Traffic Data Extraction Research Articles

Hybrid Deep Learning Model for Traffic Flow and Speed Forecasting at Urban Junction

The hybrid deep learning model H-CNN-LSTM (Hybrid Convolution Neural Network and Long Short-Term Memory) is introduced in this paper. The model combines CNN to extract traffic flow and speed features, LSTM networks to model temporal dependencies, and employs a combined matrix and a rolling forward input method during data input, enhancing the coarse-grained extraction of traffic data and further refining the utilization of adjacent data. Our research focuses on the complex dynamic traffic conditions of Fuli East Road in Xigu District, Lanzhou City of China. Using detailed traffic video data collected during one month of evening rush hours, we predict future traffic using the H-CNN-LSTM model. By comparing it with other prediction methods, we validate the effectiveness of our approach in predicting traffic flow and speed in real-world traffic scenarios

Automatic traffic data extraction tool for mixed traffic conditions using image processing techniques

Automatic traffic data extraction tool for mixed traffic conditions using image processing techniques

Traffic data extraction and labeling for machine learning based attack detection in IoT networks

Traffic data extraction and labeling for machine learning based attack detection in IoT networks

Automatic Traffic State Recognition Based on Video Features Extracted by an Autoencoder

Video surveillance has become an important measure of urban traffic monitoring and control. However, due to the complex and diverse video scenes, traffic data extraction from original videos is a sophisticated and difficult task, and corresponding algorithms are of high complexity and calculation cost. To reduce the algorithm complexity and subsequent computation cost, this study proposed an autoencoder model which effectively reduces the video dimension by optimizing structural parameters; thus several traffic recognition models can conduct image processing work based on dimension-reduced videos. Firstly, an optimal autoencoder model A ∗ with five hidden layers was constructed. Then, it was combined with a linear classifier, support vector machine, deep neural network, DNN linear classification method, and the k-means clustering method; thus, five traffic state recognition models were constructed: A ∗ -Linear, A ∗ -SVM, A ∗ -DNN, A ∗ -DNN_Linear, and A ∗ -k-means. Train and test results show that the accuracy rate and recall rate of A ∗ -linear, A ∗ -SVM, A ∗ -DNN, and A ∗ -DNN_Linear were 94.5%–97.1%, and the F1 score was 94.4%–97.1%; besides, the accuracy rate, recall rate, and F1 score of A ∗ -k-means were all approximately 95%, which suggests that the combination of the autoencoder A ∗ and common classification or clustering methods achieve good recognition performance. Comparison was also implemented among the five models proposed above and four CNN-based models such as AlexNet, LeNet, GoogLeNet, and VGG16, which shows that the five proposed modes achieve F1 scores of 94.4%–97.1%, while the four CNN-based models achieve F1 scores of 16.7%–94%, indicating that the proposed light weight design methods outperform more complex CNN-based models in traffic state recognition.

A Practical Analysis on Mirai Botnet Traffic

Distributed Denial-of-Service (DDoS) attacks are one of the biggest threats to the availability of Internet services. Behind these attacks are Botnets, such as Mirai, which exploits default and weak security credentials to take control of the host and spreads itself to other devices. This paper demonstrates a Mirai traffic analysis based on on DNS heavy-hitters streams and Mirai scanning patterns by simulating an attack and the extraction of traffic data. The Mirai Command-and-Control (CnC) traffic as well as its scanning traffic are analyzed in a local Testbed composed of six ASUS Tinker Board devices (RaspberryPi like devices) cluster nodes and a MikroTik’s RouterOS to route traffic in different internal networks. In addition to the analysis of traffic flow patterns a real-time mitigation is demonstrated in the experiments.

Background Point Filtering of Low-Channel Infrastructure-Based LiDAR Data Using a Slice-Based Projection Filtering Algorithm.

