Traffic Flow Detection Research Articles

Vehicle Traffic Flow Detection System Based on Video Images under Haze Environment

Vehicle Traffic Flow Detection System Based on Video Images under Haze Environment

Research on Prediction Method of Freeway Operation Situation Based on Short-Term Traffic Flow Multi-Parameters Regression

In order to realize the short-term prediction of traffic flow operation security situation, so as to enhance the operation safety of freeway, based on the traffic flow detection data and traffic accident data of Beijing section in Jing-ha freeway, the security situation prediction model based on short-term multi-parameters was established in the paper. Firstly, we extracted all the traffic flow data of microwave coils and videos, as well as the traffic accidents after updating the electromechanical system of Beijing section in Jing-ha freeway, so as to establish the risk prediction database, and developed the pre-analysis software of basic data; secondly, the traffic flow data of 30 minutes prior to the time of the accident were divided into six slices at 5-minute level, and the volume, speed, occupancy as well as their statistical parameters were selected as the chosen parameters of the model; next, single-parameter Logistic regression analysis was carried out in each time slice respectively; finally, based on the results of the correlation analysis of parameters and the single-parameter modeling significance, the multi-parameters Logistic regression model was established in each time slice respectively, thus obtaining the short-term prediction model of the traffic flow operation security situation. The results indicate that, the modeling fitting effect of slice 1 is the best, that is the change of the traffic flow parameters and their statistics in 5 minutes prior to the time of the accident can effectively predict the possibility of the accident, in which the average speed has a significant impact on the risk of the accident.

Camera Calibration Method Exploiting Reference Images and Roadway Information for Traffic Applications

A video-based traffic flow detection system requires calibration of cameras to generate accurate estimates of vehicle speed. Traditional manual calibration methods cannot satisfy this requirement because calibration has complex procedures. A new traffic camera calibration method is proposed, which exploits reference images and roadway information. The proposed method requires only two parallel lane markings with a known width and a line perpendicular to the lane markings. Camera parameters, including focal length, tilt angle, pan angle, and camera height, can be recovered. A method based on reference images is further proposed to calculate ill-conditioned camera parameters, in which reference images are acquired by a rotating camera while keeping focal length unchanged. Camera recalibration can be easily realized through reference images and roadway information when cameras are moved manually. Simulation experiments demonstrate that the proposed method has the advantages of simple operation and accurate parameter estimations. The method also requires no manual operations and saves manpower.

A new smart traffic monitoring method using embedded cement-based piezoelectric sensors

Cement-based piezoelectric composites are employed as the sensing elements of a new smart traffic monitoring system. The piezoelectricity of the cement-based piezoelectric sensors enables powerful and accurate real-time detection of the pressure induced by the traffic flow. To describe the mechanical-electrical conversion mechanism between traffic flow and the electrical output of the embedded piezoelectric sensors, a mathematical model is established based on Duhamel’s integral, the constitutive law and the charge-leakage characteristics of the piezoelectric composite. Laboratory tests show that the voltage magnitude of the sensor is linearly proportional to the applied pressure, which ensures the reliability of the cement-based piezoelectric sensors for traffic monitoring. A series of on-site road tests by a 10 tonne truck and a 6.8 tonne van show that vehicle weight-in-motion can be predicted based on the mechanical-electrical model by taking into account the vehicle speed and the charge-leakage property of the piezoelectric sensor. In the speed range from 20 km h−1 to 70 km h−1, the error of the repeated weigh-in-motion measurements of the 6.8 tonne van is less than 1 tonne. The results indicate that the embedded cement-based piezoelectric sensors and associated measurement setup have good capability of smart traffic monitoring, such as traffic flow detection, vehicle speed detection and weigh-in-motion measurement.

Research and Design of Road Traffic Flow Detection System

A road traffic flow detection system is designed based on induction loop, and the control platform is constructed based on the most advanced 32-bit ARM processor and CPLD. The systems hardware framework and software design process are introduced in this paper. The defects of traditional system such as deficient processing capacity and low measurement accuracy are overcome. In this system the data of the frequency change caused by the vehicles through the coil is collected, and the function of vehicles type classification in real-time is added, which is a great improvement compared to traditional induction loop detection system of vehicles.

An Intelligent Traffic Flow Control System Based on Radio Frequency Identification and Wireless Sensor Networks

This study primarily focuses on the use of radio frequency identification (RFID) as a form of traffic flow detection, which transmits collected information related to traffic flow directly to a control system through an RS232 interface. At the same time, the sensor analyzes and judges the information using an extension algorithm designed to achieve the objective of controlling the flow of traffic. In addition, the traffic flow situation is also transmitted to a remote monitoring control system through ZigBee wireless network communication technology. The traffic flow control system developed in this study can perform remote transmission and reduce traffic accidents. And it can also effectively control traffic flow while reducing traffic delay time and maintaining the smooth flow of traffic.

