1. Traffic Sign Recognition
for Computer Vision Project-Based Learning
Tripti Kumari and Vijay Pratap Singh
S7, Computer Science & Engineering
School of Engineering
Cochin University of Science & Engineering

2. Contents
•
•
•
•
•
•
•
•
•
•
•
Introduction
Why CV for TSR
Objectives
Traffic Sign Classes
Detection Method
Complexity
Approach
Image Processing in Matlab
Algorithms & Sudo Code
Conclusion
References

3. Introduction
• Traffic sign detection and recognition
have received an increasing interest in
the last years. This is due to the wide
range of applications that a system with
this capability provides, like Driving
Assistance System.
• This is an attempt to make a self learning
system that can itself understand and
interpret the meaning of new traffic
signs.

4. Why Computer Vision for Traffic Sign
• Highway maintenance: Check the presence and condition of signs along major
roads.
• Sign inventory: Creating an inventory of signs in city environments.
• Driver support systems: Assist the driver by informing of current restrictions,
limits, and warnings.
• Intelligent autonomous vehicles: Any autonomous car that is to drive on public
roads must have a means of obtaining the current traffic regulations. This can
be done through TSR.

5. Objectives
1. The system has to be able to detect traffic signs independently of their
appearance in the image. Because of that, it has to be invariant to:
•
•
•
•
Perspective distortion.
Lighting changes.
Partial occlusions.
Shadows.
2. In addition, it has to provide information about the presence of possible
problems:
• Lack of visibility.
• Bad condition.
• Bad placement

6. Traffic Sign Classes
• Guide and recreational traffic signs
•
•
•
• Regulatory traffic signs
•
•
•
•
•
•
•
Road construction traffic signs
Warning traffic signs

7. Detection Methods
• Traffic sign detection methods are inherently dependent on the nature of
data for which they were developed.
• The approaches that we are going to follow in the detection stage have
traditionally been divided into two kinds:
1. Color based methods.
2. Shape based methods.

8. Color Based Detection
• Understanding of different colors
• Color based segmentation

9. Shape Based Detection

10. Complexity
• Input type: videos or static images?
• Scope of the method: is the method
applicable for a single traffic sign
class or for multiple classes?
• Filming conditions: is the data shot in
broad daylight, in nighttime or
both? Are there adverse weather
conditions such as rain, snow, fog?

11. Complexity
• Sensor type: high resolution or low
resolution camera, grayscale or
color? Multiple cameras? Other
sensors?
• Processing requirements: should the
signs be detected in realtime or is
offline processing acceptable?
• Acceptable true positive and false
positive rates: determined by the
nature of the problem.

12. Approach
• The general flow followed by typical sign detection algorithms.

13. Approach
• Collection of frames using video segmentation

14. Block Diagram

15. Flow Chart

16. Image Processing in MATLAB
• Basic Commands
•
•
•
•
•
•
Imread
Imshow
Rgb2gray
Imhist
Imadjust
im2bw
• Useful Libraries for this project
• Image Processing Toolbox
• Image Acquisition Toolbox
• Computer Vision Toolbox

17. Algorithms & Sudo Code

18. Algorithms & Sudo Code
Video Segmentation in MATLAB
Capturing Video from External Camera (using imaqtool command)

19. Algorithms & Sudo Code
• Memory management for processing large video files.

20. Algorithms & Sudo Code
• Image Compression for minimizing the memory use.
Approach
1: Read in image
2: Convert to gray scale
3: Display
4: Take Discrete Cosine Transform
5: Toss out higher order terms
6: Compare results to original
picture
7: The built in function dct2 uses an
FFT-like algorithm to compute
transform.

21. Conclusion
• The algorithm that has been used for traffic signs it can be generalized to
deal with other kinds of objects.
• The known difficulties that exist for object recognition in outdoor
environments have been considered. This way the system is immune to
lighting changes, occlusions and object deformation being useful for
Driver Support Systems.
• Due to this knowledge of the sign status, it is believed that the system is
useful for other applications such as maintenance and inventories of
traffic sign in highways and or cities.

22. References
●
[1] ●Karla Brkic, Department of Electronics, Microelectronics,
Computer and Intelligent Systems, Electrical Engineering and
Computing, Unska 3, 10000 Zagreb, Croatia, 2011
•
[2] Andreas Møgelmose, Vision, Graphips, and Interactive Systems,
• AAU, Computer Vision and Robotics Research Lab, UCSD, 2012
•
●
●
●
[3] David Gerónimo, Joan Serrat, Antonio M. López, Member, IEEE,
and Ramon Baldrich, Traffic Sign Recognition for Computer Vision
Project-Based Learning, 2012
●

23. Thank-you…