def main():
if len(sys.argv) == 1:
print 'Usage: %s [inputfile]' % sys.argv[0]
sys.exit(1)
# initialize window
cv.NamedWindow('video', cv.CV_WINDOW_AUTOSIZE)
cv.MoveWindow('video', 10, 10)
cv.NamedWindow('threshold', cv.CV_WINDOW_AUTOSIZE)
cv.MoveWindow('threshold', 10, 500)
cv.NamedWindow('flow', cv.CV_WINDOW_AUTOSIZE)
cv.MoveWindow('flow', 500, 10)
cv.NamedWindow('edges', cv.CV_WINDOW_AUTOSIZE)
cv.MoveWindow('edges', 500, 500)
cv.NamedWindow('combined', cv.CV_WINDOW_AUTOSIZE)
cv.MoveWindow('combined', 1000, 10)
capture = cv.CreateFileCapture(sys.argv[1])
if not capture: print 'Error opening capture'; sys.exit(1)
# Load bg image
bg = cv.LoadImage('bg.png')
# Discard some frames
for i in xrange(2300):
cv.GrabFrame(capture)
frame = cv.QueryFrame(capture)
frame_size = cv.GetSize(frame)
# vars for playback
fps = 25
play = True
velx = cv.CreateImage(frame_size, cv.IPL_DEPTH_32F, 1)
vely = cv.CreateImage(frame_size, cv.IPL_DEPTH_32F, 1)
combined = cv.CreateImage(frame_size, cv.IPL_DEPTH_8U, 1)
prev = cv.CreateImage(frame_size, cv.IPL_DEPTH_8U, 1)
curr = cv.CreateImage(frame_size, cv.IPL_DEPTH_8U, 1)
frame_sub = cv.CreateImage(frame_size, cv.IPL_DEPTH_8U, 3)
edges = cv.CreateImage(frame_size, cv.IPL_DEPTH_8U, 1)
prev_edges = None
storage = cv.CreateMemStorage(0)
blob_mask = cv0.cvCreateImage (frame_size, cv.IPL_DEPTH_8U, 1)
cv0.cvSet(blob_mask, 1)
hough_in = cv.CreateImage(frame_size, cv.IPL_DEPTH_8U, 1)
hough_storage = cv.CreateMat( 100, 1, cv.CV_32FC3 )
'''
cv.CvtColor(frame, prev, cv.CV_BGR2GRAY)
frame = cv.QueryFrame(capture)
cv.CvtColor(frame, curr, cv.CV_BGR2GRAY)
# winSize can't have even numbers
cv.CalcOpticalFlowLK(prev, curr, (3,3), velx, vely)
cv.ShowImage('video', frame)
cv.ShowImage('flow', velx)
cv.WaitKey(0)
'''
while True:
if play:
frame = cv.QueryFrame(capture)
cv.Sub(frame, bg, frame_sub)
'''#detect people
found = list(cv.HOGDetectMultiScale(frame, storage, win_stride=(8,8),
padding=(32,32), scale=1.05, group_threshold=2))
for r in found:
(rx, ry), (rw, rh) = r
tl = (rx + int(rw*0.1), ry + int(rh*0.07))
br = (rx + int(rw*0.9), ry + int(rh*0.87))
cv.Rectangle(frame, tl, br, (0, 255, 0), 3)
'''
#color thresholding
hsv = cv.CreateImage(frame_size, cv.IPL_DEPTH_8U, 3);
cv.CvtColor(frame, hsv, cv.CV_BGR2HSV)
mask = cv.CreateMat(frame_size[1], frame_size[0],
cv.CV_8UC1)
cv.InRangeS(hsv, (0.06*256, 0.2*256, 0.6*256, 0),
(0.16*256, 1.0*256, 1.0*256, 0), mask)
cv.ShowImage('threshold', mask)
#optical flow method
# store previous frame
prev, curr = curr, prev
# convert next frame to single channel grayscale
cv.CvtColor(frame_sub, curr, cv.CV_BGR2GRAY)
#cv.CalcOpticalFlowLK(prev, curr, (3,3), velx, vely)
#cv.Threshold(velx, velx, 8.0, 0, cv.CV_THRESH_TOZERO)
cv.CalcOpticalFlowHS(prev, curr, 1, velx, vely, 0.5,
