_r, (255, 255, 0))
cv2.circle(blurred_eye_roi_img, (eye_roi.img.shape[1] / 2, eye_roi.img.shape[0] / 2), max_limb_r, (255, 255, 0))
draw_cross(debug_img, (pupil_x0, pupil_y0), color=(255, 255, 0), width=6)
draw_points(debug_img, pts_found, (0, 0, 255), width=1, thickness=2)
stacked_imgs = np.concatenate([eye_roi.img, blurred_eye_roi_img, debug_img], axis=1)
if debug == 1:
self.full_debug_img = stacked_imgs
elif debug == 2:
self.full_debug_img = stack_imgs_vertical([self.full_debug_img, stacked_imgs])
cv2.imshow(winname, self.full_debug_img)
elif debug == 3:
cv2.imshow(winname, stacked_imgs);
return pts_found
def get_limb_pts(eye_img, phi=20, angle_step=1, debug_index=False):
polar_img_w = 360 / angle_step # Polar image has one column per angle of interest
phi_range_1 = ((90 - phi) / angle_step, (90 + phi) / angle_step
) # Ranges of angles to be ignored (too close to lids)
phi_range_2 = ((270 - phi) / angle_step, (270 + phi) / angle_step)
eye_img_grey = cv2.cvtColor(eye_img, cv2.COLOR_BGR2GRAY) # Do BGR-grey
eye_img_grey = cv2.medianBlur(eye_img_grey, 5)
# Scale to fixed size image for re-using transform matrix
scale = eye_img.shape[0] / float(__fixed_width)
img_fixed_size = cv2.resize(eye_img_grey, (__fixed_width, __fixed_width))
# Transform image into polar coords and blur
img_polar = linpolar(img_fixed_size,
trans_w=polar_img_w,
trans_h=__fixed_width / 2)
img_polar = cv2.GaussianBlur(img_polar, (5, 5), 0)
# Take the segment between min & max radii and filter with Gabor kernel
img_polar_seg = img_polar[__min_limb_r:__max_limb_r, :]
filter_img = cv2.filter2D(img_polar_seg, -1, __gabor_kern)
# Black out ignored angles
filter_img.T[phi_range_1[0]:phi_range_1[1]] = 0
filter_img.T[phi_range_2[0]:phi_range_2[1]] = 0
# In polar image, x <-> theta, y <-> magnitude
pol_ys = np.argmax(filter_img,
axis=0) # Take highest filter response as limbus points
pol_xs = np.arange(filter_img.shape[1])[pol_ys > 0]
mags = (pol_ys + __min_limb_r)[pol_ys > 0]
thts = np.radians(pol_xs * angle_step)
# Translate each point back into fixed img coords
xs, ys = cv2.polarToCart(mags.astype(float), thts)
xs = (
xs + __fixed_width / 2
) * scale # Shift and scale cart. coords back to original eye-ROI coords
ys = (ys + __fixed_width / 2) * scale
# Points returned in form
# [[ x1 y1]
# [ x2 y2]
# ...
# [ xn yn]]
pts_cart = np.concatenate([xs, ys], axis=1)
# --------------------- Debug Drawing ---------------------
if debug_index != False:
debug_img = eye_img.copy()
debug_polar = cv2.cvtColor(img_polar, cv2.COLOR_GRAY2BGR)
cv2.imwrite("polar.jpg", debug_polar)
cv2.line(debug_polar, (0, __min_limb_r),
(img_polar.shape[1], __min_limb_r), (255, 255, 0))
cv2.line(debug_polar, (0, __max_limb_r),
(img_polar.shape[1], __max_limb_r), (255, 255, 0))
cv2.circle(debug_img, (debug_img.shape[1] / 2, debug_img.shape[0] / 2),
int(debug_img.shape[0] * __limb_r_ratios[0]), (255, 255, 0))
cv2.circle(debug_img, (debug_img.shape[1] / 2, debug_img.shape[0] / 2),
int(debug_img.shape[0] * __limb_r_ratios[1]), (255, 255, 0))
pts_polar = np.squeeze(np.dstack([pol_xs, mags]))
draw_points(debug_polar, pts_polar, (0, 0, 255), width=1)
draw_points(debug_img, pts_cart, (0, 0, 255), width=1)
stacked_imgs_polar = stack_imgs_vertical([debug_polar, filter_img])
stacked_imgs = stack_imgs_horizontal(
[debug_img, eye_img_grey, stacked_imgs_polar])
__debug_imgs[debug_index] = stacked_imgs
if debug_index == 2:
full_debug_img = stack_imgs_vertical(
[__debug_imgs[1], __debug_imgs[2]])
cv2.imshow(__winname, full_debug_img)
elif debug_index > 2:
cv2.imshow(__winname, stacked_imgs)
# --------------------- Debug Drawing ---------------------
return pts_cart
def find_lower_eyelid(eye_img, debug_index):
line_y_offset = 0 # Amount to shift eye-lid by after detection
img_blue = cv2.split(eye_img)[2]
img_w, img_h = eye_img.shape[:2]
# Indexes to extract window sub-images
w_y1, w_y2 = int(img_h * __l_win_rats_h[0]), int(img_h *
sum(__l_win_rats_h[:2]))
wl_x1, wl_x2 = int(img_w * __l_win_rats_w_l[0]), int(
img_w * sum(__l_win_rats_w_l[:2]))
wr_x1, wr_x2 = int(img_w * __l_win_rats_w_r[0]), int(
img_w * sum(__l_win_rats_w_r[:2]))
