C.E. 3.1 IntroductionTitle: Visual Language Detection and Interpretation of Traffic Signals
Geographical Location: Pune, Maharashtra
Organization: Smt. Kashibai Navale College of Engineering, Pune
Position Title: Undergraduate student of Electronics and Telecommunication Engineering
An abundance of traffic related accidents inflated by the sheer volume cars along with the lack of administrative technological interventions at traffic lights in India motivated me to take up this project. The main aim of my project was to implement the recognition of traffic symbols and control automobile actions using a PCA algorithm to take imperative actions including speed control, horn enabling/disabling and brake application. I, along with 2 colleagues (Ajinkya and Akshar) undertook this project in the 6th semester of our Bachelor’s degree under the guidance of Dr. Ingawale and Mr. Shirsat. We successfully implemented the system for the car controls by detecting traffic symbols.
C.E. 3.2 Background
The system I developed includes a camera for capturing traffic symbols as the input, an identifier and decision-making algorithm, that is, Principal Component Analysis algorithm and a Zigbee Module for transmission of the processed information to the receiver where the corresponding action of the car takes place. I made use of MAX-232, a voltage convertor to cater to the different power needs of the Zigbee and the Personal computer. This project thus, was aimed to develop a dedicated system for increased safety on the road.
C.E. 3.2.1 Project Objectives
The objectives of this project are clearly stated below
· To design and develop a dedicated system for Traffic signal analysis having identified two areas of importance – detection and categorization.
· Using the PCA for identifying patterns in data, and expressing the data in such a way as to highlight their similarities and differences.
· Detecting the sign in acquired image, carrying out segmentation to apply PCA to database and find the matching sign.
· Further, the system can be modified to include a variety of signs. In this project different actions like honking, stopping and speed reduction are highlighted.
C.E. 3.2.2 Organization Structure
Smt. Kashibai Navale College of Engineering is an AICTE approved and NBA Accredited Institute under Pune University, located in the state of Maharashtra in Western India. The project was supervised by Dr, Ingawale and Mr Shirsat who taught in the Electronics and Telecommunications Engineering Department of the aforementioned academic institute.
In a three-member team, I developed a system that was economical and was aimed at improving traffic conditions by reducing accidents through a sophisticated system. The system I developed includes a camera for capturing traffic symbols as the input, an identifier and decision-making algorithm, that is, Principal Component Analysis algorithm and a Zigbee Module for transmission of the processed information to the receiver where the corresponding action of the car takes place. I made use of MAX-232, a voltage convertor to cater to the different power needs of the Zigbee and the Personal computer. This project thus, was aimed to develop a dedicated system for increased safety on the road.
C.E. 3.3 Personal Engineering Activity
I collaborated with my team members who had different research interests, which made the united effort beneficial for the project and for the team’s knowledge pool. I took it upon myself to carry out the project layout designing and subsequently the block diagram to increase simplicity and project efficiency.
C.E. 3.3.1 Project Segments and Block Diagram:
· Zigbee Module
· Microcontroller 8051
· L293D current driver
· LCD Display
· Camera and Personal Computer
· RS 232
· 60rpm DC motor
· Power Supply
Fig. 3.1 Transmitter Block
Fig. 3.2 Receiver block
C.E. 220.127.116.11 MICROCONTROLLER 8051
• Compatible with MCS-51® Products
• 8K Bytes of In-System Programmable (ISP) Flash Memory
– Endurance: 1000 Write/Erase Cycles
• 4.0V to 5.5V Operating Range
• Fully Static Operation: 0 Hz to 33 MHz
• Three-level Program Memory Lock
• 256 x 8-bit Internal RAM
• 32 Programmable I/O Lines
• Three 16-bit Timer/Counters
• Six Interrupt Sources
• Full Duplex UART Serial Channel
• Low-power Idle and Power-down Modes
• Interrupt Recovery from Power-down Mode
• Watchdog Timer
• Dual Data Pointer
• Power-off Flag
C.E. 18.104.22.168 LCD Display
LCD is used in a project to visualize the output of the application. We have used 16x2LCD which indicates 16 columns and 2 rows. So, we can write 16 characters in each line. So, total 32 characters we can display on 16×2 LCD.
