File size: 6,385 Bytes
e338936 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 |
# pylint: disable=invalid-name, redefined-outer-name, missing-docstring, non-parent-init-called, trailing-whitespace, line-too-long
import cv2
import numpy as np
import tensorflow as tf
from tensorflow.python.keras.backend import set_session
class Label:
def __init__(self, cl=-1, tl=np.array([0., 0.]), br=np.array([0., 0.]), prob=None):
self.__tl = tl
self.__br = br
self.__cl = cl
self.__prob = prob
def __str__(self):
return 'Class: %d, top left(x: %f, y: %f), bottom right(x: %f, y: %f)' % (
self.__cl, self.__tl[0], self.__tl[1], self.__br[0], self.__br[1])
def copy(self):
return Label(self.__cl, self.__tl, self.__br)
def wh(self): return self.__br - self.__tl
def cc(self): return self.__tl + self.wh() / 2
def tl(self): return self.__tl
def br(self): return self.__br
def tr(self): return np.array([self.__br[0], self.__tl[1]])
def bl(self): return np.array([self.__tl[0], self.__br[1]])
def cl(self): return self.__cl
def area(self): return np.prod(self.wh())
def prob(self): return self.__prob
def set_class(self, cl):
self.__cl = cl
def set_tl(self, tl):
self.__tl = tl
def set_br(self, br):
self.__br = br
def set_wh(self, wh):
cc = self.cc()
self.__tl = cc - .5 * wh
self.__br = cc + .5 * wh
def set_prob(self, prob):
self.__prob = prob
class DLabel(Label):
def __init__(self, cl, pts, prob):
self.pts = pts
tl = np.amin(pts, axis=1)
br = np.amax(pts, axis=1)
Label.__init__(self, cl, tl, br, prob)
def getWH(shape):
return np.array(shape[1::-1]).astype(float)
def IOU(tl1, br1, tl2, br2):
wh1, wh2 = br1 - tl1, br2 - tl2
assert ((wh1 >= 0).all() and (wh2 >= 0).all())
intersection_wh = np.maximum(np.minimum(br1, br2) - np.maximum(tl1, tl2), 0)
intersection_area = np.prod(intersection_wh)
area1, area2 = (np.prod(wh1), np.prod(wh2))
union_area = area1 + area2 - intersection_area
return intersection_area / union_area
def IOU_labels(l1, l2):
return IOU(l1.tl(), l1.br(), l2.tl(), l2.br())
def nms(Labels, iou_threshold=0.5):
SelectedLabels = []
Labels.sort(key=lambda l: l.prob(), reverse=True)
for label in Labels:
non_overlap = True
for sel_label in SelectedLabels:
if IOU_labels(label, sel_label) > iou_threshold:
non_overlap = False
break
if non_overlap:
SelectedLabels.append(label)
return SelectedLabels
def find_T_matrix(pts, t_pts):
A = np.zeros((8, 9))
for i in range(0, 4):
xi = pts[:, i]
xil = t_pts[:, i]
xi = xi.T
A[i * 2, 3:6] = -xil[2] * xi
A[i * 2, 6:] = xil[1] * xi
A[i * 2 + 1, :3] = xil[2] * xi
A[i * 2 + 1, 6:] = -xil[0] * xi
[U, S, V] = np.linalg.svd(A)
H = V[-1, :].reshape((3, 3))
return H
def getRectPts(tlx, tly, brx, bry):
return np.matrix([[tlx, brx, brx, tlx], [tly, tly, bry, bry], [1, 1, 1, 1]], dtype=float)
def normal(pts, side, mn, MN):
pts_MN_center_mn = pts * side
pts_MN = pts_MN_center_mn + mn.reshape((2, 1))
pts_prop = pts_MN / MN.reshape((2, 1))
return pts_prop
# Reconstruction function from predict value into plate crpoped from image
def reconstruct(I, Iresized, Yr, lp_threshold):
# 4 max-pooling layers, stride = 2
net_stride = 2 ** 4
side = ((208 + 40) / 2) / net_stride
# one line and two lines license plate size
one_line = (470, 110)
two_lines = (280, 200)
Probs = Yr[..., 0]
Affines = Yr[..., 2:]
xx, yy = np.where(Probs > lp_threshold)
# CNN input image size
WH = getWH(Iresized.shape)
# output feature map size
MN = WH / net_stride
vxx = vyy = 0.5 # alpha
base = lambda vx, vy: np.matrix([[-vx, -vy, 1], [vx, -vy, 1], [vx, vy, 1], [-vx, vy, 1]]).T
labels = []
labels_frontal = []
for i in range(len(xx)):
x, y = xx[i], yy[i]
affine = Affines[x, y]
prob = Probs[x, y]
mn = np.array([float(y) + 0.5, float(x) + 0.5])
# affine transformation matrix
A = np.reshape(affine, (2, 3))
A[0, 0] = max(A[0, 0], 0)
A[1, 1] = max(A[1, 1], 0)
# identity transformation
B = np.zeros((2, 3))
B[0, 0] = max(A[0, 0], 0)
B[1, 1] = max(A[1, 1], 0)
pts = np.array(A * base(vxx, vyy))
pts_frontal = np.array(B * base(vxx, vyy))
pts_prop = normal(pts, side, mn, MN)
frontal = normal(pts_frontal, side, mn, MN)
labels.append(DLabel(0, pts_prop, prob))
labels_frontal.append(DLabel(0, frontal, prob))
final_labels = nms(labels, 0.1)
final_labels_frontal = nms(labels_frontal, 0.1)
# print(final_labels_frontal)
assert final_labels_frontal, "" # "No License plate is founded!"
# LP size and type
out_size, lp_type = (two_lines, 2) if (
(final_labels_frontal[0].wh()[0] / final_labels_frontal[0].wh()[1]) < 1.7) else (one_line, 1)
TLp = []
Cor = []
if len(final_labels):
final_labels.sort(key=lambda x: x.prob(), reverse=True)
for _, label in enumerate(final_labels):
t_ptsh = getRectPts(0, 0, out_size[0], out_size[1])
ptsh = np.concatenate((label.pts * getWH(I.shape).reshape((2, 1)), np.ones((1, 4))))
H = find_T_matrix(ptsh, t_ptsh)
Ilp = cv2.warpPerspective(I, H, out_size, borderValue=0)
# cv2.imshow("plate", Ilp)
# cv2.waitKey(0)
TLp.append(Ilp)
Cor.append(ptsh)
return final_labels, TLp, lp_type, Cor
def detect_lp(graph, sess, model, I, max_dim, lp_threshold):
min_dim_img = min(I.shape[:2])
factor = float(max_dim) / min_dim_img
w, h = (np.array(I.shape[1::-1], dtype=float) * factor).astype(int).tolist()
Iresized = cv2.resize(I, (w, h))
T = Iresized.copy()
T = T.reshape((1, T.shape[0], T.shape[1], T.shape[2]))
with graph.as_default():
set_session(sess)
Yr = model.predict(T)
# print("1: ",Yr)
Yr = np.squeeze(Yr)
# print("2: ",Yr)
# print(Yr.shape)
L, TLp, lp_type, Cor = reconstruct(I, Iresized, Yr, lp_threshold)
return L, TLp, lp_type, Cor
|