(cv.CV_TERMCRIT_ITER, 10, 0))
cv.Threshold(velx, velx, 0.5, 0, cv.CV_THRESH_TOZERO)
cv.Threshold(vely, vely, 0.5, 0, cv.CV_THRESH_TOZERO)
cv.Erode(vely, vely,
cv.CreateStructuringElementEx(2, 2, 0, 0,
cv.CV_SHAPE_ELLIPSE))
cv.Add(vely, velx, vely)
cv.ShowImage('flow', vely)
#edge detection
cv.Canny(curr, edges, 50, 100)
cv.Dilate(edges, edges,
cv.CreateStructuringElementEx(7, 7, 0, 0,
cv.CV_SHAPE_ELLIPSE))
cv.ShowImage('edges', edges)
if prev_edges:
cv.CalcOpticalFlowHS(prev_edges, edges, 1, velx, vely, 0.5,
(cv.CV_TERMCRIT_ITER, 10, 0))
cv.Threshold(velx, velx, 0.5, 0, cv.CV_THRESH_TOZERO)
cv.Threshold(vely, vely, 0.5, 0, cv.CV_THRESH_TOZERO)
cv.ShowImage('flow', vely)
prev_edges = edges
cv.Threshold(vely, combined, 0.5, 255, cv.CV_THRESH_BINARY)
cv.Min(combined, edges, combined)
cv.ShowImage('combined', combined)
# blobs
myblobs = CBlobResult(edges, blob_mask, 100, False)
myblobs.filter_blobs(10, 10000)
blob_count = myblobs.GetNumBlobs()
for i in range(blob_count):
my_enumerated_blob = myblobs.GetBlob(i)
# print "%d: Area = %d" % (i, my_enumerated_blob.Area())
my_enumerated_blob.FillBlob(frame,
hsv2rgb( i*180.0/blob_count), 0, 0)
cv.ShowImage('video', frame)
''' crashes
#hough transform on dilated image
#http://wiki.elphel.com/index.php?
# title=OpenCV_Tennis_balls_recognizing_tutorial&redirect=no
cv.Copy(edges, hough_in)
cv.Smooth(hough_in, hough_in, cv.CV_GAUSSIAN, 15, 15, 0, 0)
cv.HoughCircles(hough_in, hough_storage, cv.CV_HOUGH_GRADIENT,
4, frame_size[1]/10, 100, 40, 0, 0)
print hough_storage
'''
k = cv.WaitKey(1000/fps)
if k == 27: # ESC key
break
elif k == 'p': # play/pause
play = not play
# set the wanted image size from the camera
highgui.cvSetCaptureProperty(capture, highgui.CV_CAP_PROP_FRAME_WIDTH,
320)
highgui.cvSetCaptureProperty(capture, highgui.CV_CAP_PROP_FRAME_HEIGHT,
240)
# capture the 1st frame to get some propertie on it
frame = highgui.cvQueryFrame(capture)
# get some properties of the frame
frame_size = cv.cvGetSize(frame)
# create some images useful later
my_grayscale = cv.cvCreateImage(frame_size, 8, 1)
mask = cv.cvCreateImage(frame_size, 8, 1)
cv.cvSet(mask, 1)
blob_overlay = False
while True:
# 1. capture the current image
frame = highgui.cvQueryFrame(capture)
if frame is None:
# no image captured... end the processing
break
# mirror the captured image
cv.cvFlip(frame, None, 1)
cv.cvCvtColor(frame, my_grayscale, cv.CV_RGB2GRAY)
def blob_identification(binary_image):
from opencv.highgui import cvSaveImage, cvLoadImageM
from opencv.cv import cvCreateImage, cvGetSize, cvCreateMat, cvSet, CV_RGB, cvResize
from Blob import CBlob
from BlobResult import CBlobResult
from classification import classification
from os import chdir, environ
path = environ.get("HOME")
frame_size = cvGetSize(binary_image)
