Intelligent Traffic

Control by Using Image

Processing Technique
Group Members:
Rahul Gupta (1700161C202)
Ayush Govil (1700120C202)
 As the world is growing older, life is also getting tougher. People are
increasing with huge number despite the fact that lands are not
increasing and so traffic jam too. In modern life time is really very
expensive and major of our times are being killed by traffic jam. It is
said that ratio of cars with respect to roads, the irrational distribution
Introduction of the buildings, lack of experience of traffic police are the main
reasons for traffic jam. This problems can be sorted out by making
some good decision on infrastructure, limiting numbers of signals
and introducing some new technique on traffic controlling system.
This techniques are briefly described in the next part of our writings.
 1. Image processing is a method to convert an image into digital
form and perform some operations on it, in order to get an
enhanced image or to extract some useful information from it.

What is Image 2. It is a type of signal dispensation in which input is image, like

video frame or photograph and output may be image or
Processing characteristics associated with that image.
3. Image Processing system includes treating images as two
dimensional signals while applying already set signal processing
methods to them.
Basic Plan
Layout
 Steps of image processing:
1. Importing the image with optical scanner or by digital
photography.
Steps of image 2. Analysing and manipulating the image which includes data
compression and image enhancement and spotting patterns
Processing that are not to human eyes like satellite photographs.
3. Output is the last stage in which result can be altered image or
report that is based on image analysis.
Block Diagram
 1. In early 1920s Bartlane cable picture transmission system used to
transmit newspaper images across the Atlantic, though the images
were coded.
2. After 1920s-improvements were made to the Bartlane system resulted
in higher quality images with the increased number of tones in
reproduced images. In 1960s: Improvements in computing technology
and the onset of the space race led to a surge of work in digital image
processing.
Earlier 3. In 1964: computers used to improve the quality of images of the moon
taken by the Ranger 7 probe Such techniques were used in other space
Research missions including the Apollo landing.
4. 1970s, digital image processing begins to be used in medical
applications. In 1979, Sir Godfrey N. Hounsfield & Prof. Allan M.
Cormack share the Nobel Prize in medicine for the invention of
tomography,
5. 1980s - Today: The use of digital image processing techniques has
exploded and they are now used for all kinds of tasks in all kinds of
areas
  The project proposed a system for controlling the traffic light by
image processing.
 In this system the vehicles are not being detected by sensors,
rather it is detected by images.
 In this process initially the system will have picture of the empty
Objective of road. And the system will continuously take pictures of the road
the work and will compare those with the empty ones which will give signal
of the density of vehicles present on the road.
 By detecting the density of the vehicles, light will glow, controlling
the traffic. Since it will take the actual picture of the road, there
will be very light chance of glowing the green signal when the road
is empty.
  Automatic traffic controllers are also known as traffic light control.
These basically consist of 3 different coloured lights, a sensor and
a timer which turn ON and OFF at each interval.
Automatic  The purpose of the sensor is to capture the availability of the
controlling vehicles. In has the ability to decide the present and absence of
the traffic even the density of the traffic on a road.
method of  It can also compare the traffic with other intersection and provide
traffic light signalling message. The automatic controlling is 24/7 on service
unlike traffic police for at max 12 hours. Minor or little effect on
the weather changes.
  Most of the information about the shape of an image are located in
edges. The other benefits of edge detection is not taking more
space in computer memory. This technique reduces the image size
and filters out important information.
 There are many techniques available for edge detection. These are-
1. Prewitt edge detection technique.
Edge 2. Sobel edge detection technique.
detection 3. Roberts edge detection technique.
4. Zero cross threshold edge detection technique.
5. Canny edge detection technique.

 We have chosen the canny edge detection technique for its many
advantages
 1. If the matching is between 0 to 20% - red light is on for 90
seconds.
2. If the matching is between 20 to 40% - green light is on for 20
seconds.
3. If the matching is between 40 to 70% - green light is on for 30
Algorithm seconds.
4. If the matching is between 70 to 90% - green light is on for 60
seconds.
5. If the matching is between 90 to 100% - green light is on for 90
seconds.
Output of
Individual
Steps
Output of
Individual
Steps
Matching
between
100-90%
Matching
between
70-40%
Matching
between
40-20%
 1. Edge detecting from videos: The whole procedure can be done
through a captured image as well as through a video. By
creating algorithm through image processing edges of vehicles
will be detected.
2. Weather consideration: In this project, weather was not
considered. So when there is fog it might not get the accurate
Future Work results and provide proper signalling message. Also, at night
this type of problems may occur. So, in future research on
Image Processing can be done with the consideration of
weather by edge detecting.
3. Hardware Implementation: If this method can be
implemented in hardware than it will be a very useful system.
  More Convenience
 Energy Management & Savings
Advantages  Easy to detect than sensors
 Low cost
 1. Hacking
2. Power consumption
Potential 3. Less human interaction
problems 4. Problems in microcontroller.
5. Problems detecting the image properly in foggy weather.
 Traffic control system we introduced in this project, we overcome all
the difficulties that earlier traffic control systems had. Previously,
Conclusion traffic control systems were built with timer. Traffic management
will be much more efficient with image processing techniques. So,
this process is a solution for the previous systems.
Any Questions?
Thank you!