utils.py

import numpy as np
import cv2
import glob
import pickle
import os


def gaussian_blur(img, kernel_size):
    """Applies a Gaussian Noise kernel"""
    return cv2.GaussianBlur(img, (kernel_size, kernel_size), 0)


def abs_sobel_thresh(img, orient='x', thresh=(20, 255)):
    # Convert to grayscale
    gray = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY)
    # Apply x or y gradient with the OpenCV Sobel() function
    # and take the absolute value
    if orient == 'x':
        abs_sobel = np.absolute(cv2.Sobel(gray, cv2.CV_64F, 1, 0))
    if orient == 'y':
        abs_sobel = np.absolute(cv2.Sobel(gray, cv2.CV_64F, 0, 1))
    # Rescale back to 8 bit integer
    scaled_sobel = np.uint8(255 * abs_sobel / np.max(abs_sobel))
    # Create a copy and apply the threshold
    binary_output = np.zeros_like(scaled_sobel)
    # Here I'm using inclusive (>=, <=) thresholds, but exclusive is ok too
    binary_output[(scaled_sobel >= thresh[0]) &
                  (scaled_sobel <= thresh[1])] = 1

    # Return the result
    return binary_output

# Define a function to return the magnitude of the gradient
# for a given sobel kernel size and threshold values


def mag_thresh(img, sobel_kernel=3, thresh=(0, 255)):
    # Convert to grayscale
    gray = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY)
    # Take both Sobel x and y gradients
    sobelx = cv2.Sobel(gray, cv2.CV_64F, 1, 0, ksize=sobel_kernel)
    sobely = cv2.Sobel(gray, cv2.CV_64F, 0, 1, ksize=sobel_kernel)
    # Calculate the gradient magnitude
    gradmag = np.sqrt(sobelx**2 + sobely**2)
    # Rescale to 8 bit
    scale_factor = np.max(gradmag) / 255
    gradmag = (gradmag / scale_factor).astype(np.uint8)
    # Create a binary image of ones where threshold is met, zeros otherwise
    binary_output = np.zeros_like(gradmag)
    binary_output[(gradmag >= thresh[0]) & (gradmag <= thresh[1])] = 1

    # Return the binary image
    return binary_output

# Define a function to threshold an image for a given range and Sobel kernel


def dir_thresh(img, sobel_kernel=3, thresh=(0, np.pi / 2)):
    # Grayscale
    gray = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY)
    # Calculate the x and y gradients
    sobelx = cv2.Sobel(gray, cv2.CV_64F, 1, 0, ksize=sobel_kernel)
    sobely = cv2.Sobel(gray, cv2.CV_64F, 0, 1, ksize=sobel_kernel)
    # Take the absolute value of the gradient direction,
    # apply a threshold, and create a binary image result
    absgraddir = np.arctan2(np.absolute(sobely), np.absolute(sobelx))
    binary_output = np.zeros_like(absgraddir)
    binary_output[(absgraddir >= thresh[0]) & (absgraddir <= thresh[1])] = 1

    # Return the binary image
    return binary_output

# Define a function that thresholds the S-channel of HLS


def hls_select(img, thresh=(90, 255)):
    hls = cv2.cvtColor(img, cv2.COLOR_RGB2HLS)
    s_channel = hls[:, :, 2]
    binary_output = np.zeros_like(s_channel)
    binary_output[(s_channel > thresh[0]) & (s_channel <= thresh[1])] = 1
    return binary_output


# X,Y
img_size = (1280, 720)

# MMa 2017-06-27 Why it failed immediately when top source points are less then half of the height ??!
src = np.float32([[img_size[0] / 2 - 116, img_size[1] / 2 + 150],
                  [img_size[0] / 2 + 116, img_size[1] / 2 + 150],
                  [img_size[0] / 2 + 320, img_size[1]],
                  [img_size[0] / 2 - 320, img_size[1]]])

offset_x = 300  # offset for dst points
offset_y = 400
dst = np.float32([[offset_x, offset_y],
                  [img_size[0] - offset_x, offset_y],
                  [img_size[0] - offset_x, img_size[1]],
                  [offset_x, img_size[1]]])