# Split image into two halves
window_img_l = img_blue[w_y1:w_y2, wl_x1:wl_x2]
window_img_r = img_blue[w_y1:w_y2, wr_x1:wr_x2]
window_img_l = cv2.GaussianBlur(window_img_l, (5, 5), 20)
window_img_r = cv2.GaussianBlur(window_img_r, (5, 5), 20)
filter_img_l = cv2.filter2D(window_img_l, -1, __gabor_kern_diag)
filter_img_r = cv2.filter2D(window_img_r, -1,
cv2.flip(__gabor_kern_diag, 1))
filter_img = np.concatenate([filter_img_l, filter_img_r], axis=1)
# In polar image, x <-> theta, y <-> magnitude
max_vals = np.max(filter_img, axis=0)
ys = np.argmax(filter_img,
axis=0) # Take highest filter response as limbus points
xs = (np.arange(filter_img.shape[1]) + wl_x1)[max_vals > __min_thresh]
ys = (ys + w_y1)[max_vals > __min_thresh]
l_lid_pts = np.squeeze(np.dstack([xs, ys]), axis=0)
# Only RANSAC fit eyelid if there are enough points
if l_lid_pts.size < __min_num_pts_u * 2:
eyelid_lower_line = None
else:
eyelid_lower_line = ransac_line(l_lid_pts)
if eyelid_lower_line is not None:
a, b = eyelid_lower_line
b = b + line_y_offset
eyelid_lower_line = a, b
if debug_index:
debug_img = eye_img.copy()
filter_img = cv2.cvtColor(filter_img, cv2.COLOR_GRAY2BGR)
if l_lid_pts.size > 2:
draw_points(debug_img, l_lid_pts, (0, 0, 255), 1, 2)
if eyelid_lower_line is not None:
cv2.line(debug_img, (0, int(b)), (img_w, int(a * img_w + b)),
(0, 255, 0))
window_img = np.concatenate([window_img_l, window_img_r], axis=1)
stacked_windows = stack_imgs_vertical([window_img, filter_img])
stacked_imgs = stack_imgs_horizontal([stacked_windows, debug_img])
__debug_imgs_lower[debug_index] = stacked_imgs
if debug_index > 2:
cv2.imshow(__winname + repr(debug_index) + "l", stacked_imgs)
return eyelid_lower_line
def find_upper_eyelid(eye_img, debug_index):
u_2_win_rats_w = [0.0, 1.0, 0.0] # Margins around ROI windows
u_2_win_rats_h = [0.0, 0.5, 0.5]
# FIXME - using r channel?
img_blue = cv2.split(eye_img)[2]
img_w, img_h = eye_img.shape[:2]
# Indexes to extract window sub-images
w_y1, w_y2 = int(img_h * u_2_win_rats_h[0]), int(img_h *
sum(u_2_win_rats_h[:2]))
w_x1, w_x2 = int(img_w * u_2_win_rats_w[0]), int(img_w *
sum(u_2_win_rats_w[:2]))
# Split image into two halves
window_img = img_blue[w_y1:w_y2, w_x1:w_x2]
# Supress eyelashes
morph_kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (5, 5))
window_img = cv2.morphologyEx(window_img, cv2.MORPH_CLOSE, morph_kernel)
# Filter right half with inverse kernel of left half to ignore iris/sclera boundary
filter_img_win = cv2.filter2D(window_img, -1, __gabor_kern_horiz)
# Copy windows back into correct places in full filter image
filter_img = np.zeros(eye_img.shape[:2], dtype=np.uint8)
filter_img[w_y1:w_y2, w_x1:w_x2] = filter_img_win
# Mask with circles
cv2.circle(filter_img,
(3 * filter_img.shape[1] / 7, filter_img.shape[0] / 2),
filter_img.shape[1] / 4, 0, -1)
cv2.circle(filter_img,
(4 * filter_img.shape[1] / 7, filter_img.shape[0] / 2),
filter_img.shape[1] / 4, 0, -1)
ys = np.argmax(filter_img, axis=0)
xs = np.arange(filter_img.shape[1])[ys > 0]
ys = (ys)[ys > 0]
u_lid_pts = []
for i, x in enumerate(xs):
col = filter_img.T[x]
start_ind, end_ind = ys[i] + 5, min(ys[i] + 100, len(col) - 2)
col_window = col[start_ind:end_ind]
max_col = np.max(col)
max_win = np.max(col_window)
if max_col - max_win < 50:
new_y = np.argmax(col_window) + ys[i] + 5
u_lid_pts.append((x, new_y))
else:
u_lid_pts.append((x, ys[i]))
# Only RANSAC fit eyelid if there are enough points
if len(u_lid_pts) < __min_num_pts_u * 2:
eyelid_upper_parabola = None
u_lid_pts = []
else:
u_lid_pts_l = [(x, y) for (x, y) in u_lid_pts
if x < filter_img.shape[1] / 2]
u_lid_pts_r = [(x, y) for (x, y) in u_lid_pts
if x > filter_img.shape[1] / 2]
# Fit eye_img coord points of sclera-segs to degree 2 polynomial
# a(x^2) + b(x) + c
eyelid_upper_parabola = ransac_parabola(u_lid_pts_l,
u_lid_pts_r,
ransac_iters_max=5,
refine_iters_max=2,
max_err=4)
if eyelid_upper_parabola is not None:
a, b, c = eyelid_upper_parabola
c = c - __parabola_y_offset
eyelid_upper_parabola = a, b, c
# --------------------- Debug Drawing ---------------------
if debug_index:
debug_img = eye_img.copy()
if eyelid_upper_parabola is not None:
