The goals / steps of this project are the following:
Note: for those first two steps don't forget to normalize your features and randomize a selection for training and testing. Implement a sliding-window technique and use your trained classifier to search for vehicles in images.
In [1]:
import numpy as np
import cv2
import matplotlib.pyplot as plt
import matplotlib.image as mpimg
%matplotlib inline
image = cv2.imread('test_images/cutout1.jpg')
# Define a function to compute color histogram features
def color_hist(img, nbins=32, bins_range=(0, 256)):
# Compute the histogram of the RGB channels separately
rhist = np.histogram(img[:,:,0], bins=nbins, range=bins_range)
ghist = np.histogram(img[:,:,1], bins=nbins, range=bins_range)
bhist = np.histogram(img[:,:,2], bins=nbins, range=bins_range)
# Generating bin centers
bin_edges = rhist[1]
bin_centers = (bin_edges[1:] + bin_edges[0:len(bin_edges)-1])/2
# Concatenate the histograms into a single feature vector
hist_features = np.concatenate((rhist[0], ghist[0], bhist[0]))
# Return the individual histograms, bin_centers and feature vector
return rhist, ghist, bhist, bin_centers, hist_features
rh, gh, bh, bincen, feature_vec = color_hist(image, nbins=32, bins_range=(0, 256))
# Plot a figure with all three bar charts
if rh is not None:
fig = plt.figure(figsize=(12,3))
plt.subplot(131)
plt.bar(bincen, rh[0])
plt.xlim(0, 256)
plt.title('R Histogram')
plt.subplot(132)
plt.bar(bincen, gh[0])
plt.xlim(0, 256)
plt.title('G Histogram')
plt.subplot(133)
plt.bar(bincen, bh[0])
plt.xlim(0, 256)
plt.title('B Histogram')
fig.tight_layout()
else:
print('Your function is returning None for at least one variable...')
Images could be differentiated by intensity and range of colour however perhaps other colour spaces are better to differentiate car from non-car. Lets explore HSV, LUV, HLS, YUV, YCrCB
In [6]:
import cv2
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.image as mpimg
from mpl_toolkits.mplot3d import Axes3D
%matplotlib inline
def plot3d(pixels, colors_rgb,
axis_labels=list("RGB"), axis_limits=((0, 255), (0, 255), (0, 255))):
"""Plot pixels in 3D."""
# Create figure and 3D axes
fig = plt.figure(figsize=(4, 4))
ax = Axes3D(fig)
# Set axis limits
ax.set_xlim(*axis_limits[0])
ax.set_ylim(*axis_limits[1])
ax.set_zlim(*axis_limits[2])
# Set axis labels and sizes
ax.tick_params(axis='both', which='major', labelsize=8, pad=0)
ax.set_xlabel(axis_labels[0], fontsize=8, labelpad=2)
ax.set_ylabel(axis_labels[1], fontsize=8, labelpad=2)
ax.set_zlabel(axis_labels[2], fontsize=8, labelpad=2)
# Plot pixel values with colors given in colors_rgb
ax.scatter(
pixels[:, :, 0].ravel(),
pixels[:, :, 1].ravel(),
pixels[:, :, 2].ravel(),
c=colors_rgb.reshape((-1, 3)), edgecolors='none')
return ax # return Axes3D object for further manipulation
images = ["test_images/2.png","test_images/3.png","test_images/8.png","test_images/25.png","test_images/31.png","test_images/53.png"]
for file in images:
# Read a color image
img = cv2.imread(file) # imports as BGR
img_rgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
# Select a small fraction of pixels to plot by subsampling it
scale = max(img.shape[0], img.shape[1], 64) / 64 # at most 64 rows and columns
img_small = cv2.resize(img, (np.int(img.shape[1] / scale), np.int(img.shape[0] / scale)), interpolation=cv2.INTER_NEAREST)
# Convert subsampled image to desired color space(s)
img_small_RGB = cv2.cvtColor(img_small, cv2.COLOR_BGR2RGB) # OpenCV uses BGR, matplotlib likes RGB
img_small_LUV = cv2.cvtColor(img_small, cv2.COLOR_BGR2LUV)
img_small_rgb = img_small_RGB / 255. # scaled to [0, 1], only for plotting
plt.figure(figsize=(2,2))
plt.imshow(img_rgb)
plot3d(img_small_RGB, img_small_rgb, axis_labels=list("RGB"))
plot3d(img_small_LUV, img_small_rgb, axis_labels=list("LUV"))
plt.show()
In [7]:
import numpy as np
import cv2
import matplotlib.pyplot as plt
import matplotlib.image as mpimg
# Read in an image
# You can also read cutout2, 3, 4 etc. to see other examples
image = cv2.imread('test_images/cutout1.jpg')
image = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
# Define a function to compute color histogram features
# Pass the color_space flag as 3-letter all caps string
# like 'HSV' or 'LUV' etc.
# KEEP IN MIND IF YOU DECIDE TO USE THIS FUNCTION LATER
# IN YOUR PROJECT THAT IF YOU READ THE IMAGE WITH
# cv2.imread() INSTEAD YOU START WITH BGR COLOR!
def bin_spatial(img, color_space='RGB', size=(32, 32)):
# Convert image to new color space (if specified)
# Convert image to new color space (if specified)
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)
# Use cv2.resize().ravel() to create the feature vector
features = cv2.resize(feature_image, size).ravel()
# Return the feature vector
return features
# Plot features
#plt.plot(feature_vec)
#plt.title('Spatially Binned Features')
colours = ['HSV', 'LUV', 'HLS', 'YUV', 'YCrCb']
fig, axes = plt.subplots(len(colours), sharex=True, sharey=True)
for i, ax in enumerate(axes.flatten()):
feature_vec = bin_spatial(image, color_space=colours[i], size=(32, 32))
ax.plot(feature_vec)
ax.set_title(colours[i])
plt.subplots_adjust(left=None, bottom=None, right=None, top=None, wspace=None, hspace=1.0)
#title('Spatially Binned Features')
plt.show()
In [8]:
import matplotlib.image as mpimg
import matplotlib.pyplot as plt
import numpy as np
import cv2
import glob
#from skimage.feature import hog
#from skimage import color, exposure
# images are divided up into vehicles and non-vehicles
images = glob.glob('combined/*.png', recursive=True)
cars = []
notcars = []
for image in images:
if 'image' in image or 'extra' in image:
notcars.append(image)
else:
cars.append(image)
# Define a function to return some characteristics of the dataset
def data_look(car_list, notcar_list):
data_dict = {}
# Define a key in data_dict "n_cars" and store the number of car images
data_dict["n_cars"] = len(car_list)
# Define a key "n_notcars" and store the number of notcar images
data_dict["n_notcars"] = len(notcar_list)
# Read in a test image, either car or notcar
example_img = mpimg.imread(car_list[0])
# Define a key "image_shape" and store the test image shape 3-tuple
data_dict["image_shape"] = example_img.shape
# Define a key "data_type" and store the data type of the test image.
data_dict["data_type"] = example_img.dtype
# Return data_dict
return data_dict
data_info = data_look(cars, notcars)
print('Your function returned a count of',
data_info["n_cars"], ' cars and',
data_info["n_notcars"], ' non-cars')
print('of size: ',data_info["image_shape"], ' and data type:',
data_info["data_type"])
# Just for fun choose random car / not-car indices and plot example images
car_ind = np.random.randint(0, len(cars))
notcar_ind = np.random.randint(0, len(notcars))
# Read in car / not-car images
car_image = mpimg.imread(cars[car_ind])
notcar_image = mpimg.imread(notcars[notcar_ind])
# Plot the examples
fig = plt.figure()
plt.subplot(121)
plt.imshow(car_image)
plt.title('Example Car Image')
plt.subplot(122)
plt.imshow(notcar_image)
plt.title('Example Not-car Image')
Out[8]:
We now create a histogram of gradient directions or orientations for a block of cells. Binning the gradient magnitudes in a block of cells helps reduce noise. This HOG feature can be used to provide a signature of of an objects shape.
