def reconstruct(Iorig, I, Y, out_size, threshold=.9):
net_stride = 2**4
side = ((208. + 40.) / 2.) / net_stride # 7.75
Probs = Y[..., 0]
Affines = Y[..., 2:]
rx, ry = Y.shape[:2]
ywh = Y.shape[1::-1]
iwh = np.array(I.shape[1::-1], dtype=float).reshape((2, 1))
xx, yy = np.where(Probs > threshold)
WH = getWH(I.shape)
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 = []
for i in range(len(xx)):
y, x = xx[i], yy[i]
affine = Affines[y, x]
prob = Probs[y, x]
mn = np.array([float(x) + .5, float(y) + .5])
A = np.reshape(affine, (2, 3))
A[0, 0] = max(A[0, 0], 0.)
A[1, 1] = max(A[1, 1], 0.)
pts = np.array(A * base(vxx, vyy)) #*alpha
pts_MN_center_mn = pts * side
pts_MN = pts_MN_center_mn + mn.reshape((2, 1))
pts_prop = pts_MN / MN.reshape((2, 1))
labels.append(DLabel(0, pts_prop, prob))
final_labels = nms(labels, .1)
TLps = []
if len(final_labels):
final_labels.sort(key=lambda x: x.prob(), reverse=True)
for i, label in enumerate(final_labels):
t_ptsh = getRectPts(0, 0, out_size[0], out_size[1])
ptsh = np.concatenate((label.pts * getWH(Iorig.shape).reshape(
(2, 1)), np.ones((1, 4))))
H = find_T_matrix(ptsh, t_ptsh)
Ilp = cv2.warpPerspective(Iorig, H, out_size, borderValue=.0)
TLps.append(Ilp)
return final_labels, TLps
def reset_view(self):
self.cx, self.cy = .5, .5
wh = np.array([self.width, self.height], dtype=float)
self.zoom_factor = (wh / getWH(self.Iorig.shape)).min()
self.mouse_center = np.array([.5, .5])
self.angles = np.array([0., 0., 0.])
self._setPerspective()
def __pts2xys(self, pts):
N = pts.shape[1]
pts = pts * getWH(self.Iorig.shape).reshape((2, 1))
pts = np.concatenate((pts, np.ones((1, N))))
pts = np.squeeze(np.array(np.matmul(self.R, pts)))
pts = pts[:2] / pts[2]
return pts
def __pt2xy(self, pt):
pt = np.squeeze(
np.array(
np.matmul(self.R, np.append(pt * getWH(self.Iorig.shape),
1.))))
pt = pt[:2] / pt[2]
return tuple(pt.astype(int).tolist())
def augment_sample(I,pts, dim_w, dim_h, cls):
maxsum,maxangle = 50,np.array([20.,20.,25.])
angles = np.random.rand(3)*maxangle
if angles.sum() > maxsum:
angles = (angles/angles.sum())*(maxangle/maxangle.sum())
I = im2single(I)
iwh = getWH(I.shape)
# codigo original
# whratio = random.uniform(2., 4.)
# wsiz = random.uniform(dim * .2, dim * 1.)
# carro
if cls=='0':
whratio = random.uniform(2.75, 3.25)
wsiz = random.uniform(dim_w * .2, dim_w * 0.7)
else:
whratio = random.uniform(0.7, 1.2)
wsiz = random.uniform(dim_w * .2, dim_w * 0.7)
# whratio = 1.
# wsiz = random.uniform(dim_w*.2, dim_w*1.)
# moto
# whratio = random.uniform(0.7, 1.2)
# wsiz = random.uniform(dim_w * .3, dim_w * 0.7)
hsiz = wsiz/whratio
dx = random.uniform(0.,dim_w - wsiz)
dy = random.uniform(0.,dim_h - hsiz)
pph = getRectPts(dx,dy,dx+wsiz,dy+hsiz)
pts = pts*iwh.reshape((2,1))
T = find_T_matrix(pts2ptsh(pts),pph)
H = perspective_transform((dim_w,dim_h),angles=angles)
H = np.matmul(H,T)
Iroi,pts = project(I,H,pts,dim_w, dim_h)
# hsv_mod = np.random.rand(3).astype('float32')
# hsv_mod = (hsv_mod - .5)*.3
# hsv_mod[0] *= 360
# Iroi = hsv_transform(Iroi,hsv_mod)
Iroi = np.clip(Iroi,0.,1.)
