Traffic Density Count Using Image Processing
India is a large country and around the world India is second most populous country and fast-growing economy. In today's life we have to face different kinds of problem one of which is increasing number of vehicles it becomes increase in traffic and chaos. Infrastructure growth in India and growth in number of vehicles is not equal, because of large population speed of increase in no of vehicles is much faster than infrastructure growth. Roads capacity and interaction along the roads (cross-roads / junctions) are not capable to handle higher number of vehicles. Major drawback of Indian traffic is non-lane based and chaotic. So, it is necessary to efficiently manage the traffic flow by completely utilizing the existing capacity of the road. Modern Cities are facing a lot of trouble due to the traffic congestion. Increasing population results in subsequent increase in the vehicles causing congestion. Traffic jams and congestion create several issues like wastage of time, excess fuel consumption. Apart from these, it directly affects routine life and sometimes may result in loss of life. E.g. In emergency cases, the ambulance boarding a critical patient cannot reach the destined hospital on time due to the congestion, where every second counts. A smart traffic control system can be one of the solutions to the above problem. This can be done by measuring the vehicular density on that road wherein real time image and video processing techniques will be used. The main aim is to coordinate the traffic by keeping a check of its density from all the sides and thereby controlling the traffic signal intelligently.
Literature review
Alisha Janrao, Mudit Gupta, Divya Chandwani, U. A. Joglekar proposed method to co-ordinate the traffic by keeping a check of its density from all the sides and thereby controlling the traffic signal. In this they present density counting algorithm to determine the number of vehicles on that road. This density counting algorithm work by the comparison between one frame of the live video (real time) and the reference image.
Ashwini D. Bharade, Surabhi S. Gaopande presents a real time traffic monitoring system that’s make use of image processing algorithm to detect and estimate the count of vehicles using motion detection approach.
Daisik Nam, Riju Lavanya, Inchul Yang, Woo Hoon Jeon, R Jayakrishnan develop a new algorithm for traffic density estimation using probe vehicles equipped with various sensors. A radar-equipped probe vehicle has multiple sensors at various points. With the combination of high resolution 77 GHz radars, Cameras, Global Positioning System (GPS), digital map aided systems, and telecommunication technologies, probe vehicles can sense current traffic conditions.
Pejman Niksaz proposed a system that estimates the size of traffic in highways by using image processing has been proposed and as a result a message is shown to inform the number of cars in highway. This project has been implemented by using the MATLAB software.
Mohammad Shahab Uddin, Ayon Kumar Das, Md. Abu Taleb the main contribution of this research lies in the development of a new technique that detects traffic density according to the area of the edges of vehicles for controlling traffic congestion. Specialized algorithm, morphology and images captured with cameras will be used for the detection of traffic density for the intelligent traffic control system.
Osman Ibrahim, Hazem ElGendy, and Ahmed M. ElShafee, they propose a speed detection camera system (SDCS) is applicable as radar alternative. SDCS uses several image processing techniques on video stream in online captured from single camera. It uses a hybrid algorithm based on combining an adaptive background subtraction technique with a three-frame differencing algorithm. Hong sheng He, Member, Zhenzhou Shao, and Jindong Tan, recognizes car models from a single image captured by a camera. Due to various configurations of traffic cameras, a traffic image may be captured in different viewpoints and lighting conditions and the image quality varies in resolution and color depth.
S. Sri Harsha, Ch. Sandeep present the Vehicle counting is done by Background subtraction and finding the centroid. Classification is done by thresholding method and the rush or peak hour implies the high time in which the traffic increases to maximum which would certainly lead to road blocks.
Anurag Kanungo, Ayush Sharma, Chetan Singla proposed the method to use live video feed from the cameras at traffic junctions for real time traffic density calculation using video and image processing. It also focuses on the algorithm for switching the traffic lights according to vehicle density on road, thereby aiming at reducing the traffic congestion on roads which will help lower the number of accidents.
Mallikharjuna Rao, Santhi Kiran Bhathula, Pavankumar Yadavalli and Ramarao Kandula the system utilizes new technologies for real-time collection, organization and transmission which provide the information to estimate the accurate traffic density exploited by traffic-aware applications. The system is based on ARDIUNOM.
Vidhyia, S. Elayaraja, M. Anitha, M. Divya and S. Divya Barathi they try to reduce possibilities of traffic jams, caused by traffic lights, to an extent. The system is based on raspberry-pi. The system contains IR transmitter and IR receiver which are mounted on either side of roads respectively.
J. Naga Phanindra, V. Srinivas presents method which is used for traffic surveillance purpose where the traffic is continuously monitored and viewed through live streaming and also used for detecting the traffic report to the travellers.
Methodology
The work is divided into 4 parts. The first part is to process the video signal and image acquisition from fixed camera using MATLAB. The second part is to select the target area where the vehicles could be present by using image cropping technique. The third part is the object detection which is performed by enhancing features of the image. Finally, the last part is the density counting, where the number of vehicles is being counted. The overall block diagram of the proposed system is illustrated below.
Processing of Video Signal and Image Acquisition: The work starts with processing the live video using MATLAB software. The video camera is stationary, which is mounted on the pole near the traffic signal. The next stage is to extract the frames continuously from the real time video coming from the stationary camera. This raw digital data is further processed by converting the images from RGB (Red-Green-Blue) to grayscale in order to further process the images. Initially the system captures the image of a vacant road when there is no vehicle present; this image is used as a reference image.
Image Cropping: The second step is to select the targeted area by designing image cropping algorithms in MATLAB. The purpose of cropping is to identify the road region where the vehicles are present and exclude the unnecessary background information. This unnecessary information is fixed in every frame of the live video because the camera is stationary. To crop the required area, reference image has been used, which has no road traffic. First, a binary image of having the same dimensions is created, as in the reference image, then the road area has been shaded white, and the leftover region as black. Finally, the multiplication of the reference image with the cropping black and white image results in the final desired target area.
Object Detection: The third step is the object or vehicle detection in order to identify and count the vehicles which are present in the targeted area. To perform the object detection, first the frame from the real time video sequence is extracted. The next step is to convert both images; the reference image and the real time image into grayscale and then the absolute difference of two images will be determined.
Traffic Density: The next step is to calculate the traffic density in the desired target area. In order to determine the traffic density, the vehicles are marked first and then their numbers are counted. The algorithm search for a set of connecting pixels. In order to consider a connected region as a vehicle, a minimum threshold has been defined.