The parameters to tweak here at the:
In [9]:
import matplotlib.image as mpimg
import matplotlib.pyplot as plt
import numpy as np
import cv2
import glob
from skimage.feature import hog
# Read in our vehicles and non-vehicles
images = glob.glob('combined/*.png')
cars = []
notcars = []
for image in images:
if 'image' in image or 'extra' in image:
notcars.append(image)
else:
cars.append(image)
# Define a function to return HOG features and visualization
def get_hog_features(img, orient, pix_per_cell, cell_per_block, vis=False, feature_vec=True):
if vis == True:
# Use skimage.hog() to get both features and a visualization
features, hog_image = hog(img, orientations=orient, pixels_per_cell=(pix_per_cell, pix_per_cell), cells_per_block=(cell_per_block, cell_per_block), visualise=True, feature_vector=feature_vec)
return features, hog_image
else:
# Use skimage.hog() to get features only
features, hog_image = hog(img, orientations=orient, pixels_per_cell=(pix_per_cell, pix_per_cell), cells_per_block=(cell_per_block, cell_per_block), visualise=False, feature_vector=feature_vec)
return features
# Generate a random index to look at a car image
ind = np.random.randint(0, len(cars))
# Read in the image
image = mpimg.imread(cars[ind])
gray = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY)
# Define HOG parameters
orient = 9
pix_per_cell = 8
cell_per_block = 2
# Call our function with vis=True to see an image output
features, hog_image = get_hog_features(gray, orient,
pix_per_cell, cell_per_block,
vis=True, feature_vec=False)
# Plot the examples
print("Here is an example visualisation of the HOG")
fig = plt.figure()
plt.subplot(121)
plt.imshow(image, cmap='gray')
plt.title('Example Car Image')
plt.subplot(122)
plt.imshow(hog_image, cmap='gray')
plt.title('HOG Visualization')
Out[9]:
In [ ]:
In [10]:
import matplotlib.image as mpimg
import matplotlib.pyplot as plt
import numpy as np
import cv2
import glob
def convert_color(img, conv='RGB2YCrCb'):
if conv == 'RGB2YCrCb':
return cv2.cvtColor(img, cv2.COLOR_RGB2YCrCb)
if conv == 'BGR2YCrCb':
return cv2.cvtColor(img, cv2.COLOR_BGR2YCrCb)
if conv == 'RGB2LUV':
return cv2.cvtColor(img, cv2.COLOR_RGB2LUV)
# Define a function to compute binned color features
def bin_spatial(img, size=(32, 32)):
# Use cv2.resize().ravel() to create the feature vector
features = cv2.resize(img, size).ravel()
# Return the feature vector
return features
# Define a function to compute color histogram features
def color_hist(img, nbins=32, bins_range=(0, 256)):
# Compute the histogram of the color channels separately
channel1_hist = np.histogram(img[:,:,0], bins=nbins, range=bins_range)
channel2_hist = np.histogram(img[:,:,1], bins=nbins, range=bins_range)
channel3_hist = np.histogram(img[:,:,2], bins=nbins, range=bins_range)
# Concatenate the histograms into a single feature vector
hist_features = np.concatenate((channel1_hist[0], channel2_hist[0], channel3_hist[0]))
# Return the individual histograms, bin_centers and feature vector
return hist_features
# Define a function to extract features from a list of images
# Have this function call bin_spatial() and color_hist()
def extract_features(imgs, cspace='RGB', spatial_size=(32, 32),
hist_bins=32, hist_range=(0, 256)):
# Create a list to append feature vectors to
features = []
# Iterate through the list of images
for file in imgs:
# Read in each one by one
image = mpimg.imread(file)
# apply color conversion if other than 'RGB'
if cspace != 'RGB':
if cspace == 'HSV':
feature_image = cv2.cvtColor(image, cv2.COLOR_RGB2HSV)
elif cspace == 'LUV':
feature_image = cv2.cvtColor(image, cv2.COLOR_RGB2LUV)
elif cspace == 'HLS':
feature_image = cv2.cvtColor(image, cv2.COLOR_RGB2HLS)
elif cspace == 'YUV':
feature_image = cv2.cvtColor(image, cv2.COLOR_RGB2YUV)
else: feature_image = np.copy(image)
# Apply bin_spatial() to get spatial color features
spatial_features = bin_spatial(feature_image, size=spatial_size)
# Apply color_hist() also with a color space option now
hist_features = color_hist(feature_image, nbins=hist_bins, bins_range=hist_range)
# Append the new feature vector to the features list
features.append(np.concatenate((spatial_features, hist_features)))
# Return list of feature vectors
return features
In [11]:
images = glob.glob('combined/*.png')
cars = []
notcars = []
for image in images:
if 'image' in image or 'extra' in image:
notcars.append(image)
else:
cars.append(image)
car_features = extract_features(cars, cspace='RGB', spatial_size=(32, 32),
hist_bins=32, hist_range=(0, 256))
notcar_features = extract_features(notcars, cspace='RGB', spatial_size=(32, 32),
hist_bins=32, hist_range=(0, 256))
In [13]:
import time
from sklearn.svm import LinearSVC
from sklearn.preprocessing import StandardScaler
if len(car_features) > 0:
# Create an array stack of feature vectors
X = np.vstack((car_features, notcar_features)).astype(np.float64)
# Fit a per-column scaler
X_scaler = StandardScaler().fit(X)
# Apply the scaler to X
scaled_X = X_scaler.transform(X)
car_ind = np.random.randint(0, len(cars))
# Plot an example of raw and scaled features
fig = plt.figure(figsize=(12,4))
plt.subplot(131)
plt.imshow(mpimg.imread(cars[car_ind]))
plt.title('Original Image')
plt.subplot(132)
plt.plot(X[car_ind])
plt.title('Raw Features')
plt.subplot(133)
plt.plot(scaled_X[car_ind])
plt.title('Normalized Features')
fig.tight_layout()
else:
print('Your function only returns empty feature vectors...')