lid_xs = np.arange(21) * img_w / 20
lid_ys = a * lid_xs**2 + b * lid_xs + c
lid_pts = np.dstack([lid_xs, lid_ys]).astype(int)
cv2.polylines(debug_img, lid_pts, False, (0, 255, 0), 1)
draw_points(debug_img, u_lid_pts, (0, 0, 255), 1, 2)
filter_img = cv2.cvtColor(filter_img, cv2.COLOR_GRAY2BGR)
draw_points(filter_img, u_lid_pts, (0, 0, 255), 1, 2)
stacked_windows = stack_imgs_vertical([window_img, filter_img])
stacked_imgs = stack_imgs_horizontal([stacked_windows, debug_img])
__debug_imgs_upper[debug_index] = stacked_imgs
if debug_index > 2:
cv2.imshow(__winname + repr(debug_index) + "u", stacked_imgs)
# --------------------- Debug Drawing ---------------------
return eyelid_upper_parabola
def get_gaze_from_frame(self, frame):
frame = cv2.undistort(frame, cam_mat_n7, dist_coefs_n7)
frame_pyr = image_utils.make_gauss_pyr(frame, 4)
full_frame = frame_pyr[1].copy()
half_frame = frame_pyr[2].copy()
limbuses = [None, None]
gaze_pts_mm = [None, None]
gaze_pts_px = [None, None]
try:
sub_img_cx0, sub_img_cy0 = None, None
eye_r_roi, eye_l_roi = eye_extractor.get_eye_rois(
frame_pyr, 4, debug=self.debug, device=self.device)
for i, eye_roi in enumerate([eye_r_roi, eye_l_roi]):
try:
if eye_roi.img is None: break
# Gives unique winnames for each ROI
debug_index = ((i + 1) if self.debug else False)
eye_roi.img = self.pre_proc.erase_specular(
eye_roi.img, debug=debug_index)
pupil_x0, pupil_y0 = eye_center_locator_combined.find_pupil(
eye_roi.img,
fast_width_grads=25.0,
fast_width_iso=80.0,
weight_grads=0.8,
weight_iso=0.2,
debug_index=debug_index)
eye_roi.refine_pupil((pupil_x0, pupil_y0), full_frame)
roi_x0, roi_y0, roi_w, roi_h = eye_roi.roi_x0, eye_roi.roi_y0, eye_roi.roi_w, eye_roi.roi_h
u_eyelid, l_eyelid = find_eyelids(eye_roi.img, debug_index)
pts_found = get_limb_pts(eye_img=eye_roi.img,
phi=20,
angle_step=1,
debug_index=debug_index)
pts_found = eyelid_locator.filter_limbus_pts(
u_eyelid, l_eyelid, pts_found)
ellipse = ransac_ellipse.ransac_ellipse_fit(
points=pts_found,
bgr_img=eye_roi.img,
roi_pos=(roi_x0, roi_y0),
ransac_iters_max=5,
refine_iters_max=3,
max_err=1,
debug=False)
# Shift 2D limbus ellipse and points to account for eye ROI coords
(ell_x0, ell_y0), (ell_w,
ell_h), angle = ellipse.rotated_rect
new_rotated_rect = (roi_x0 + ell_x0,
roi_y0 + ell_y0), (ell_w, ell_h), angle
ellipse = Ellipse(new_rotated_rect)
pts_found_to_draw = [(px + roi_x0, py + roi_y0)
for (px, py) in pts_found]
# Correct coords when extracting eye for half-frame
(sub_img_cx0, sub_img_cy0) = (roi_x0 + ell_x0,
roi_y0 + ell_y0)
# Ignore incorrect limbus
limbus = gaze_geometry.ellipse_to_limbuses_persp_geom(
ellipse, self.device)
limbuses[i] = limbus
# Draw eye features onto debug image
draw_utils.draw_limbus(full_frame,
limbus,
color=debug_colors[i],
scale=1)
draw_utils.draw_points(full_frame,
pts_found_to_draw,
color=debug_colors[i],
width=1,
thickness=2)
draw_utils.draw_normal(full_frame,
limbus,
self.device,
color=debug_colors[i],
scale=1)
draw_utils.draw_normal(half_frame,
limbus,
self.device,
color=debug_colors[i],
scale=0.5,
arrow_len_mm=20)
eye_img = full_frame[eye_roi.roi_y0:(eye_roi.roi_y0 +
eye_roi.roi_h),
eye_roi.roi_x0:(eye_roi.roi_x0 +
eye_roi.roi_w)]
draw_utils.draw_eyelids(u_eyelid, l_eyelid, eye_img)
except ransac_ellipse.NoEllipseFound:
if self.debug: print 'No Ellipse Found'
cv2.rectangle(full_frame, (roi_x0, roi_y0),
(roi_x0 + roi_w, roi_y0 + roi_h),
(0, 0, 255),
thickness=4)
except ransac_ellipse.CoverageTooLow as e:
if self.debug:
print 'Ellipse Coverage Too Low : %s' % e.msg
cv2.rectangle(full_frame, (roi_x0, roi_y0),
(roi_x0 + roi_w, roi_y0 + roi_h),
(0, 0, 255),
thickness=4)
finally:
# Extract only eye_roi block after other drawing methods
if sub_img_cx0 is not None:
eye_img = full_frame[sub_img_cy0 - 60:sub_img_cy0 + 60,
sub_img_cx0 - 60:sub_img_cx0 + 60]
else:
eye_img = full_frame[eye_roi.roi_y0:(eye_roi.roi_y0 +
eye_roi.roi_h),
eye_roi.roi_x0:(eye_roi.roi_x0 +
eye_roi.roi_w)]
# Transfer eye_img block to section of half_frame
half_frame[half_frame.shape[0] -
eye_img.shape[0]:half_frame.shape[0],
(half_frame.shape[1] - eye_img.shape[1]) *
i:half_frame.shape[1] if i else eye_img.
