Analysis and Designing of Proposed Intelligent Road Traffic Congestion Control System with Image Mosaicking Technique

Transcription

1 27 Analysis and Designing of Proposed Intelligent Road Traffic Congestion Control System with Image Mosaicking Technique Prof. (Dr.) Y.P.Singh, Director, KLS Institute of Engineering & Technology, Chandok, Bijnor U.P. Pradeep Kumar Mittal, Research Scholar, Jodhpur National University, Jodhpur ABSTRACT As the problem of urban traffic congestion spreads, there is a pressing need for the introduction of advanced technology and equipment to improve the state-of-the-art of traffic control. As on date Traffic problems are increasing because of the number of vehicles are increasing by leaps and bounds beside the resources available with the current infrastructure are limited. A methodology has been obtained by Structured System Analysis to analyze the existing problem and Designing new model by using image mosaicking based Techniques. Problems were identified with current traffic control system. Beside, to analysis and design of new and effective system to solve the existing problems. Keywords Traffic congestion, image mosaicking, Fuzzy Expert System, Artificial Neural Network,. An Intelligence Decision-making system for Urban Traffic-Control (IDUTC), Conventional Automatic road traffic] 1. INTRODUCTION Traffic congestion is a severe problem in many modern cities around the world. Traffic congestion has been causing many critical problems and challenges in the major and most populated cities. To travel to different places within the city is becoming more difficult for the travelers in traffic. Due to these congestion problems, people lose time, miss opportunities, and get frustrated. Traffic congestion directly impacts the companies. Due to traffic congestions there is a loss in productivity from workers, trade opportunities are lost, delivery gets delayed, and thereby the costs goes on increasing. All above mentioned factors leads to a bad impact on the economy of country. To solve these congestion problems, we have to build new facilities and infrastructure, but at the same time make it smart. The only disadvantage of making new roads on facilities is that it makes the surroundings more congested. So for that reason we need to change the system rather than making new infrastructure twice. Therefore many countries are working to manage their existing transportation systems to improve mobility, safety and traffic flows in order to reduce the demand of vehicle use. By enhancing public transport, route guidance systems, traffic signal improvements, and incident management, congestion can be improved greatly from the statistical analysis of US department of transportation in 2007, it has been found that half of the congestion caused is due to the recurring congestion. These congestion problems are recurring congestion problems are caused due to poor guidance of travelers. The other half of the congestions are due to the non-recurring congestions which are due to traffic incidents, work zones, weather on special events. Nonrecurring events dramatically reduce available capacity and reliability of the entire transportation system. The researches done on these goals would be started by stating about the simulation model created by Schaefer, Upcburch and Asbur (1998) which evaluated the freeway lane control signing. The simulation showed that lane control had some influence that lane control had some influence on congestion. 2. LITERATURE REVIEW It has been observed that there are different types of systems were used for solving traffic congestion problems are: 1. Fuzzy Expert System 2. Artificial Neural Network 3. An Intelligence Decision-making system for Urban Traffic-Control (IDUTC) 2.1 Fuzzy Expert System Fuzzy expert system was used to control the traffic light in most cities. It was the most common system used in major areas. The fuzzy expert system [1] composed of seven elements i.e. a radio frequency identification reader (RFID), an active RFID tag, a personal digital assistance (PDA), a wireless network, a database, a knowledge base and a backend server. The Figure (1) gives a brief knowledge about the connections of the different elements of the system.