In [14]:
import time
from sklearn.svm import LinearSVC
from sklearn.preprocessing import StandardScaler
# NOTE: the next import is only valid
# for scikit-learn version <= 0.17
# if you are using scikit-learn >= 0.18 then use this:
from sklearn.model_selection import train_test_split
#from sklearn.cross_validation import train_test_split
# TODO play with these values to see how your classifier
# performs under different binning scenarios
spatial = 36
histbin = 16
car_features = extract_features(cars, cspace='LUV', spatial_size=(spatial, spatial),
hist_bins=histbin, hist_range=(0, 256))
notcar_features = extract_features(notcars, cspace='LUV', spatial_size=(spatial, spatial),
hist_bins=histbin, hist_range=(0, 256))
# Create an array stack of feature vectors
X = np.vstack((car_features, notcar_features)).astype(np.float64)
# Fit a per-column scaler
X_scaler = StandardScaler().fit(X)
# Apply the scaler to X
scaled_X = X_scaler.transform(X)
# Define the labels vector
y = np.hstack((np.ones(len(car_features)), np.zeros(len(notcar_features))))
# Split up data into randomized training and test sets
rand_state = np.random.randint(0, 100)
X_train, X_test, y_train, y_test = train_test_split(
scaled_X, y, test_size=0.2, random_state=rand_state)
print('Using spatial binning of:',spatial,
'and', histbin,'histogram bins')
print('Feature vector length:', len(X_train[0]))
# Use a linear SVC
svc = LinearSVC(verbose=True)
# Check the training time for the SVC
t=time.time()
svc.fit(X_train, y_train)
t2 = time.time()
print(round(t2-t, 2), 'Seconds to train SVC...')
# Check the score of the SVC
print('Test Accuracy of SVC = ', round(svc.score(X_test, y_test), 4))
# Check the prediction time for a single sample
t=time.time()
n_predict = 10
print('My SVC predicts: ', svc.predict(X_test[0:n_predict]))
print('For these',n_predict, 'labels: ', y_test[0:n_predict])
t2 = time.time()
print(round(t2-t, 5), 'Seconds to predict', n_predict,'labels with SVC')
In [20]:
import matplotlib.image as mpimg
import matplotlib.pyplot as plt
import numpy as np
import cv2
import glob
import time
from sklearn.svm import LinearSVC
from sklearn.preprocessing import StandardScaler
from skimage.feature import hog
# NOTE: the next import is only valid for scikit-learn version <= 0.17
# for scikit-learn >= 0.18 use:
from sklearn.model_selection import train_test_split
#from sklearn.cross_validation import train_test_split
# Divide up into cars and notcars
images = glob.glob('combined/*.png')
cars = []
notcars = []
for image in images:
if 'image' in image or 'extra' in image:
notcars.append(image)
else:
cars.append(image)
# Reduce the sample size because HOG features are slow to compute
# The quiz evaluator times out after 13s of CPU time
sample_size = 500
cars = cars[0:sample_size]
notcars = notcars[0:sample_size]
### TODO: Tweak these parameters and see how the results change.
# LUV is best
colorspace = 'LUV' # Can be RGB, HSV, LUV, HLS, YUV, YCrCb
# higher is less accurate and slower, lower is less accurate
orient = 9
# higher pix means faster but less accurate, lower also is less accurate
pix_per_cell = 8
# higher is faster but less accurate
cell_per_block = 2
hog_channel = "ALL" # Can be 0, 1, 2, or "ALL"
t=time.time()
car_features = extract_features(cars, cspace=colorspace, orient=orient, pix_per_cell=pix_per_cell, cell_per_block=cell_per_block, hog_channel=hog_channel)
notcar_features = extract_features(notcars, cspace=colorspace, orient=orient, pix_per_cell=pix_per_cell, cell_per_block=cell_per_block, hog_channel=hog_channel)
t2 = time.time()
print(round(t2-t, 2), 'Seconds to extract HOG features...')
# Create an array stack of feature vectors
X = np.vstack((car_features, notcar_features)).astype(np.float64)
# Fit a per-column scaler
X_scaler = StandardScaler().fit(X)
# Apply the scaler to X
scaled_X = X_scaler.transform(X)
# Define the labels vector
y = np.hstack((np.ones(len(car_features)), np.zeros(len(notcar_features))))
# Split up data into randomized training and test sets
rand_state = np.random.randint(0, 100)
X_train, X_test, y_train, y_test = train_test_split(
scaled_X, y, test_size=0.2, random_state=rand_state)
print('Using:',orient,'orientations',pix_per_cell,
'pixels per cell and', cell_per_block,'cells per block')
print('Feature vector length:', len(X_train[0]))
# Use a linear SVC
svc = LinearSVC()
# Check the training time for the SVC
t=time.time()
svc.fit(X_train, y_train)
t2 = time.time()
print(round(t2-t, 2), 'Seconds to train SVC...')
