def plikelihood(self):
(x, y), (h, w), a = self.det
det = np.floor(np.array([[x, y, h, w]]))
yrep = np.ones((self.num_p, 4)) * det
R2 = np.sum(np.power(self.p - yrep, 2), 1)
width = 2 * (np.amax(np.sqrt(R2)) - np.amin(np.sqrt(R2)))
prob = np.exp(-R2 / width)
prob = prob / np.sum(prob)
self.prob = prob
self.sortprob()
def plikelihood(self):
if self.update:
(x, y), (h, w), a = self.rb
det = np.floor(np.array([[x, y, h, w, x - self.p_star[0], y - self.p_star[1]]]))
yrep = np.ones((self.num_p, 6)) * det
R2 = np.sum(np.power(self.p[:, 0:6] - yrep, 2), 1)
width = 2 * (np.amax(np.sqrt(R2)) - np.amin(np.sqrt(R2)))
prob = np.exp(- R2 / width)
a = np.sum(prob)
if a != 0.0:
prob = prob / np.sum(prob)
self.prob = prob
self.sortprob()
self.calculatepstar()
def checkoverlap(x1, y1, r1, x2, y2, r2):
dxy = np.sqrt(np.power(y2 - y1, 2) + np.power(x2 - x1, 2))
dr = np.power(r2 + r1, 2)
if dxy <= dr:
return True
else:
return False
def checkoverlap(x1, y1, r1, x2, y2, r2):
dxy = np.sqrt(np.power(y2 - y1, 2) + np.power(x2 - x1, 2))
dr = np.power(r2 + r1, 2)
if dxy <= dr:
return True
else:
return False
def calculatesubjectdistance(self, subject, threshold): # Future change
(xt, yt), radius = self.subject.circle
(xs, ys), radius = subject.circle
loss = int(np.sqrt(np.power(xt - xs, 2) + np.power(yt - ys, 2)))
if loss <= threshold:
return True
else:
return False
def plikelihood(self):
if self.update:
(x, y), (h, w), a = self.rb
det = np.floor(
np.array([[x, y, h, w, x - self.p_star[0],
y - self.p_star[1]]]))
yrep = np.ones((self.num_p, 6)) * det
R2 = np.sum(np.power(self.p[:, 0:6] - yrep, 2), 1)
width = 2 * (np.amax(np.sqrt(R2)) - np.amin(np.sqrt(R2)))
prob = np.exp(-R2 / width)
a = np.sum(prob)
if a != 0.0:
prob = prob / np.sum(prob)
self.prob = prob
self.sortprob()
self.calculatepstar()
def calculatesubjectdistance(self, subject, threshold): # Future change
(xt, yt), radius = self.subject.circle
(xs, ys), radius = subject.circle
loss = int(np.sqrt(np.power(xt - xs, 2) + np.power(yt - ys, 2)))
print 'Deassociate loss'
print loss
if loss <= threshold:
return True
else:
return False
def plikelihood_new(self):
if self.update:
(x, y), (h, w), a = self.rb
detectionExtended = np.floor(np.array([[x, y, h, w, x - self.p_star[0], y - self.p_star[1]]]))
yrep = np.ones((self.num_p, 6)) * detectionExtended
prob = gaussMixModelPDF(oneParticle,detectionExtended,p_star)
R2 = np.sum(np.power(self.p[:, 0:6] - yrep, 2), 1)
width = 2 * (np.amax(np.sqrt(R2)) - np.amin(np.sqrt(R2)))
prob = np.exp(- R2 / width)
a = np.sum(prob)
if a != 0.0:
prob = prob / np.sum(prob)
self.prob = prob
self.sortprob()
self.calculatepstar()
def plikelihood_new(self):
if self.update:
(x, y), (h, w), a = self.rb
detectionExtended = np.floor(
np.array([[x, y, h, w, x - self.p_star[0],
y - self.p_star[1]]]))
yrep = np.ones((self.num_p, 6)) * detectionExtended
prob = gaussMixModelPDF(oneParticle, detectionExtended, p_star)
R2 = np.sum(np.power(self.p[:, 0:6] - yrep, 2), 1)
width = 2 * (np.amax(np.sqrt(R2)) - np.amin(np.sqrt(R2)))
prob = np.exp(-R2 / width)
a = np.sum(prob)
if a != 0.0:
prob = prob / np.sum(prob)
self.prob = prob
self.sortprob()