A light detection and ranging (LiDAR) sensor can obtain richer and more detailed traffic flow information than traditional traffic detectors, which could be valuable data input for various novel intelligent transportation applications. However, the point cloud generated by LiDAR scanning not only includes road user points but also other surrounding object points. It is necessary to remove the worthless points from the point cloud by using a suitable background filtering algorithm to accelerate the micro-level traffic data extraction. This paper presents a background point filtering algorithm using a slice-based projection filtering (SPF) method. First, a 3-D point cloud is projected to 2-D polar coordinates to reduce the point data dimensions and improve the processing efficiency. Then, the point cloud is classified into four categories in a slice unit: Valuable object points (VOPs), worthless object points (WOPs), abnormal ground points (AGPs), and normal ground points (NGPs). Based on the point cloud classification results, the traffic objects (pedestrians and vehicles) and their surrounding information can be easily identified from an individual frame of the point cloud. We proposed an artificial neuron network (ANN)-based model to improve the adaptability of the algorithm in dealing with the road gradient and LiDAR-employing inclination. The experimental results showed that the algorithm of this paper successfully extracted the valuable points, such as road users and curbstones. Compared to the random sample consensus (RANSAC) algorithm and 3-D density-statistic-filtering (3-D-DSF) algorithm, the proposed algorithm in this paper demonstrated better performance in terms of the run-time and background filtering accuracy.

Traffic big data prediction and visualization using Fast Incremental Model Trees-Drift Detection (FIMT-DD)

Information extraction using distributed sensors has been widely used to obtain information knowledge from various regions or areas. Vehicle traffic data extraction is one of the ways to gather information in order to get the traffic condition information. This research intends to predict and visualize the traffic conditions in a particular road region. Traffic data was obtained from Department of Transport UK. These data are collected using hundreds of sensors for 24 h. Thus, the size of data is very huge. In order to get the behavior of the traffic condition, we need to analyze the huge dataset which was obtained from the sensors. The uses of conventional data mining methods are not sufficient to use, due to the process of knowledge building that should store data temporary in the memory. The fact that data is continuously becoming larger over time, therefore we need to find a method that could automatically adapt to process data in the form of streams. We use method called FIMT-DD (Fast Incremental Model Trees-Drift Detection) to analyze and predict the very large traffic dataset. Based on the prediction system that we have developed, we also visualize the prediction of traffic flow condition within generated sensor point in the real map simulation.

A Bilevel Traffic Data Extraction Procedure via Cellular Phone Network for Intercity Travel

The absence of traffic surveillance infrastructure, in many developing countries, hinders any efforts for dealing with the daily witnessed traffic chaos. The use of the cellular phone (CP) network data for traffic data collection is a promising option for large-scale coverage, given a high CP penetration rate. This article presents a bilevel procedure for the extraction of classified vehicular traffic counts for different vehicle types, in a given roadway segment, for intercity travel. The bilevel procedure operates in an offline setting, independent from any secondary traffic surveillance system. At the first level, cellular phones on board the same vehicle are clustered using a “data swarm clustering” algorithm. At the second level, a genetic fuzzy classifier (GFC) is used for vehicles classification. The development and testing of the proposed procedure was conducted using a traffic/CP simulation platform. At the development phase, the swarm-based clustering algorithm achieved 93% clustering accuracy (vehicle count accuracy). At the second level, the fuzzy classifier successfully classified around 85% of the vehicles. The procedure was further evaluated using a microsimulation model of a major travel corridor in the Greater Cairo Region, Egypt. Superior performance was achieved, at the clustering level, with an accuracy of 97.6%. The revealed accuracy demonstrates the efficiency of the developed procedure for extracting unclassified vehicular counts from CP data. At the classification level, accuracy was reduced to 70.6 ± 11.5%. Achieved classification results are promising from a conceptual perspective. Nevertheless, further investigation is crucial for enhanced classification performance and robustness.