M = cv2.getPerspectiveTransform(src, dst)
M_inv = cv2.getPerspectiveTransform(dst, src)


def binary_warp(img, mtx, dist):
    hls_binary = hls_select(img, thresh=(50, 255))
    img_new = cv2.undistort(hls_binary, mtx, dist, None, mtx)
    warped = cv2.warpPerspective(img_new, M, img_size, flags=cv2.INTER_LINEAR)
    return warped


def poly_fit(img):
    histogram = np.sum(img[int(img.shape[0] / 2):, :], axis=0)
    # Create an output image to draw on and  visualize the result
    out_img = np.dstack((img, img, img)) * 255
    # Find the peak of the left and right halves of the histogram
    # These will be the starting point for the left and right lines

    midpoint = np.int(histogram.shape[0] / 2)
    leftx_base = np.argmax(histogram[:midpoint])
    rightx_base = np.argmax(histogram[midpoint:]) + midpoint
#     print("left base {},right base {}".format(leftx_base,rightx_base))

    # Choose the number of sliding windows
    nwindows = 10
    # Set height of windows
    window_height = np.int(img.shape[0] / nwindows)
#     print("Using window height {}".format(window_height))

    # Identify the x and y positions of all nonzero pixels in the image
    nonzero = img.nonzero()
    nonzeroy = np.array(nonzero[0])
    nonzerox = np.array(nonzero[1])

    # Current positions to be updated for each window
    leftx_current = leftx_base
    rightx_current = rightx_base

    # Set the width of the windows +/- margin
    margin = 100
    # Set minimum number of pixels found to recenter window
    minpix = 50
    # Create empty lists to receive left and right lane pixel indices
    left_lane_inds = []
    right_lane_inds = []

    # Step through the windows one by one
    for window in range(nwindows):
        # Identify window boundaries in x and y (and right and left)
        win_y_low = img.shape[0] - (window + 1) * window_height
        win_y_high = img.shape[0] - window * window_height
        win_xleft_low = leftx_current - margin
        win_xleft_high = leftx_current + margin
        win_xright_low = rightx_current - margin
        win_xright_high = rightx_current + margin

        # Draw the windows on the visualization image
        cv2.rectangle(out_img, (win_xleft_low, win_y_low),
                      (win_xleft_high, win_y_high), (0, 255, 0), 3)
        cv2.rectangle(out_img, (win_xright_low, win_y_low),
                      (win_xright_high, win_y_high), (0, 255, 0), 3)

        # Identify the nonzero pixels in x and y within the window
        good_left_inds = ((nonzeroy >= win_y_low) & (nonzeroy < win_y_high) &
                          (nonzerox >= win_xleft_low) & (nonzerox < win_xleft_high)).nonzero()[0]
        good_right_inds = ((nonzeroy >= win_y_low) & (nonzeroy < win_y_high) &
                           (nonzerox >= win_xright_low) & (nonzerox < win_xright_high)).nonzero()[0]

        # Append these indices to the lists
        left_lane_inds.append(good_left_inds)
        right_lane_inds.append(good_right_inds)

        # If you found > minpix pixels, recenter next window on their mean position
        if len(good_left_inds) > minpix:
            leftx_current = np.int(np.mean(nonzerox[good_left_inds]))
        if len(good_right_inds) > minpix:
            rightx_current = np.int(np.mean(nonzerox[good_right_inds]))

    # Concatenate the arrays of indices
    left_lane_inds = np.concatenate(left_lane_inds)
    right_lane_inds = np.concatenate(right_lane_inds)

    # Extract left and right line pixel positions
    leftx = nonzerox[left_lane_inds]
    lefty = nonzeroy[left_lane_inds]
    rightx = nonzerox[right_lane_inds]
    righty = nonzeroy[right_lane_inds]

    # Fit a second order polynomial to each
    left_fit, right_fit = None, None
    if lefty.any() and leftx.any():
        left_fit = np.polyfit(lefty, leftx, 2)
    if righty.any() and rightx.any():
        right_fit = np.polyfit(righty, rightx, 2)
#     print(left_fit)
#     print(right_fit)
    return left_fit, right_fit