self.calculatepstar()
def lossfunction__old1(tr, sub):
#@Borja(orginal)1
# Where to create the loss using data from the subject class
# First simple loss function---------------------------------------
# Based in simple distance to subject base
(xt, yt), radius = tr.pf.circle
(xs, ys), radius = sub.circle
distance = int(np.sqrt(np.power(xt - xs, 2) + np.power(yt - ys, 2)))
# Second loss function---------------------------------------------
# Based in normal probability density function of particles for
# position and detection size
(x, y), (h, w), a = sub.rot_box
p = tr.pf.p
p_star = tr.pf.p_star
p_mean = tr.pf.p_mean
# optimizacion --> no calcular constantemente mean y std, sino hacerlo antes de entrar aqui
# loss = -x -y -vx -vy
loss = - np.log(normpdf(x, np.mean(p[:, 0]), np.std(p[:, 0]))) \
- np.log(normpdf(y, np.mean(p[:, 1]), np.std(p[:, 1]))) \
- np.log(normpdf(x - p_star[0], np.mean(p[:, 4]), np.std(p[:, 4]))) \
- np.log(normpdf(y - p_star[1], np.mean(p[:, 5]), np.std(p[:, 5])))
#- np.log(normpdf(sub.h, np.mean(p[:, 4]), np.std(p[:, 4])))
debug_flag=0
if debug_flag:
"""
print '###'
print normpdf(p_star[1] - y, np.mean(p[:, 5]), np.std(p[:, 5]))
print x
print y
"""
"""
print '----'
print 'x, y, h: %s, %s, %s' % (x, y, sub.h)
#print 'x: %s' % - np.log(normpdf(x, np.mean(p[:, 0]), np.std(p[:, 0])))
print 'vx: %s' % - np.log(normpdf(p_star[0] - x, np.mean(p[:, 4]), np.std(p[:, 4])))
print 'vy: %s' % - np.log(normpdf(p_star[1] - y, np.mean(p[:, 5]), np.std(p[:, 5])))
print '----'
"""
return loss, distance
def lossfunction__old1(tr, sub):
#@Borja(orginal)1
# Where to create the loss using data from the subject class
# First simple loss function---------------------------------------
# Based in simple distance to subject base
(xt, yt), radius = tr.pf.circle
(xs, ys), radius = sub.circle
distance = int(np.sqrt(np.power(xt - xs, 2) + np.power(yt - ys, 2)))
# Second loss function---------------------------------------------
# Based in normal probability density function of particles for
# position and detection size
(x, y), (h, w), a = sub.rot_box
p = tr.pf.p
p_star = tr.pf.p_star
p_mean = tr.pf.p_mean
# optimizacion --> no calcular constantemente mean y std, sino hacerlo antes de entrar aqui
# loss = -x -y -vx -vy
loss = - np.log(normpdf(x, np.mean(p[:, 0]), np.std(p[:, 0]))) \
- np.log(normpdf(y, np.mean(p[:, 1]), np.std(p[:, 1]))) \
- np.log(normpdf(x - p_star[0], np.mean(p[:, 4]), np.std(p[:, 4]))) \
- np.log(normpdf(y - p_star[1], np.mean(p[:, 5]), np.std(p[:, 5])))
#- np.log(normpdf(sub.h, np.mean(p[:, 4]), np.std(p[:, 4])))
debug_flag = 0
if debug_flag:
"""
print '###'
print normpdf(p_star[1] - y, np.mean(p[:, 5]), np.std(p[:, 5]))
print x
print y
"""
"""
print '----'
print 'x, y, h: %s, %s, %s' % (x, y, sub.h)
#print 'x: %s' % - np.log(normpdf(x, np.mean(p[:, 0]), np.std(p[:, 0])))
print 'vx: %s' % - np.log(normpdf(p_star[0] - x, np.mean(p[:, 4]), np.std(p[:, 4])))
print 'vy: %s' % - np.log(normpdf(p_star[1] - y, np.mean(p[:, 5]), np.std(p[:, 5])))
print '----'
"""
return loss, distance
def lossfunction(tr, sub):
#@CIA june-25-2015
loss=0
distance=0
#----prepare variables