Traffic Flow Detection Algorithm Based on Gaussian Mixture Background Modeling

This paper aims to solve the problem of traffic flow detection through video analysis. To tackle with this problem, we propose a novel traffic flow detection algorithm based on Gaussian Mixture Background Modeling which mainly utilizes the advantages of two existing traffic flow detection methods combined with some other technologies, such as improved canny edge detection algorithm, Gaussian Mixture Background Modeling method and background difference techniques. Extensive experiments and comparative studies show the superiority of our traffic flow detection algorithm in real time performance and accuracy.

Path Reconstruction of Intelligent Traffic Based on Positive Feedback System

Traffic congestion are prevalent in worldwide cities. The imbalance between demand and supply of urban traffic is the root cause of this problem. So taking effective measures to regulate traffic demand, and guiding the traffic problems of the supply and demand balance is the best way to solve traffic congestion. This paper improves the TDM measure, and combines with intelligent information platform for the design of a new urban transport demand management adaptability of dynamic traffic data analysis platform. The platform supported by the technology of wireless sensor communications, intelligent terminals, the Internet and cloud computing is facing with the dynamic needs of traffic flow and traffic congestion state to carry out the operations of spatiotemporal data mining, clustering, and track detection, and to apply it into the traffic hot spots, abnormal driving track, traffic congestion trends and traffic flow detection and analysis, which has a good reference value for the improvement of management and service level of traffic intelligent systems.

Implementation of Vehicle Detection System Using WSN

Vehicle Detection System plays a basic role in the field of intelligent transportation, and is the cornerstone of constructing modern intelligent transportation system. This paper presents a new vehicle detection algorithm using WSN that called the adaptive state machine. The algorithm can adaptively update the threshold and baseline; use the state machine to achieve the aim of the accurate and efficient vehicle detection. It can be used for the detection of road traffic flow, and can be used in large parking vehicle guidance system. On the road, we have deployed 76 Sensor Nodes to evaluate the performance. We observe the accurate of the road vehicle detection rate of vehicle detection system is nearly 98%.

Traffic Flow Detection Based on Wireless Sensor Network

Detecting traffic flow by in-road inductive loop is the most common methods, but inductive loop is physically large, it is hard to install and maintain, also the classification rate is low. The inductive loops cannot communicate with each other, so they cannot share traffic data with each other. The wireless sensor network has these features: real-time, fault tolerance, scalability and coordination. Applying wireless sensor network into traffic area for traffic flow detection is easier to install, and provide real-time traffic flow for coordinate traffic control, also it can improve the classification rate. A lot of researchers applied the wireless sensor network for traffic flow detection, but no one referred to the coordinate traffic flow detection method. In this paper, we provided a coordinate traffic flow detection framework. Based on this framework, we set up a simple traffic flow detection platform by wireless sensor nodes produced by cross box company to verify this method. We selected four periods, for each period, we got a more than 90% classification rate.

Video-based method for highway traffic flow detection

Video-based traffic flow detection systems are easily influenced by background changing and vehicle shadows.A method for traffic flow detection using self-adaptive background difference and shadow removing was proposed.First,the adaptive background model was constructed and used to extract image background;and then interested vehicles were detected from video candidate area by self-adaptive background difference.The difference image was changed into binary image by given threshold,and the holes were filled within the extracted objects using morphological reconstruction by erosion.Second,according to the fact that the gray value of the shadow area was less than that of the vehicle area,the binary image object along the direction from shadow area to vehicle area was compared.By this way,most vehicle shadows can be removed.Simulations show that this method can efficiently detect the highway traffic flow and is less influenced by vehicle shadows and background changing.

Pedestrian Safety Analysis in Mixed Traffic Conditions Using Video Data

With the dramatic development of image processing technology, a growing number of traffic flow detection and analyses have been conducted by using video data. Time to collision (TTC) and postencroachment time (PET) are two major parameters used to indicate the severity of a potential collision and to capture an imminent vehicular accident. However, microlevel pedestrian-involved collisions are less studied because they are hard to observe or record. This paper tries to extract the traffic object locations from video data, to define the time difference to collision (TDTC) parameter as a variation from TTC and PET to fit the pedestrian-involved potential collisions/conflicts, analyze the interaction behavior between pedestrian and vehicles, and validate the TDTC parameter in indicating pedestrian safety performance by using 100 groups of interaction data. The results show that the interaction cases with larger TDTC values are safer, whereas the cases with continuously closer to zero TDTC values are more dangerous. About 80% of the cases classified by the TDTC parameter have the same result with the independent observation; if TDTC is combined with vehicle speed, the classification result can be improved. More mixed traffic scenes will be conducted based on this research in the future.