# Check the score of the SVC
print('Test Accuracy of SVC = ', round(svc.score(X_test, y_test), 4))
# Check the prediction time for a single sample
t=time.time()
n_predict = 10
print('My SVC predicts: ', svc.predict(X_test[0:n_predict]))
print('For these',n_predict, 'labels: ', y_test[0:n_predict])
t2 = time.time()
print(round(t2-t, 5), 'Seconds to predict', n_predict,'labels with SVC')
In [17]:
import matplotlib.image as mpimg
import numpy as np
import cv2
from skimage.feature import hog
# Define a function to return HOG features and visualization
def get_hog_features(img, orient, pix_per_cell, cell_per_block,
vis=False, feature_vec=True):
# Call with two outputs if vis==True
if vis == True:
features, hog_image = hog(img, orientations=orient,
pixels_per_cell=(pix_per_cell, pix_per_cell),
cells_per_block=(cell_per_block, cell_per_block),
transform_sqrt=True,
visualise=vis, feature_vector=feature_vec)
return features, hog_image
# Otherwise call with one output
else:
features = hog(img, orientations=orient,
pixels_per_cell=(pix_per_cell, pix_per_cell),
cells_per_block=(cell_per_block, cell_per_block),
transform_sqrt=True,
visualise=vis, feature_vector=feature_vec)
return features
# Define a function to compute binned color features
def bin_spatial(img, size=(32, 32)):
# Use cv2.resize().ravel() to create the feature vector
features = cv2.resize(img, size).ravel()
# Return the feature vector
return features
# Define a function to compute color histogram features
# NEED TO CHANGE bins_range if reading .png files with mpimg!
def color_hist(img, nbins=32, bins_range=(0, 256)):
# Compute the histogram of the color channels separately
channel1_hist = np.histogram(img[:,:,0], bins=nbins, range=bins_range)
channel2_hist = np.histogram(img[:,:,1], bins=nbins, range=bins_range)
channel3_hist = np.histogram(img[:,:,2], bins=nbins, range=bins_range)
# Concatenate the histograms into a single feature vector
hist_features = np.concatenate((channel1_hist[0], channel2_hist[0], channel3_hist[0]))
# Return the individual histograms, bin_centers and feature vector
return hist_features
# Define a function to extract features from a list of images
# Have this function call bin_spatial() and color_hist()
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=0,
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
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 == True:
spatial_features = bin_spatial(feature_image, size=spatial_size)
file_features.append(spatial_features)
if hist_feat == True:
# Apply color_hist()
hist_features = color_hist(feature_image, nbins=hist_bins)
file_features.append(hist_features)
if hog_feat == True:
# Call get_hog_features() with vis=False, feature_vec=True
if hog_channel == 'ALL':
hog_features = []
for channel in range(feature_image.shape[2]):
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)
else:
hog_features = get_hog_features(feature_image[:,:,hog_channel], orient,
pix_per_cell, cell_per_block, vis=False, feature_vec=True)
# 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 features
# Define a function that takes an image,
# start and stop positions in both x and y,
# window size (x and y dimensions),
# and overlap fraction (for both x and y)
def slide_window(img, x_start_stop=[None, None], y_start_stop=[None, None],
xy_window=(64, 64), xy_overlap=(0.5, 0.5)):
# If x and/or y start/stop positions not defined, set to image size
if x_start_stop[0] == None:
x_start_stop[0] = 0
if x_start_stop[1] == None:
x_start_stop[1] = img.shape[1]
if y_start_stop[0] == None:
y_start_stop[0] = 0
if y_start_stop[1] == None:
y_start_stop[1] = img.shape[0]
# Compute the span of the region to be searched
xspan = x_start_stop[1] - x_start_stop[0]
yspan = y_start_stop[1] - y_start_stop[0]
# Compute the number of pixels per step in x/y
nx_pix_per_step = np.int(xy_window[0]*(1 - xy_overlap[0]))
ny_pix_per_step = np.int(xy_window[1]*(1 - xy_overlap[1]))
# Compute the number of windows in x/y
nx_buffer = np.int(xy_window[0]*(xy_overlap[0]))
ny_buffer = np.int(xy_window[1]*(xy_overlap[1]))
