Continue to Site

Welcome to EDAboard.com

Welcome to our site! EDAboard.com is an international Electronics Discussion Forum focused on EDA software, circuits, schematics, books, theory, papers, asic, pld, 8051, DSP, Network, RF, Analog Design, PCB, Service Manuals... and a whole lot more! To participate you need to register. Registration is free. Click here to register now.

Image processing for self drive car

Status
Not open for further replies.

alexgrame

Newbie
Joined
Aug 9, 2018
Messages
1
Helped
0
Reputation
0
Reaction score
0
Trophy points
1
Activity points
18
Hi experts!
this is my first post in this forum. thanks edaboard

I am final year engineering student. My final year project is Self drive car in which i will use Raspberry pi development board.
My flow char for this project is:

capture image from front camera ==> lane detection using python==> steer the car in between the lines

I think i will successfully perform first two steps. but i am really confused in third step.
How i will transform image into a signal which steers the car motors to remain in center of the road lanes either the road is curved or straight.
Please help me to find the solution. Thank you so much:cool::cool:
 

Hi,

Do a test with two humans on a closed road:
* one person simulates the camera and the lane detection
* the other person is steering the car

Blindfold the person who is steering the car.
He must just perform your commands.
"Left", "right" ....


****
The same needs to happen with your application:
The python software needs to output similar commands. "Left", "right" ....

And a motor(controller) needs to receive the commands and control the steering wheel.

Either you can use the built in motor for servo controlled steering or you must install an additional motor.


Klaus
 

On a technical level, you need to find where the lines are in the image and then find the center point between them. If the center of the image is to the left of the center of the lines, steer right, if it's to the right, steer left. The critical points are the center of the camera image (assuming it looks along the vehicle axis) and the center point of the two lines.

You need to do some image analysis to find the center of the lines, the image center is just half the horizontal camera resolution. As the image is mapped to video memory space, it may be possible to scan addresses corresponding to a horizontal line in the picture to find the two lighter points or you could do it by sampling brightness at a set of points within the image to find them. It would be wise to scan several horizontal lines, the danger of scanning a single one is it can only find gradual bends in the path, if for example there was an abrupt turn, one of the lines could fall outside the image area and the center calculation would fail.

Brian.
 

Status
Not open for further replies.

Part and Inventory Search

Welcome to EDABoard.com

Sponsor

Back
Top