Traffic Density analysis based on Image Processing

Traffic Density analysis based on Image Processing
of 6
All materials on our website are shared by users. If you have any questions about copyright issues, please report us to resolve them. We are always happy to assist you.
Related Documents
  Traffic Density analysis based on Image Processing  Jobin George Dept. of Electronics Engg RIT Kottayam  jobing4@gmail.com Honey Thomas Dept. of Electronics Engg RIT Kottayam honeytom01@gmail.com Abstract-   Traffic congestion has become a significant problem in recent years. Efficient traffic control system by detecting and counting the vehicle numbers at various times and locations are required. Traffic estimate from the static images is the key issue for automating traffic light controls. In this work, we address the problem of estimating the traffic congestion and vehicles density on the roads. Based on study of available methods in estimating the traffic density, we tried to modify some of the algorithms to improve the congestion estimate. In visual surveillance applications, detection by background subtraction is a common approach for differentiating moving objects from the static parts of the video frames.   One of the ways to overcome traffic problems in large cities is through the development of an intelligent traffic control system which is based on the measurement of traffic density on the road. The system is implemented and simulated in Matlab, and it performance is tested on real video. It is observed from the experiment that based effective density in the road ,the traffic can be controlled effectively.  Keywords-Intelligent Transportation systems ,TLC.   I. I  NTRODUCTION  In recent years, traffic congestion has become a significant  problem. The simplest solution is to lay more lanes to reduce traffic density, but adding more lanes is not a feasible solution on account of time, cost and efficient utilization of the infrastructure. Also, the use of surveillance cameras by law enforcement agencies is on the rise. Automatic traffic monitoring and surveillance are important for road usage and management. Traffic parameter estimation has been an active research area for the development of Intelligent Transportation systems (ITS). For ITS applications traffic- information needs to be collected and distributed. Various sensors have been employed to estimate traffic parameters for updating traffic information. Magnetic loop detectors have  been the most used technologies, but their installation and maintenance are inconvenient and might become incompatible with future ITS infrastructure. Traffic sensors have been developed from a rich array of technologies such as video, radar, magnetic and acoustics. It is well recognized that vision-based camera system are more versatile for traffic  parameter estimation. In addition to qualitative description of road congestion, image measurement can provide quantitative description of traffic status including speeds, vehicle counts, etc. Moreover, quantitative traffic parameters can give us complete traffic flow information, which fulfills the requirement of traffic management theory. Image tracking of moving vehicles can give us quantitative description of traffic flow. Feature based tracking for the task of tracking vehicles under congestion is reported in[1].Background based image detection techniques are used in the work[2].Real time tracking techniques along with specific tuning of the dynamics is to enable the tracker to accurately predict the target location is mentioned in[3].Traffic monitoring based on rule based on rule based monitoring on visual data is done in the work[4]. In the present work the designed system aims to achieve the following: 1) Distinguish the presence and absence of vehicles in road images; 2) Signal the traffic light to go red if the road is empty; 3) Signal the traffic light to go red if the maximum time for the green light has elapsed even if there are still vehicles  present on the road. The work is to improve the existing traffic control and improve the utilization efficiency of surveillance systems by multi-tasking the cameras of surveillance systems to control traffic flow. This improved traffic control system will take into account wider range of subtleties in traffic patterns using image processing techniques. Traffic problems nowadays are increasing because of the growing number of vehicles and the limited resources  provided by current infrastructures. Traffic on roads may consist of pedestrians, ridden or herded animals, vehicles, streetcars and other conveyances, either singly or together, while using the public way for purposes of travel. Traffic laws are the laws which govern traffic and regulate vehicles, while rules of the road are both the laws and the informal rules that may have developed over time to facilitate the orderly and timely flow of traffic. Traffic signs or road signs are signs erected at the side of roads to provide information to road users. ITS helps to identify traffic parameters and congestion density so that traffic can be handled effectively. Section II deals with existing systems, Section III & IV deals with the present work. Section V deals with methods adopted.  II. C LASSICAL TRAFFIC CONTROL SYSTEM    A. Manual Controlling    Manual controlling the name instance it require man power to control the traffic. Depending on the countries and states the traffic polices are allotted for a required area or city to control the traffic. The traffic polices will have things like sign board, sign light and whistle to control the traffic. They will be instructed to wear specific uniforms in order to control the traffic.  