nx_windows = np.int((xspan-nx_buffer)/nx_pix_per_step)
ny_windows = np.int((yspan-ny_buffer)/ny_pix_per_step)
# Initialize a list to append window positions to
window_list = []
# Loop through finding x and y window positions
# Note: you could vectorize this step, but in practice
# you'll be considering windows one by one with your
# classifier, so looping makes sense
for ys in range(ny_windows):
for xs in range(nx_windows):
# Calculate window position
startx = xs*nx_pix_per_step + x_start_stop[0]
endx = startx + xy_window[0]
starty = ys*ny_pix_per_step + y_start_stop[0]
endy = starty + xy_window[1]
# Append window position to list
window_list.append(((startx, starty), (endx, endy)))
# Return the list of windows
return window_list
# Define a function to draw bounding boxes
def draw_boxes(img, bboxes, color=(0, 0, 255), thick=6):
# Make a copy of the image
imcopy = np.copy(img)
# Iterate through the bounding boxes
for bbox in bboxes:
# Draw a rectangle given bbox coordinates
cv2.rectangle(imcopy, bbox[0], bbox[1], color, thick)
# Return the image copy with boxes drawn
return imcopy
import matplotlib.image as mpimg
import matplotlib.pyplot as plt
import numpy as np
import cv2
import glob
import time
from sklearn.svm import LinearSVC
from sklearn.preprocessing import StandardScaler
from skimage.feature import hog
# NOTE: the next import is only valid for scikit-learn version <= 0.17
# for scikit-learn >= 0.18 use:
from sklearn.model_selection import train_test_split
#from sklearn.cross_validation import train_test_split
# Define a function to extract features from a single image window
# This function is very similar to extract_features()
# just for a single image rather than list of images
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=0,
spatial_feat=True, hist_feat=True, hog_feat=True):
#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 == 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 == 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 == True:
if hog_channel == 'ALL':
hog_features = []
for channel in range(feature_image.shape[2]):
hog_features.extend(get_hog_features(feature_image[:,:,channel],
orient, pix_per_cell, cell_per_block,
vis=False, feature_vec=True))
else:
hog_features = get_hog_features(feature_image[:,:,hog_channel], orient,
pix_per_cell, cell_per_block, vis=False, feature_vec=True)
#8) Append features to list
img_features.append(hog_features)
#9) Return concatenated array of features
return np.concatenate(img_features)
# Define a function you will pass an image
# and the list of windows to be searched (output of slide_windows())
def search_windows(img, windows, clf, scaler, color_space='RGB',
spatial_size=(32, 32), hist_bins=32,
hist_range=(0, 256), orient=9,
pix_per_cell=8, cell_per_block=2,
hog_channel=0, spatial_feat=True,
hist_feat=True, hog_feat=True):
#1) Create an empty list to receive positive detection windows
on_windows = []
#2) Iterate over all windows in the list
for window in windows:
#3) Extract the test window from original image
test_img = cv2.resize(img[window[0][1]:window[1][1], window[0][0]:window[1][0]], (64, 64))
#4) Extract features for that window using single_img_features()
features = single_img_features(test_img, 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)
#5) Scale extracted features to be fed to classifier
test_features = scaler.transform(np.array(features).reshape(1, -1))
#6) Predict using your classifier
prediction = clf.predict(test_features)
#7) If positive (prediction == 1) then save the window
if prediction == 1:
on_windows.append(window)
#8) Return windows for positive detections
return on_windows
In [19]:
# Read in cars and notcars
images = glob.glob('combined/*.png')
cars = []
notcars = []
for image in images:
if 'image' in image or 'extra' in image:
notcars.append(image)
else:
cars.append(image)
# Reduce the sample size because
# The quiz evaluator times out after 13s of CPU time
#sample_size = 10
#cars = cars[0:sample_size]
#notcars = notcars[0:sample_size]
