Project Title : JamFree
Introduction: Traffic Management is an issue which impacts us almost daily. Use of technology and real time analysis can actually lead to a smooth traffic management. The common reason for traffic congestion is due to poor traffic prioritisation.
While the number of vehicles are increasing at a fast pace, the infrastructure in the cities are not being able to match this growth. Our solution to this problem can be used for many urban cities where traffic jams during rush hours are becoming a routine affair, especially in the internal sectors where long queues of vehicles can be seen stranded. Therefore, we have tried to address the problem with the help of our project wherein the focus would be to minimise the vehicular congestion. We have achieved this with the help of image processing that can be obtained from surveillance cameras and eventually to deploy a feedback mechanism in the working of the traffic lights where the density of the traffic would also be factored in the decision making process.
OBJECTIVE: The Objective of our hack is to design a robust and efficient system to solve the traffic jam issues in urban areas.
PROBLEM with Present System: The present system uses traffic signals which are based on timer ICs to control traffic. Suppose an intersection of four roads in which three roads have varying traffic and one road is empty. The present system will just show a green light for the empty road on its turn for 2-3 mins. and in meantime, the traffic on the other roads will go on increasing and thus lead to traffic jams.
Also, a lot of fuel is wasted on red lights as people don’t turn off the engine.
HARDWARE ARCHITECTURE: We shall use Raspberry Pi that is connected to 4 sets of LEDs that represent the traffic lights. The captured images and the reference images are fed to the Raspberry Pi. In real implementation, we will have an automated way to do this via a CCTV camera.
OpenCV (Open Source Computer Vision Library)
ThingSpeak Cloud (For data analytics)
Data Analytics will also be performed which will help in future traffic planning and analysis.
HACK: We plan to design a system to solve above problem using image processing techniques like edge detection, image matching etc. Detailed implementation is discussed in presentation. We take, say, an intersection of four roads, our system will be taking pictures of all the four roads and will extract the traffic density on all the four roads by edge detection and then matching processed images with the reference image, i.e. image of empty road. Then based on matching percentage it will assign a fixed amount of time to each road signal to be green accordingly. The system will use RaspberryPi board to run which can be locally fixed in the signal. The reason for R-Pi is that it is easily available and interfaceable with sensors as well as the internet thus we can upload the traffic data continuously on to the cloud (We use the ThingSpeak Cloud in our implementation). This data can be used for various analytical purposes in future. Also, we have a sample analysis for Daily Traffic Analysis included in snapshots below.
In this way number of jams will decrease significantly and also a lot of fuel will be saved.
FUTURE ENHANCEMENTS: 1. We can apply some suitable image processing techniques and enable the system to detect emergency vehicles like ambulances and fire engines to let them pass as soon as possible i.e. providing priority to such vehicles which will save a lot of lives and property.
We can also enable the system to detect number plates of all the vehicles and extract the registration number of vehicles. So that, if needed it can help the Police and other authorities to track criminals by identifying the number plate of vehicle in which criminal is escaping. There can also be many other uses of this module in the system. Some snapshots of our implementation are attached in the snapshots section. We built a model of road intersection using thermocol and applied same algorithm on to it. we got better results as we expected. Also, we analysed an?d? plotted? the? daily traffic by uploading traffic density values onto the ThingSpeak cloud.
GitHub Code Repository:
Instructions on how to execute the code are included in the above mentioned GitHub Repository in the ReadMe File.
Let’s use technology to make our country move forward!