def cluster_train(clear_data):
global cc, ccnames, kat, ax, fig1, wall_cart, TP, FP, TN, FN, annotations_checked, fig3
hogs=[]
surfaces=[]
ann=[]
Eps, cluster_labels= dbscan(clear_data,3) # DB SCAN
print len(clear_data),' points in ', np.amax(cluster_labels),'clusters'
#print 'Eps = ', Eps, ', outliers=' ,len(np.where(cluster_labels==-1))
max_label=int(np.amax(cluster_labels))
human=np.zeros(len(clear_data))
[xi,yi,zi] = [clear_data[:,0] , clear_data[:,1] , clear_data[:,2]]
fig1.clear()
kat.clear()
kat.plot(wall_cart[:,0],wall_cart[:,1])
for k in range(1,max_label+1) :
filter=np.where(cluster_labels==k)
if len(filter[0])>timewindow :
ax.scatter(xi[filter],yi[filter], zi[filter], 'z', 30,c=cc[k%12])
fig1.add_axes(ax)
#kat.scatter(xi[filter],yi[filter],s=20, c=cc[k-1])
kat.scatter(xi[filter],yi[filter],s=20, c=cc[k%12])
grid=gridfit(yi[filter], zi[filter], xi[filter], 16, 16) #extract surface
grid=grid-np.amin(grid) #build surface grid
fig3.clear()
ax3 = fig3.add_subplot(1,1,1, projection='3d')
X, Y = np.mgrid[:16, :16]
surf = ax3.plot_surface(X, Y, grid, rstride=1, cstride=1, cmap=cm.gray,
linewidth=0, antialiased=False)
surfaces.append(grid)
hogs.append(hog(grid)) #extract features
plt.pause(0.0001)
#print ccnames[k-1],' cluster size :',len(filter[0]), 'Is',ccnames[k-1],'human? '
print ccnames[k%12],' cluster size :',len(filter[0]), 'Is',ccnames[k%12],'human? '
while True:
ha = raw_input()
if RepresentsInt(timewindow) and (int(ha)==1 or int(ha)==0):
#print timewindow
ha = int(ha)
break
else:
print 'Try again, 1 for human or 0 for obstacle'
if ha == classifier_annotations[0,annotations_checked]:
if ha == 1:
TP+=1
print 'TP'
print TP
else:
TN+=1
print 'TN'
print TN
else:
if classifier_annotations[0,annotations_checked] == 1:
FP+=1
print 'FP'
print FP
else:
FN+=1
print 'FN'
print FN
annotations_checked+=1
human[filter]=ha
ann.append(ha)
return cluster_labels,human,hogs,ann,surfaces
def main_cb(cloud_msg):
#DECLARE GLOBAL VARIABLES
global slot_count
global final_data
global all_hogs
global train_surfaces
global surfacesX
global all_surf
global labels
#CONVERT TO XYZ
rospy.loginfo('converting pointcloud %d to XYZ array ',slot_count)
raw_data = pointclouds.pointcloud2_to_xyz_array(cloud_msg, remove_nans=True)
#
mode=0 # mode=0 -->COLLECT DATA mode=1 --> TRAIN AND TEST
#BUILD CLUSTER
filter_zeros=np.where(raw_data[:, 0] != 0)[0]
clear_data = raw_data[filter_zeros,:] # ignore the zeros on X
filter_zeros=np.where(clear_data[:, 1] != 0)[0]
clear_data = clear_data[filter_zeros,:] # ignore the zeros on Y
cluster_labels =np.zeros((len(clear_data),1),int)
#% TRAINING
eps = 0.5
min_points = 5
rospy.loginfo('call DBscan ')
[core_samples,cluster_labels, n_clusters, human, surfacesX]=scikit_dbscan.dbscan(clear_data, eps, min_points,mode,False)
clear_data=clear_data[core_samples,:]
# SURFACE & HOG Features EXTRACTION
all_surf.append(surfacesX)
rospy.loginfo('Done.')
#EXTRACT AND SAVE HOGS FEATURES
rospy.loginfo('extract hogs for timeslot %d',slot_count)
[hogs,hog_image] = myhog.hog(surfacesX)
#pl.plot(hog_image)
#pl.show(0.5)
final_data.append(clear_data)
labels.append(cluster_labels)
human_detection.append(human)
all_hogs.append(hogs)
rospy.loginfo('all_hogs length %d',len(all_hogs))
rospy.loginfo('final_data length %d',len(final_data))
rospy.loginfo('human_detection length %d',len(human_detection))
if mode==0:
f = open("train_hogs.txt","a")
simplejson.dump(all_hogs,f)
f.close()
f = open("train_classifications.txt","a")
simplejson.dump(all_human_detection,f)
f.close()
if mode==1:
with open("train_hogs.txt") as f:
train_hogs = simplejson.load(f)
with open("train_classifications.txt") as f2:
train_labels = simplejson.load(f2)
X=array(train_hogs)
y=array(train_labels)
clf = svm.SVC()
clf.fit(X, y)
#[p0V,p1V,pAb]= trainNB0(array(train_hogs),array(train_labels))
#print testEntry,'classified as: ',classifyNB(array(hogs),p0V,p1V,pAb)
slot_count = slot_count + 1