### TODO: Tweak these parameters and see how the results change.
color_space = 'LUV' # Can be RGB, HSV, LUV, HLS, YUV, YCrCb
orient = 9 # HOG orientations
pix_per_cell = 8 # HOG pixels per cell
cell_per_block = 2 # HOG cells per block
hog_channel = "ALL" # Can be 0, 1, 2, or "ALL"
spatial_size = (32, 32) # Spatial binning dimensions
hist_bins = 16 # Number of histogram bins
spatial_feat = False # Spatial features on or off
hist_feat = False # Histogram features on or off
hog_feat = True # HOG features on or off
y_start_stop = [480, 720] # Min and max in y to search in slide_window()
print("Extracting Car Features")
car_features = extract_features(cars, 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("Extracting No Car Features")
notcar_features = extract_features(notcars, 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("Car Features Shape: ", len(car_features))
print("No Car Features Shape: ", len(notcar_features))
X = np.vstack((car_features, notcar_features)).astype(np.float64)
# Fit a per-column scaler
X_scaler = StandardScaler().fit(X)
# Apply the scaler to X
scaled_X = X_scaler.transform(X)
# Define the labels vector
y = np.hstack((np.ones(len(car_features)), np.zeros(len(notcar_features))))
# Split up data into randomized training and test sets
print("Splitting Train and Test sets")
rand_state = np.random.randint(0, 100)
X_train, X_test, y_train, y_test = train_test_split(
scaled_X, y, test_size=0.2, random_state=rand_state)
print('Using:',orient,'orientations',pix_per_cell,
'pixels per cell and', cell_per_block,'cells per block')
print('Feature vector length:', len(X_train[0]))
# Use a linear SVC
svc = LinearSVC()
# Check the training time for the SVC
t=time.time()
svc.fit(X_train, y_train)
t2 = time.time()
print(round(t2-t, 2), 'Seconds to train SVC...')
# Check the score of the SVC
print('Test Accuracy of SVC = ', round(svc.score(X_test, y_test), 4))
# Check the prediction time for a single sample
t=time.time()
image = cv2.imread('test_images/bbox-example-image.jpg')
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
draw_image = np.copy(image)
# 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)
#image = image.astype(np.float32)/255
windows = slide_window(image, x_start_stop=[None, None], y_start_stop=y_start_stop,
xy_window=(96, 96), xy_overlap=(0.5, 0.5))
#color_space = 'LUV'
hot_windows = search_windows(image, windows, svc, X_scaler, 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)
window_img = draw_boxes(draw_image, hot_windows, color=(0, 0, 255), thick=6)
plt.imshow(window_img)
#src_pickle = {'svc': svc, 'scaler': X_scaler, 'orient': orient, 'pix_per_cell': pix_per_cell, 'cell_per_block': cell_per_block, 'spatial_size': spatial_size, 'hist_bins': hist_bins}
#pickle.dump( src_pickle, open( "svc_pickle.p", "wb" ) )
Out[19]:
In [ ]:
import matplotlib.image as mpimg
import matplotlib.pyplot as plt
import numpy as np
import pickle
import cv2
dist_pickle = pickle.load( open("svc_pickle.p", "rb" ) )
svc = dist_pickle["svc"]
print("SVC", svc)
X_scaler = dist_pickle["scaler"]
print("X_scaler", X_scaler)
orient = dist_pickle["orient"]
print("orient", orient)
pix_per_cell = dist_pickle["pix_per_cell"]
print("pix_per_cell", pix_per_cell)
cell_per_block = dist_pickle["cell_per_block"]
print("cell_per_block", cell_per_block)
spatial_size = dist_pickle["spatial_size"]
print("spatial_size", spatial_size)
hist_bins = dist_pickle["hist_bins"]
print("hist_bins", hist_bins)
#color_space = 'LUV' # Can be RGB, HSV, LUV, HLS, YUV, YCrCb
#orient = 9 # HOG orientations
#pix_per_cell = 8 # HOG pixels per cell
#cell_per_block = 2 # HOG cells per block
#hog_channel = "ALL" # Can be 0, 1, 2, or "ALL"
#spatial_size = (32, 32) # Spatial binning dimensions
#hist_bins = 16 # Number of histogram bins
#spatial_feat = False # Spatial features on or off
#hist_feat = False # Histogram features on or off
#hog_feat = True # HOG features on or off
#y_start_stop = [480, 720] # Min and max in y to search in slide_window()
def convert_color(img, conv='RGB2YCrCb'):
if conv == 'RGB2YCrCb':
return cv2.cvtColor(img, cv2.COLOR_RGB2YCrCb)
if conv == 'BGR2YCrCb':
return cv2.cvtColor(img, cv2.COLOR_BGR2YCrCb)
if conv == 'RGB2LUV':
return cv2.cvtColor(img, cv2.COLOR_RGB2LUV)
def get_hog_features(img, orient, pix_per_cell, cell_per_block,
vis=False, feature_vec=False):
# Call with two outputs if vis==True
if vis == True:
features, hog_image = hog(img, orientations=orient,
