Real Time Traffic Sign Analysis- This subject deals with Recognition and Detection of Traffic sign by Image Processing Techniques...

1. REAL TIME TRAFFIC
SIGN ANALYSIS
Presented By-
Rakesh Ravaso Patil
T CO ‘B’ 12276
Guided By-
Ms. P. P. Lokhande

2. Overview
 Introduction
 Traffic sign analysis
 Color segmentation
 Edge detection
 Shape based detection
 Recognition
 Binary Thresholding
 Recognition and Matching using IPP
 Recognition of traffic signs using FPGA hardware
 How TSR is works?
 Conclusion

3. INTRODUCTION
 Advanced Driver Assistance Systems (ADAS)
 Lane Departure Warning
 Night Vision
 Automatic Parking
 Blind Spot Detection
 Traffic Sign Recognition
 First used In
 BMW 7 Series
 Volkswagen Phaeton

4. WHY WE REQUIRE THIS?
 Sleepy driver crashes SUV on Mumbai-Pune
Expressway, 7 passengers killed. (TOI, March 5)
 Human error behind most Expressway mishaps.
(TOI, March 5)
 In 2012, the expressway, witnessed 475 accidents in
which 105 people died.
 MSRDC plan:
 Trauma Care & Copter Service
 CCTV Cameras
 Truck Terminals
 Reducing U-Turns

5. TRAFFIC SIGN
Possible
Sign Type Sign Shape
(Border) Colors
Triangle,
Restricting &
Red, Blue, Black Rectangle, Octagon,
Warning
Circle
Information Blue, Red Rectangle
Highway
Green Rectangle
Information
Table: Standard Traffic Sign

6. REAL TIME TRAFFIC SIGN ANALYSIS
 Detection
 Recognition
 Problem facing
 Illumination affects the color analysis.
 Occlusion affects the shape analysis.
 Weather conditions such as rain, snow or fog
affect the shape extraction.
 Physically damaged or changed surface metal of
traffic signs affects the recognition.

7. TRAFFIC SIGN ANALYSIS
Fig: Steps of TSR System

8. COLOR SEGMENTATION
Fig: Traffic sign and Red/Blue segmented image

9. COLOR SEGMENTATION-ADVANTAGES
 Eliminates undesired colors, thus the number of
edge pixels in the edge detection process decreases.
 The complexity decreases since only edge pixels are
processed.
 Fault detections decrease in the detection process.
 Color segmentation gives information about the
border color and the inner color of the sign.

10. EDGE DETECTION
 Identifying points in a digital image at which the
image brightness changes sharply
Fig: Edge image with color segmentation

11. SHAPE BASED DETECTION
 Types: Triangle, Circle and Rectangle
 TRIANGULAR SIGN DETECTION
 Hough Transform using Slope-Intercept Line equ.
y=a.x + b
where: x,y are coordinates
a is the slope of the line
b is the constant parameter…
 Use of Polar Coordinates instead of Cartesian
Coordinates.

12. TRIANGULAR SIGN DETECTION
x.cosΘ + y.sinΘ=r
Where: r is distance between line & Origin
Θ is angle from origin to the closest point to line

13. TRIANGULAR SIGN DETECTION
Fig: Edge Image of a Triangular Fig: Detected Lines after applying
Traffic sign Hough Transform

14. CIRCULAR SIGN DETECTION
 Circular Hough Transform using parametric equation
of Circle:
(x-xc)² + (y-yc)² = r²
 Because of Perspective distortion Circular traffic
sign may appear as elliptical.
(x-xc)² + k.(y-yc)² = r²

15. CIRCULAR SIGN DETECTION
Fig: Detected Circle after applying CHT Fig: Detected Ellipse after applying
Ellipse Detection

16. RECTANGULAR SIGN DETECTION
Fig: Detected Lines of Rectangular
Traffic Sign

17. RECOGNITION
 A binary image is generated using ROI of the image.
 Morphological operations are applied to the binary
image in order to remove the unwanted pixels.
 Informative Pixel Percentage (IPP).

18. BINARY THRESHOLDING
 ROI is the informative part of the image.
 Traffic sign consists of only two different colors. One
is the informative color of ROI and the other is the
background color.
Fig: Output of Binarization Process

19. RECOGNITION AND MATCHING
USING IPP
 TRIANGULAR SIGN RECOGNITION
Fig: Divided Regions of Triangular Sign

20. CIRCULAR, RECTANGULAR SIGN
RECOGNITION
Fig: Divided Regions of Circular and Rectangular Sign

21. RECOGNITION OF TRAFFIC SIGNS
USING FPGA HARDWARE
 VIRTEX5-FX70T FPGA
 XILINX Platform flash PROM
 DDR2 SDRAM
 LCD Display

22. HOW TSR IS WORKS?

23. CONCLUSION
 Automatic traffic sign detection and recognition is an
important part of an ADAS.
 Traffic symbols have several distinguishing features
that may be used for their recognition and
detection.
 There are several factors that can hinder effective
detection and recognition of traffic signs.
 The performance of the TSR system can be improved
with increasing the number of divided regions.