shape[1]] = eye_img
except eye_extractor.NoEyesFound as e:
if self.debug: print 'No Eyes Found: %s' % e.msg
# Remove any extreme outliers
limbuses = limbus_outlier_removal.remove_outliers(limbuses)
# Get gaze points
for i, limbus in enumerate(limbuses):
if limbus is None: continue
gaze_pts_mm[i] = gaze_geometry.get_gaze_point_mm(limbus)
gaze_pts_px[i] = gaze_geometry.convert_gaze_pt_mm_to_px(
gaze_pts_mm[i], self.device)
smoothed_gaze_pt_mm = self.smoother.smooth_gaze(gaze_pts_mm)
smoothed_gaze_pt_px = gaze_geometry.convert_gaze_pt_mm_to_px(
smoothed_gaze_pt_mm, self.device)
# Visualize in 2D and 3D
cv2.imshow('gaze system', half_frame)
self.visualizer3d.update_vis(limbuses, smoothed_gaze_pt_mm)
# If recording, take a screenshot of vpython and add to vid. capture
if self.recording:
vis_screen = self.visualizer3d.take_screenshot()
stacked_imgs = image_utils.stack_imgs_horizontal(
[vis_screen, half_frame])
self.vid_writer.write(stacked_imgs)
return smoothed_gaze_pt_px
def find_lower_eyelid(eye_img, debug_index):
line_y_offset = 0 # Amount to shift eye-lid by after detection
img_blue = cv2.split(eye_img)[2]
img_w, img_h = eye_img.shape[:2]
# Indexes to extract window sub-images
w_y1, w_y2 = int(img_h * __l_win_rats_h[0]), int(img_h * sum(__l_win_rats_h[:2]))
wl_x1, wl_x2 = int(img_w * __l_win_rats_w_l[0]), int(img_w * sum(__l_win_rats_w_l[:2]))
wr_x1, wr_x2 = int(img_w * __l_win_rats_w_r[0]), int(img_w * sum(__l_win_rats_w_r[:2]))
# Split image into two halves
window_img_l = img_blue[w_y1:w_y2, wl_x1:wl_x2]
window_img_r = img_blue[w_y1:w_y2, wr_x1:wr_x2]
window_img_l = cv2.GaussianBlur(window_img_l, (5, 5), 20)
window_img_r = cv2.GaussianBlur(window_img_r, (5, 5), 20)
filter_img_l = cv2.filter2D(window_img_l, -1, __gabor_kern_diag)
filter_img_r = cv2.filter2D(window_img_r, -1, cv2.flip(__gabor_kern_diag, 1))
filter_img = np.concatenate([filter_img_l, filter_img_r], axis=1)
# In polar image, x <-> theta, y <-> magnitude
max_vals = np.max(filter_img, axis=0)
ys = np.argmax(filter_img, axis=0) # Take highest filter response as limbus points
xs = (np.arange(filter_img.shape[1]) + wl_x1)[max_vals > __min_thresh]
ys = (ys + w_y1)[max_vals > __min_thresh]
l_lid_pts = np.squeeze(np.dstack([xs, ys]), axis=0)
# Only RANSAC fit eyelid if there are enough points
if l_lid_pts.size < __min_num_pts_u * 2:
eyelid_lower_line = None
else:
eyelid_lower_line = ransac_line(l_lid_pts)
if eyelid_lower_line is not None:
a, b = eyelid_lower_line
b = b + line_y_offset
eyelid_lower_line = a, b
if debug_index:
debug_img = eye_img.copy()
filter_img = cv2.cvtColor(filter_img, cv2.COLOR_GRAY2BGR)
if l_lid_pts.size > 2:
draw_points(debug_img, l_lid_pts, (0, 0, 255), 1, 2)
if eyelid_lower_line is not None:
cv2.line(debug_img, (0, int(b)), (img_w, int(a * img_w + b)), (0, 255, 0))
window_img = np.concatenate([window_img_l, window_img_r], axis=1)
stacked_windows = stack_imgs_vertical([window_img, filter_img])
stacked_imgs = stack_imgs_horizontal([stacked_windows, debug_img])
__debug_imgs_lower[debug_index] = stacked_imgs
if debug_index > 2:
cv2.imshow(__winname + repr(debug_index) + "l", stacked_imgs)
return eyelid_lower_line
def find_upper_eyelid(eye_img, debug_index):
u_2_win_rats_w = [0.0, 1.0, 0.0] # Margins around ROI windows
u_2_win_rats_h = [0.0, 0.5, 0.5]
