Neural-edge-based vehicle detection and traffic parameter extraction
Introduction
In recent years, laying new pavement or adding more lanes is becoming less and less feasible, thus that is no longer efficient solution for serious traffic congestion problem due to consistent increment of vehicles. One of the realistic solutions is to use the existing infrastructure more efficiently. Road traffic monitoring and control is the essential component of this solution. To monitor road traffic, it is necessary to extract traffic parameters that describe the characteristics of vehicles and their movement on the road. Vehicle counts, vehicle speed, vehicle path, flow rates, vehicle density, vehicle dimension, vehicle class and vehicle identity via the number plate are all example of useful traffic parameters. Various kinds of traffic control systems, for example, law enforcement, automatic tolls, congestion and incident detection, and increasing road capacity via automatic routing and variable speed limit, can be implemented with these traffic parameters.
Magnetic loop detector is most common method of traffic parameter extraction for traffic monitoring and control. Magnetic loops are very inexpensive and provide traffic parameters such as average speed, vehicle flow, and vehicle density. But, they have some problems as follows. First, they are very inflexible and modifications or additions require digging grooves in the road, thus producing traffic disturbances. Second, they cannot be used for more sophisticated tasks such as queue length measurement, tracking, etc. [8]. In recent years, an image-based traffic monitoring system is a remarkable alternative for magnetic loop detectors.
Current interest in the image-based traffic monitoring system is due to its ability to solve magnetic loop detector's problems described above. Also, image-based traffic monitoring systems offer a number of advantages. In addition to vehicle counts, a much larger set of traffic parameters, such as queue length, vehicle speed, vehicle class, vehicle path, etc. can be extracted. Besides, image-based traffic monitoring systems are much less disruptive to install than magnetic loops, thus they don't produce serious traffic disturbances [5]. In spite of these advantages, the vehicle detection error due to variation of ambient lighting condition, shadows and different shape or size of vehicles makes serious difficulties to extract traffic parameters [3], [4].
In this paper, we propose a neural-edge-based vehicle detection method for improvement of vehicle detection and vehicle classification accuracy. This paper starts by describing an overview of related work in Section 2 and the object region extraction method based on background subtraction is presented in Section 3. In 4 Neural-edge-based vehicle detection, 5 Traffic parameter extraction via vehicle tracking, the neural-edge-based vehicle detection method and the traffic parameter extraction via vehicle tracking is described. Experimental result and conclusion are given in 6 Experimental result, 7 Conclusion.
Section snippets
Related work
Vehicle detection is a fundamental component of image-based traffic monitoring system, and has been implemented by various different approaches. For vehicle detection, the commonly used approaches are gray-level comparison, inter-frame subtraction, background subtraction, edge detection-based method, etc. In England, TULIP (Traffic analysis Using Image Processing) performed the vehicle detection operation with gray-level comparison [11]. There are some systems that achieved the vehicle
Object region extraction
The first step in vehicle detection is to extract an object region from the current input image. In this paper, we use a background subtraction method for object region extraction. In this method, we introduce a selective background updating scheme to adapt background to the change of ambient lighting and weather conditions. Also, the initial background is extracted by an automatic background extraction. Our object region extraction method consists of three steps: background subtraction,
Neural-edge-based vehicle detection
The object region extraction is the basic step of vehicle detection as previously described. An example of object region extraction result that is used in this paper is given in Fig. 2. In the figure, there is a big shadow of the first vehicle projected on the left lane and the shadow is so big that it may be mistaken as a vehicle. The active shadow due to moving vehicle produces non-vehicle region, and it ultimately makes vehicle detection error. Therefore, we propose a neural-edge-based
Traffic parameter extraction via vehicle tracking
In this paper, traffic parameters, such as vehicle count, vehicle speed, and vehicle class, are extracted via vehicle detection and tracking method. The vehicle object and its class are recognized via the neural-edge-based vehicle detection method that proposed in Section 4. The individual vehicle is tracked within a tracking area on each lane. The vehicle tracking area has a trapezoidal shape and an entrance zone and an exit zone are located at the top and bottom of the area as shown in Fig. 2
Experimental environment
The block diagram for the neural-edge-based vehicle detection and traffic parameter extraction method proposed in this paper is presented in Fig. 4. The analog image output from the video camera that mounted over the road is converted to digital data by the frame grabber embedded in a personal computer system and the digitized traffic image is used for algorithm processing. In this paper, the computer system and software configuration given below is used to implement and evaluate the
Conclusion
In this paper, we propose the neural-edge-based vehicle detection and traffic parameter extraction method. In the proposed vehicle detection method, the feature information is extracted by using the seed-filling-based feature extraction method that combines background subtraction and moving edge detection result. And then, we improved the accuracy of vehicle detection and classification by using this feature information as an input of neural network. The method is effective and the correct rate
References (13)
- et al.
Interactive computer graphics: functional, procedural and device-level methods
(1989) - et al.
Image processing applied to traffic: a general review
Traffic Eng. Contr.
(1984) - et al.
Real-time image processing approach to measure traffic queue parameters
IEE Proc.—Vis. Image Signal Process.
(1995) - et al.
A window-based image processing technique for quantitative and qualitative analysis of road traffic parameters
IEEE Trans. Vehicular Technol.
(1998) - et al.
Detection and classification of vehicles
IEEE Trans. Intell. Transport. Syst.
(2002) Development of an image processing traffic flow measurement system
Sumitomo Electron. Tech. Rev.
(1988)
Cited by (86)
Vehicle Classification in Intelligent Transport Systems: An Overview, Methods and Software Perspective
2021, IEEE Open Journal of Intelligent Transportation SystemsTraffic parameters survey methodology for traffic modelling of intersections: Case of study lima, peru
2020, 2020 IEEE ANDESCON, ANDESCON 2020A review on vehicle classification and potential use of smart vehicle-assisted techniques
2020, Sensors (Switzerland)Dynamic Spatial Predicted Background
2020, IEEE Transactions on Image ProcessingAn IoT-based dynamic traffic management system in perspective of Bangladesh
2019, World Review of Intermodal Transportation Research