Semiautomated Tool for Extraction of Microlevel Traffic Data from Videographic Survey

Real-world traffic data collection, extraction, and analysis at a microscopic level is necessary for modeling various traffic and transportation phenomena. In developing countries such as India, where the traffic is characterized by different vehicle types and non-lane-based vehicle movement, an effective tool for vehicle data extraction and analysis is necessary. Development of a fully automated software tool for vehicle trajectory extraction is practically impossible because of the weak lane-based movement of vehicles and occlusion. For addressing these issues, a semiautomated tool, a traffic data extractor, was developed to extract the details of vehicle movements with good accuracy (0.1 s). A videographic survey followed by a camera calibration technique was used to obtain the real-world coordinates from two-dimensional image coordinates. The concept of a vanishing point–based camera calibration technique was used in this tool. The steps involved in handling the developed tool and its applications in microscopic traffic data extraction and analysis are presented.

Towards automatic near real-time traffic monitoring with an airborne wide angle camera system

Abstract Purpose Large area traffic monitoring with high spatial and temporal resolution is a challenge that cannot be served by today available static infrastructure. Therefore, we present an automatic near real-time traffic monitoring approach using data of an airborne digital camera system with a frame rate of up to 3 fps. Methods By performing direct georeferencing on the obtained aerial images with the use of GPS/IMU data we are able to conduct near real-time traffic data extraction. The traffic processor consists mainly of three steps which are road extraction supported by a priori knowledge of road axes obtained from a road database, vehicle detection by edge extraction, and vehicle tracking based on normalized cross correlation. Results Traffic data is obtained with a correctness of up to 79% at a completeness of 68%. Conclusions With this system we are able to perform area-wide traffic monitoring with high actuality independent from any stationed infrastructure which makes the system well suited for deployments on demand in case of disasters and mass events.

Work domain analysis for air traffic controller weather displays

Introduction: Adverse weather conditions have a major impact on National Airspace System (NAS) operations. They create safety hazards for pilots, constrain the usable airspace for air traffic control (ATC), and reduce the overall capacity of the NAS. A system-wide dissemination of weather information to controllers could theoretically improve safety and efficiency. Problem: However, it is currently unclear what weather information would be beneficial for tactical operations. Furthermore, no previous research has empirically evaluated optimal presentation designs for ATC weather displays. Ill-designed weather displays can cause safety hazards by presenting redundant information (i.e., by increasing the cognitive load) and display clutter (e.g., by interfering with the visual extraction of traffic data). Method: In the present paper, we outline our use of cognitive work analysis (CWA) techniques for the assessment of weather information needs for terminal controllers. Results: Specifically, we describe how the CWA modeling tools helped us reveal instances in the terminal domain where weather information is lacking or insufficiently disseminated. We used our CWA results to drive the development of weather display concepts and to set up a high-fidelity simulation capability. Impact on Industry: By means of high-fidelity simulations, we can empirically evaluate controller weather information needs in order to propose weather displays for increased aircraft safety and efficiency of terminal operations.

A PARALLEL PROCESSING MODEL FOR REAL-TIME COMPUTER VISION-AIDED ROAD TRAFFIC MONITORING

A transputer-based parallel processing paradjgm for real-time extraction of road traffic data from video images of roadway scenes is proposed. The model can monitor three lanes of motorway traffic in real-time by processing images from two windows associated with each lane. Parallel algorithms are distributed among a network of transputers to perform similar and/or different tasks concerning image data analysis and traffic data extraction. The model can be expanded to cover more lanes or duplicated to monitor a further multi-lane carriageway.

Dynamic Scene Modeling for Automatic Traffic Data Extraction

Motion analysis in a road scene from a sequence of T.V. images is the key problem for automatic data extraction. The task of estimating the motion parameters requires the computer to identify moving vehicles and pedestrians in each frame of the sequence. In this paper, we propose a new technique for dynamic road scene modeling. Moving edges are first detected by combining differencing and differential operations on successive frames of the sequence, a technique that is quite insensitive to the variations of the illumination of the scene. The knowledge of the boundaries of the moving objects is then used to generate minimum bounding octagonal models of vehicles and pedestrians. Thanks to this new model, it is possible to locate simply any moving object in any frame of the sequence of images. The algorithm, implemented on a high‐speed image processor, has been tested using videotapes of real‐world urban street crossings under various natural lighting conditions.