def test_template_select():
# simple initial checks
ae = assert_equal
r1 = create_region(10, 5)
t1 = create_region(3, 3)
r1_a, t1_a = template.template_select(r1, t1, 0, 0)
ae(r1_a.shape, (3, 3))
ae(t1_a.shape, (3, 3))
ae(r1_a[0, 0], 0)
ae(r1_a[2, 2], 22)
ae(t1_a[0, 0], 0)
ae(t1_a[2, 2], 8)
# simple offset
r1 = create_region(10, 5)
t1 = create_region(3, 3)
r1_a, t1_a = template.template_select(r1, t1, 1, 2)
ae(r1_a.shape, (3, 3))
ae(t1_a.shape, (3, 3))
ae(r1_a[0, 0], 21)
ae(r1_a[2, 2], 43)
ae(t1_a[0, 0], 0)
ae(t1_a[2, 2], 8)
# lower-right corner, almost
r1 = create_region(10, 5)
t1 = create_region(3, 3)
r1_a, t1_a = template.template_select(r1, t1, 9, 3)
ae(r1_a.shape, (2, 1))
ae(t1_a.shape, (2, 1))
ae(r1_a[0, 0], 39)
ae(r1_a[1, 0], 49)
ae(t1_a[0, 0], 0)
ae(t1_a[1, 0], 3)
# negative x-y spots
r1 = create_region(10, 5)
t1 = create_region(3, 4)
r1_a, t1_a = template.template_select(r1, t1, -2, -1)
ae(r1_a.shape, (3, 1))
ae(t1_a.shape, (3, 1))
ae(r1_a[0, 0], 0)
ae(r1_a[2, 0], 20)
ae(t1_a[0, 0], 5)
ae(t1_a[2, 0], 11)
# crazy values
r1 = create_region(320, 240)
t1 = create_region(34, 34)
r1_a, t1_a = template.template_select(r1, t1, -17., -17.)
def score_state_full(self, state, img):
assert len(img.shape)== 2
x = state['x']
y = state['y']
theta = state['theta']
phi = state['phi']
if self.cached_img == None or (self.cached_img != img).any():
regions = filters.extract_region_filter(img,
self.likeli_params['region-size-thold'], mark_min = self.likeli_params['mark-min'],
mark_max = self.likeli_params['mark-max'])
img_thold = (regions > 0).astype(np.uint8)*255
# pylab.imshow(img_thold)
# pylab.show()
self.cached_img = img
self.cached_img_thold = img_thold
img_thold = self.cached_img_thold
x_pix, y_pix = self.env.gc.real_to_image(x, y)
x_pix = int(x_pix)
y_pix = int(y_pix)
template_img = self.template_obj.render(phi, theta)
template_pix = template_img*255
img_region, template_region = template.template_select(img_thold, template_pix,
x_pix - template_pix.shape[1]/2,
y_pix - template_pix.shape[0]/2)
img_region = img_region.astype(np.float32) / 255.0
template_region = template_region.astype(np.float32)/255.0
tr_size = template_region.count()
if self.similarity == "dist":
MINSCORE = -1e80
if tr_size == 0:
return MINSCORE
delta = (template_region - img_region)*self.likeli_params['delta_scale']
deltatot = np.sum(np.abs(delta)**self.likeli_params['power'])
if self.likeli_params['transform'] == 'log':
if deltatot > 0:
s = - np.log(deltatot / tr_size) * self.likeli_params['multiply']
else:
s = 0.0
elif self.likeli_params['transform'] == 'exp':
s = - np.exp(deltatot/tr_size)
else:
s = -deltatot / tr_size # * self.likeli_params['multiply']
# pylab.figure()
# pylab.subplot(1, 2, 1)
# pylab.imshow(template_region)
# pylab.subplot(1, 2, 2)
# pylab.imshow(img_region)
# pylab.title("score=%f" % s)
# pylab.show()
return s