pixels_per_cell=(pix_per_cell, pix_per_cell),
cells_per_block=(cell_per_block, cell_per_block),
transform_sqrt=False,
visualise=vis, feature_vector=feature_vec)
return features, hog_image
# Otherwise call with one output
else:
features = hog(img, orientations=orient,
pixels_per_cell=(pix_per_cell, pix_per_cell),
cells_per_block=(cell_per_block, cell_per_block),
transform_sqrt=False,
visualise=vis, feature_vector=feature_vec)
return features
#def bin_spatial(img, size=(32, 32)):
# color1 = cv2.resize(img[:,:,0], size).ravel()
# color2 = cv2.resize(img[:,:,1], size).ravel()
# color3 = cv2.resize(img[:,:,2], size).ravel()
# return np.hstack((color1, color2, color3))
def color_hist(img, nbins=32): #bins_range=(0, 256)
# Compute the histogram of the color channels separately
channel1_hist = np.histogram(img[:,:,0], bins=nbins)
channel2_hist = np.histogram(img[:,:,1], bins=nbins)
channel3_hist = np.histogram(img[:,:,2], bins=nbins)
# Concatenate the histograms into a single feature vector
hist_features = np.concatenate((channel1_hist[0], channel2_hist[0], channel3_hist[0]))
# Return the individual histograms, bin_centers and feature vector
return hist_features
# Define a single function that can extract features using hog sub-sampling and make predictions
def find_cars(img, ystart, ystop, scale, svc, X_scaler, orient, pix_per_cell, cell_per_block, spatial_size, hist_bins):
bboxes = []
#img = img.astype(np.float32)/255 # use this if using png images
img_tosearch = img[ystart:ystop,:,:]
ctrans_tosearch = convert_color(img_tosearch, conv='RGB2LUV')
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
nysteps = (nyblocks - nblocks_per_window) // cells_per_step
# 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)
#print("spatial_features", spatial_features.shape)
#print("hist_features", hist_features.shape)
#print("hog_features", hog_features.shape)
# 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)
bboxes.append(((int(xbox_left), int(ytop_draw+ystart)),(int(xbox_left+win_draw),int(ytop_draw+win_draw+ystart))))
return bboxes
scale = 1
img = cv2.imread('test_images/bbox-example-image.jpg')
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
draw_img = np.copy(img)
bboxes = find_cars(img, y_start_stop[0], y_start_stop[1], scale, svc, X_scaler, orient, pix_per_cell, cell_per_block, spatial_size, hist_bins)
print(bboxes[1])
print(bboxes[1][0])
print(bboxes[1][0][0])
for i in range(0,len(bboxes)):
cv2.rectangle(draw_img,(bboxes[i][0][0], bboxes[i][0][1]),(bboxes[i][1][0],bboxes[i][1][1]),(0,0,255),6)
plt.imshow(out_img)
In [ ]:
import matplotlib.image as mpimg
import matplotlib.pyplot as plt
import numpy as np
import cv2
def add_heat(heatmap, bbox_list):
# Iterate through list of bboxes
for box in bbox_list:
# Add += 1 for all pixels inside each bbox
# Assuming each "box" takes the form ((x1, y1), (x2, y2))
heatmap[box[0][1]:box[1][1], box[0][0]:box[1][0]] += 1
# Return updated heatmap
return heatmap
def apply_threshold(heatmap, threshold):
# Zero out pixels below the threshold
heatmap[heatmap <= threshold] = 0
# Return thresholded map
return heatmap
from scipy.ndimage.measurements import label
heat = np.zeros_like(image[:,:,0]).astype(np.float)
heat = add_heat(heat,bboxes)
plt.imshow(heat, cmap='hot', interpolation='nearest')
plt.show()
#windowed_image = draw_boxes(out_img, hot_windows, color=(0,255,0), thick=6)
#heat = apply_threshold(heat,1)
#heatmap = np.clip(heat, 0, 255)
#labels = label(heatmap)
heatmap = apply_threshold(heat, 3)
labels = label(heatmap)
print(labels[1], 'cars found')
plt.imshow(labels[0], cmap='gray')
In [ ]:
def draw_labeled_bboxes(img, labels):
# Iterate through all detected cars
for car_number in range(1, labels[1]+1):
# Find pixels with each car_number label value
nonzero = (labels[0] == car_number).nonzero()
# Identify x and y values of those pixels
nonzeroy = np.array(nonzero[0])
nonzerox = np.array(nonzero[1])
# Define a bounding box based on min/max x and y
bbox = ((np.min(nonzerox), np.min(nonzeroy)), (np.max(nonzerox), np.max(nonzeroy)))
# Draw the box on the image
cv2.rectangle(img, bbox[0], bbox[1], (0,0,255), 6)
# Return the image
return img
# Read in the last image above
image = cv2.imread('test_images/bbox-example-image.jpg')
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
# Draw bounding boxes on a copy of the image
draw_img = draw_labeled_bboxes(np.copy(image), labels)
# Display the image
plt.imshow(draw_img)
In [ ]: