def meanshiftUsingIntensityAndLocation(path):
im = cv2.LoadImageM(path, cv2.CV_LOAD_IMAGE_GRAYSCALE)
#creat a mat from the pixel intensity and its location
mat = cv2.LoadImageM(path)
for i in range(0, im.height):
for j in range(0, im.width):
value = (im[i, j], i, j)
mat[i, j] = value
#print mat[i,j]
(segmentedImage, labelsImage, numberRegions) = pms.segmentMeanShift(mat)
clusters = {}
for i in range(0, labelsImage.height):
for j in range(0, labelsImage.width):
v = labelsImage[i, j]
if v in clusters:
clusters[v].append(im[i, j])
else:
clusters[v] = [im[i, j]]
means = {}
for c in clusters:
means[c] = sum(clusters[c]) / len(clusters[c])
for i in range(0, im.height):
for j in range(0, im.width):
lbl = labelsImage[i, j]
im[i, j] = means[lbl]
print("number of region", numberRegions)
return im
def __init__(self, video, csv_file, background=None, xls_sheet=None):
self.sample_name = video.split("/")[-1]
self.capture = cv2.VideoCapture(video)
self.numframes = self.capture.get(CV_CAP_PROP_FRAME_COUNT)
print >> sys.stderr, self.numframes
self.fps = self.capture.get(CV_CAP_PROP_FPS)
print >> sys.stderr, self.fps
self.increaser = int(self.fps / 5)
if self.increaser == 0:
self.increaser = 1
self.length_cali = 250
self.width = self.capture.get(CV_CAP_PROP_FRAME_WIDTH)
self.height = self.capture.get(CV_CAP_PROP_FRAME_HEIGHT)
if xls_sheet:
self.xls_sheet = xls_sheet
if background:
self.background = cv2.LoadImageM(background)
else:
self.background = self.get_background()
self.clip = me.VideoFileClip(video)
#clip = (VideoFileClip("./frozen_trailer.mp4")
# .subclip((1,22.65),(1,23.2))
# .resize(0.3))
self.report = report.Report(csv_file)
self.report.read_csv()
self.offset = 0
self.get_offset()
def meanshiftUsingILM(path):
# Load original image given the image path
im = cv2.LoadImageM(path)
# Load bank of filters
filterBank = lmfilters.loadLMFilters()
# Resize image to decrease dimensions during clustering
resize_factor = 1
thumbnail = cv2.CreateMat(im.height / resize_factor,
im.width / resize_factor, cv2.CV_8UC3)
cv2.Resize(im, thumbnail)
# now work with resized thumbnail image
response = np.zeros(shape=((thumbnail.height) * (thumbnail.width), 4),
dtype=float)
for f in range(0, 48):
filter = filterBank[f]
# Resize the filter with the same factor for the resized image
dst = cv2.CreateImage(cv2.GetSize(thumbnail), cv2.IPL_DEPTH_32F, 3)
resizedFilter = cv2.CreateMat(filter.height / resize_factor,
filter.width / resize_factor,
filter.type)
cv2.Resize(filter, resizedFilter)
# Apply the current filter
cv2.Filter2D(thumbnail, dst, resizedFilter)
featureIndex = getFilterTypeIndex(f)
for j in range(0, thumbnail.height):
for i in range(0, thumbnail.width):
# Select the max. along the three channels
maxRes = max(dst[j, i])
if math.isnan(maxRes):
maxRes = 0.0
if maxRes > response[thumbnail.width * j + i, featureIndex]:
# Store the max. response for the given feature index
response[thumbnail.width * j + i, featureIndex] = maxRes
# Create new mean shift instance
ms = MeanShift(bandwidth=10, bin_seeding=True)
# Apply the mean shift clustering algorithm
ms.fit(response)
labels = ms.labels_
n_clusters_ = np.unique(labels)
print("Number of clusters: ", len(n_clusters_))
repaintImage(thumbnail, labels)
cv2.Resize(thumbnail, im)
return im
def meanshiftUsingYUV(path):
im = cv2.LoadImageM(path)
cv2.CvtColor(im, im, cv2.CV_BGR2YCrCb)
(segmentedImage, labelsImage, numberRegions) = pms.segmentMeanShift(im)
print("number of region", numberRegions)
return segmentedImage
def meanshiftUsingRGB(path):
im = cv2.LoadImageM(path)
(segmentedImage, labelsImage, numberRegions) = pms.segmentMeanShift(im)
print("number of region", numberRegions)
return segmentedImage
def meanshiftUsingPCA(path):
# Load original image given the image path
im = cv2.LoadImageM(path)
#convert image to YUV color space
cv.CvtColor(im, im, cv2.CV_BGR2YCrCb)
# Load bank of filters
filterBank = lmfilters.loadLMFilters()
# Resize image to decrease dimensions during clustering
resize_factor = 1
thumbnail = cv2.CreateMat(im.height / resize_factor,
im.width / resize_factor, cv2.CV_8UC3)
cv2.Resize(im, thumbnail)
# now work with resized thumbnail image
response = np.zeros(shape=((thumbnail.height) * (thumbnail.width), 51),
dtype=float)
for f in range(0, 48):
filter = filterBank[f]
# Resize the filter with the same factor for the resized image
dst = cv2.CreateImage(cv2.GetSize(thumbnail), cv2.IPL_DEPTH_32F, 3)
resizedFilter = cv2.CreateMat(filter.height / resize_factor,
filter.width / resize_factor,
filter.type)
cv2.Resize(filter, resizedFilter)
# Apply the current filter
cv2.Filter2D(thumbnail, dst, resizedFilter)
for j in range(0, thumbnail.height):
for i in range(0, thumbnail.width):
# Select the max. along the three channels
maxRes = max(dst[j, i])
if math.isnan(maxRes):
maxRes = 0.0
if maxRes > response[thumbnail.width * j + i, f]:
# Store the max. response for the given feature index
response[thumbnail.width * j + i, f] = maxRes
#YUV features
count = 0
for j in range(0, thumbnail.height):
for i in range(0, thumbnail.width):
response[count, 48] = thumbnail[j, i][0]
response[count, 49] = thumbnail[j, i][1]
response[count, 50] = thumbnail[j, i][2]
count += 1
#get the first 4 primary components using pca
pca = PCA(response)
pcaResponse = zeros([thumbnail.height * thumbnail.width, 4])
for i in range(0, thumbnail.height * thumbnail.width):
pcaResponse[i] = pca.getPCA(response[i], 4)
# Create new mean shift instance
ms = MeanShift(bandwidth=10, bin_seeding=True)
# Apply the mean shift clustering algorithm
ms.fit(pcaResponse)
labels = ms.labels_
n_clusters_ = np.unique(labels)
print("Number of clusters: ", len(n_clusters_))
repaintImage(thumbnail, labels)
cv2.Resize(thumbnail, im)
return im
def meanshiftUsingIntensity(path):
im = cv2.LoadImageM(path, cv2.CV_LOAD_IMAGE_GRAYSCALE)
(segmentedImage, labelsImage, numberRegions) = pms.segmentMeanShift(im)
print("number of region", numberRegions)
return segmentedImage