International Journal of Computer Applications (0975 – 8887) Volume 182 – No.4, July 2018 9 Autonomous Vehicle Density-based Traffic Control System Benjamin Kommey Kwame Nkrumah University of Science and Technology Department of Computer Engineering Knust – Kumasi, Ghana Seth Djanie Kotey Kwame Nkrumah University of Science and Technology Department of Computer Engineering Knust – Kumasi, Ghana Andrew Selasi Agbemenu Kwame Nkrumah University of Science and Technology Department of Computer Engineering Knust – Kumasi, Ghana ABSTRACT Vehicular traffic congestion is an increasingly growing problem in this modern world. The increase in vehicles purchased per year in no way reduces the number of vehicles on our roads. There is therefore the need to devise a system to ensure smooth flow of vehicles, especially at intersections. Standard traffic lights, with fixed intervals between light changes, have helped reduce this issue over the years. However, the increase in the number of vehicles on roads, especially during rush hours, has rendered the standard traffic lights incapable of efficiently and effectively reducing traffic jams. In this paper, we present an autonomous vehicle density-based traffic control system. This traffic control system makes us of infrared sensors to determine the number of vehicles from each direction at an intersection and dynamically allocates traffic signal lights to ensure smooth and fair flow of vehicles at an intersection. The control system requires no human inputs and thus eliminates the possibility of human error. The system was designed and simulated using Proteus software. Keywords Infrared sensor, traffic light, autonomous, density-based, congestion. 1. INTRODUCTION Vehicular traffic congestion is a major issue all over the world due to the increase in urbanization [1]. With the number of people owning vehicles increasing, this problem can only get worse with time. Aside this, traffic congestion contributes to environmental pollution and unpredictable travel times [2]. To curtail this problem, traffic lights were introduced. Much as the standard traffic lights have helped alleviate congestion on roads, they have at times been the culprits of congestion. Standard traffic lights ensure vehicles at an intersection proceed from each direction in a fixed amount of time [3]. This system does not take into consideration constantly changing traffic flow and the likelihood of an unbalanced density of vehicles waiting to proceed from each direction at the intersection. This causes the situation where there are no vehicles at a section of the intersection, yet there is a signal for vehicles from that section to proceed whilst other vehicles at the other sections have been signalled to wait. This causes an unnecessary waste of time at intersections and also contributes to traffic congestion, especially during rush hours [1]. There is therefore the need for an optimised traffic control system to deal with these problems. In this paper, we present an autonomous density-based traffic control system. Our proposed system determines vehicle density with the aid of infrared sensors positioned at each section of the intersection and autonomously decides the best light designations to reduce traffic congestion at the intersection. The rest of the paper is organised as follows: related works are discussed in section 2, the proposed model is presented in section 3, testing and simulation is in section 4, results are presented in section 5 and the paper is concluded in section 6. 2. RELATED WORKS Traffic congestion control is an issue of great concern in the modern world and different solutions have been proposed to combat it. Gaikwad et al [4] proposed an image processing-based traffic control system which works by measuring the area covered by vehicles on the road. The system goes through three main process: image acquisition, transformation to grayscale and image enhancement. Green lines are drawn on the road at arbitrary distances which the camera has to detect. If parts of the lines are not detected, then there is a level of traffic on the road and the traffic lights are adjusted to suit the situation. The system was implemented using MATLAB software. Ali et al. [5] proposed an autonomous road surveillance system (ARSS) using cameras. The system consists of cameras for image detection, a storage device for the images detected, an object detection algorithm, background object subtraction and shadow removal, blob segmentation and object classification. The system was designed to be integrated with existing video surveillance systems. For each lane, detected images are analysed and the blob ratio is used to determine the type of vehicle which has been detected. Based on the number of vehicles detected in all directions, the traffic lights are adjusted to ease congestion. Traffic control systems using cameras require storage space to store images and extra processing power to process images. Promila Sinhmar [6] proposed an intelligent traffic using infrared sensors. The system is connected to a computer and is managed by an administrator. In this paper, we present an autonomous traffic control system using infrared sensors. The system does not require special storage or processing capabilities and also does not require human input to function efficiently. 3. PROPOSED MODEL The proposed model is shown in figure 1. The system consists of two microcontrollers, one as a counter for the sensors‟ inputs and the second for controlling the traffic lights. Infrared sensors are used at each section of the intersection to determine vehicle density. An RF module is used for communication between the microcontrollers.