Road Detection

Objective: Use OpenCV Code to explore features that are effective for lane detection such as Binary, Edge, Line, Difference, RGB, and HSV transformations. Add HSV decomposition to the code.

import threading
import numpy as np
import cv2 as cv
from PIL import Image, ImageTk
from tkinter import Tk, Frame, Button, BOTH, Label, Scale, Radiobutton       # Graphical User Inetrface Stuff
from tkinter import font as tkFont
import tkinter as tk

camera = cv.VideoCapture(0)
width = int(camera.get(cv.CAP_PROP_FRAME_WIDTH))
height = int(camera.get(cv.CAP_PROP_FRAME_HEIGHT))
videoout = cv.VideoWriter('./Video.avi', cv.VideoWriter_fourcc(*'XVID'), 25, (width, height))   # Video format

# Button Definitions
ORIGINAL = 0
BINARY = 1
EDGE = 2
LINE = 3
ABSDIFF = 4
RGB = 5
HSV = 6

def cvMat2tkImg(arr):           # Convert OpenCV image Mat to image for display
    rgb = cv.cvtColor(arr, cv.COLOR_BGR2RGB)
    img = Image.fromarray(rgb)
    return ImageTk.PhotoImage(img)

class App(Frame):
    def __init__(self, winname='OpenCV'):       # GUI Design

        self.root = Tk()
        self.stopflag = True
        self.buffer = np.zeros((height, width, 3), dtype=np.uint8)

        global helv18
        helv18 = tkFont.Font(family='Helvetica', size=18, weight='bold')
        # print("Width",windowWidth,"Height",windowHeight)
        self.root.wm_title(winname)
        positionRight = int(self.root.winfo_screenwidth() / 2 - width / 2)
        positionDown = int(self.root.winfo_screenheight() / 2 - height / 2)
        # Positions the window in the center of the page.
        self.root.geometry("+{}+{}".format(positionRight, positionDown))
        self.root.wm_protocol("WM_DELETE_WINDOW", self.exitApp)
        Frame.__init__(self, self.root)
        self.pack(fill=BOTH, expand=1)
        # capture and display the first frame
        ret0, frame = camera.read()
        image = cvMat2tkImg(frame)
        self.panel = Label(image=image)
        self.panel.image = image
        self.panel.pack(side="top")
        # buttons
        global btnStart
        btnStart = Button(text="Start", command=self.startstop)
        btnStart['font'] = helv18
        btnStart.pack(side='right', pady = 2)
        # sliders
        global Slider1, Slider2
        Slider2 = Scale(self.root, from_=0, to=255, length= 255, orient='horizontal')
        Slider2.pack(side='right')
        Slider2.set(255)
        Slider1 = Scale(self.root, from_=0, to=255, length= 255, orient='horizontal')
        Slider1.pack(side='right')
        Slider1.set(0)
        # radio buttons
        global mode
        mode = tk.IntVar()
        mode.set(ORIGINAL)
        Radiobutton(self.root, text="Original", variable=mode, value=ORIGINAL).pack(side = 'left', pady = 4)
        Radiobutton(self.root, text="Binary", variable=mode, value=BINARY).pack(side = 'left', pady = 4)
        Radiobutton(self.root, text="Edge", variable=mode, value=EDGE).pack(side = 'left', pady = 4)
        Radiobutton(self.root, text="Line", variable=mode, value=LINE).pack(side='left', pady=4)
        Radiobutton(self.root, text="Abs Diff", variable=mode, value=ABSDIFF).pack(side='left', pady=4)
        Radiobutton(self.root, text="RGB", variable=mode, value=RGB).pack(side='left', pady=4)
        Radiobutton(self.root, text="HSV", variable=mode, value=HSV).pack(side='left', pady=4)
        # threading
        self.stopevent = threading.Event()
        self.thread = threading.Thread(target=self.capture, args=())
        self.thread.start()

