traffic sign recognition

31
Traffic Sign Recognition Jacob Carlson Sean St. Onge Advisor: Dr. Thomas L. Stewart

Upload: zada

Post on 14-Jan-2016

164 views

Category:

Documents


5 download

DESCRIPTION

Traffic Sign Recognition. Jacob Carlson Sean St. Onge Advisor: Dr. Thomas L. Stewart. Traffic Sign Recognition. Project Overview System Description Current Functionality Future Work. Traffic Sign Recognition. Project Overview System Description Current Functionality Future Work. - PowerPoint PPT Presentation

TRANSCRIPT

Page 1: Traffic Sign Recognition

Traffic Sign Recognition

Jacob Carlson Sean St. OngeAdvisor: Dr. Thomas L. Stewart

Page 2: Traffic Sign Recognition

Traffic Sign Recognition Project Overview System Description Current

Functionality Future Work

Page 3: Traffic Sign Recognition

Traffic Sign Recognition Project Overview System Description Current

Functionality Future Work

Page 4: Traffic Sign Recognition

Project OverviewObject 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.

Page 5: Traffic Sign Recognition

Project Overview 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.

Page 6: Traffic Sign Recognition

Traffic Sign Recognition Project Overview System

Description Current

Functionality Future Work

Page 7: Traffic Sign Recognition

System Description

PreprocessApply Processing

AlgorithmsClassify Sign (if

present)

Highlight ImageRecommend

Appropriate Action

Page 8: Traffic Sign Recognition

System Description

When the program is initialized, an image, previously saved on the system’s hard drive, is loaded for analysis.

At this point, some preliminary analysis will be performed, and preprocessing will be performed manually.

Page 9: Traffic Sign Recognition

System Description This portion of the

program will gather and analyze color data, and will also perform edge detection.

Red Green Blue

Page 10: Traffic Sign Recognition

System Description Additional methods (dilation, opening,

closing, erosion) may also be applied at this time.

The sign will be classified based on color.

Page 11: Traffic Sign Recognition

System Description 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.

Page 12: Traffic Sign Recognition

Traffic Sign Recognition Project Overview System Description Current

Functionality Future Work

Page 13: Traffic Sign Recognition

Current Functionality Currently our program divides the

color image into the three color planes.

We first look for red signs (stop sign, do not enter, wrong way). Our algorithm currently isolates most red signs effectively.

It can also isolate yellow signs, but this still requires some optimization.

Page 14: Traffic Sign Recognition

Current Functionality Initial Image

Page 15: Traffic Sign Recognition

Current Functionality Red Plane

Page 16: Traffic Sign Recognition

Current Functionality Red Plane, after Thresholding

Page 17: Traffic Sign Recognition

Current Functionality Green Plane

Page 18: Traffic Sign Recognition

Current Functionality Blue Plane

Page 19: Traffic Sign Recognition

Current Functionality Threshold red plane after median filter.

Page 20: Traffic Sign Recognition

Current Functionality Sobel Masks – Used for edge detection

(differentiation).

Page 21: Traffic Sign Recognition

Current Functionality Horizontal Edge Detection using Sobel masks.

Page 22: Traffic Sign Recognition

Current Functionality Vertical Edge Detection using Sobel masks.

Page 23: Traffic Sign Recognition

Current Functionality Sum of horizontal and vertical edge detection.

Page 24: Traffic Sign Recognition

Current Functionality Image after erosion by a line structuring element.

Page 25: Traffic Sign Recognition

Current Functionality Image after closing with octagon structuring element.

Page 26: Traffic Sign Recognition

Current Functionality Stop sign identified using ‘blob’ recognition techniques.

Page 27: Traffic Sign Recognition

Current Functionality Final image with stop sign highlighted.

Page 28: Traffic Sign Recognition

Traffic Sign Recognition Project Overview System Description Current

Functionality Future Work

Page 29: Traffic Sign Recognition

Traffic Sign Recognition Current problem is having the computer

recognize that the shape is a stop sign.

*

Page 30: Traffic Sign Recognition

Traffic Sign Recognition

Identifying a region of interest and cropping out the background prior to performing main processing would streamline calculations.

Speed could also be increased by using C or C++ to implement the processing algorithms.

Page 31: Traffic Sign Recognition

Questions?