def extract_single_img_features(img):
"""
combine spatial bin, color histogram and gradient histogram features for a single image
"""
# Create a list to append feature vectors to
features = []
# apply color conversion if other than 'RGB'
feature_image = Helper.change_cspace(img)
# get hog features for either specific channel or for all channels
if config["hog_channel"] == 'ALL':
hog_features = []
channels = feature_image.shape[2]
# get features for all 3 channels
for channel in range(channels):
hog_features.append(
FeatureExtraction.get_hog_features(feature_image[:, :,
channel],
feature_vec=True))
hog_features = np.ravel(hog_features)
else:
# get features for specific channel
hog_features = FeatureExtraction.get_hog_features(
feature_image[:, :, config["hog_channel"]], feature_vec=True)
# Apply bin_spatial() to get spatial color features
bin_features = FeatureExtraction.bin_spatial(feature_image,
config["spatial_size"])
# Apply color_hist() to get color histogram features
color_hist_features = FeatureExtraction.color_hist(
feature_image, config["hist_bins"])
# concatenate all 3 types of features
feature = np.concatenate(
(bin_features, color_hist_features, hog_features), axis=0)
# Append the new feature vector to the features list
features.append(feature)
# Return list of feature vectors
return features
def get_bounding_boxes(img, classifier, x_start_stop, y_start_stop):
# get window parameters
n_xsteps, n_ysteps, w = WindowSearch.get_window_params(img,
x_start_stop,
y_start_stop)
n_blocks_per_window, ctrans_tosearch = w
# get hog features for full image
hog1, hog2, hog3 = WindowSearch.get_frame_hog(ctrans_tosearch)
svc, scaler = classifier
x_start, x_stop = x_start_stop
y_start, y_stop = y_start_stop
bounding_boxes = []
t_start = int(time.time())
for xb in range(n_xsteps):
for yb in range(n_ysteps):
y_pos = yb * config["cells_per_step"]
x_pos = xb * config["cells_per_step"]
# Extract HOG for this patch
hog_feat1 = hog1[y_pos:y_pos + n_blocks_per_window, x_pos:x_pos + n_blocks_per_window].ravel()
hog_feat2 = hog2[y_pos:y_pos + n_blocks_per_window, x_pos:x_pos + n_blocks_per_window].ravel()
hog_feat3 = hog3[y_pos:y_pos + n_blocks_per_window, x_pos:x_pos + n_blocks_per_window].ravel()
x_left = x_pos * config["pix_per_cell"]
y_stop = y_pos * config["pix_per_cell"]
# Extract the image patch
sub_sample_img = cv.resize(
ctrans_tosearch[y_stop:y_stop + config["window_size"], x_left:x_left + config["window_size"]],
(config["window_size"], config["window_size"])
)
# Get color and gradient features for each image patch
hog_features = np.hstack((hog_feat1, hog_feat2, hog_feat3))
spatial_features = FeatureExtraction.bin_spatial(sub_sample_img, size=config["spatial_size"])
hist_features = FeatureExtraction.color_hist(sub_sample_img, nbins=config["hist_bins"])
# append merge features
features = np.hstack((spatial_features, hist_features, hog_features))
# normalize the features
features = scaler.transform(np.array(features).reshape(1, -1))
# predict the label for the features: 1 = car, 0 = not car
predicted_labels = svc.predict(features)
# get the bounding box for detected cars
if predicted_labels == 1:
bounding_boxes.append(WindowSearch.get_box(x_start,
x_left,
y_start,
y_stop))
t_end = int(time.time())
print("prediction time: {}".format(t_end - t_start))
return bounding_boxes