blo = cvCreateImage(frame_size, 8, 1)
resblo = cvCreateMat(240, 320, binary_image.type)
mask = cvCreateImage(frame_size, 8, 1)
cvSet(mask, 255)
myblobs = CBlobResult(binary_image, mask, 0, True)
myblobs.filter_blobs(325, 2000)
blob_count = myblobs.GetNumBlobs()
count = 0
pixr = []
pixrm = []
for i in range(blob_count):
value = []
rowval = []
colval = []
cvSet(blo, 0)
my_enum_blob = myblobs.GetBlob(i)
my_enum_blob.FillBlob(blo, CV_RGB(255, 0, 255), 0, 0)
cvSet(resblo, 0)
cvResize(blo, resblo, 1)
for rowitem in range(resblo.rows):
for colitem in range(resblo.cols):
if resblo[rowitem, colitem] != 0:
rowval.append(rowitem)
colval.append(colitem)
value.append(resblo[rowitem, colitem])
pixr.append(rowval[0])
pixrm.append(rowval[-1])
rowmin = min(rowval)
rowedit = []
for item in rowval:
rowedit.append(item - rowmin)
coledit = []
colmin = min(colval)
for item in colval:
coledit.append(int(item) - colmin)
rowmax = max(rowedit)
colmax = max(colval) - colmin
moved = cvCreateMat(rowmax + 10, colmax + 10, blo.type)
cvSet(moved, 0)
for i in range(len(rowval)):
moved[int(rowedit[i]) + 5, int(coledit[i]) + 5] = int(value[i])
chdir(path + "/alpr/latest/blobs")
cvSaveImage("pic" + str(count) + ".png", moved)
count += 1
avoid = classification(pixr, pixrm)
blob_image = cvCreateImage(frame_size, 8, 1)
cvSet(blob_image, 0)
for i in range(blob_count):
if i not in avoid:
my_enum_blob = myblobs.GetBlob(i)
my_enum_blob.FillBlob(blob_image, CV_RGB(255, 0, 255), 0, 0)
cvSaveImage("blob.jpg", blob_image)
return
def main():
if len(sys.argv) == 1:
print 'Usage: %s [inputfile]' % sys.argv[0]
sys.exit(1)
# initialize window
cv.NamedWindow('video', cv.CV_WINDOW_AUTOSIZE)
cv.MoveWindow('video', 10, 10)
cv.NamedWindow('threshold', cv.CV_WINDOW_AUTOSIZE)
cv.MoveWindow('threshold', 10, 500)
cv.NamedWindow('flow', cv.CV_WINDOW_AUTOSIZE)
cv.MoveWindow('flow', 500, 10)
cv.NamedWindow('edges', cv.CV_WINDOW_AUTOSIZE)
cv.MoveWindow('edges', 500, 500)
cv.NamedWindow('combined', cv.CV_WINDOW_AUTOSIZE)
cv.MoveWindow('combined', 1000, 10)
capture = cv.CreateFileCapture(sys.argv[1])
if not capture:
print 'Error opening capture'
sys.exit(1)
# Load bg image
bg = cv.LoadImage('bg.png')
# Discard some frames
for i in xrange(2300):
cv.GrabFrame(capture)
frame = cv.QueryFrame(capture)
frame_size = cv.GetSize(frame)
# vars for playback
fps = 25
play = True
velx = cv.CreateImage(frame_size, cv.IPL_DEPTH_32F, 1)
vely = cv.CreateImage(frame_size, cv.IPL_DEPTH_32F, 1)
combined = cv.CreateImage(frame_size, cv.IPL_DEPTH_8U, 1)
prev = cv.CreateImage(frame_size, cv.IPL_DEPTH_8U, 1)
curr = cv.CreateImage(frame_size, cv.IPL_DEPTH_8U, 1)
frame_sub = cv.CreateImage(frame_size, cv.IPL_DEPTH_8U, 3)
edges = cv.CreateImage(frame_size, cv.IPL_DEPTH_8U, 1)
prev_edges = None
storage = cv.CreateMemStorage(0)