2 28 Figure 1: A framework for dynamic and automatic traffic light control expert systems [1]. In this system, the RFID reader detects a RF-ACTIVE code at 1024 MHz from the active tag pasted on the car. The active tag has a battery, which is inbuilt inside it, so that it can periodically and actively transmit messages stored in the tag. As soon as the data is received, the reader will save all information in the PDA. When the PDA accumulates the required amount of data, it will use its wireless card and connect to the backend server and store them in to the database in the server. Now the server uses the data stored in the database to calculate maximum flow, interarrival time and average car speed. When all possible congestion roads and car speed are collected, then these data would be used as the input parameters of the traffic light control simulation model in the server. After getting the simulation results, the system is able to automatically give different alternatives in terms of varieties of traffic situations and then the red light or green light duration is being set via a traffic light control interface for improving the traffic congestion problems. All the rules and reasoning are used in the IF-THEN format. The system is using the forward chaining approach, which is a data driven approach, starting from a basic idea and then tries to draw conclusions. The simulation model running in this system give three optimal alternatives; the best, second and third best traffic light duration. The system uses these alternatives as well as the collected data to choose the best and the most suitable solution for that particular traffic congestion situation. 2.2 Artificial Neural Network Approach The adaptive traffic light problem was modeled using the ANN approach [2]. The researchers Patel and Ranganathan created an ANN model which included predicting the traffic parameters for the next time frame and computing the cycle-time adjustment values. This model consisted of nine inputs (one of each past and present traffic parameters one hidden layers with 70 hidden nodes and three output nodes. The ANN model, if drawn a sketch, would like as shown in Figure (2) Figure 2: ANN traffic Model [2] The input given to the ANN models are the list of data collected by the sensors which are placed around the traffic lights. The sensors give the traffic light ANN model all the data which are related to the past and present traffic parameters. The model after getting the input used the hidden layer to decide which nodes suites the current traffic situation. Each hidden nodes is given a membership function (i.e. between 0 and 1). After comparing the nodes and matching it with the current situation with the help of membership function, the most suitable results or alternatives are selected as the output are then used by the traffic lights to set the timing for the red and green lights. The output of the ANN model will be in the form of membership functions ranging from 0 to Intelligent Decision making system for Urban Traffic Control (IDUTC) IDUTC [3] is a real time intelligent decision making

3 29 system that computes decisions within a dynamically changing application environment. The architecture of the IDUTC is shown in figure (3) Figure 3: IDUTC Architecture [3] The IDUTC model consists of seven elements. The names of the element are as follows: Artificial Neural Network (ANN). Fuzzification element Fuzzy expert systems (FES) Defuzzification Element. Application environment. Controllers Sensors The IDUTC is a self adjusting traffic light control system. The sensors of the system are placed at the road to sense the different parameters of the traffic conditions. The sensors are the actual input of the IDUTC model. Sensors collect the past data of the traffic conditions, which is all known as the application environments shown in the figure above. After the surrounding environmental conditions, the sensors send crisp data inputs to the artificial neural network. The ANN model collects all the data from the systems and process it through the hidden layers and gives the desired output. Now the output of ANN model are assigned fuzzy labels indicates the degree to which each crisp value is a member of a domain. Then the fuzzy expert system fires the rules based on these fuzzy values. The Defuzzification unit converts the computed decisions into crisp values that are used to control the environment through the controllers installed at the traffic lights. After running the simulation on the traffic light, past data are being collected along with the present data by the sensors. The cycle goes on repeating and tries to change the traffic light timings condition. This shows that the system is self-adjusting according to the situation. Major Problems encountered in Conventional Automatic road traffic congestion control system 1. If the position of vehicle does not come in alignment of infrared rays then IR sensor would not give response. 2. If the vehicle is under faulty condition in the range of IR rays then the response given by IR sensor would not be accurate. 3. If a single camera is used as a vision sensor for acquiring the image of traffic then it is difficult to detect the space between two vehicles means projection of camera would be crucial factor for measuring the traffic density. 3. METHODOLOGY A novel methodology was described in this proposed system for analysis and design of the intelligent traffic lights control system by using Image Mosaicking Techniques. This is obtained by Structured System Analysis and Designing the traffic light control system by using the Image Mosaic Based Design Methodology

