Abstract:
As society has advanced, cars have become a means of transportation. The narrow road has more vehicles of various types. Car accidents kill more people each year as more cars are on the road. How to drive safely on congested roads has become the focus.
Lane detection is hard. It has fascinated computer vision researchers for years. Computer vision and machine learning methods have struggled with multi-feature lane detection. The Lane Detection System uses complex lane markers to accurately estimate the vehicle’s position and trajectory in the lane.
Canny Edge Detection starts this system. It reads and detects edges in the frame, then converts it to grayscale using cv2’s convert colour function and blurs it with Gaussian Blur to reduce edges. Our lane is cropped next. The region of interest function extracts the height and width of the canny edge detection image and applies a mask to remove everything except the mask.
NumPy will crop the frame and create a triangle to locate the lanes. Third, apply the Hough Line Transform. The algorithm estimates a line in a canny image. CV2 includes it.
Fourth operation: Average Slope-Intercept. It locates lines using Hough Line Transform images. Out of all lines, the function only cares about lanes. This function uses make_points, which uses the Slope intercept function to detect line slopes.
Operation Display Lines 5. This function accepts an original frame and the Average Slope intercept lines. Lines are detected and plotted on blank images. The function returns a line-drawn image. The sixth step adds display lines to the frame. Combining the original frame and detected lines yields a combo image.
Note: Please discuss with our team before submitting this abstract to the college. This Abstract or Synopsis varies based on student project requirements.
Did you like this final year project?
To download this project Code with thesis report and project training... Click Here
