Traffic Sign Recognition

1
Traffic Sign Recognition

• Jacob Carlson Sean St. Onge
• Advisor Dr. Thomas L. Stewart

2
Traffic Sign Recognition

• Project Overview
• System Description
• Performance Expectations
• Preliminary Work
• Schedule of Tasks

3
Traffic Sign Recognition

• Project Overview
• System Description
• Performance Expectations
• Preliminary Work
• Schedule of Tasks

4
Traffic Sign Recognition

• Object identification has many applications in
  various fields. This project aims to identify a
  traffic sign from a digital image. This would be
  useful in an autonomous vehicle application.
  These ideas and methods could also be used in
  other areas.

5
Traffic Sign Recognition

• The overall objective of this project is to write
  a program what will identify a traffic sign from
  a digital photograph.
• Traffic signs appear in diverse background
  situations and, at times, may be partially
  obscured.
• The software should be able to function in spite
  of these issues.

6
Traffic Sign Recognition

• Project Overview
• System Description
• Performance Expectations
• Preliminary Work
• Schedule of Tasks

7
Traffic Sign Recognition
8
Traffic Sign Recognition

• When the program is initialized, an image,
  previously saved on the systems hard drive, is
  loaded for analysis.
• At this point, some preliminary analysis will be
  performed, and preprocessing algorithms will be
  applied, if necessary.

9
Traffic Sign Recognition

• Once the image is adjusted as needed, the
  software will apply the main image processing
  algorithms.
• This portion of the program will gather and
  analyze color data, and will also perform edge
  detection.
• Additional methods requiring further research may
  also be applied at this time.

10
Traffic Sign Recognition

• If a sign is identified in the image, it will be
  classified.
• After classification, the software will highlight
  the image or area of interest.
• The software will then write pertinent data to
  either the screen or an output file.

11
Traffic Sign Recognition

• Project Overview
• System Description
• Performance Expectations
• Preliminary Work
• Schedule of Tasks

12
Traffic Sign Recognition

• Sample calculation for real-time implementation
• Image size of 500x500 pixels.
• 250,000 data points time three color planes.
  This gives 750,000 data points.
• At 30 frames per second this equates to 22.5
  million data points per second.

13
Traffic Sign Recognition

• At 22.5 million data points per second the speed
  required for processing images is too ambitious
  for this project.
• For this reason we will process discrete images
  only.

14
Traffic Sign Recognition

• Project Overview
• System Description
• Performance Expectations
• Preliminary Work
• Schedule of Tasks

15
Traffic Sign Recognition

• Design team has done preliminary research into
  the fundamentals of image processing.
• Design team has completed several digital image
  processing tutorials and experimented with basic
  color detection.

16
Traffic Sign Recognition

• Add color plane breakdown here.

17
Traffic Sign Recognition

• Average intensity.

18
Traffic Sign Recognition

• Project Overview
• System Description
• Performance Expectations
• Preliminary Work
• Schedule of Tasks

19
Traffic Sign Recognition
20
Traffic Sign Recognition

• If sufficient progress is made on this problem,
  the design team may also decide to apply some of
  these image processing algorithms to camouflage
  recognition.

21
Questions?