Smart Traffic Control System and Traffic Density Calculation Using Image Processing

Abstract

In the times, urban centres are growing at a really high rate. Growing with them is road traffic jam. Traffic jams, especially at peak hours, became routine. As a result, traffic management is one among the foremost pressing issues in today’s towns. Several alternatives are being sought to affect the matter. These include: expansion of road networks, regulating the amount of vehicles on the roads, and deployment of Intelligent Transportation Systems (ITSs). aside from the ITSs, the opposite alternatives (however effective) have many practical challenges in their implementation.

ITSs are supported a good range of technologies like loop sensors and video surveillance systems. Vision based ITSs have proved advantageous over the normal methods supported loop sensors. In these modern systems, video surveillance cameras are installed along the roads and road intersections where they're wont to collect traffic data. the info is then analysed to get traffic parameters like the road traffic density.

during this paper, an easy and stylish approach for estimating the road traffic density during daytime using image processing and computer vision algorithms is presented.

Get quality help now

Sweet V

Verified writer

Proficient in: Science

4.9 (984)

“ Ok, let me say I’m extremely satisfy with the result while it was a last minute thing. I really enjoy the effort put in. ”

+84 relevant experts are online

Hire writer

The video data collected is first weakened into frames which are then pre-processed during a series of steps. Finally, the vehicles are detected and extracted from the pictures and Density estimated. Then the traffic density is obtained because the number of vehicles per unit area of the road section. The proposed approach was implemented in MATLAB R2013a and average vehicle detection accuracies of 96.0% and 82.1% were achieved for fast paced and slow moving traffic scenes respectively.

Introduction

As urbanization increases the transportation requirements also are increased. the wants of high transportation cause traffic jam within the urban areas. The fuel requirements and time requirements are increased thanks to the heavy holdup . The holdup not only depend the vehicles on the road but also depends the subsequent factors like weather, day, time, some unpredictable situations like accidents, road maintenance and a few special events. One method to unravel the traffic jam is to construct new roads and flyovers. the most dis advantage of this method is that it requires more natural resource . But the matter is that the difficulties in acquiring land due to the commercial and therefore the residential buildings are beside the road.

It requires longer to evacuate them and construct the new one. So thanks to these reasons a traffic management system are often adopted with the available infrastructure instead of making new infrastructures. A control system with continuous monitoring of auto density on the safety island can solve the traffic jam problems by controlling the traffic light duration consistent with the vehicle density within the traffic island. Advantages of this sort of intelligent transportation systems are reduced cost of capital also because the maintenance cost. Traffic data are often stored and effectively used for transportation planning for future developments.

In the era , one among the foremost exigent issues that our society is facing is vehicular congestion increasing at an exponential rate. allow us to take the case study of Chandigarh, one of the Union Territories of India. Chandigarh has the most important number of vehicles per capita in India. consistent with Chandigarh Transport Undertaking, quite 45,000 vehicles were registered this year in Chandigarh making the entire count of quite 8 lakhs vehicles on the road. While the amount of vehicles are increasing at a quick pace, the infrastructure within the city isn't having the ability to match this growth. Traffic jams during rush hours are getting a routine affair, especially within the internal sectors where long queues of vehicles are often seen stranded.

Therefore, we've tried to deal with the matter with the help of our research paper wherein the main target would be to minimize the vehicular congestion with virtually no installation of any quite hardware. we've achieved this with the assistance of video processing of the live feed which will be obtained from surveillance cameras and eventually to deploy a feedback mechanism within the working of the traffic lights where the density of the traffic would even be factored within the decision making process.

The main aim in designing and developing of the Smart traffic light Simulator is to scale back the waiting time of every lane of the cars and also to maximise the entire number of cars which will cross an intersection given the function to calculate the waiting time. The traffic light system consists of three important parts.

An intelligent traffic management system mainly uses the advantage of the digital image processing

Literature Survey

In this paper, a UAV and deep learning based vehicle detecting, tracking, and counting system has been presented with some advantages in the traffic density estimation system. The proposed DVCF effectively and efficiently extracts traffic den- sity data from the high-resolution UAV videos at various ge- olocations with complex traffic view scopes. To summarize, the following three significant features of our approach have been demonstrated. A UavCT is created to help estimate the real-world city traffic density and is also aiming to motivate research in vision-based traffic flow analysis in intricate traffic views.

