canxunwangluo / carnd-vehicle-detection Goto Github PK

# 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:
        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=True, feature_vector=False)
        return features, hog_image
    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=False, feature_vector=feature_vec)
        return features

t = time.time()
car_features = utils.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 = utils.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 features...')

# Create an array stack of feature vectors
X = np.vstack((car_features, notcar_features))
X = X.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(
    X, y, test_size=0.2, random_state=rand_state)


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()
t2 = time.time()
print(round(t2-t, 2), 'Seconds to train classfier...')
# Check the score of the SVC
print('Test Accuracy of classfier = ', round(svc.score(X_test, y_test), 4))
# Check the prediction time for a single sample
t=time.time()
n_predict = 10
print('My classfier 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 classfier')

# 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
    windows = []

    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(img)

    # 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 = utils.get_hog_features(ch1, orient, pix_per_cell, cell_per_block, feature_vec=False)
    if hog_channel == 'ALL':
        hog2 = utils.get_hog_features(ch2, orient, pix_per_cell, cell_per_block, feature_vec=False)
        hog3 = utils.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



            test_prediction = svc.predict(hog_features)

            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)
                windows.append(
                    ((xbox_left, ytop_draw + ystart), (xbox_left + win_draw, ytop_draw + win_draw + ystart)))

    return windows

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

def apply_threshold(heatmap, threshold):
    # Zero out pixels below the threshold
    heatmap[heatmap <= threshold] = 0
    # Return thresholded map
    return heatmap