LCD can also be used in a project to check the output of different modules interfaced with the microcontroller. Thus, LCD plays a vital role in a project to see the output and to debug the system module wise in case of system failure in order to rectify the problem.
C.E. 22.214.171.124 RS232 Interface
RS 232 IC is a driver IC to convert the µC TTL logic (0-5) to the RS 232 logic (+-9v). Many device today work on RS 232 logic such as PC, GSM modem , GPS etc. so in order to communicate with such devices we have to bring the logic levels to the 232 logic (+/-9v).
C.E. 126.96.36.199 DC Motor
DC motors are used to physically drive the application as per the requirement provided in software. We have used a 60rpm dc motor that works on 12V.
To drive a dc motor, we need a dc motor driver called L293D. This dc motor driver is capable of driving 2 dc motors at a time. In order to protect the dc motor from a back EMF generated by the dc motor while changing the direction of rotation, the dc motor driver have an internal protection suit. We can also provide the back-EMF protection suit by connecting 4 diode configurations across each dc motor.
C.E. 188.8.131.52 Power Supply Design
The steps involved in the designing of the power supply are:
1. To determine the total current that the system sinks from the supply
2. To determine the voltage rating required for the different components.
Figure 3.3 Power supply
Minimum input for 7805 is
= Drop across IC 7805 + Required Output voltage
= 3 V+ 5V
= 8 V
Consider drop across diode 0.7, so for two diodes the drop is 1.4 V
= 1.4 V +8 V
= 9.4 V
At secondary we required 12 V
For filter capacitor design,
Vr= ripple voltage
I= load current
I = (O/P current of IC 89s52 +
Current req. for display+max232)
=80mA + 3mA+15mA
C = (I* t1)/Vr
= (120.2 mA * 8.4 ms)/ 1 V
= 976.04 µF ; So we select 1000 µf capacitor
For diode design
PIV = Vm
Vm = 2 Vin
= 28 V
From the above specification, diode 1N4007 was selected, PIV =50V
Fig. 3.4 System circuitry
C.E. 3.4 Results
C.E. 3.4.1 Database and Identification results
The database image is the image captured by the camera on the PC. One frame is captured at a time. In real time applications, continuous stream of frames (video) are taken and processed using a high-resolution camera.
Fig. 3.5 Captured Image
Fig. 3.6 Segmented Image
This is the segmented image of our captured image. Using this, we can differentiate between the traffic sign and unwanted data.
C.E. 3.4.2 Model Car Setup
Fig. 3.7 Project Setup
Figure 12 shows the transmitter (PC) unit and receiver (robot) unit along with the RF module for wirelessly transmitting commands.
Fig 3.8 Robot
Figure 13 shows the robot i.e. receiver unit with PCB, RF module and battery for power supply.
Highlights and Problems faced:
The positive aspects of this system were the uniqueness of the design of traffic signs, colours contrast usually very well against the environment, the signs are strictly positioned relative to the environment and are often set up in a clear sight to the driver. Some other advantages are listed below
· Less time delays
· Quick response time
· Fully automate system
· Robust system
· Low power requirement
On the other hand, there are still a number of negative aspects. We can distinguish the following aspects:
· Lightning conditions are changeable and not controllable. Lightning is different according to the time of the day and season, weather conditions and local light variations such as direction of light.
· The presence of other objects like pedestrians, trees, other vehicles, billboards, and buildings. This can cause partial occlusion and shadows. The objects or surrounding could be similar to traffic signs by color or shape.
The sign installation and surface material can physically change over time, influenced by accidents and weather, thus resulting in disoriented and damaged signs and degenerated colors.
The retrieved images from the camera of a moving car often suffer from motion blur and car vibration.
The detection and recognition of traffic signs are caught up with the performance of a system in real-time. This requires a system with efficient algorithms and powerful hardware.
C.E. 3.3.5 Conclusion
After a thorough analysis of the above stated literature it is evident that not only is there plenty of scope for the application of such a system but in fact there is an urgent need for such a system. Hence, by implementing this system we can reduce the high rate of fatality in case of road accidents to a minimum and get automated assistance for driving.