Sie sind auf Seite 1von 5

Chapter 1 Introduction

Chapter - 1 Introduction

1.1 Project Background

The Road Sign Detection (TSR) is a field of applied computer vision research concerned with
the automatically detection and classification of traffic signs in traffic scene images acquired
from a moving car. The result of TSR research effort will be the subsystem of Driver Support
System (DSS). The aim is to provide DSS with the ability to understand its neighborhood
environment and so permit advanced driver support such as collision prediction and
avoidance. Illustrate on figure 1-1.

Figure 1-1 TSR System Architecture

Driving is a task based fully on visual information processing. The road signs and traffic
signals define a visual language interpreted by drivers. Road signs carry many information
necessary for successful driving - they describe current traffic situation, define right-of-way,
prohibit or permit certain directions, warn about risky factors etc. Road signs also help drivers
with navigation.
Many methods for road-sign detection have been developed over these years. However,
identification of road signs invariantly with respect to various natural viewing conditions still
remains a challenging task. Because:
Road signs are acquired from car moving on the road surface by considerable speed, therefore,
the traffic scene images then often suffer from vibrations;
Color information is affected by varying illumination;
Road signs are frequently occluded partially by other vehicles;
Many objects are present in traffic scenes which make the sign detection hard;
Road signs exist in hundreds of variants often different from legally defined standard;

2
Chapter 1 Introduction

The algorithms must be suitable for the real-time implementation


From above problem definition follows, that to design a successful road sign detection system
must provide a large number of sign examples to make the system responding correctly to real
traffic scenes. This so-called statistical approach to machine learning requires acquiring of
large image databases what is both expensive and time-consuming task.

1.2 Objectives and Scope

The primary objective of this project is to develop an algorithm, use Matlab program, which
will identify various types of road signs from real time camera, video file and static digital
images in a reasonable time frame.

This algorithm should be able to meet the requirements and goals as stated below:
The algorithm could lead to a cheaper and faster way of enhancing and determined the
performance of the detection system
The algorithm will be executed on a personal computer

The program first uses color processing techniques to isolate relevant color data from the
image which have obtained from website. A variety of MATLAB Image Processing Toolbox
commands are used to determine if a road sign is present in current image. Neuron network
are applied in order to classify the road signs. Finally, the relevant sign is highlighted and
output to the screen.

This algorithm could output information to a theoretical autonomous vehicle, head sup
display, or other DSS in the future. The whole system will have the potential to help in
improving road safety, and also important to a robotic vehicle that automatically drive on
roads.

3
Chapter 1 Introduction

The objectives are thus:


1. To understand the properties of road and traffic signs and their implications for image
processing for the recognition task.
2. To understand color, color spaces and color space conversion.
3. To develop robust color segmentation algorithms that can be used in a wide range of
environmental conditions.
4. To develop a recognizer that is invariant to in-plane transformations such as translation,
rotation, and scaling based on invariant shape measures.
5. To identify the most appropriate approach for feature extraction from road signs.
6. To develop an appropriate road sign classification algorithm.
7. To evaluate the performance of the aforementioned methods for robustness under different
conditions of weather, lighting geometry, and sign.

4
Chapter 1 Introduction

1.3 Project Management

The required hardware that will be used for the project is basically a Laptop or windows tablet.
Specification as below:
Intel Pentium CPU2.8GHz (2CPUs)
14" Led (1024 x 768) display
60GB, 7200RPM Hard Drive
2GB DDR3 SDRAM
Usb2 webcam

MATLAB programming version 8.5.0 will be used as it is user friendly and image processing
can be easily done too. MATLAB also give a high performance at numeric computation and
provides easy toolbox function for Neural Network to concentrate on the image dataset.

1.3.1 Project Tasks

Project tasks are divided into seven sections:


Research of TSR
Preparation of initial report
Algorithm development of road sign detection
Algorithm development of road sign classification
Create GUI
Evaluating and fine tuning
Preparation for final report and oral presentation

5
Chapter 1 Introduction

1.4 Layout of the Thesis

This thesis contains of seven chapters and is organized as follows:

Chapter 1: Introduction, background of TSR system, objectives and scope of project, project
tasks.

Chapter 2: Introduction of how the TSR system works and various types of road signs;
Review of different detection methods, highlight the importance factors that could affect the
TSR system accuracy and states my direction.

Chapter 3: Practical work, implementation and result.

Chapter 4: Discuss the project improvement over present project and suggestion for future
work.

Das könnte Ihnen auch gefallen