International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 08 Issue: 04 | Apr 2021 www.irjet.net p-ISSN: 2395-0072 © 2021, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 1662 Road Congestion Detection using Image Texture Analysis Amruta K. Dhayafule 1 , Dr. S.R.Gengaje 2 1 M.E. Student, Dept. of Electronics Engineering, Walchand Institute of Technology, Solapur, Maharashtra, India 2 Head of Department, Dept. of Electronics Engineering, Walchand Institute of Technology, Solapur, Maharashtra, India ---------------------------------------------------------------------***---------------------------------------------------------------------- Abstract - Extensive number of traffic on roads and improper methods of control of that traffic creates traffic jam. Bad traffic management leads to wastage of time, person-hour and increase in pollution. Existing methods work well in free-flow traffic but in the case of heavy congestion, these methods have to face challenges. Therefore, for better traffic management image processing methods serves as a better option. In proposed system, for the vast increase in congestion problem and problems related to existing detectors, an intelligent traffic controller based on the concept of real time image processing is proposed. Through image grayscale relegation, gray level co-occurrence matrix calculation and feature extraction, the energy and entropy features that reflect vehicle density will be obtained from vehicle area. The density is calculated for every 50th frame(approx. 2sec). While calculating the density we have calculated the vehicles manually from every 50th frame and then to verify results ,correlation graph is plotted between x-axis(no. of vehicles) & y- axis(density).After feature training, the decision threshold will be obtained and traffic congestion is detected. Extensive experiments on four different videos demonstrate that the proposed framework achieves good performance for road congestion detection. Key Words: Traffic management, congestion, gray level co-occurence matrix, energy, entropy, density, correlation 1. INTRODUCTION Traffic congestion is a situation on road networks that arises as use increases. It is distinguished by slower speeds, longer journey times and increased vehicular queuing. Extreme traffic congestion happens as demand exceeds the capacity of a road. When vehicles are stopped for periods of time, traffic jam occurs. There are number of situations which cause or magnify congestion; most of them reduce the capacity of a road at a given point or over a certain length or increase the number of vehicles required for a given volume of people or goods. According to a study of vehicles, around half of traffic congestion is attributed to sheer weight of traffic; while most of the rest is attributed to traffic incidents, road work and weather events. Traffic research still cannot fully predict under which conditions a “traffic jam” may suddenly occur. It has been found that individual incidents may cause wave effects which then spread out and create a sustained traffic jam. Road traffic monitoring involves the collection of data describing the characteristics of vehicles and their movement through road networks. Vehicle count, vehicle speed, vehicle path flow rates, vehicle density, vehicle length, weight, class (car, van, bus) and vehicle identities via the number plate are all examples of useful data. Such data can be very useful for traffic surveillance applications. Through the continuous efforts of researchers, there is a set of relatively fixed process of road congestion detection based on image processing, which contains training monitoring background, road foreground detection, features extraction and training, road congestion estimation. However, in this process, training background is time-consuming, and some factors can easily influence the result, such as scenes change, camera shaking, and the light changes. But in reality, accurately obtaining traffic conditions in real time is the key to relieve road congestion. In this project, a real-time road congestion detection algorithm based on texture analysis is proposed, which deals with image data from road surveillance systems and carries out the accurate identification of vehicle density in different scenes. It is considered to successfully provide quick and reliable traffic information to the traffic administrative departments. The proposed project aims at development of system to detect congestion of traffic based on image processing approach using video of traffic on the road. The rate of accident is increasing very speedily in today’s fast moving world, The over-speed of vehicles is one of the main reason for this. Speed detection of moving vehicle using speed cameras is one of the major steps taken towards this issue so as to bring down the rate of accidents and enhance road safety. As the single biggest cause of road accidents is speed most of the research is going on to detect speed of vehicle. Many speed detection instruments are available for moving vehicle speed detection. The need to use radar systems is growing in importance. This is not only for military applications but also for civilian applications. The latter includes (but not limited to) monitoring speeds of vehicles on high ways, sport competitions, airplanes, etc. The spread of use of radar systems is affected negatively with the high cost of radar systems and also with the increasing requirements on the accuracy of the outputs. This motivated the research on alternative technologies that offer both higher