# FIXME - using r channel?
img_blue = cv2.split(eye_img)[2]
img_w, img_h = eye_img.shape[:2]
# Indexes to extract window sub-images
w_y1, w_y2 = int(img_h * u_2_win_rats_h[0]), int(img_h * sum(u_2_win_rats_h[:2]))
w_x1, w_x2 = int(img_w * u_2_win_rats_w[0]), int(img_w * sum(u_2_win_rats_w[:2]))
# Split image into two halves
window_img = img_blue[w_y1:w_y2, w_x1:w_x2]
# Supress eyelashes
morph_kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (5, 5))
window_img = cv2.morphologyEx(window_img, cv2.MORPH_CLOSE, morph_kernel)
# Filter right half with inverse kernel of left half to ignore iris/sclera boundary
filter_img_win = cv2.filter2D(window_img, -1, __gabor_kern_horiz)
# Copy windows back into correct places in full filter image
filter_img = np.zeros(eye_img.shape[:2], dtype=np.uint8)
filter_img[w_y1:w_y2, w_x1:w_x2] = filter_img_win
# Mask with circles
cv2.circle(filter_img, (3 * filter_img.shape[1] / 7, filter_img.shape[0] / 2), filter_img.shape[1] / 4, 0, -1)
cv2.circle(filter_img, (4 * filter_img.shape[1] / 7, filter_img.shape[0] / 2), filter_img.shape[1] / 4, 0, -1)
ys = np.argmax(filter_img, axis=0)
xs = np.arange(filter_img.shape[1])[ys > 0]
ys = (ys)[ys > 0]
u_lid_pts = []
for i, x in enumerate(xs):
col = filter_img.T[x]
start_ind, end_ind = ys[i] + 5, min(ys[i] + 100, len(col) - 2)
col_window = col[start_ind:end_ind]
max_col = np.max(col)
max_win = np.max(col_window)
if max_col - max_win < 50:
new_y = np.argmax(col_window) + ys[i] + 5
u_lid_pts.append((x, new_y))
else:
u_lid_pts.append((x, ys[i]))
# Only RANSAC fit eyelid if there are enough points
if len(u_lid_pts) < __min_num_pts_u * 2:
eyelid_upper_parabola = None
u_lid_pts = []
else:
u_lid_pts_l = [(x, y) for (x, y) in u_lid_pts if x < filter_img.shape[1] / 2]
u_lid_pts_r = [(x, y) for (x, y) in u_lid_pts if x > filter_img.shape[1] / 2]
# Fit eye_img coord points of sclera-segs to degree 2 polynomial
# a(x^2) + b(x) + c
eyelid_upper_parabola = ransac_parabola(
u_lid_pts_l, u_lid_pts_r, ransac_iters_max=5, refine_iters_max=2, max_err=4
)
if eyelid_upper_parabola is not None:
a, b, c = eyelid_upper_parabola
c = c - __parabola_y_offset
eyelid_upper_parabola = a, b, c
# --------------------- Debug Drawing ---------------------
if debug_index:
debug_img = eye_img.copy()
if eyelid_upper_parabola is not None:
lid_xs = np.arange(21) * img_w / 20
lid_ys = a * lid_xs ** 2 + b * lid_xs + c
lid_pts = np.dstack([lid_xs, lid_ys]).astype(int)
cv2.polylines(debug_img, lid_pts, False, (0, 255, 0), 1)
draw_points(debug_img, u_lid_pts, (0, 0, 255), 1, 2)
filter_img = cv2.cvtColor(filter_img, cv2.COLOR_GRAY2BGR)
draw_points(filter_img, u_lid_pts, (0, 0, 255), 1, 2)
stacked_windows = stack_imgs_vertical([window_img, filter_img])
stacked_imgs = stack_imgs_horizontal([stacked_windows, debug_img])
__debug_imgs_upper[debug_index] = stacked_imgs
if debug_index > 2:
cv2.imshow(__winname + repr(debug_index) + "u", stacked_imgs)
# --------------------- Debug Drawing ---------------------
return eyelid_upper_parabola
def get_limb_pts(eye_img, phi=20, angle_step=1, debug_index=False):
polar_img_w = 360 / angle_step # Polar image has one column per angle of interest
phi_range_1 = ((90 - phi) / angle_step, (90 + phi) / angle_step) # Ranges of angles to be ignored (too close to lids)
phi_range_2 = ((270 - phi) / angle_step, (270 + phi) / angle_step)
eye_img_grey = cv2.cvtColor(eye_img, cv2.COLOR_BGR2GRAY) # Do BGR-grey
eye_img_grey = cv2.medianBlur(eye_img_grey, 5)
# Scale to fixed size image for re-using transform matrix
scale = eye_img.shape[0] / float(__fixed_width)
img_fixed_size = cv2.resize(eye_img_grey, (__fixed_width, __fixed_width))
# Transform image into polar coords and blur
img_polar = linpolar(img_fixed_size, trans_w=polar_img_w, trans_h=__fixed_width / 2)
img_polar = cv2.GaussianBlur(img_polar, (5, 5), 0)
# Take the segment between min & max radii and filter with Gabor kernel
img_polar_seg = img_polar[__min_limb_r:__max_limb_r, :]
filter_img = cv2.filter2D(img_polar_seg, -1, __gabor_kern)
# Black out ignored angles
filter_img.T[ phi_range_1[0] : phi_range_1[1] ] = 0
filter_img.T[ phi_range_2[0] : phi_range_2[1] ] = 0
# In polar image, x <-> theta, y <-> magnitude
pol_ys = np.argmax(filter_img, axis=0) # Take highest filter response as limbus points
pol_xs = np.arange(filter_img.shape[1])[pol_ys > 0]
mags = (pol_ys + __min_limb_r)[pol_ys > 0]
thts = np.radians(pol_xs * angle_step)
# Translate each point back into fixed img coords
xs, ys = cv2.polarToCart(mags.astype(float), thts)
xs = (xs + __fixed_width / 2) * scale # Shift and scale cart. coords back to original eye-ROI coords