(x, y), (h, b), a = sub.rot_box
p = tr.pf.p
p_star = tr.pf.p_star
p_mean = tr.pf.p_mean
#----obtain loss(tr,sub)
#--distance(tr,sub)
sqDistance = np.power(x - p_mean[0], 2) + np.power(y - p_mean[1], 2)
distance = np.sqrt(sqDistance)
#--mix of gaussians
w_star = 0.20
w_mean = 0.80
#sigma_mean = 1
#sigma_star = 1
"""
TODO
----
cov --> anchura de las particulas en vez de 1
"""
"""
COLOR_CUBES
---
1 vector de 8 cubos por canal de color BGR
---
SUBJECT (Deteccion)
b, g, r = sub.rgb_cubes
TRACKER
b, g, r = tr.rgb_cubes
"""
#.for X
mu_starX = p_star[0] # x_star
mu_meanX = p_mean[0] # x_mean
sigma_starX = p_star[3]#/2
sigma_meanX = p_mean[3]#/2
lossX = w_star*norm.pdf(x,mu_starX,sigma_starX) + w_mean*norm.pdf(x,mu_meanX,sigma_meanX)
#.for Y
mu_starY = p_star[1] # x_star
mu_meanY = p_mean[1] # x_mean
sigma_starY = p_star[2]#/2
sigma_meanY = p_mean[2]#/2
lossY = w_star*norm.pdf(y,mu_starY,sigma_starY) + w_mean*norm.pdf(y,mu_meanY,sigma_meanY) #.neglog of joint(X,Y) assuming independence
# For appareance
lossApp = cv2.compareHist(tr.rgb_cubes.ravel().astype('float32'),
sub.rgb_cubes.ravel().astype('float32'),
cv2.cv.CV_COMP_BHATTACHARYYA)
#print cv2.normalize(sub.rgb_cubes.ravel().astype('float32'))
#print cv2.normalize(tr.rgb_cubes.ravel().astype('float32'))
loss = - np.log(lossX) - np.log(lossY) + np.log(lossApp)
if loss == float('Inf') or loss == -float('Inf'):
loss = 100
return loss, distance
def normpdf(x, m, v):
return (1 / (np.sqrt(2 * np.pi) * v)) * np.exp(-(1./2) * np.power((x - m) / v, 2))
def lossfunction(tr, sub):
#@CIA june-25-2015
loss = 0
distance = 0
#----prepare variables
(x, y), (h, b), a = sub.rot_box
p = tr.pf.p
p_star = tr.pf.p_star
p_mean = tr.pf.p_mean
#----obtain loss(tr,sub)
#--distance(tr,sub)
sqDistance = np.power(x - p_mean[0], 2) + np.power(y - p_mean[1], 2)
distance = np.sqrt(sqDistance)
#--mix of gaussians
w_star = 0.20
w_mean = 0.80
#sigma_mean = 1
#sigma_star = 1
"""
TODO
----
cov --> anchura de las particulas en vez de 1
"""
"""
COLOR_CUBES
---
1 vector de 8 cubos por canal de color BGR
---
SUBJECT (Deteccion)
b, g, r = sub.rgb_cubes
TRACKER
b, g, r = tr.rgb_cubes
"""
#.for X
mu_starX = p_star[0] # x_star
mu_meanX = p_mean[0] # x_mean
sigma_starX = p_star[3] #/2
sigma_meanX = p_mean[3] #/2
lossX = w_star * norm.pdf(x, mu_starX, sigma_starX) + w_mean * norm.pdf(
x, mu_meanX, sigma_meanX)
#.for Y
mu_starY = p_star[1] # x_star
mu_meanY = p_mean[1] # x_mean
sigma_starY = p_star[2] #/2
sigma_meanY = p_mean[2] #/2
lossY = w_star * norm.pdf(y, mu_starY, sigma_starY) + w_mean * norm.pdf(
y, mu_meanY, sigma_meanY) #.neglog of joint(X,Y) assuming independence
# For appareance
lossApp = cv2.compareHist(tr.rgb_cubes.ravel().astype('float32'),
sub.rgb_cubes.ravel().astype('float32'),
cv2.cv.CV_COMP_BHATTACHARYYA)
#print cv2.normalize(sub.rgb_cubes.ravel().astype('float32'))
#print cv2.normalize(tr.rgb_cubes.ravel().astype('float32'))
loss = -np.log(lossX) - np.log(lossY) + np.log(lossApp)
if loss == float('Inf') or loss == -float('Inf'):
loss = 100
return loss, distance
def normpdf(x, m, v):
return (1 / (np.sqrt(2 * np.pi) * v)) * np.exp(-(1. / 2) * np.power(
(x - m) / v, 2))