# def poly_fit(img,left_fit,right_fit):
#     # Assume you now have a new warped binary image
#     # from the next frame of video (also called "binary_warped")
#     # It's now much easier to find line pixels!
#     nonzero = binary_warped.nonzero()
#     nonzeroy = np.array(nonzero[0])
#     nonzerox = np.array(nonzero[1])
#     margin = 100
#     left_lane_inds = ((nonzerox > (left_fit[0]*(nonzeroy**2) + left_fit[1]*nonzeroy + left_fit[2] - margin)) &
#                       (nonzerox < (left_fit[0]*(nonzeroy**2) + left_fit[1]*nonzeroy + left_fit[2] + margin)))
#     right_lane_inds = ((nonzerox > (right_fit[0]*(nonzeroy**2) + right_fit[1]*nonzeroy + right_fit[2] - margin)) &
#                        (nonzerox < (right_fit[0]*(nonzeroy**2) + right_fit[1]*nonzeroy + right_fit[2] + margin)))

#     # Again, extract left and right line pixel positions
#     leftx = nonzerox[left_lane_inds]
#     lefty = nonzeroy[left_lane_inds]
#     rightx = nonzerox[right_lane_inds]
#     righty = nonzeroy[right_lane_inds]

#     # Fit a second order polynomial to each
#     left_fit = np.polyfit(lefty, leftx, 2)
#     right_fit = np.polyfit(righty, rightx, 2)

#     return left_fitx, right_fit


def curvature(ploty, leftx, rightx):
    # Define conversions in x and y from pixels space to meters
    ym_per_pix = 30 / 720  # meters per pixel in y dimension
    xm_per_pix = 3.7 / 700  # meters per pixel in x dimension

    # Define y-value where we want radius of curvature
    # I'll choose the maximum y-value, corresponding to the bottom of the image
    y_eval = np.max(ploty)

    # Fit new polynomials to x,y in world space
    left_fit_cr = np.polyfit(ploty * ym_per_pix, leftx * xm_per_pix, 2)
    right_fit_cr = np.polyfit(ploty * ym_per_pix, rightx * xm_per_pix, 2)
    # Calculate the new radii of curvature
    left_curverad = ((1 + (2 * left_fit_cr[0] * y_eval * ym_per_pix +
                           left_fit_cr[1])**2)**1.5) / np.absolute(2 * left_fit_cr[0])
    right_curverad = ((1 + (2 * right_fit_cr[0] * y_eval * ym_per_pix +
                            right_fit_cr[1])**2)**1.5) / np.absolute(2 * right_fit_cr[0])
    # Now our radius of curvature is in meters
#     print(left_curverad, 'm', right_curverad, 'm')
#     print(left_fit_cr[0]*y_eval*ym_per_pix, 'm', right_fit_cr[0]*y_eval*ym_per_pix, 'm')
    return left_curverad, right_curverad


def draw_lane(img, ploty, left_fitx, right_fitx):
    img_new = img.copy()
    # Create an image to draw the lines on
    warp_zero = np.zeros_like(img).astype(np.uint8)
    color_warp = warp_zero  # np.dstack((warp_zero, warp_zero, warp_zero))

    # Recast the x and y points into usable format for cv2.fillPoly()
    pts_left = np.array([np.transpose(np.vstack([left_fitx, ploty]))])
    pts_right = np.array(
        [np.flipud(np.transpose(np.vstack([right_fitx, ploty])))])
    pts = np.hstack((pts_left, pts_right))

    # Draw the lane onto the warped blank image
    cv2.fillPoly(color_warp, np.int_([pts]), (0, 255, 0))

    # Warp the blank back to original image space using inverse perspective matrix (Minv)
    newwarp = cv2.warpPerspective(
        color_warp, M_inv, (img.shape[1], img.shape[0]))