In this paper, the DVCF is specifically designed for vehicle detection, classification, tracking, and counting. However, it is easy to be extended to detect and track many other types of objects (e.g., people, bicycles, etc.). The proposed DVCF presents a successful attempt to integrate conventional vision-based algorithms and deep learning based approaches. Compared with recent methods, our approach considers both the accuracy and the efficiency, while exhibiting good robustness.

In this paper, we propose an outlier detection algorithm based on KDE to improve the data quality in crowdsensing ITS. Compared with the traditional detection method, our algorithm can estimate the probability density of the traffic data gathered by smartphones directly without making an assumption of dataset’s distribution or defining the feature of outliers. Thus, our algorithm can improve the performance of ITS effectively, which is proved by simulation results. Moreover, we solve the boundary bias problem in KDE by modifying the kernel function which can offer an important reference for other researchers in other academic fields.

Proposed a traffic density estimation technique using image processing based on the area occupied by the edges of vehicles. The proposed method can easily estimate traffic density according to experiment results. This area based traffic density estimation method can be easily populated country. Our proposed method will play an implemented in an intelligent traffic control system in a dense important role in estimating traffic congestion to control traffic signals but it still requires development to attain higher accuracy.

The proposed traffic control strategy collect the live status of traffic island by using a camera. The control algorithm uses the advantages of image processing and support vector machine to identify and categorize the vehicle. Beside on the traffic density traffic lights are controlled and it also save the data of traffic violated vehicles. In future traffic points in cities can be connected through networking which helps to make an efficient traffic management system.

In this project, a method for estimating the traffic using Image Processing is presented. This is done by using the camera images captured from the highway and videos taken are converted to the image sequences. Each image is processed separately and the number of cars has been counted. If the number of cars exceeds a specific threshold, warning of heavy traffic will be shown automatically. The advantages of this new method include such benefits as use of image processing over sensors, low cost, easy setup and relatively good accuracy and speed. Because this method has been implemented using Image Processing and Mat lab software, production costs are low while achieving high speed and accuracy.

Proposed System

Within the proposed device, we degree the visitors density and layout asystem of site visitors clearance for emergency car the use of imageprocessing by using matlab and % microcontroller to control the site visitors signal.the controlling of site visitors violation processing machine especially comprises detection of the violation, and identity of the vehicle concerned.

Following are the generalized foremost steps worried inside the image processing:

• image acquisition
• rgb to grey conversion
• picture enhancement
• picture matching the use of part detection

Algorithm steps involved:

• preprocessing
• background modeling
• foreground detection
• datavalidation
• moving object detection

Fi=A pixel in current frame

i= frame index

u=pixel of the background model

di=absolute difference between fi and m

bi=B/F mask-o :background.0xFF= foreground

T=Threshold

Alpha=learning the rate of background

Section I

• initially image acquisition is accomplished with the assist of digicam
• first image of the street is captured, while there's no traffic on the road
• this empty street’s image is saved as reference photograph at a selected vicinity distinct in the software
• rgb to gray conversion is performed at the reference picture
• histogram equalization is done on the reference grey image to gain image enhancement

Segment II

• images of the road with motors are captured.
• rgb to gray conversion is accomplished at the collection of captured images
• histogram equalization is carried out on each of the captured grey image to obtain image enhancement
• area detection of these real time images of the road is now finished with Background subtraction method based on IMSTL methodology

Segment III

• after background subtraction procedure both reference and actual time snap shots are matched and visitors lighting may be managed based totally on percent of matching.

Conclusion

This paper offers a technique to reduce visitors congestion on roads overriding the older device of difficult coded lights which cause unwanted delays. Reducing congestion and ready time will lessen the variety of injuries and also reduces fuel intake which in-flip will help in controlling the air pollution. Moreover, the purview of our project may be augmented for IMSTL based historical past subtraction method for traffic density estimation which places site visitors indicators on a coordinated system so that drivers come upon lengthy strings of inexperienced lighting. This will also provide facts for destiny avenue design and construction or where upgrades are required and which are urgent like which junction has higher waiting times.

