def extract_features(
image, color_space='RGB', spatial_size=(32, 32), hist_bins=32,
orient=9, pix_per_cell=8, cell_per_block=2, hog_channel=0,
use_spatial_features=True, use_hist_features=True, use_hog_features=True):
"""
extract spatial, hist and hog features from given img with given parameters
"""
#1) define an empty list to store image features
image_features = []
#2) apply color convertion if the color space is not RGB
feature_image = Helpers.convert_color(image, color_space=color_space)
#3) compute spatial features if flag is set
if use_spatial_features:
spatial_color_feature = FeatureExtractor.extract_spatial_features(feature_image, size=spatial_size)
image_features.append(spatial_color_feature)
#4) compute histogram features if flag is set
if use_hist_features:
color_hist_feature = FeatureExtractor.extract_hist_features(feature_image, nbins=hist_bins)
image_features.append(color_hist_feature)
#5) compute HOG features if flag is set
if use_hog_features:
hog_feature = FeatureExtractor.extract_hog_features(
image=feature_image,
orient=orient,
pix_per_cell=pix_per_cell,
cell_per_block=cell_per_block,
hog_channel=hog_channel)
image_features.append(hog_feature)
#6) return concatenated array of features
return np.concatenate(image_features)
def get_color_features_from_pngs(image_pathes, cspace='RGB', spatial_size=(32, 32), hist_bins=32, hist_range=(0, 256)):
"""
extract features from a list of images
"""
features = []
for img_file in image_pathes:
image = Helpers.load_png(img_file)
feature_image = Helpers.convert_color(image, cspace)
spatial_color_feature = FeatureExtractor.extract_spatial_features(feature_image, size=spatial_size)
color_hist_feature = FeatureExtractor.extract_hist_features(feature_image, nbins=hist_bins, bins_range=hist_range)
feature = np.concatenate((spatial_color_feature, color_hist_feature), axis=0)
features.append(feature)
return features
def get_hog_features_from_pngs(image_pathes, cspace='RGB', orient=9, pix_per_cell=8, cell_per_block=2, hog_channel=0):
"""
extract the hog features from given list of image file pathes
"""
features = []
for file in image_pathes:
image = Helpers.load_png(file)
feature_image = Helpers.convert_color(image, cspace)
hog_features = FeatureExtractor.extract_hog_features(
image=feature_image,
orient=orient,
pix_per_cell=pix_per_cell,
cell_per_block=cell_per_block,
hog_channel=hog_channel)
features.append(hog_features)
return features
def visualize_hog_features(image,
color_space='YCrCb',
orient=8,
pixel_per_cell=8,
cell_per_block=2):
"""visualize the hog features of the given image"""
PlotHelper.color_image(image, 'car image')
converted_img = Helpers.convert_color(image, color_space=color_space)
channel1 = converted_img[:, :, 0]
_, hog1 = FeatureExtractor.get_hog_features(image=channel1,
orient=orient,
pixel_per_cell=pixel_per_cell,
cell_per_block=cell_per_block,
vis=True,
feature_vec=True)
channel2 = converted_img[:, :, 1]
_, hog2 = FeatureExtractor.get_hog_features(image=channel2,
orient=orient,
pixel_per_cell=pixel_per_cell,
cell_per_block=cell_per_block,
vis=True,
feature_vec=True)
channel3 = converted_img[:, :, 2]
_, hog3 = FeatureExtractor.get_hog_features(image=channel3,
orient=orient,
pixel_per_cell=pixel_per_cell,
cell_per_block=cell_per_block,
vis=True,
feature_vec=True)
PlotHelper.grayscale_images(
[channel1, hog1, channel2, hog2, channel3, hog3], [
'channel1', 'channel1 hog', 'channel2', 'channel2 hog', 'channel3',
'channel3 hog'
], 6)
def find_cars(image, classifier, ystart, ystop, scale=1.0):
"""
scan the image within given ystart and ystop for car
"""
img_tosearch = image[ystart:ystop, :, :]
ctrans_tosearch = Helpers.convert_color(img_tosearch, color_space=classifier.color_space)
if scale != 1:
imshape = ctrans_tosearch.shape
ctrans_tosearch = cv2.resize(ctrans_tosearch, (np.int(imshape[1]/scale), np.int(imshape[0]/scale)))
ch1 = ctrans_tosearch[:, :, 0]
ch2 = ctrans_tosearch[:, :, 1]
ch3 = ctrans_tosearch[:, :, 2]
# define blocks and steps as above
nxblocks = (ch1.shape[1] // classifier.pix_per_cell) - classifier.cell_per_block + 1
nyblocks = (ch1.shape[0] // classifier.pix_per_cell) - classifier.cell_per_block + 1
# 64 was the original sampling rate, with 8 cells and 8 pix per cell
window = 64
nblocks_per_window = (window // classifier.pix_per_cell) - classifier.cell_per_block + 1
# compute individual channel HOG features for the entire image
hog1 = FeatureExtractor.get_hog_features(ch1, classifier.orient, classifier.pix_per_cell, classifier.cell_per_block, vis=False, feature_vec=False)
hog2 = FeatureExtractor.get_hog_features(ch2, classifier.orient, classifier.pix_per_cell, classifier.cell_per_block, vis=False, feature_vec=False)
hog3 = FeatureExtractor.get_hog_features(ch3, classifier.orient, classifier.pix_per_cell, classifier.cell_per_block, vis=False, feature_vec=False)
bboxes = []
max_x_step = nxblocks - nblocks_per_window
max_y_step = nyblocks - nblocks_per_window
for y_step in range(max_y_step):
y_pos_cells = y_step
x_step = 0
while x_step < max_x_step:
x_pos_cells = x_step
# extract hog for this patch
hog_feat1 = hog1[y_pos_cells:y_pos_cells+nblocks_per_window, x_pos_cells:x_pos_cells+nblocks_per_window].ravel()
hog_feat2 = hog2[y_pos_cells:y_pos_cells+nblocks_per_window, x_pos_cells:x_pos_cells+nblocks_per_window].ravel()
hog_feat3 = hog3[y_pos_cells:y_pos_cells+nblocks_per_window, x_pos_cells:x_pos_cells+nblocks_per_window].ravel()
hog_features = np.hstack((hog_feat1, hog_feat2, hog_feat3))
x_left_pixels = x_pos_cells * classifier.pix_per_cell
y_top_pixels = y_pos_cells * classifier.pix_per_cell
# extract the image patch
subimg = cv2.resize(ctrans_tosearch[y_top_pixels:y_top_pixels+window, x_left_pixels:x_left_pixels+window], (64, 64))
# get color features
spatial_features = FeatureExtractor.extract_spatial_features(subimg, size=classifier.spatial_size)
hist_features = FeatureExtractor.extract_hist_features(subimg, nbins=classifier.hist_bins)
# scale features and make a prediction
test_features = classifier.x_scaler.transform(np.hstack((spatial_features, hist_features, hog_features)).reshape(1, -1))
test_prediction = classifier.svc.predict(test_features)
if test_prediction == 1:
xbox_left = np.int(x_left_pixels*scale)
ytop_draw = np.int(y_top_pixels*scale)
win_draw = np.int(window*scale)
bbox = [(xbox_left, ytop_draw + ystart), (xbox_left + win_draw, ytop_draw + ystart + win_draw)]
bboxes.append(bbox)
x_step += 1
else:
x_step += 2
return bboxes