ys = (ys + __fixed_width / 2) * scale
# Points returned in form
# [[ x1 y1]
# [ x2 y2]
# ...
# [ xn yn]]
pts_cart = np.concatenate([xs, ys], axis=1)
# --------------------- Debug Drawing ---------------------
if debug_index != False:
debug_img = eye_img.copy()
debug_polar = cv2.cvtColor(img_polar, cv2.COLOR_GRAY2BGR)
cv2.imwrite("polar.jpg",debug_polar)
cv2.line(debug_polar, (0, __min_limb_r), (img_polar.shape[1], __min_limb_r), (255, 255, 0))
cv2.line(debug_polar, (0, __max_limb_r), (img_polar.shape[1], __max_limb_r), (255, 255, 0))
cv2.circle(debug_img, (debug_img.shape[1] / 2, debug_img.shape[0] / 2), int(debug_img.shape[0] * __limb_r_ratios[0]), (255, 255, 0))
cv2.circle(debug_img, (debug_img.shape[1] / 2, debug_img.shape[0] / 2), int(debug_img.shape[0] * __limb_r_ratios[1]), (255, 255, 0))
pts_polar = np.squeeze(np.dstack([pol_xs, mags]))
draw_points(debug_polar, pts_polar, (0, 0, 255), width=1)
draw_points(debug_img, pts_cart, (0, 0, 255), width=1)
stacked_imgs_polar = stack_imgs_vertical([debug_polar, filter_img])
stacked_imgs = stack_imgs_horizontal([debug_img, eye_img_grey, stacked_imgs_polar])
__debug_imgs[debug_index] = stacked_imgs
if debug_index == 2:
full_debug_img = stack_imgs_vertical([__debug_imgs[1], __debug_imgs[2]]);
cv2.imshow(__winname, full_debug_img)
elif debug_index > 2:
cv2.imshow(__winname, stacked_imgs);
# --------------------- Debug Drawing ---------------------
return pts_cart
def get_gaze_from_frame(self, frame):
frame = cv2.undistort(frame, cam_mat_n7, dist_coefs_n7)
frame_pyr = image_utils.make_gauss_pyr(frame, 4)
full_frame = frame_pyr[1].copy()
half_frame = frame_pyr[2].copy()
limbuses = [None, None]
gaze_pts_mm = [None, None]
gaze_pts_px = [None, None]
try:
sub_img_cx0, sub_img_cy0 = None, None
eye_r_roi, eye_l_roi = eye_extractor.get_eye_rois(frame_pyr, 4, debug=self.debug, device=self.device)
for i, eye_roi in enumerate([eye_r_roi, eye_l_roi]):
try:
if eye_roi.img is None: break
# Gives unique winnames for each ROI
debug_index = ((i + 1) if self.debug else False)
eye_roi.img = self.pre_proc.erase_specular(eye_roi.img, debug=debug_index)
pupil_x0, pupil_y0 = eye_center_locator_combined.find_pupil(eye_roi.img,
fast_width_grads=25.0,
fast_width_iso=80.0,
weight_grads=0.8,
weight_iso=0.2,
debug_index=debug_index)
eye_roi.refine_pupil((pupil_x0, pupil_y0), full_frame)
roi_x0, roi_y0, roi_w, roi_h = eye_roi.roi_x0, eye_roi.roi_y0, eye_roi.roi_w, eye_roi.roi_h
u_eyelid, l_eyelid = find_eyelids(eye_roi.img, debug_index)
pts_found = get_limb_pts(eye_img=eye_roi.img,
phi=20,
angle_step=1,
debug_index=debug_index)
pts_found = eyelid_locator.filter_limbus_pts(u_eyelid, l_eyelid, pts_found)
ellipse = ransac_ellipse.ransac_ellipse_fit(points=pts_found,
bgr_img=eye_roi.img,
roi_pos=(roi_x0, roi_y0),
ransac_iters_max=5,
refine_iters_max=3,
max_err=1,
debug=False)
# Shift 2D limbus ellipse and points to account for eye ROI coords
(ell_x0, ell_y0), (ell_w, ell_h), angle = ellipse.rotated_rect
new_rotated_rect = (roi_x0 + ell_x0, roi_y0 + ell_y0), (ell_w, ell_h), angle
ellipse = Ellipse(new_rotated_rect)
pts_found_to_draw = [(px + roi_x0, py + roi_y0) for (px, py) in pts_found]
# Correct coords when extracting eye for half-frame
(sub_img_cx0, sub_img_cy0) = (roi_x0 + ell_x0, roi_y0 + ell_y0)
# Ignore incorrect limbus
limbus = gaze_geometry.ellipse_to_limbuses_persp_geom(ellipse, self.device)
limbuses[i] = limbus
# Draw eye features onto debug image
draw_utils.draw_limbus(full_frame, limbus, color=debug_colors[i], scale=1)
draw_utils.draw_points(full_frame, pts_found_to_draw, color=debug_colors[i], width=1, thickness=2)
draw_utils.draw_normal(full_frame, limbus, self.device, color=debug_colors[i], scale=1)
draw_utils.draw_normal(half_frame, limbus, self.device, color=debug_colors[i], scale=0.5, arrow_len_mm=20)
eye_img = full_frame[eye_roi.roi_y0:(eye_roi.roi_y0 + eye_roi.roi_h),
eye_roi.roi_x0:(eye_roi.roi_x0 + eye_roi.roi_w)]
draw_utils.draw_eyelids(u_eyelid, l_eyelid, eye_img)
except ransac_ellipse.NoEllipseFound:
if self.debug: print 'No Ellipse Found'
cv2.rectangle(full_frame, (roi_x0, roi_y0), (roi_x0 + roi_w, roi_y0 + roi_h), (0, 0, 255), thickness=4)
except ransac_ellipse.CoverageTooLow as e:
if self.debug: print 'Ellipse Coverage Too Low : %s' % e.msg
cv2.rectangle(full_frame, (roi_x0, roi_y0), (roi_x0 + roi_w, roi_y0 + roi_h), (0, 0, 255), thickness=4)
finally:
# Extract only eye_roi block after other drawing methods
if sub_img_cx0 is not None:
eye_img = full_frame[sub_img_cy0 - 60:sub_img_cy0 + 60,
sub_img_cx0 - 60:sub_img_cx0 + 60]
else:
eye_img = full_frame[eye_roi.roi_y0:(eye_roi.roi_y0 + eye_roi.roi_h),
eye_roi.roi_x0:(eye_roi.roi_x0 + eye_roi.roi_w)]