blob_mask = cv0.cvCreateImage(frame_size, cv.IPL_DEPTH_8U, 1)
cv0.cvSet(blob_mask, 1)
hough_in = cv.CreateImage(frame_size, cv.IPL_DEPTH_8U, 1)
hough_storage = cv.CreateMat(100, 1, cv.CV_32FC3)
'''
cv.CvtColor(frame, prev, cv.CV_BGR2GRAY)
frame = cv.QueryFrame(capture)
cv.CvtColor(frame, curr, cv.CV_BGR2GRAY)
# winSize can't have even numbers
cv.CalcOpticalFlowLK(prev, curr, (3,3), velx, vely)
cv.ShowImage('video', frame)
cv.ShowImage('flow', velx)
cv.WaitKey(0)
'''
while True:
if play:
frame = cv.QueryFrame(capture)
cv.Sub(frame, bg, frame_sub)
'''#detect people
found = list(cv.HOGDetectMultiScale(frame, storage, win_stride=(8,8),
padding=(32,32), scale=1.05, group_threshold=2))
for r in found:
(rx, ry), (rw, rh) = r
tl = (rx + int(rw*0.1), ry + int(rh*0.07))
br = (rx + int(rw*0.9), ry + int(rh*0.87))
cv.Rectangle(frame, tl, br, (0, 255, 0), 3)
'''
#color thresholding
hsv = cv.CreateImage(frame_size, cv.IPL_DEPTH_8U, 3)
cv.CvtColor(frame, hsv, cv.CV_BGR2HSV)
mask = cv.CreateMat(frame_size[1], frame_size[0], cv.CV_8UC1)
cv.InRangeS(hsv, (0.06 * 256, 0.2 * 256, 0.6 * 256, 0),
(0.16 * 256, 1.0 * 256, 1.0 * 256, 0), mask)
cv.ShowImage('threshold', mask)
#optical flow method
# store previous frame
prev, curr = curr, prev
# convert next frame to single channel grayscale
cv.CvtColor(frame_sub, curr, cv.CV_BGR2GRAY)
#cv.CalcOpticalFlowLK(prev, curr, (3,3), velx, vely)
#cv.Threshold(velx, velx, 8.0, 0, cv.CV_THRESH_TOZERO)
cv.CalcOpticalFlowHS(prev, curr, 1, velx, vely, 0.5,
(cv.CV_TERMCRIT_ITER, 10, 0))
cv.Threshold(velx, velx, 0.5, 0, cv.CV_THRESH_TOZERO)
cv.Threshold(vely, vely, 0.5, 0, cv.CV_THRESH_TOZERO)
cv.Erode(
vely, vely,
cv.CreateStructuringElementEx(2, 2, 0, 0, cv.CV_SHAPE_ELLIPSE))
cv.Add(vely, velx, vely)
cv.ShowImage('flow', vely)
#edge detection
cv.Canny(curr, edges, 50, 100)
cv.Dilate(
edges, edges,
cv.CreateStructuringElementEx(7, 7, 0, 0, cv.CV_SHAPE_ELLIPSE))
cv.ShowImage('edges', edges)
if prev_edges:
cv.CalcOpticalFlowHS(prev_edges, edges, 1, velx, vely, 0.5,
(cv.CV_TERMCRIT_ITER, 10, 0))
cv.Threshold(velx, velx, 0.5, 0, cv.CV_THRESH_TOZERO)
cv.Threshold(vely, vely, 0.5, 0, cv.CV_THRESH_TOZERO)
cv.ShowImage('flow', vely)
prev_edges = edges
cv.Threshold(vely, combined, 0.5, 255, cv.CV_THRESH_BINARY)
cv.Min(combined, edges, combined)
cv.ShowImage('combined', combined)
# blobs
myblobs = CBlobResult(edges, blob_mask, 100, False)
myblobs.filter_blobs(10, 10000)
blob_count = myblobs.GetNumBlobs()
for i in range(blob_count):
my_enumerated_blob = myblobs.GetBlob(i)
# print "%d: Area = %d" % (i, my_enumerated_blob.Area())
my_enumerated_blob.FillBlob(frame,
hsv2rgb(i * 180.0 / blob_count), 0,
0)
cv.ShowImage('video', frame)
''' crashes
#hough transform on dilated image
#http://wiki.elphel.com/index.php?