    # Combine the result with the original image
    img_new = cv2.addWeighted(img_new, 1, newwarp, 0.3, 0)
    return img_new


def draw_info(img, curv, center_dist):
    img_new = np.copy(img)
    h = img_new.shape[0]
    font = cv2.FONT_HERSHEY_SIMPLEX
    text = 'Curvature : {:4.2f}'.format(curv) + 'm'
    cv2.putText(img_new, text, (40, 70), font, 1,
                (255, 255, 255), 2, cv2.LINE_AA)
    direction = ''
    if center_dist > 0:
        direction = 'right'
    elif center_dist < 0:
        direction = 'left'
    abs_center_dist = abs(center_dist)
    text = '{:4.3f}'.format(abs_center_dist) + 'm ' + direction + ' of center'
    cv2.putText(img_new, text, (40, 120), font, 1,
                (255, 255, 255), 2, cv2.LINE_AA)
    return img_new


def pipeline(img):
    undistort = cv2.undistort(img, mtx, dist, None, mtx)
    hls_binary = hls_select(undistort, thresh=(100, 255))
    warped = cv2.warpPerspective(
        hls_binary, M, img_size, flags=cv2.INTER_LINEAR)
    left_fit, right_fit = poly_fit(warped)
    if left_fit == None or right_fit == None:
        return img
    # Generate x and y values for plotting
    ploty = np.linspace(0, img.shape[0] - 1, img.shape[0])
    left_fitx = left_fit[0] * ploty**2 + left_fit[1] * ploty + left_fit[2]
    right_fitx = right_fit[0] * ploty**2 + right_fit[1] * ploty + right_fit[2]

    curv_left, curv_right = curvature(ploty, left_fitx, right_fitx)
    result = draw_lane(undistort, ploty, left_fitx, right_fitx)
    result = draw_info(result, (curv_left + curv_right) / 2, 0)
    return result


def poly_fit_update(img, left_fit, right_fit):
    # Choose the number of sliding windows
    nwindows = 10
    # Set height of windows
    window_height = np.int(img.shape[0] / nwindows)
#     print("Using window height {}".format(window_height))

    # Identify the x and y positions of all nonzero pixels in the image
    nonzero = img.nonzero()
    nonzeroy = np.array(nonzero[0])
    nonzerox = np.array(nonzero[1])

    # Current positions to be updated for each window
    leftx_current = np.int(left_fit[2])
    rightx_current = np.int(right_fit[2])

    # Set the width of the windows +/- margin
    margin = 50
    # Set minimum number of pixels found to recenter window
    minpix = 25
    # Create empty lists to receive left and right lane pixel indices
    left_lane_inds = []
    right_lane_inds = []

    # Step through the windows one by one
    for window in range(nwindows):
        poly_y = (window + 1) * window_height
        # Identify window boundaries in x and y (and right and left)
        win_y_low = img.shape[0] - (window + 1) * window_height
        win_y_high = img.shape[0] - window * window_height
        win_xleft_low = leftx_current - margin
        win_xleft_high = leftx_current + margin
        win_xright_low = rightx_current - margin
        win_xright_high = rightx_current + margin

        # Identify the nonzero pixels in x and y within the window
        good_left_inds = ((nonzeroy >= win_y_low) & (nonzeroy < win_y_high) &
                          (nonzerox >= win_xleft_low) & (nonzerox < win_xleft_high)).nonzero()[0]
        good_right_inds = ((nonzeroy >= win_y_low) & (nonzeroy < win_y_high) &
                           (nonzerox >= win_xright_low) & (nonzerox < win_xright_high)).nonzero()[0]

        # Append these indices to the lists
        left_lane_inds.append(good_left_inds)
        right_lane_inds.append(good_right_inds)

        # If you found > minpix pixels, recenter next window on their mean position
        if len(good_left_inds) > minpix:
            leftx_current = np.int(
                left_fit[0] * poly_y**2 + left_fit[1] * poly_y + left_fit[2])
        if len(good_right_inds) > minpix:
            rightx_current = np.int(
                right_fit[0] * poly_y**2 + right_fit[1] * poly_y + right_fit[2])

    # Concatenate the arrays of indices
    left_lane_inds = np.concatenate(left_lane_inds)
    right_lane_inds = np.concatenate(right_lane_inds)

    # Extract left and right line pixel positions
    leftx = nonzerox[left_lane_inds]
    lefty = nonzeroy[left_lane_inds]
    rightx = nonzerox[right_lane_inds]
    righty = nonzeroy[right_lane_inds]

    # Fit a second order polynomial to each
    left_fit, right_fit = None, None
    if lefty.any() and leftx.any():
        left_fit = np.polyfit(lefty, leftx, 2)
    if righty.any() and rightx.any():
        right_fit = np.polyfit(righty, rightx, 2)
    return left_fit, right_fit