pts = np.array(pts)
# if random.random() > .5:
# Iroi,pts = flip_image_and_pts(Iroi,pts)
tl,br = pts.min(1),pts.max(1)
llp = Label(0,tl,br)
return Iroi,llp,pts
def updatePerspectiveMatrix(self): zf = self.zoom_factor w,h = getWH(self.Iorig.shape) self.dx = self.cx*w*zf - self.width/2. self.dy = self.cy*h*zf - self.height/2. R = np.eye(3) R = np.matmul(R,np.matrix([[zf,0,-self.dx],[0,zf,-self.dy],[0,0,1]],dtype=float)) R = np.matmul(R,perspective_transform((w,h),angles=self.angles)) self.R = R self.Rinv = np.linalg.inv(R)
def rectifyToPts(self, pts):
if pts.shape[1] != 4:
return
ptsh = pts * getWH(self.Iorig.shape).reshape((2, 1))
ptsh = np.concatenate((ptsh, np.ones((1, 4))))
to_pts = self.__pts2xys(pts)
wi, hi = (to_pts.min(1)[:2]).tolist()
wf, hf = (to_pts.max(1)[:2]).tolist()
to_pts = np.matrix([[wi, wf, wf, wi], [hi, hi, hf, hf], [1, 1, 1, 1]])
self.R = find_T_matrix(ptsh, to_pts)
self.Rinv = np.linalg.inv(self.R)
self._setPerspective(update=False)
def augment_sample(I,pts,dim):
maxsum,maxangle = 120,np.array([80.,80.,45.])
angles = np.random.rand(3)*maxangle
if angles.sum() > maxsum:
angles = (angles/angles.sum())*(maxangle/maxangle.sum())
I = im2single(I) # /255.0 归一化
iwh = getWH(I.shape) #得到宽高
whratio = random.uniform(2.,4.) # 随即取一个2-4的值作为宽高比
wsiz = random.uniform(dim*.2,dim*1.) # 宽取0.2*208 到 208之间
hsiz = wsiz/whratio
dx = random.uniform(0.,dim - wsiz)
dy = random.uniform(0.,dim - hsiz)
#下面涉及到整个变换
# In the first 3 lines, the original corner points are transformed into a rectangular bounding box with aspect ratio
# varying between 2:1 and 4:1. In other words, T matrix rectifies the LP with a random aspect ratio. Then,
pph = getRectPts(dx,dy,dx+wsiz,dy+hsiz)
pts = pts*iwh.reshape((2,1)) #将点恢复到真实坐标值
T = find_T_matrix(pts2ptsh(pts),pph)
#in the next two lines, a perspective transformation with random rotation (H) is combined with T to
#generate the final transformation.
H = perspective_transform((dim,dim),angles=angles)
H = np.matmul(H,T)
Iroi,pts = project(I,H,pts,dim)
hsv_mod = np.random.rand(3).astype('float32')
hsv_mod = (hsv_mod - .5)*.3
hsv_mod[0] *= 360
Iroi = hsv_transform(Iroi,hsv_mod)
Iroi = np.clip(Iroi,0.,1.)
pts = np.array(pts)
if random.random() > .5:
Iroi,pts = flip_image_and_pts(Iroi,pts)
tl,br = pts.min(1),pts.max(1)
llp = Label(0,tl,br)
return Iroi,llp,pts
def augment_sample(I,pts,dim):
maxsum,maxangle = 120,np.array([80.,80.,45.])
angles = np.random.rand(3)*maxangle
if angles.sum() > maxsum:
angles = (angles/angles.sum())*(maxangle/maxangle.sum())
# chuyển qua ma trận float32, chia cho 255
I = im2single(I)
# Lấy w, h dạng ma trận
iwh = getWH(I.shape)
whratio = random.uniform(2.,4.)
wsiz = random.uniform(dim*.2,dim*1.)
hsiz = wsiz/whratio
dx = random.uniform(0.,dim - wsiz)
dy = random.uniform(0.,dim - hsiz)
pph = getRectPts(dx,dy,dx+wsiz,dy+hsiz)
# Lấy tọa độ thật
pts = pts*iwh.reshape((2,1))
T = find_T_matrix(pts2ptsh(pts),pph)
H = perspective_transform((dim,dim),angles=angles)
H = np.matmul(H,T)
Iroi,pts = project(I,H,pts,dim)
hsv_mod = np.random.rand(3).astype('float32')
hsv_mod = (hsv_mod - .5)*.3
hsv_mod[0] *= 360
Iroi = hsv_transform(Iroi,hsv_mod)
Iroi = np.clip(Iroi,0.,1.)
pts = np.array(pts)
if random.random() > .5:
Iroi,pts = flip_image_and_pts(Iroi,pts)
# lấy giá trị tọa độ top-left, bot-right
tl,br = pts.min(1),pts.max(1)
llp = Label(0,tl,br)
return Iroi,llp,pts
def mouse_callback(self, event, x, y, flags, param):
mc = np.array([x, y], dtype=float)
mc = np.matmul(self.Rinv, np.append(mc, 1.))
mc = np.squeeze(np.array(mc))
self.mouse_center = (mc[:2] / mc[2]) / getWH(self.Iorig.shape)