# title=OpenCV_Tennis_balls_recognizing_tutorial&redirect=no
cv.Copy(edges, hough_in)
cv.Smooth(hough_in, hough_in, cv.CV_GAUSSIAN, 15, 15, 0, 0)
cv.HoughCircles(hough_in, hough_storage, cv.CV_HOUGH_GRADIENT,
4, frame_size[1]/10, 100, 40, 0, 0)
print hough_storage
'''
k = cv.WaitKey(1000 / fps)
if k == 27: # ESC key
break
elif k == 'p': # play/pause
play = not play
def compute_saliency(image):
global thresh
global scale
saliency_scale = int(math.pow(2,scale));
bw_im1 = cv.cvCreateImage(cv.cvGetSize(image), cv.IPL_DEPTH_8U,1)
cv.cvCvtColor(image, bw_im1, cv.CV_BGR2GRAY)
bw_im = cv.cvCreateImage(cv.cvSize(saliency_scale,saliency_scale), cv.IPL_DEPTH_8U,1)
cv.cvResize(bw_im1, bw_im)
highgui.cvShowImage("BW", bw_im)
realInput = cv.cvCreateImage( cv.cvGetSize(bw_im), cv.IPL_DEPTH_32F, 1);
imaginaryInput = cv.cvCreateImage( cv.cvGetSize(bw_im), cv.IPL_DEPTH_32F, 1);
complexInput = cv.cvCreateImage( cv.cvGetSize(bw_im), cv.IPL_DEPTH_32F, 2);
cv.cvScale(bw_im, realInput, 1.0, 0.0);
cv.cvZero(imaginaryInput);
cv.cvMerge(realInput, imaginaryInput, None, None, complexInput);
dft_M = saliency_scale #cv.cvGetOptimalDFTSize( bw_im.height - 1 );
dft_N = saliency_scale #cv.cvGetOptimalDFTSize( bw_im.width - 1 );
dft_A = cv.cvCreateMat( dft_M, dft_N, cv.CV_32FC2 );
image_Re = cv.cvCreateImage( cv.cvSize(dft_N, dft_M), cv.IPL_DEPTH_32F, 1);
image_Im = cv.cvCreateImage( cv.cvSize(dft_N, dft_M), cv.IPL_DEPTH_32F, 1);
# copy A to dft_A and pad dft_A with zeros
tmp = cv.cvGetSubRect( dft_A, cv.cvRect(0,0, bw_im.width, bw_im.height));
cv.cvCopy( complexInput, tmp, None );
if(dft_A.width > bw_im.width):
tmp = cv.cvGetSubRect( dft_A, cv.cvRect(bw_im.width,0, dft_N - bw_im.width, bw_im.height));
cv.cvZero( tmp );
cv.cvDFT( dft_A, dft_A, cv.CV_DXT_FORWARD, complexInput.height );
cv.cvSplit( dft_A, image_Re, image_Im, None, None );
# Compute the phase angle
image_Mag = cv.cvCreateImage(cv.cvSize(dft_N, dft_M), cv.IPL_DEPTH_32F, 1);
image_Phase = cv.cvCreateImage(cv.cvSize(dft_N, dft_M), cv.IPL_DEPTH_32F, 1);
#compute the phase of the spectrum
cv.cvCartToPolar(image_Re, image_Im, image_Mag, image_Phase, 0)
log_mag = cv.cvCreateImage(cv.cvSize(dft_N, dft_M), cv.IPL_DEPTH_32F, 1);
cv.cvLog(image_Mag, log_mag)
#Box filter the magnitude, then take the difference
image_Mag_Filt = cv.cvCreateImage(cv.cvSize(dft_N, dft_M), cv.IPL_DEPTH_32F, 1);
filt = cv.cvCreateMat(3,3, cv.CV_32FC1);
cv.cvSet(filt,cv.cvScalarAll(-1.0/9.0))
cv.cvFilter2D(log_mag, image_Mag_Filt, filt, cv.cvPoint(-1,-1))
cv.cvAdd(log_mag, image_Mag_Filt, log_mag, None)
cv.cvExp(log_mag, log_mag)
cv.cvPolarToCart(log_mag, image_Phase, image_Re, image_Im,0);
cv.cvMerge(image_Re, image_Im, None, None, dft_A)
cv.cvDFT( dft_A, dft_A, cv.CV_DXT_INVERSE, complexInput.height)
tmp = cv.cvGetSubRect( dft_A, cv.cvRect(0,0, bw_im.width, bw_im.height));
cv.cvCopy( tmp, complexInput, None );
cv.cvSplit(complexInput, realInput, imaginaryInput, None, None)
min, max = cv.cvMinMaxLoc(realInput);
