test2.py

from skimage.feature import hog
from sklearn.svm import LinearSVC
from sklearn.preprocessing import StandardScaler
# for scikit-learn >= 0.18 use:
from sklearn.model_selection import train_test_split
# from sklearn.cross_validation import train_test_split
from scipy.ndimage.measurements import label
import matplotlib.image as mpimg
import matplotlib.pyplot as plt
from moviepy.editor import VideoFileClip
from IPython.display import HTML
import numpy as np
import pickle
import cv2
import glob
import time

%matplotlib inline

print('...')





# car_images = glob.glob('training_dataset/vehicles/**/*.png')
# noncar_images = glob.glob('training_dataset/non-vehicles/**/*.png')
car_images = glob.glob('../CarND-my-Vehicle-Detection/dataset/vehicles/**/*.png')
noncar_images = glob.glob('../CarND-my-Vehicle-Detection/dataset/non-vehicles/**/*.png')

print(len(car_images), len(noncar_images))




fig, axs = plt.subplots(8,8, figsize=(16, 16))
fig.subplots_adjust(hspace = .2, wspace=.001)
axs = axs.ravel()

# Step through the list and search for chessboard corners
for i in np.arange(32):
    img = cv2.imread(car_images[np.random.randint(0, len(car_images) )])
    img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
    axs[i].axis('off')
    axs[i].set_title('car', fontsize=10)
    axs[i].imshow(img)
for i in np.arange(32,64):
    img = cv2.imread(noncar_images[np.random.randint(0,len(noncar_images))])
    img = cv2.cvtColor(img,cv2.COLOR_BGR2RGB)
    axs[i].axis('off')
    axs[i].set_title('nope', fontsize=10)
    axs[i].imshow(img)



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=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

print('...')




car_img = mpimg.imread(car_images[5])
_, car_dst = get_hog_features(car_img[:,:,2], 9, 8, 8, vis=True, feature_vec=True)
noncar_img = mpimg.imread(noncar_images[5])
_, noncar_dst = get_hog_features(noncar_img[:,:,2], 9, 8, 8, vis=True, feature_vec=True)

# Visualize
f, ((ax1, ax2), (ax3, ax4)) = plt.subplots(2, 2, figsize=(7,7))
f.subplots_adjust(hspace = .4, wspace=.2)

ax1.imshow(car_img)
ax1.set_title('Car Image', fontsize=16)
ax2.imshow(car_dst, cmap='gray')
ax2.set_title('Car HOG', fontsize=16)
ax3.imshow(noncar_img)
ax3.set_title('Non-Car Image', fontsize=16)
ax4.imshow(noncar_dst, cmap='gray')
ax4.set_title('Non-Car HOG', fontsize=16)
print('...')



# Define a function to extract features from a list of image locations
# This function could also be used to call bin_spatial() and color_hist() (as in the lessons) to extract
# flattened spatial color features and color histogram features and combine them all (making use of StandardScaler)
# to be used together for classification
def extract_features(imgs, cspace='RGB', orient=9,
                        pix_per_cell=8, cell_per_block=2, hog_channel=0):
    # 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)
            elif cspace == 'YCrCb':
                feature_image = cv2.cvtColor(image, cv2.COLOR_RGB2YCrCb)
        else: feature_image = np.copy(image)

        # 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
        features.append(hog_features)
    # Return list of feature vectors
    return features

print('...')




# Feature extraction parameters
colorspace = 'YUV' # Can be RGB, HSV, LUV, HLS, YUV, YCrCb
orient = 11
pix_per_cell = 16
cell_per_block = 2
hog_channel = 'ALL' # Can be 0, 1, 2, or "ALL"

t = time.time()
car_features = extract_features(car_images, cspace=colorspace, orient=orient,
                        pix_per_cell=pix_per_cell, cell_per_block=cell_per_block,
                        hog_channel=hog_channel)
notcar_features = extract_features(noncar_images, 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 - this will be necessary if combining different types of features (HOG + color_hist/bin_spatial)
#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(
    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')


# Define a single function that can extract features using hog sub-sampling and make predictions
def find_cars(img, ystart, ystop, scale, cspace, hog_channel, svc, X_scaler, orient,
              pix_per_cell, cell_per_block, spatial_size, hist_bins, show_all_rectangles=False):
    # array of rectangles where cars were detected
    rectangles = []

    img = img.astype(np.float32) / 255

    img_tosearch = img[ystart:ystop, :, :]