References

1.  J. Zhu et al., “Urban Traffic Density Estimation Based on Ultrahigh-Resolution UAV Video and Deep Neural Network,” IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., vol. 11, no. 12, pp. 4968–4981, 2018, doi: 10.1109/JSTARS.2018.2879368.
2. Y. Xu, N. Xu, and X. Feng, “A New Outlier Detection Algorithm Based on Kernel Density Estimation for ITS,” Proc. - 2016 IEEE Int. Conf. Internet Things; IEEE Green Comput. Commun. IEEE Cyber, Phys. Soc. Comput. IEEE Smart Data, iThings-GreenCom-CPSCom-Smart Data 2016, pp. 258–262, 2017, doi: 10.1109/iThings-GreenCom-CPSCom-SmartData.2016.67.
3. M. S. Uddin, A. K. Das, and M. A. Taleb, “Real-time area based traffic density estimation by image processing for traffic signal control system: Bangladesh perspective,” 2nd Int. Conf. Electr. Eng. Inf. Commun. Technol. iCEEiCT 2015, no. May, pp. 21–23, 2015, doi: 10.1109/ICEEICT.2015.7307377.
4. R. Soman and P. K. Radhakrishnan, “Traffic Light Control and Violation Detection Using Image Processing,” vol. 08, no. 4, pp. 23–27, 2018.
5. M. Panjwani, N. Tyagi, K. Venkata Lakshmi Narayana, and D. Shalini, “Smart traffic control using image processing,” Int. J. Appl. Eng. Res., vol. 9, no. 16, pp. 3429–3442, 2014.
6. Salama, A.S.; Saleh, B.K.; Eassa, M.M., 'Intelligent cross road traffic management system (ICRTMS),' Computer Technology and Development (ICCTD), 2010 2nd International Conference on , vol., no., pp.27,31, 2-4 Nov. 2010
7. Haimeng Zhao; Xifeng Zheng; Weiya Liu, 'Intelligent Traffic Control System Based on DSP and Nios II,' Informatics in Control, Automation and Robotics, 2009. CAR '09. International Asia Conference on , vol., no., pp.90,94, 1-2 Feb. 2009
8. Dian-xia Hu; Zhi-peng Zheng, 'Intelligent traffic management system,' Artificial Intelligence, Management Science and Electronic Commerce (AIMSEC), 2011 2nd International Conference on , vol., no., pp.3075,3076, 8-10 Aug. 2011
9. Chavan, S.S.; Deshpande, R. S.; Rana, J. G., 'Design of Intelligent Traffic Light Controller Using Embedded System,' Emerging Trends in Engineering and Technology (ICETET), 2009 2nd International Conference on , vol., no., pp.1086,1091, 16-18 Dec. 2009
10. J. Leitloff, S.Hinz, andU. Stilla, “Vehicle detection in very high resolution satellite images of city areas,” IEEE Trans. Geosci. Remote Sens., vol. 48, no. 7, pp. 2795–2806, 2010.
11. S. Hinz, “Detection and counting of cars in aerial images,” in Proc. Int. Conf. Image Process., 2003, vol. 3, pp. 997–1000.
12. W. Yao and U. Stilla, “Comparison of two methods for vehicle extraction from airborne lidar data toward motion analysis,” IEEE Geosci. Remote Sens. Lett., vol. 8, no. 4, pp. 607–611, Jul. 2011.
13. T. N. Mundhenk, G. Konjevod, W. A. Sakla, and K. Boakye, “A large contextual dataset for classification, detection and counting of cars with deep learning,” in Proc. Eur. Conf. Comput. Vis., 2016, pp. 785–800.
14. C. Romero-Trigueros et al., “Effects of saline reclaimed waters and deficit irrigation on citrus physiology assessed by UAV remote sensing,” Agricultural Water Manage., vol. 183, pp. 60–69, 2017.
15. B. L. Machovina, K. J. Feeley, and B. J.Machovina, “UAV remote sensing of spatial variation in banana production,” Crop Pasture Sci., vol. 67, no. 12, pp. 1281–1287, 2017.
16. M. D. Larson, A. S. Milas, R. K. Vincent, and J. E. Evans, “Multi-depth suspended sediment estimation using high-resolution remote-sensing UAV in Maumee river, Ohio,” Int. J. Remote Sens., vol. 39, pp. 1–18, 2018.