#cv.cvScale(realInput, realInput, 1.0/(max-min), 1.0*(-min)/(max-min));
cv.cvSmooth(realInput, realInput);
threshold = thresh/100.0*cv.cvAvg(realInput)[0]
cv.cvThreshold(realInput, realInput, threshold, 1.0, cv.CV_THRESH_BINARY)
tmp_img = cv.cvCreateImage(cv.cvGetSize(bw_im1),cv.IPL_DEPTH_32F, 1)
cv.cvResize(realInput,tmp_img)
cv.cvScale(tmp_img, bw_im1, 255,0)
return bw_im1
def blob_identification(binary_image):
from opencv.highgui import cvSaveImage,cvLoadImageM
from opencv.cv import cvCreateImage,cvGetSize,cvCreateMat,cvSet,CV_RGB,cvResize
from Blob import CBlob
from BlobResult import CBlobResult
from classification import classification
from os import chdir,environ
path = environ.get("HOME")
frame_size = cvGetSize (binary_image)
blo = cvCreateImage(frame_size, 8, 1)
resblo=cvCreateMat(240,320,binary_image.type)
mask = cvCreateImage (frame_size, 8, 1)
cvSet(mask, 255)
myblobs = CBlobResult(binary_image, mask, 0, True)
myblobs.filter_blobs(325,2000)
blob_count = myblobs.GetNumBlobs()
count=0
pixr=[]
pixrm=[]
for i in range(blob_count):
value=[]
rowval=[]
colval=[]
cvSet(blo,0)
my_enum_blob = myblobs.GetBlob(i)
my_enum_blob.FillBlob(blo,CV_RGB(255,0,255),0,0)
cvSet(resblo,0)
cvResize(blo,resblo,1)
for rowitem in range(resblo.rows):
for colitem in range(resblo.cols):
if resblo[rowitem,colitem]!=0:
rowval.append(rowitem)
colval.append(colitem)
value.append(resblo[rowitem,colitem])
pixr.append(rowval[0])
pixrm.append(rowval[-1])
rowmin=min(rowval)
rowedit=[]
for item in rowval:
rowedit.append(item-rowmin)
coledit=[]
colmin=min(colval)
for item in colval:
coledit.append(int(item)-colmin)
rowmax=max(rowedit)
colmax=max(colval)-colmin
moved=cvCreateMat(rowmax+10,colmax+10,blo.type)
cvSet(moved,0)
for i in range(len(rowval)):
moved[int(rowedit[i])+5,int(coledit[i])+5]=int(value[i])
chdir(path+"/alpr/latest/blobs")
cvSaveImage("pic"+ str(count)+".png",moved)
count+=1
avoid=classification(pixr,pixrm)
blob_image = cvCreateImage(frame_size, 8, 1)
cvSet(blob_image,0)
for i in range(blob_count):
if i not in avoid:
my_enum_blob = myblobs.GetBlob(i)
my_enum_blob.FillBlob(blob_image,CV_RGB(255,0,255),0,0)
cvSaveImage("blob.jpg",blob_image)
return
capture = highgui.cvCreateCameraCapture(device)
# set the wanted image size from the camera
highgui.cvSetCaptureProperty(capture, highgui.CV_CAP_PROP_FRAME_WIDTH, 320)
highgui.cvSetCaptureProperty(capture, highgui.CV_CAP_PROP_FRAME_HEIGHT, 240)
# capture the 1st frame to get some propertie on it
frame = highgui.cvQueryFrame(capture)
# get some properties of the frame
frame_size = cv.cvGetSize(frame)
# create some images useful later
my_grayscale = cv.cvCreateImage(frame_size, 8, 1)
mask = cv.cvCreateImage(frame_size, 8, 1)
cv.cvSet(mask, 1)
blob_overlay = False
while True:
# 1. capture the current image
frame = highgui.cvQueryFrame(capture)
if frame is None:
# no image captured... end the processing
break
# mirror the captured image
cv.cvFlip(frame, None, 1)
cv.cvCvtColor(frame, my_grayscale, cv.CV_RGB2GRAY)