4 30 (Figure 4). The systems study leads to the analysis and thereafter preliminary design was carried out and using first step of the Image Mosaic Based Design Methodology as shown in the broken arc in figure 4. The Image Mosaicking-based methodology was chosen as the paradigm for an alternative design methodology; applied in developing the systems for traffic congestion control. Therefore, the physical and logical design phases of the Structured System Analysis and Design were replaced by the two steps of the Image Mosaicking-based methodology to complete the crossing of the two methodologies. A hybrid methodology was necessary because there was a need to examine the existing systems, classify the intersections as Y and + junction with the view of determining the major causes of traffic deadlock on road junction. There was also the need to design the traffic control system using fuzzy rules and simulation to implement an intelligent traffic control system that will eliminate logjam. Figure 4. Proposed Methodology 4. PROPOSED SCHEME Rather than use of sensor/multiple sensors or single camera, multiple cameras has been used in proposed scheme where using image mosaicking technique the data from various cameras are collected and integrated (mosaicking) for matching the two images (test image & reference image) whose result manuplates the timing of green signals/red signals. Proposed work technique is shown in figure (5). Image matching is also possible with image registration technique or some another methods like correlation between two images (by pixels). The decision making algorithm decides the timing of Red/Green Signal according to the density measured on the road. Figure 5: Proposed Schematic Diagram

5 31 5. CONCLUSION Road traffic congestion is a central problem in most developing regions. Most urban areas have poorly managed traffic networks with several traffic potential congestion areas. In this scheme, we attempted to solve the problem of road traffic congestion in high congestion hotspots in developing regions through analysis & design of intelligent system. We first present a simple image processing algorithm to estimate traffic density at a hotspot using CCTV cameras feeds. Based on analysis of traffic images from live traffic feeds, we show evidence of congestion collapse which last for elongated time periods. Based on the image comparing after integrating the images from various projections, it is shown that intelligent decision making algorithm has been developed for controlling the heavy congestion on roads. 6. REFERENCES [1] W.Wen, A dynamic and automatic traffic light control expert system for solving the road congestion problem, Science direct: Expert system with applications, 34, pp , 2008 [2] Yujie Dai, Jinzong Hu, Dongbin Zhao, Fenghua Zhu, Neural network based online traffic signal controller design, IEEE conference on Intelligent Transportation System, pp , 5-7 Oct [3] Patel.M, Ranganathan.N, IDUTC: an intelligent decision-making system for urban traffic control applications, IEEE Transactions on Vehicular Technology, pp , May [4] E. Fern andez and R. Marti, GRASP for seam drawing in mosaicking of aerial photographic maps, J. Heuristics, vol. 5, pp , [5] M. Brown and D. G. Lowe, Automatic panoramic image stitching using invariant features, Int l J. Computer Vision, vol. 74, no. 1, pp , [6] P. Mclauchlan and A. Jaenicke, Image mosaicing using sequential bundle adjustment, Image and Vision Computing, vol. 20, pp , [7] G. M. Cortelazzo and L. Lucchese, A new method of image mosaicking and its application to cultural heritage representation, Proc. Eurographics,vol. 88, no. 3, [8] R. Szeliski, Image alignment and stitching: A tutorial, in Handbook of Mathematical Models in Computer Vision, Springer, pp , [9] Lisa Brown, A survey of image registration techniques," ACM Computing Surveys, vol. 24, no. 4, pp , Dec [10] Jan Kybic, Philippe Th_evenaz, and Michael Unser, Multiresolution spline warping for EPI registration," in Proceedings of SPIE, Denver, Colorado, July 1999, vol. 3813, pp , SPIE. [11] Ruzena Bajcsy and Stane Kova_ci_c, Multiresolution elastic matching," Computer Vision, Graphics, and Image Processing, vol. 46, pp. 1-21, ABOUT THE AUTHOR 1. Prof. Y.P. Singh, currently working as Director, KLS Institute of Engg.& Technology, Chandok, Bijnor U.P. has also worked about 27 years as Lecturer, Dean of academics & Principal in many Engineering institutions and organization. He has also served with Training and Technical Deptt. Govt.Of Delhi, almost for 17 years. He has about 33 research paper published in National and 12 papers published in international journals in his credit. He has been selected and awarded by Govt. of Delhi as Best Technical Teacher-2004.He is also an expert and Master Trainer for the Teachers, empanelled by SCERT/NCERT. He is also the guide of research scholar for almost dozen of Universities. 2. Mr. Pradeep Kumar Mittal, is working as a ECE faculty, with NIT Jullundhar, Punjab and also pursuing his research from Jodhpur National University Jodhpur