# Transfer eye_img block to section of half_frame
half_frame[half_frame.shape[0] - eye_img.shape[0]:half_frame.shape[0],
(half_frame.shape[1] - eye_img.shape[1]) * i: half_frame.shape[1] if i else eye_img.shape[1]] = eye_img
except eye_extractor.NoEyesFound as e:
if self.debug: print 'No Eyes Found: %s' % e.msg
# Remove any extreme outliers
limbuses = limbus_outlier_removal.remove_outliers(limbuses)
# Get gaze points
for i, limbus in enumerate(limbuses):
if limbus is None: continue
gaze_pts_mm[i] = gaze_geometry.get_gaze_point_mm(limbus)
gaze_pts_px[i] = gaze_geometry.convert_gaze_pt_mm_to_px(gaze_pts_mm[i], self.device)
smoothed_gaze_pt_mm = self.smoother.smooth_gaze(gaze_pts_mm)
smoothed_gaze_pt_px = gaze_geometry.convert_gaze_pt_mm_to_px(smoothed_gaze_pt_mm, self.device)
# Visualize in 2D and 3D
cv2.imshow('gaze system', half_frame)
self.visualizer3d.update_vis(limbuses, smoothed_gaze_pt_mm)
# If recording, take a screenshot of vpython and add to vid. capture
if self.recording:
vis_screen = self.visualizer3d.take_screenshot()
stacked_imgs = image_utils.stack_imgs_horizontal([vis_screen, half_frame])
self.vid_writer.write(stacked_imgs)
return smoothed_gaze_pt_px
def ransac_ellipse_fit(points, bgr_img, roi_pos, ransac_iters_max=50, refine_iters_max=3, max_err=2, debug=False):
if points.size == 0: raise NoEllipseFound()
blurred_grey_img = cv2.blur(cv2.cvtColor(bgr_img, cv2.COLOR_BGR2GRAY), (3, 3))
image_dx = cv2.Sobel(blurred_grey_img, ddepth=cv2.CV_32F, dx=1, dy=0, ksize=5)
image_dy = cv2.Sobel(blurred_grey_img, ddepth=cv2.CV_32F, dx=0, dy=1, ksize=5)
pts_x, pts_y = np.split(points, 2, axis=1)
pts_x, pts_y = np.squeeze(pts_x), np.squeeze(pts_y)
if debug:
img_points = np.copy(bgr_img)
draw_points(img_points, points, (0, 0, 255), 1, 2)
cv2.imshow(winname, img_points)
cv2.waitKey()
best_ellipse = None
best_support = float('-inf')
best_inliers = None
# Points on right and left of predicted pupil location (center of ROI-img)
r_inds, l_inds = np.squeeze([pts_x > (bgr_img.shape[1] / 2)]), np.squeeze([pts_x < (bgr_img.shape[1] / 2)])
# Not enough points to start process
if r_inds.size < 3 or l_inds.size < 3: raise NoEllipseFound()
points_r = points[r_inds]
points_l = points[l_inds]
if len(points_r) < 3 or len(points_l) < 3: raise NoEllipseFound()
# Perform N RANSAC iterations
for ransac_iter in range(ransac_iters_max):
try:
sample = random.sample(points_r, 3) + (random.sample(points_l, 3))
ellipse = fit_ellipse(sample, bgr_img.shape[:2])
if debug:
img_least_sqs = np.copy(bgr_img)
draw_points(img_least_sqs, points, (0, 0, 255), 1, 2)
draw_points(img_least_sqs, sample, (0, 255, 255), 6, 2)
cv2.ellipse(img_least_sqs, ellipse.rotated_rect, (0, 255, 255), 1)
print 'initial fit: ' + str(ransac_iter + 1)
cv2.imshow(winname, img_least_sqs)
cv2.imwrite("ransac_initial" + str(ransac_iter) + ".png", img_least_sqs)
cv2.waitKey()
# Image-aware sample rejection
for (p_x, p_y) in sample:
grad_x, grad_y = ellipse.algebraic_gradient_dir((p_x, p_y))
dx, dy = image_dx[p_y][p_x], image_dy[p_y][p_x]
# If sample and ellipse gradients don't agree, move to next set of samples
if dx * grad_x + dy * grad_y <= 0:
if debug: print 'Sample and ellipse gradients do not agree, reject'
break
else: # Only continues for else-block did not break on above line (image-aware sample rejection)
# Iteratively refine inliers further
for _ in range(refine_iters_max):
pts_distances = ellipse.distances(pts_x, pts_y)
inlier_inds = np.squeeze([np.abs(get_err_scale(ellipse) * pts_distances) < max_err])
inliers = points[inlier_inds]
if len(inliers) < 5: raise NotEnoughInliers()
ellipse = fit_ellipse(inliers, bgr_img.shape[:2])
if debug:
img_refined = np.copy(bgr_img)
draw_points(img_refined, points, (0, 0, 255), 1, 2)
draw_points(img_refined, sample, (0, 255, 255), 6, 2)
cv2.ellipse(img_refined, ellipse.rotated_rect, (0, 255, 255), 1)
draw_points(img_refined, inliers, (0, 255, 0), 1, 2)
cv2.imshow(winname, img_refined)
cv2.waitKey()
# Calculate the image aware support of the ellipse
if image_aware_support:
inliers_pts_x, inliers_pts_y = np.split(inliers, 2, axis=1)
inliers_pts_x, inliers_pts_y = np.squeeze(inliers_pts_x), np.squeeze(inliers_pts_y)
# Ellipse gradients at inlier points
grads_x, grads_y = ellipse.algebraic_gradient_dirs(inliers_pts_x, inliers_pts_y)
# Image gradients at inlier points
dxs = image_dx[inliers_pts_y.astype(int), inliers_pts_x.astype(int)]
dys = image_dy[inliers_pts_y.astype(int), inliers_pts_x.astype(int)]
support = np.sum(dxs.dot(grads_x) + dys.dot(grads_y))
else: support = len(inliers)
if support > best_support:
best_ellipse = ellipse
best_support = support
best_inliers = inliers
# Early termination for > 95% inliers
print len(inliers) / float(len(points))
if len(inliers) / float(len(points)) > 0.95:
print "Early Termination"