    # apply color conversion if other than 'RGB'
    if cspace != 'RGB':
        if cspace == 'HSV':
            ctrans_tosearch = cv2.cvtColor(img_tosearch, cv2.COLOR_RGB2HSV)
        elif cspace == 'LUV':
            ctrans_tosearch = cv2.cvtColor(img_tosearch, cv2.COLOR_RGB2LUV)
        elif cspace == 'HLS':
            ctrans_tosearch = cv2.cvtColor(img_tosearch, cv2.COLOR_RGB2HLS)
        elif cspace == 'YUV':
            ctrans_tosearch = cv2.cvtColor(img_tosearch, cv2.COLOR_RGB2YUV)
        elif cspace == 'YCrCb':
            ctrans_tosearch = cv2.cvtColor(img_tosearch, cv2.COLOR_RGB2YCrCb)
    else:
        ctrans_tosearch = np.copy(image)

    # rescale image if other than 1.0 scale
    if scale != 1:
        imshape = ctrans_tosearch.shape
        ctrans_tosearch = cv2.resize(ctrans_tosearch, (np.int(imshape[1] / scale), np.int(imshape[0] / scale)))

    # select colorspace channel for HOG
    if hog_channel == 'ALL':
        ch1 = ctrans_tosearch[:, :, 0]
        ch2 = ctrans_tosearch[:, :, 1]
        ch3 = ctrans_tosearch[:, :, 2]
    else:
        ch1 = ctrans_tosearch[:, :, hog_channel]

    # Define blocks and steps as above
    nxblocks = (ch1.shape[1] // pix_per_cell) + 1  # -1
    nyblocks = (ch1.shape[0] // pix_per_cell) + 1  # -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) - 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)
    if hog_channel == 'ALL':
        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()
            if hog_channel == 'ALL':
                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))
            else:
                hog_features = hog_feat1

            xleft = xpos * pix_per_cell
            ytop = ypos * pix_per_cell

            ################ ONLY FOR BIN_SPATIAL AND COLOR_HIST ################

            #             # 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)

            ######################################################################

            # print("hog_features: ", hog_features)
            #             test_prediction = svc.predict(hog_features) # shape: (1188, )
            test_prediction = svc.predict(hog_features.reshape(1, -1))  # reshape(1.-1) => shape: (1,1188)

            if test_prediction == 1 or show_all_rectangles:
                xbox_left = np.int(xleft * scale)
                ytop_draw = np.int(ytop * scale)
                win_draw = np.int(window * scale)
                rectangles.append(
                    ((xbox_left, ytop_draw + ystart), (xbox_left + win_draw, ytop_draw + win_draw + ystart)))

    return rectangles


print('...')










test_img = mpimg.imread('./test_images/test1.jpg')

ystart = 400
ystop = 656
scale = 1.5
colorspace = 'YUV' # Can be RGB, HSV, LUV, HLS, YUV, YCrCb
orient = 11
pix_per_cell = 16
cell_per_block = 2
hog_channel = 'ALL' # Can be 0, 1, 2, or "ALL"

rectangles = find_cars(test_img, ystart, ystop, scale, colorspace, hog_channel, svc, None, orient, pix_per_cell, cell_per_block, None, None)

print(len(rectangles), 'rectangles found in image')





# Here is your draw_boxes function from the previous exercise
def draw_boxes(img, bboxes, color=(0, 0, 255), thick=6):
    # Make a copy of the image
    imcopy = np.copy(img)
    random_color = False
    # Iterate through the bounding boxes
    for bbox in bboxes:
        if color == 'random' or random_color:
            color = (np.random.randint(0,255), np.random.randint(0,255), np.random.randint(0,255))
            random_color = True
        # Draw a rectangle given bbox coordinates
        cv2.rectangle(imcopy, bbox[0], bbox[1], color, thick)
    # Return the image copy with boxes drawn
    return imcopy

print('...')



test_img_rects = draw_boxes(test_img, rectangles)
plt.figure(figsize=(10,10))
plt.imshow(test_img_rects)
print('...')