def custom_extract_features(imgs,
spatial_size=(32, 32),
hist_bins=32,
orient=9,
pix_per_cell=8,
cell_per_block=2,
spatial_feat=True,
hist_feat=True,
hog_feat=True):
# Create a list to append feature vectors to
features = []
# Iterate through the list of images
for file in imgs:
file_features = []
# Read in each one by one
print(file)
image = cv2.imread(file)
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
spatial_img = cv2.cvtColor(image, cv2.COLOR_RGB2HLS)
hist_img = cv2.cvtColor(image, cv2.COLOR_RGB2HLS)
if spatial_feat is True:
spatial_features = bin_spatial(spatial_img, size=spatial_size)
file_features.append(spatial_features)
if hist_feat is True:
# Apply color_hist()
hist_features = color_hist(hist_img, nbins=hist_bins)
file_features.append(hist_features)
if hog_feat is True:
# Call get_hog_features() with vis=False, feature_vec=True
hog_features = []
image_hls = cv2.cvtColor(image, cv2.COLOR_RGB2HLS)
image_luv = cv2.cvtColor(image, cv2.COLOR_RGB2LUV)
hog_features.append(
get_hog_features(image_hls[:, :, 0],
orient,
pix_per_cell,
cell_per_block,
vis=False,
feature_vec=True))
hog_features.append(
get_hog_features(image_hls[:, :, 1],
orient,
pix_per_cell,
cell_per_block,
vis=False,
feature_vec=True))
hog_features.append(
get_hog_features(image_luv[:, :, 1],
orient,
pix_per_cell,
cell_per_block,
vis=False,
feature_vec=True))
hog_features = np.ravel(hog_features)
# Append the new feature vector to the features list
file_features.append(hog_features)
features.append(np.concatenate(file_features))
# Return list of feature vectors
return np.array(features)
def custom_single_img_features(image,
spatial_size=(32, 32),
hist_bins=32,
orient=9,
pix_per_cell=8,
cell_per_block=2,
spatial_feat=True,
hist_feat=True,
hog_feat=True):
# 1) Define an empty list to receive features
img_features = []
spatial_img = cv2.cvtColor(image, cv2.COLOR_RGB2HLS)
hist_img = cv2.cvtColor(image, cv2.COLOR_RGB2HLS)
# 3) Compute spatial features if flag is set
if spatial_feat is True:
spatial_features = bin_spatial(spatial_img, size=spatial_size)
# 4) Append features to list
img_features.append(spatial_features)
# 5) Compute histogram features if flag is set
if hist_feat is True:
hist_features = color_hist(hist_img, nbins=hist_bins)
# 6) Append features to list
img_features.append(hist_features)
# 7) Compute HOG features if flag is set
if hog_feat is True:
hog_features = []
image_hls = cv2.cvtColor(image, cv2.COLOR_RGB2HLS)
image_luv = cv2.cvtColor(image, cv2.COLOR_RGB2LUV)
hog_features.append(
get_hog_features(image_hls[:, :, 0],
orient,
pix_per_cell,
cell_per_block,
vis=False,
feature_vec=True))
hog_features.append(
get_hog_features(image_hls[:, :, 1],
orient,
pix_per_cell,
cell_per_block,
vis=False,
feature_vec=True))
hog_features.append(
get_hog_features(image_luv[:, :, 1],
orient,
pix_per_cell,
cell_per_block,
vis=False,
feature_vec=True))
hog_features = np.ravel(hog_features)
# 8) Append features to list
img_features.append(hog_features)
# 9) Return concatenated array of features
return np.concatenate(img_features)
def single_img_features(img,
color_space='RGB',
spatial_size=(32, 32),
hist_bins=32,
orient=9,
pix_per_cell=8,
cell_per_block=2,
hog_channel=None,
spatial_feat=True,
hist_feat=True,
hog_feat=True):
if hog_channel is None:
hog_channel = [0]
# 1) Define an empty list to receive features
img_features = []
# 2) Apply color conversion if other than 'RGB'
if color_space != 'RGB':
if color_space == 'HSV':
feature_image = cv2.cvtColor(img, cv2.COLOR_RGB2HSV)
elif color_space == 'LUV':
feature_image = cv2.cvtColor(img, cv2.COLOR_RGB2LUV)
elif color_space == 'HLS':
feature_image = cv2.cvtColor(img, cv2.COLOR_RGB2HLS)
elif color_space == 'YUV':
feature_image = cv2.cvtColor(img, cv2.COLOR_RGB2YUV)
elif color_space == 'YCrCb':
feature_image = cv2.cvtColor(img, cv2.COLOR_RGB2YCrCb)
else:
feature_image = np.copy(img)
# 3) Compute spatial features if flag is set
if spatial_feat is True:
spatial_features = bin_spatial(feature_image, size=spatial_size)
# 4) Append features to list
img_features.append(spatial_features)
# 5) Compute histogram features if flag is set
if hist_feat is True:
hist_features = color_hist(feature_image, nbins=hist_bins)
# 6) Append features to list
img_features.append(hist_features)
# 7) Compute HOG features if flag is set
if hog_feat is True:
hog_features = []
for channel in hog_channel:
hog_features.append(
get_hog_features(feature_image[:, :, channel],
orient,
pix_per_cell,
cell_per_block,
vis=False,
feature_vec=True))
hog_features = np.ravel(hog_features)
# 8) Append features to list
img_features.append(hog_features)
# 9) Return concatenated array of features
return np.concatenate(img_features)
def extract_features(imgs,
color_space='RGB',
spatial_size=(32, 32),
hist_bins=32,
orient=9,
pix_per_cell=8,
cell_per_block=2,
hog_channel=None,
spatial_feat=True,
hist_feat=True,
hog_feat=True):
if hog_channel is None:
hog_channel = [0]
# Create a list to append feature vectors to
features = []
# Iterate through the list of images
for file in imgs:
file_features = []
# Read in each one by one
print(file)
image = cv2.imread(file)
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
# apply color conversion if other than 'RGB'
if color_space != 'RGB':
if color_space == 'HSV':
feature_image = cv2.cvtColor(image, cv2.COLOR_RGB2HSV)
elif color_space == 'LUV':
feature_image = cv2.cvtColor(image, cv2.COLOR_RGB2LUV)
elif color_space == 'HLS':
feature_image = cv2.cvtColor(image, cv2.COLOR_RGB2HLS)
elif color_space == 'YUV':
feature_image = cv2.cvtColor(image, cv2.COLOR_RGB2YUV)
elif color_space == 'YCrCb':
feature_image = cv2.cvtColor(image, cv2.COLOR_RGB2YCrCb)
else:
feature_image = np.copy(image)
if spatial_feat is True:
spatial_features = bin_spatial(feature_image, size=spatial_size)
file_features.append(spatial_features)
if hist_feat is True:
# Apply color_hist()
hist_features = color_hist(feature_image, nbins=hist_bins)
file_features.append(hist_features)
if hog_feat is True:
# Call get_hog_features() with vis=False, feature_vec=True
hog_features = []
for channel in hog_channel:
hog_features.append(
get_hog_features(feature_image[:, :, channel],
orient,
pix_per_cell,
cell_per_block,
vis=False,
feature_vec=True))
hog_features = np.ravel(hog_features)
# Append the new feature vector to the features list
file_features.append(hog_features)
features.append(np.concatenate(file_features))
# Return list of feature vectors
return np.array(features)
def find_cars(img, ystart, ystop, scale, svc, X_scaler, color_space, orient,
pix_per_cell, cell_per_block, spatial_size, hist_bins,
hog_channel):
draw_img = np.copy(img)
img = img.astype(np.float32) / 255
img_tosearch = img[ystart:ystop, :, :]
if color_space == 'HSV':
ctrans_tosearch = cv2.cvtColor(img_tosearch, cv2.COLOR_RGB2HSV)
elif color_space == 'LUV':
ctrans_tosearch = cv2.cvtColor(img_tosearch, cv2.COLOR_RGB2LUV)
elif color_space == 'HLS':
ctrans_tosearch = cv2.cvtColor(img_tosearch, cv2.COLOR_RGB2HLS)
elif color_space == 'YUV':
ctrans_tosearch = cv2.cvtColor(img_tosearch, cv2.COLOR_RGB2YUV)
elif color_space == 'YCrCb':
ctrans_tosearch = cv2.cvtColor(img_tosearch, cv2.COLOR_RGB2YCrCb)
else:
ctrans_tosearch = np.copy(img_tosearch)
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] // pix_per_cell) - cell_per_block + 1
nyblocks = (ch1.shape[0] // pix_per_cell) - cell_per_block + 1
nfeat_per_block = orient * cell_per_block**2
# 64 was the orginal sampling rate, with 8 cells and 8 pix per cell
window = 64
nblocks_per_window = (window // pix_per_cell) - cell_per_block + 1
cells_per_step = 2 # Instead of overlap, define how many cells to step
nxsteps = (nxblocks - nblocks_per_window) // cells_per_step + 1
nysteps = (nyblocks - nblocks_per_window) // cells_per_step + 1
# Compute individual channel HOG features for the entire image
hog1 = get_hog_features(ch1,
orient,
pix_per_cell,
cell_per_block,
feature_vec=False)
hog2 = get_hog_features(ch2,
orient,
pix_per_cell,
cell_per_block,
feature_vec=False)
hog3 = get_hog_features(ch3,
orient,
pix_per_cell,
cell_per_block,
feature_vec=False)
for xb in range(nxsteps):
for yb in range(nysteps):
ypos = yb * cells_per_step
xpos = xb * cells_per_step
# Extract HOG for this patch
hog_feat1 = hog1[ypos:ypos + nblocks_per_window,
xpos:xpos + nblocks_per_window].ravel()
hog_feat2 = hog2[ypos:ypos + nblocks_per_window,
xpos:xpos + nblocks_per_window].ravel()
hog_feat3 = hog3[ypos:ypos + nblocks_per_window,
xpos:xpos + nblocks_per_window].ravel()
hog_features = np.hstack((hog_feat1, hog_feat2, hog_feat3))
xleft = xpos * pix_per_cell
ytop = ypos * pix_per_cell
# Extract the image patch
subimg = cv2.resize(
ctrans_tosearch[ytop:ytop + window, xleft:xleft + window],
(64, 64))
# Get color features
spatial_features = bin_spatial(subimg, size=spatial_size)
hist_features = color_hist(subimg, nbins=hist_bins)
# Scale features and make a prediction
test_features = X_scaler.transform(
np.hstack((spatial_features, hist_features,
hog_features)).reshape(1, -1))
# test_features = X_scaler.transform(np.hstack((shape_feat, hist_feat)).reshape(1, -1))
test_prediction = svc.predict(test_features)
if test_prediction == 1:
xbox_left = np.int(xleft * scale)
ytop_draw = np.int(ytop * scale)
win_draw = np.int(window * scale)
cv2.rectangle(
draw_img, (xbox_left, ytop_draw + ystart),
(xbox_left + win_draw, ytop_draw + win_draw + ystart),
(0, 0, 255), 6)
return draw_img