B. Automatic Controlling    Automatic traffic light is controlled by timers and electrical sensors. In traffic light each phase a constant numerical value loaded in the timer. The lights are automatically getting ON and OFF depending on the timer value changes. While using electrical sensors it will capture the availability of the vehicle and signals on each phase, depending on the signal the lights automatically switch ON and OFF. In the manual controlling system we need more man power. As we have poor strength of traffic police we cannot control traffic manually in all area of a city or town. So we need a better solution to control the traffic. On the other side, automatic traffic controlling a traffic light uses timer for each phase. Another way is to use electronic sensors in order to detect vehicles, and produce signal that to this method the time is being wasted by a green light on an empty road.Traffic congestion also occurred while using the electronic sensors for controlling the traffic. III. P ROPOSED SYSTEM  We propose a system for controlling the traffic light by image processing. The system will detect vehicles through images instead of using electronic sensors embedded in the  pavement. A camera will be installed alongside the traffic light. It will capture image sequences. Image processing is a  better technique to control the state change of the traffic light. It shows that it can reduce the traffic congestion and avoids the time being wasted by a green light on an empty road. It is also more consistent in detecting vehicle presence because it uses actual traffic images. It visualizes the reality so it functions much better than those systems that rely on the detection of the vehicles’ metal content.  IV. E XISTING SYSTEM  Present Traffic Light Controllers (TLC) is based on microcontroller and microprocessor.These TLC have limitations because it uses the pre-defined hardware, which is functioning according to the program that does not have the flexibility of modification on real time basis. Due to the fixed time intervals of green, orange and red signals the waiting time is more and car uses more fuel. It Is not efficient in terms of waiting time, more distance traveled by average vehicles and efficient operation during emergency mode. The monitoring and control of city traffic is becoming a major  problem in many countries. With the ever increasing number of vehicles on the road, the Traffic Monitoring Authority has to find new methods of overcoming such a problem. The measures taken are development of new roads and flyovers in the middle of the city; building of several ring such as the inner ring road, middle ring road and outer ring road; introduction of city trains such as the light rapid transit (LRT), and monorails; restricting of large vehicles in the city during peak hours; and also development of sophisticated traffic monitoring and control systems. Growing numbers of road users and the limited resourcesprovided by current infrastructures lead to ever increasing traveling times.  A. .Limitations of Existing System 1)   Heavy Traffic Jams 2)    No traffic, but still need to wait:At certain junctions, sometimes even if there is no traffic, people have to wait. Because the traffic light remains red for the preset time  period, the road users should wait until the light turn to green. If they run the red light, they have to pay fine. 3)   Lack of Traffic Information to users:Present traffic systems fail to provide traffic information including congested roads and alternate routes available in case of congestion V. M ETHODOLOGY    A. Procedure:   Phase1: Initially image acquisition is done with the help of video camera. First image of the road is captured, when there is no traffic on the road. This empty road’s image is saved as reference image at a particular location specified in the  program. RGB to gray conversion is done on the reference image. Now gamma correction is done on the reference gray image to achieve image enhancement. Edge detection of this reference image is done thereafter with the help of horizontal and vertical filters and normalization. Phase2: Images of the road are captured.RGB to gray conversion is done on the sequence of captured images. Now gamma correction is done on each of the captured gray image to achieve image enhancement. Edge detection of these real time images of the road is now done with the help of horizontal and vertical filters and normalization. Phase3: After edge detection procedure both reference and real time images are matched and traffic lights can be controlled based on percentage of matching (Effective density).If the matching is between 0 to 10% - green light is on for 90 seconds. If the matching is between 10 to 50% - green light is on for 60 seconds. If the matching is between 50 to 70% - green light is on for 30 seconds. If the matching is between 70 to 90% - green light is on for 20 seconds. If the matching is between 90 to 100% red light is on for 60 seconds.   B. Operations   1)   Image acquisition The first stage of any image processing operation is the image acquisition stage. Acquired images are shown in Fig1, Fig2, Fig3, Fig4 & Fig5. After the image has been obtained, various methods of processing can be applied to the image to  perform the many different tasks required today. However, if the image has not been acquired satisfactorily then the intended tasks may not be achievable, even with the aid of some form of image enhancement. Digital image acquisition is the creation of digital images, typically from a physical scene. The term is often assumed to imply or include the  processing, compression, storage, printing, and display of such images. The most usual method is video camera but other methods are also employed. Fig.1. Road with no traffic 2)   RGB to gray conversion Fig.2. Road traffic status at time t1 Fig.3. Road traffic status at time t2 In photography and computing, a grayscale or grayscale digital image is an image in which the value of each pixel is a single sample, that is, it carries only intensity information. Images of this sort, also known as black-and-white, are composed exclusively of shades of gray, varying from blackat the weakest intensity to white at the strongest. Fig.4. Road traffic status at time t3 Fig.5. Road traffic status at time t4 In photography and computing, a grayscale or grayscale digital image is an image in which the value of each pixel is a single sample, that is, it carries only intensity information. Images of this sort, also known as black-and-white, are composed exclusively of shades of gray, varying from black at the weakest intensity to white at the strongest. Grayscale images are distinct from one-bit bi-tonal black-and-white images, which in the context of computer imaging are images with only the two colors, black, and white (also called bilevel or binary images). Grayscale images have many shades of gray in between. Grayscale images are also called monochromatic, denoting the presence of only one (mono) color (chrome).   