    def capture(self):
        while not self.stopevent.is_set():
            if not self.stopflag:
                ret0, frame = camera.read()
                if mode.get() == BINARY:
                    if Slider1.get() > 0 and Slider1.get() < 255:
                        frame = cv.inRange(frame, (Slider1.get(), Slider1.get(), Slider1.get()), (Slider2.get(), Slider2.get(), Slider2.get()))
                elif mode.get() == EDGE:
                    frame = cv.Canny(frame, Slider1.get(), Slider2.get())
                elif mode.get() == LINE:
                    gray = cv.Canny(frame, Slider1.get(), Slider2.get())
                    lines = cv.HoughLinesP(gray, 1, np.pi/180, 100, minLineLength=10, maxLineGap=30)
                    if lines is None: continue
                    for line in lines:
                        x1, y1, x2, y2 = line[0]
                        cv.line(frame, (x1, y1), (x2, y2), (0, 255, 0), 2)
                elif mode.get() == ABSDIFF:
                    temp = frame
                    frame = cv.absdiff(frame, self.buffer)
                    self.buffer = temp
                elif mode.get() == RGB:
                    half = cv.resize(frame, (int(width/2), int(height/2)))
                    b,g,r = cv.split(half)
                    top = cv.hconcat([half, cv.merge((r, r, r))])
                    bottom = cv.hconcat([cv.merge((g, g, g)), cv.merge((b, b, b))])
                    frame = cv.vconcat([top, bottom])

                image = cvMat2tkImg(frame)
                self.panel.configure(image=image)
                self.panel.image = image
                videoout.write(frame)

    def startstop(self):        #toggle flag to start and stop
        if btnStart.config('text')[-1] == 'Start':
            btnStart.config(text='Stop')
        else:
            btnStart.config(text='Start')
        self.stopflag = not self.stopflag

    def run(self):              #run main loop
        self.root.mainloop()

    def exitApp(self):          #exit loop
        self.stopevent.set()
        self.root.quit()


app = App()
app.run()
#release the camera
camera.release()
cv.destroyAllWindows()

Lane Detection

Alerts from driving assist and self-driving cars must detect the road path. There are many strategies to detect the lane and road path. A preliminary step is to create contrast between lane markings and road surface. This is important to determine the continuity of a lane boundary even when there are dashed lines. The region of interest (ROI) helps to focus on specific parts of the image such as the lower half so that the sky is ignored. The ROI may be predicted using the previous frame if the car is changing incline over a hill. Conditions such as fixed or smoothly varying lane width can also limit the search to parallel lane markings and help to reduce false positives.

There are also many road geometry assumptions such as straight, curved, parabola, quadratic, and 3D horizontal and vertical curvature models. Multi-cue fusion includes lane markers, road edges, road color, non-road color, road width, and elastic lanes. Prior work includes hypothesis validation, mean shift algorithm, neural network based (e.g. ALVINN), and temporal correction with position and orientation with respect to the center line between two lane markings. Autopilot features have advanced to the point of commercialized self-driving cars with driver assist when needed. Full autonomy may soon be a standard feature.

Exercise

Start with the OpenCV Demo script to explore various methods to increase the contrast for lane detection. Add a quad split similar to the RGB option but that shows Hue, Saturation, and Value (HSV) in this alternate color space. Point the camera at a photo of a road and adjust the lower and upper tolerance to clearly distinguish the road area.

Run the Demo_OpenCV.py script and click Start to begin the image capture. Select the radio buttons to switch between modes.

The radio button for HSV is missing the correct code to split and view the image in separate channels. Add the HSV code and display the separate channels. Adjust the tolerance sliders to improve the road and lane detection.

elif mode.get() == HSV:
    half = cv.resize(frame, (int(width/2), int(height/2)))
    hsv = cv.cvtColor(half, cv.COLOR_BGR2HSV)
    h,s,v = cv.split(hsv)
    if Slider1.get() > 0 and Slider1.get() < 255:
        kernel = cv.getStructuringElement(cv.MORPH_RECT, (3, 3))
        s = cv.inRange(s, Slider1.get(), Slider2.get())
        s = cv.morphologyEx(s, cv.MORPH_OPEN, kernel)
        v = cv.inRange(v, Slider1.get(), Slider2.get())
        v = cv.morphologyEx(v, cv.MORPH_OPEN, kernel)
    top = cv.hconcat([half, cv.merge((h, h, h))])
    bottom = cv.hconcat([cv.merge((s, s, s)), cv.merge((v, v, v))])
    frame = cv.vconcat([top, bottom])

Thanks to DJ Lee, BYU ECE Professor, for the computer vision material and for sharing research and industrial experience with the class.

💬