Addis Ababa University AAiT School of Electrical and Computer Engineering February 20, 201 Semester Project Automatic Density Based Traffic Light Control Using Image Processing
Addis Ababa UniversityAAiT
School of Electrical and Computer Engineering
February 20, 2015
Semester Project
Automatic Density Based Traffic Light Control Using Image Processing
Prepared By: Abebe Alemu Yohannes Fitsum
Getinet Ayenew Abenet Ashagre
February 20, 2015
Advisor: Andinet Negash
Introduction Traffic Light System Using Image Processing?
Significance Traffic Congestion, Green Light for empty road
How it differs from existing system Traditional Systems With IR Sensors
1
3
2. Objective
Select & Implement Proper Image Processing Techniques Design a traffic light system that accepts signal from the image processing output
Select a stepper motor that is used to rotate the camera
To integrate all the three systems
4
Image Processing (MATLAB)
Camera mounted on
Stepper Motor(Proteus)
Traffic Light System
(LabVIEW)
Implementation
5
Reference image Captured Image
RGB to gray conversion
RGB to gray conversion
Image Resizing Image Resizing
Image enhancement
Image enhancement
Edge Detection Edge Detection
Image Matching
Timing Allocation
Image Processing
%match = No. of pixels matched successfully total no. of pixels
• If the matching is between 0 to 10% - green light is on for 90 seconds.• If the matching is between 10 to 50% - green light is on for 60 seconds.• If the matching is between 50 to 70% - green light is on for 30 seconds.• If the matching is between 70 to 90% - green light is on for 20 seconds.• If the matching is between 90 to 100% - green light is on for 10 seconds.
7
Why Canny Edge Detection?less sensitive to noise, adaptive in nature, resolved the problem of streaking, provides good localization detects sharper edges
Why Edge Detection, Why Not Counting Number Of Cars? Accuracy
Estimation
11
Traffic Light System
Survey at Kidist Mariam roundabout Implemented using LabVIEW
For Vehicles
Road 1 Road 2 Road 3 Road 4Red Green Red RedGreen Red Red RedRed Red Red GreenRed Red Green Red
For Pedestrians
Stop Stop Stop WalkStop Stop Walk StopWalk Walk Stop StopWalk Walk Stop Stop
12
Stepper Motor Why Stepper Motor?
Accuracy Low power consumption Cheap compared to servo motors Have low inertia
13
IntegrationImage
Processing (MATLAB)
Camera mounted on Stepper
Motor(Proteus)
Traffic Light System
(LabVIEW)
VSP Emulator VSP Emulator
To increase the efficiency of the image processing part
6
To implement the integrated system using DSP
Future Wok