def load_frame_matrix(file_name, data_dir, drop_no_action=False, down_sample=None): """ Converting everything to grayscale currently Only using frames the corresponding to an action :param file_names: a list of names of files to load (e.g. "Seq01.zip") :return: x, y """ # is this the test or training data # is_training = 'train' in data_dir # read in RGB images from using action sample function actionSample = ActionSample(data_dir + file_name) # read in ground truth seqXX_labels.csv # columns: ActorID, ActionID, StartFrame, EndFrame seq_labels = np.array(actionSample.getActions()) num_frames = actionSample.getNumFrames() # num_frames = seq_labels[:,3].max() # if file_name == 'Seq02.zip': # num_frames = 840 # elif file_name == 'Seq06.zip': # num_frames = 870 # elif file_name == 'Seq08.zip': # num_frames = 960 # elif file_name == 'Seq09.zip': # num_frames = 840 # initialize output data # store each image as a row sample_image = actionSample.getRGB(1) if down_sample is not None: sample_image = im.imresize(sample_image[:, :, 0], size=down_sample) print sample_image.shape x = np.zeros([num_frames, sample_image.shape[0]*sample_image.shape[1]]) y = np.zeros(num_frames) # loop through each frame in the mp4 video for i in range(num_frames): # is this frame part of an action sequence there_is_a_label = np.any(np.logical_and(seq_labels[:, 2] <= i, seq_labels[:, 3] >= i)) if there_is_a_label: # lookup which action this is label_row = np.where((seq_labels[:, 2] <= i) & (seq_labels[:, 3] >= i))[0] num_labels = len(label_row) if num_labels > 1: # multiple action occurring in this frame # choose action that occurs the most most_frames = 0 for l in label_row: if (seq_labels[l, 3] - seq_labels[l, 2]) > most_frames: action = seq_labels[l, 1] most_frames = seq_labels[l, 3] - seq_labels[l, 2] else: action = seq_labels[label_row[0], 1] y[i] = action else: # assign action #12 to the observation y[i] = 12 # load the image and convert it to a gray-scale image matrix img = actionSample.getRGB(i+1) gray_img = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY) if down_sample is not None: gray_img = im.imresize(gray_img, size=down_sample) x[i, :] = gray_img.flatten() if drop_no_action: keep_rows = np.where(y != 12)[0] x = x[keep_rows, :] y = y[keep_rows] return x, y, seq_labels
def predict(model,data,output):
""" Access the sample information to predict the pose. """
actionID = 0 #initialize
# Get the list of training samples
samples=os.listdir(data);
print samples
# Access to each sample
for file in samples:
# Create the object to access the sample
smp=ActionSample(os.path.join(data,file));
print file
# Create a random set of actions for this sample
numFrame=0;
pred=[];
seqn = os.path.splitext(file)[0];
while numFrame<smp.getNumFrames():
# Generate an initial displacement
#start=numFrame+random.randint(1,100);
start = numFrame
# Generate the action duration
#end=min(start+random.randint(10,100),smp.getNumFrames());
end = min(numFrame+30,smp.getNumFrames())
actionFileName = "test_%s_frame%d-%d.avi" % (seqn,start,end)
actionFileFullName = "%s%s%s%s%s" % (trainingVideos,os.path.sep,seqn, os.path.sep, actionFileName)
w=int(smp.rgb.get(cv2.cv.CV_CAP_PROP_FRAME_WIDTH))
h=int(smp.rgb.get(cv2.cv.CV_CAP_PROP_FRAME_HEIGHT))
fps=int(smp.rgb.get(cv2.cv.CV_CAP_PROP_FPS))
if os.path.exists(actionFileFullName) and os.path.getsize(actionFileFullName) > 0:
print actionFileFullName, ' exists'
else:
out = cv2.VideoWriter(actionFileFullName,cv2.cv.CV_FOURCC('X','V','I','D'),fps,(w,h))
for n in range(start,end):
image=smp.getRGB(n+1);
#print type(image)
#print n
#img=cv2.cv.fromarray(image)
#cv2.imshow('my',image)
#cv2.waitKey(10)
#print type(img)
out.write(image)
out.release()
featureFileName = "densetr_%s_frame%d-%d.txt" % (seqn,start,end)
featureFileFullName = "%s%s%s%s%s" % (denseFeatures,os.path.sep,seqn, os.path.sep, featureFileName)
#if not os.path.exists(featureFileFullName):
# continue
if os.path.exists(featureFileFullName) and os.path.getsize(featureFileFullName) > 0:
print featureFileFullName, ' exists'
else:
fout = open(featureFileFullName,"w")
print featureFileFullName
cmd = []
cmd.append(denseTrajectoryExe)
seqn = os.path.splitext(file)[0];
cmd.append(actionFileFullName)
print cmd
proc = Popen(cmd, stdout=PIPE, stderr=PIPE)
#proc[actionID].stdout.flush()
#proc[actionID].stderr.flush()
stdout, stderr = proc.communicate()
fout.write(stdout)
fout.close()
hst = numpy.zeros(bowTraj.vocszHOG)
if not os.path.exists(featureFileFullName):
print featureFileFullName, ' not found'
continue
htot = 0
fin = open(featureFileFullName,"r")
for line in fin:
D.read(line)
#descHOG.append(D.HOG)
#X = bowTraj.calcFeatures(scipy.vstack(tuple(D.HOG)))
#actionID = model.predict(X)
idx = bowTraj.bowHOG.kmeans.predict(D.HOG)
hst[idx] = hst[idx] + 1
htot = htot + 1
if htot > 0:
hst = (1.0 / float(htot)) * hst
fin.close()
print 'Retrieved model:'
print model
actionID = model.predict(hst)[0]
print hst
print 'Predicted: ', actionID
# Generate the action ID
#actionID=random.randint(1,11);
# Check if the number of frames are correct
if start<end-1 and end<smp.getNumFrames():
# Store the prediction
pred.append([actionID,start,end])
# Move ahead
#numFrame=end+1;
numFrame=start+15;
# Store the prediction
smp.exportPredictions(pred,output);
# Remove the sample object
del smp;
print file
print smp.getNumFrames()
seqn=os.path.splitext(file)[0]
name='trainingVideos/'+seqn
os.mkdir(name)
for action in actionList:
# Get the action ID, and start and end frames for the action
actionID,startFrame,endFrame=action;
print startFrame,endFrame
# fourcc=int(smp.rgb.get(cv2.cv.CV_CAP_PROP_FOURCC))
w=int(smp.rgb.get(cv2.cv.CV_CAP_PROP_FRAME_WIDTH))
h=int(smp.rgb.get(cv2.cv.CV_CAP_PROP_FRAME_HEIGHT))
fps=int(smp.rgb.get(cv2.cv.CV_CAP_PROP_FPS))
out=cv2.VideoWriter(name+'/output_%s_%d_frame%d-%d.avi'%(seqn,actionID,startFrame,endFrame),cv2.cv.CV_FOURCC('X','V','I','D'),fps,(w,h))
for numFrame in range(startFrame,endFrame):
image=smp.getRGB(numFrame);
#print type(image)
print numFrame
img=cv2.cv.fromarray(image)
cv2.imshow('my',image)
cv2.waitKey(10)
#print type(img)
out.write(image)