Virtual vectors and network traffic analysis

In a high-speed network, traffic monitoring modules should be compact in size to fit into a fast but small memory (e.g., SRAM). We propose two compact algorithms for network traffic monitoring and analysis, for the purposes of per-flow traffic measurement and long-duration flow detection. The proposed schemes are based on the data structure of a virtual vector that was recently invented, but limited to the purpose of estimating spread value. We found that the virtual vector can be applied to a range of different problems in the area of network traffic monitoring and analysis. In this article, we propose a counting virtual vector that counts the number of packets for per-flow traffic measurement. For long-duration flow detection, we observe that the attackers can easily evade the previous work and propose a new detection scheme to catch even evasive flows. Through experiments on real Internet traffic traces, we show that the proposed schemes outperform previous work or make up for its weaknesses.

Traffic information collecting algorithms for road selection decision support in vehicle ad hoc networks

Traffic information collection is critical issue for vehicle drivers. How to gather the traffic information is a challenge problem. We know that the more the traffic density is, the faster the data delivery is in a vehicle ad hoc network. We also know that the more traffic density is, the more traffic jam probability maybe. So the traffic density is a double edged sword. We may use the road with dense traffic density to transmit road information while use the road with thin traffic density to drive. This paper provides novel ideas to identify traffic density, traffic flow and to support road selection in vehicle ad hoc networks. Using the hop counter, speed detector in packet header, we give traffic density, traffic flow detection algorithm. Consider real time decision of road selection, road dynamic selection algorithm is presented by packet delay. Consider there may be no path to select, all the paths are jammed, carry-and-forward scheme maybe a robust transmit mode in disconnected and delay network, we present a carry-and-forward method to collect road information and predict the road situation in the end.

A Traffic Flow Detection Algorithm in the Intersection Electronic Police System Based on Video

The Electronic Police System is an important trend of the development of the Intelligent Traffic System present. Aim at video images taken by the Electronic Police System, a kind of vehicle detection algorithm based on detecting area is proposed. This method combines background difference with edge difference and morphological steps to detect vehicles, and the accuracy of the algorithm is further improved by correcting the frame data stream. Experimental results demonstrate that the algorithm is effective and can meet the needs of real-time requirement.

Traffic Flow Detection on Highways in the Intelligent Transportation System

A traffic flow detection method is brought forward which can adapt to Pan Tilt Zoom camera automatically.Road marks are used to establish the coordinate mapping between image and road in order to realize raffic flow statistic and traffic surveillance.Parameters are updated in time automatically when scene is changed.The system is proved to be intelligent and robust in practiceal applications.

An Efficient and Robust Moving Shadow Removal Algorithm and Its Applications in ITS

We propose an efficient algorithm for removing shadows of moving vehicles caused by non-uniform distributions of light reflections in the daytime. This paper presents a brand-new and complete structure in feature combination as well as analysis for orientating and labeling moving shadows so as to extract the defined objects in foregrounds more easily in each snapshot of the original files of videos which are acquired in the real traffic situations. Moreover, we make use of Gaussian Mixture Model (GMM) for background removal and detection of moving shadows in our tested images, and define two indices for characterizing non-shadowed regions where one indicates the characteristics of lines and the other index can be characterized by the information in gray scales of images which helps us to build a newly defined set of darkening ratios (modified darkening factors) based on Gaussian models. To prove the effectiveness of our moving shadow algorithm, we carry it out with a practical application of traffic flow detection in ITS (Intelligent Transportation System)—vehicle counting. Our algorithm shows the faster processing speed, 13.84 ms/frame, and can improve the accuracy rate in 4%~ 10% for our three tested videos in the experimental results of vehicle counting.

Traffic Flow Detection and Forecasting

In order to improve traffic conditions in the urban streets, traffic flow forecasting precision is one of the major tasks. How to improve traffic flow prediction precision remains an important problem of intelligent transportation systems. A lot of methods of Short- term traffic flow forecasting are designed. The methods are developed and optimized in order to obtain more accurate forecasting information. Often traffic flow forecasting accurate depends of traffic flow data collection accurate. We propose short- term traffic flow forecasting method based on improved data detection technology. Method tested with different forecasting models. Results show that proposed method is very suitable for short- term traffic flow forecasting.