def plot_bounding_box_old(clf, scaler, params, index, image_type, image_shape):
'''
given a new image, plot a bounding box
around all the cars detected by the
classification algorithm.
'''
print ('image_shape = ', image_shape)
image = mpimg.imread('bbox-example-image.jpg')
image = mpimg.imread('test/frame300.jpg')
draw_image = np.copy(image)
imy, imx = image.shape[:2]
print ('in old: ', image_type, image.shape)
# Uncomment the following line if you extracted training
# data from .png images (scaled 0 to 1 by mpimg) and the
# image you are searching is a .jpg (scaled 0 to 255)
if image_type == 'png':
image = image.astype(np.float32)/255
# extract parameters from dictionary
color_space = params['color_space']
spatial_size = params['spatial_size']
hist_bins = params['hist_bins']
orient = params['orient']
pix_per_cell = params['pix_per_cell']
cell_per_block = params['cell_per_block']
hog_channel = params['hog_channel']
spatial_feat = params['spatial_feat']
hist_feat = params['hist_feat']
hog_feat = params['hog_feat']
# multi box search
min_fraction = 6
max_fraction = 10
step_fraction = 2
aspect_ratio = 1.0
hot_windows = []
start_scan = int(imy/2)
for f in range(min_fraction, max_fraction+1, step_fraction):
y_start_stop = [start_scan, min(start_scan + (f - 1) * int(imy/f), imy)] # Min and max in y to search in slide_window()
xy_window = (int(imy/f), int(imy/f*aspect_ratio))
windows = ro.slide_window(image, x_start_stop=[None, None], y_start_stop=y_start_stop,
xy_window=xy_window, xy_overlap=(0.5, 0.5))
print (f, len(windows))
new_hot_windows = ro.search_windows(image, windows, clf, scaler, image_shape, color_space=color_space,
spatial_size=spatial_size, hist_bins=hist_bins,
orient=orient, pix_per_cell=pix_per_cell,
cell_per_block=cell_per_block,
hog_channel=hog_channel, spatial_feat=spatial_feat,
hist_feat=hist_feat, hog_feat=hog_feat)
print (f, y_start_stop, xy_window, len(new_hot_windows)) #, new_hot_windows)
if len(new_hot_windows) > 0:
hot_windows = hot_windows + new_hot_windows
print ('size of hot_windows before plotting: ', len(hot_windows))
window_img = ro.draw_boxes(draw_image, hot_windows, color=(0, 0, 255), thick=3)
'''
plt.show()
'''
plt.imshow(window_img)
fig1 = plt.gcf()
plt.draw()
fig1.savefig('new_fig%d.jpg' %index, dpi=100)
heatmap = np.zeros([draw_image.shape[0], draw_image.shape[1]])
heatmap = ro.add_heat(heatmap, hot_windows)
plt.figure()
plt.imshow(heatmap, cmap='gray')
heatmap = ro.apply_threshold(heatmap, 1)
labels = label(heatmap)
print(labels[1], 'cars found')
plt.figure()
plt.imshow(labels[0], cmap='gray')
draw_img = ro.draw_labeled_bboxes(np.copy(draw_image), labels)
# Display the image
plt.figure()
plt.imshow(draw_img)
plt.show()
def plot_bounding_box(image, clf, scaler, params, plot_box=False, plot_heat=False):
'''
given a new image, plot a bounding box
around all the cars detected by the
classification algorithm.
'''
if type(image) is str:
image_type = image.split('.')[-1]
image = mpimg.imread(image)
elif type(image) is np.ndarray:
if image.max() > 1:
image_type = 'jpg'
else:
image_type = 'png'
else:
print ("input not recognized")
return None
draw_image = np.copy(image)
imy, imx = image.shape[:2]
if (image_type=='jpeg' or image_type=='jpg'): # and params['training_image_type']=='png':
image = image.astype(np.float32)/255
# extract parameters from dictionary
color_space = params['color_space']
spatial_size = params['spatial_size']
hist_bins = params['hist_bins']
orient = params['orient']
pix_per_cell = params['pix_per_cell']
cell_per_block = params['cell_per_block']
hog_channel = params['hog_channel']
spatial_feat = params['spatial_feat']
hist_feat = params['hist_feat']
hog_feat = params['hog_feat']
training_image_shape = params['training_image_shape']
# multi box search
min_fraction = 6
max_fraction = 10
step_fraction = 2
aspect_ratio = 1.0
hot_windows = []
start_scan = int(imy/2)
for f in range(min_fraction, max_fraction+1, step_fraction):
y_start_stop = [start_scan, min(start_scan + (f - 1) * int(imy/f), imy)] # Min and max in y to search in slide_window()
xy_window = (int(imy/f), int(imy/f*aspect_ratio))
windows = ro.slide_window(image, x_start_stop=[None, None], y_start_stop=y_start_stop,
xy_window=xy_window, xy_overlap=(0.5, 0.5))
#print (f, len(windows))
new_hot_windows = ro.search_windows(image, windows, clf, scaler, training_image_shape, color_space=color_space,
spatial_size=spatial_size, hist_bins=hist_bins,
orient=orient, pix_per_cell=pix_per_cell,
cell_per_block=cell_per_block,
hog_channel=hog_channel, spatial_feat=spatial_feat,
hist_feat=hist_feat, hog_feat=hog_feat)
#print (f, y_start_stop, xy_window, len(new_hot_windows)) #, new_hot_windows)
if len(new_hot_windows) > 0:
hot_windows = hot_windows + new_hot_windows
window_img = ro.draw_boxes(draw_image, hot_windows, color=(0, 0, 255), thick=3)
heatmap = np.zeros([draw_image.shape[0], draw_image.shape[1]])
heatmap = ro.add_heat(heatmap, hot_windows)
if plot_box:
if plot_heat:
plt.figure()
plt.subplot(121)
plt.imshow(window_img)
plt.subplot(122)
plt.imshow(heatmap)
plt.show()
else:
plt.figure()
plt.imshow(window_img)
return heatmap