def score_state_full(self, state, img):
assert len(img.shape) == 2
x = state['x']
y = state['y']
theta = state['theta']
phi = state['phi']
if self.cached_img == None or (self.cached_img != img).any():
regions = filters.extract_region_filter(
img,
self.likeli_params['region-size-thold'],
mark_min=self.likeli_params['mark-min'],
mark_max=self.likeli_params['mark-max'])
img_thold = (regions > 0).astype(np.uint8) * 255
# pylab.imshow(img_thold)
# pylab.show()
self.cached_img = img
self.cached_img_thold = img_thold
img_thold = self.cached_img_thold
x_pix, y_pix = self.env.gc.real_to_image(x, y)
x_pix = int(x_pix)
y_pix = int(y_pix)
template_img = self.template_obj.render(phi, theta)
template_pix = template_img * 255
img_region, template_region = template.template_select(
img_thold, template_pix, x_pix - template_pix.shape[1] / 2,
y_pix - template_pix.shape[0] / 2)
img_region = img_region.astype(np.float32) / 255.0
template_region = template_region.astype(np.float32) / 255.0
tr_size = template_region.count()
if self.similarity == "dist":
MINSCORE = -1e80
if tr_size == 0:
return MINSCORE
delta = (template_region -
img_region) * self.likeli_params['delta_scale']
deltatot = np.sum(np.abs(delta)**self.likeli_params['power'])
if self.likeli_params['transform'] == 'log':
if deltatot > 0:
s = -np.log(
deltatot / tr_size) * self.likeli_params['multiply']
else:
s = 0.0
elif self.likeli_params['transform'] == 'exp':
s = -np.exp(deltatot / tr_size)
else:
s = -deltatot / tr_size # * self.likeli_params['multiply']
# pylab.figure()
# pylab.subplot(1, 2, 1)
# pylab.imshow(template_region)
# pylab.subplot(1, 2, 2)
# pylab.imshow(img_region)
# pylab.title("score=%f" % s)
# pylab.show()
return s
def test_template_select():
# simple initial checks
ae = assert_equal
r1 = create_region(10, 5)
t1 = create_region(3, 3)
r1_a, t1_a = template.template_select(r1, t1, 0, 0)
ae(r1_a.shape, (3, 3))
ae(t1_a.shape, (3, 3))
ae(r1_a[0, 0], 0)
ae(r1_a[2, 2], 22)
ae(t1_a[0, 0], 0)
ae(t1_a[2, 2], 8)
# simple offset
r1 = create_region(10, 5)
t1 = create_region(3, 3)
r1_a, t1_a = template.template_select(r1, t1, 1, 2)
ae(r1_a.shape, (3, 3))
ae(t1_a.shape, (3, 3))
ae(r1_a[0, 0], 21)
ae(r1_a[2, 2], 43)
ae(t1_a[0, 0], 0)
ae(t1_a[2, 2], 8)
# lower-right corner, almost
r1 = create_region(10, 5)
t1 = create_region(3, 3)
r1_a, t1_a = template.template_select(r1, t1, 9, 3)
ae(r1_a.shape, (2, 1))
ae(t1_a.shape, (2, 1))
ae(r1_a[0, 0], 39)
ae(r1_a[1, 0], 49)
ae(t1_a[0, 0], 0)
ae(t1_a[1, 0], 3)
# negative x-y spots
r1 = create_region(10, 5)
t1 = create_region(3, 4)
r1_a, t1_a = template.template_select(r1, t1, -2, -1)
ae(r1_a.shape, (3, 1))
ae(t1_a.shape, (3, 1))
ae(r1_a[0, 0], 0)
ae(r1_a[2, 0], 20)
ae(t1_a[0, 0], 5)
ae(t1_a[2, 0], 11)
# crazy values
r1 = create_region(320, 240)
t1 = create_region(34, 34)
r1_a, t1_a = template.template_select(r1, t1, -17., -17.)