break
except NotEnoughInliers:
if debug: print 'Not Enough Inliers'
except BadEllipseShape as e:
if debug: print 'Bad Ellipse Shape: %s' % e.msg
if best_ellipse == None:
raise NoEllipseFound()
coverage = calculate_coverage(best_ellipse, best_inliers)
if coverage < min_coverage:
raise CoverageTooLow('Minimum inlier coverage: %d, actual coverage: %d' % (min_coverage, coverage))
if debug:
img_bgr_img = np.copy(bgr_img)
cv2.ellipse(img_bgr_img, best_ellipse.rotated_rect, (0, 255, 0), 2)
cv2.imshow(winname, img_bgr_img)
cv2.waitKey()
return best_ellipse
def ransac_ellipse_fit(points,
bgr_img,
roi_pos,
ransac_iters_max=50,
refine_iters_max=3,
max_err=2,
debug=False):
if points.size == 0: raise NoEllipseFound()
blurred_grey_img = cv2.blur(cv2.cvtColor(bgr_img, cv2.COLOR_BGR2GRAY),
(3, 3))
image_dx = cv2.Sobel(blurred_grey_img,
ddepth=cv2.CV_32F,
dx=1,
dy=0,
ksize=5)
image_dy = cv2.Sobel(blurred_grey_img,
ddepth=cv2.CV_32F,
dx=0,
dy=1,
ksize=5)
pts_x, pts_y = np.split(points, 2, axis=1)
pts_x, pts_y = np.squeeze(pts_x), np.squeeze(pts_y)
if debug:
img_points = np.copy(bgr_img)
draw_points(img_points, points, (0, 0, 255), 1, 2)
cv2.imshow(winname, img_points)
cv2.waitKey()
best_ellipse = None
best_support = float('-inf')
best_inliers = None
# Points on right and left of predicted pupil location (center of ROI-img)
r_inds, l_inds = np.squeeze([pts_x > (bgr_img.shape[1] / 2)]), np.squeeze(
[pts_x < (bgr_img.shape[1] / 2)])
# Not enough points to start process
if r_inds.size < 3 or l_inds.size < 3: raise NoEllipseFound()
points_r = points[r_inds]
points_l = points[l_inds]
if len(points_r) < 3 or len(points_l) < 3: raise NoEllipseFound()
# Perform N RANSAC iterations
for ransac_iter in range(ransac_iters_max):
try:
sample = random.sample(points_r, 3) + (random.sample(points_l, 3))
ellipse = fit_ellipse(sample, bgr_img.shape[:2])
if debug:
img_least_sqs = np.copy(bgr_img)
draw_points(img_least_sqs, points, (0, 0, 255), 1, 2)
draw_points(img_least_sqs, sample, (0, 255, 255), 6, 2)
cv2.ellipse(img_least_sqs, ellipse.rotated_rect, (0, 255, 255),
1)
print 'initial fit: ' + str(ransac_iter + 1)
cv2.imshow(winname, img_least_sqs)
cv2.imwrite("ransac_initial" + str(ransac_iter) + ".png",
img_least_sqs)
cv2.waitKey()
# Image-aware sample rejection
for (p_x, p_y) in sample:
grad_x, grad_y = ellipse.algebraic_gradient_dir((p_x, p_y))
dx, dy = image_dx[p_y][p_x], image_dy[p_y][p_x]
# If sample and ellipse gradients don't agree, move to next set of samples
if dx * grad_x + dy * grad_y <= 0:
if debug:
print 'Sample and ellipse gradients do not agree, reject'
break
else: # Only continues for else-block did not break on above line (image-aware sample rejection)
# Iteratively refine inliers further
for _ in range(refine_iters_max):
pts_distances = ellipse.distances(pts_x, pts_y)
inlier_inds = np.squeeze([
np.abs(get_err_scale(ellipse) * pts_distances) <
max_err
])
inliers = points[inlier_inds]
if len(inliers) < 5: raise NotEnoughInliers()
ellipse = fit_ellipse(inliers, bgr_img.shape[:2])
if debug:
img_refined = np.copy(bgr_img)
draw_points(img_refined, points, (0, 0, 255), 1, 2)
draw_points(img_refined, sample, (0, 255, 255), 6, 2)
cv2.ellipse(img_refined, ellipse.rotated_rect,
(0, 255, 255), 1)
draw_points(img_refined, inliers, (0, 255, 0), 1, 2)
cv2.imshow(winname, img_refined)
cv2.waitKey()
# Calculate the image aware support of the ellipse
if image_aware_support:
inliers_pts_x, inliers_pts_y = np.split(inliers, 2, axis=1)
inliers_pts_x, inliers_pts_y = np.squeeze(
inliers_pts_x), np.squeeze(inliers_pts_y)
# Ellipse gradients at inlier points
grads_x, grads_y = ellipse.algebraic_gradient_dirs(
inliers_pts_x, inliers_pts_y)
# Image gradients at inlier points
dxs = image_dx[inliers_pts_y.astype(int),
inliers_pts_x.astype(int)]
dys = image_dy[inliers_pts_y.astype(int),
inliers_pts_x.astype(int)]
support = np.sum(dxs.dot(grads_x) + dys.dot(grads_y))
else:
support = len(inliers)
if support > best_support:
best_ellipse = ellipse
best_support = support
best_inliers = inliers
# Early termination for > 95% inliers
print len(inliers) / float(len(points))
if len(inliers) / float(len(points)) > 0.95:
print "Early Termination"
break
except NotEnoughInliers:
if debug: print 'Not Enough Inliers'
except BadEllipseShape as e:
if debug: print 'Bad Ellipse Shape: %s' % e.msg
if best_ellipse == None:
raise NoEllipseFound()
coverage = calculate_coverage(best_ellipse, best_inliers)
if coverage < min_coverage:
raise CoverageTooLow(
'Minimum inlier coverage: %d, actual coverage: %d' %
(min_coverage, coverage))
if debug:
img_bgr_img = np.copy(bgr_img)
cv2.ellipse(img_bgr_img, best_ellipse.rotated_rect, (0, 255, 0), 2)
cv2.imshow(winname, img_bgr_img)
cv2.waitKey()
return best_ellipse