3)   Image Enhancement The acquired image in RGB is first converted into gray.  Now we want to bring our image in contrast to background so that a proper threshold level may be selected while binary conversion is carried out. This calls for image enhancement techniques. The objective of enhancement is to process an image so that result is more suitable than the srcinal image for the specific application. There are many techniques that may be used to play with the features in an image but may not  be used in every case. Listed below are a few fundamental functions used frequently for image enhancement. 1 Linear (negative and identity transformations) 2 Logarithmic (log and inverse log transformations) 3 Power law transformations (gamma correction) 4 Piecewise linear transformation functions The third method i.e., power law transformation has been used in this work. S=    (1) The power law transformations have the basic form Where S is output gray level, r is input gray level, c and γ are  positive constants. 4)   Edge detection Edge detection is a fundamental tool in image processing and computer vision, particularly in the areas of feature detection and feature extraction, which aim at identifying  points in a digital image at which the image brightness changes sharply or, more formally, has discontinuities. The same problem of finding discontinuities in 1D signal is known as step detection. The purpose of detecting sharp changes in image brightness is to capture important events and changes in properties of the world. It can be shown that under rather general assumptions for an image formation model, discontinuities in image brightness are likely to correspond to, 1 Discontinuities in depth, 2 Discontinuities in surface orientation, 3 Changes in material properties and 4 Variations in scene illumination 5) Image matching Edge based matching is the process in which two representatives of the same objects are paired together. Any edge or its representation on one image is compared and evaluated against all the edges on the other image. Then these edge detected images are matched and accordingly the traffic light durations can be set. Fig 6&7 shows the edge detected images. These cameras will take frames of the four ways at time t1, t2…etc. And these frames will be given to an image  processing tool to find out the effective density of each frame and based on this result traffic light will be controlled. In this work instead of four videos we are considering video of a single road. At time t1, we are having frame number 1 and its effective density   is calculated by image processing. We have selected a threshold for effective traffic density. Fig.6. Grey scale conversion and edge detection VI. I MPLEMENTATION  In a four way junction, real time traffic light control system is implemented by placing cameras towards the four Fig.7. Effective traffic density on the road  If the current frame’s effective density  exceeds that threshold, green light will glow for a duration   depending on its density. If it is below the threshold, red light will glow. Here, we are considering the traffic density of the selected road for four different times (four different frames). And signalling is given based on the effective density calculation. This can be extended to a four way junction traffic control by taking four different video inputs corresponding to four roads coming into that junction   VII. O BSERVATION   Fig.8. Effective density at four different times t1,t2,t2,t4 Depending upon the density of the traffic on the road we get the following results regarding on time durations of various traffic lights: 1. Frame No.1  –   Effective density> 10 (Threshold) - Duration of green light 10 seconds. 2. Frame No.2  –   Effective density> 10 (Threshold) - Duration of green light 12 seconds 3. Frame No.3  –   Effective density< 10 (Threshold)  –   Duration of red light 7 seconds 4. Frame No.4  –   Effective density< 10 (Threshold) - Duration of red light 5 seconds VIII. R  ESULTS The table shows the effective traffic density at different times t1,t2,t3 and t4 .Based on this effective traffic density signal decision can be made so that congestion is avoided. Table.1. Effective density at four different times t1,t2,t2,t3&t4 IX. C ONCLUSIONS  The proposed system is a cost effective solution for the high density traffic existing today and scope for improvement of the system is limitless. The ARM processor can be incorporated to control the traffic based on priority and it can incorporate more advanced features like number plate recognition, automatic booking of vehicle in case of traffic violation, automatic recognition and alerting of accidents etc can be added on to this system. Sound processing technique can be use to improve ambulance detection accuracy. Also infrared cameras can be used for detecting moving vehicles at night. The system can utilize the DSP core and thereby enhance the processing capability as well as features involved. Pedestrians can also be accounted in the traffic control system. For further advancement, the time given for PASS/STOP at a junction can be dynamically determined using a Self Adjusting Algorithm from the data acquired using a camera. This can be further improved by a self learning algorithm where the time remaining for the RED/GREEN signal can be displayed. In case the background colour and the object colour are the same, there are chances of failure of background subtraction algorithm. The detection during night time also poses a challenge to the subtraction algorithm. Hence the background subtraction can be replaced by more complex algorithm like optical flow and particle filter algorithms. Estimation of the vehicle speed can also be included on to the system using optical flow techniques. Frame number Effective density 1 11.0262 2 11.3631 3 8.8963 4 9.9000
Related Search
We Need Your Support
Thank you for visiting our website and your interest in our free products and services. We are nonprofit website to share and download documents. To the running of this website, we need your help to support us.

Thanks to everyone for your continued support.

No, Thanks