Driving Speed Estimation and Trapped Drivers’ Detection inside Tunnels Using Distributed MIMO Bluetooth Devices

Accidents in highway tunnels involving trucks carrying flammable cargoes can be dangerous, needing immediate confrontation to detect and safely evacuate the trapped people to lead them to the safety exits. Unfortunately, existing sensing technologies fail to detect and track trapped persons or moving vehicles inside tunnels in such an environment. This paper presents a distributed Bluetooth system architecture that uses detection equipment following a MIMO approach. The proposed equipment uses two long-range Bluetooth and one BLE transponder to locate vehicles and trapped people in motorway tunnels. Moreover, the detector’s parts and distributed architecture are analytically described, along with interfacing with the authors’ resources management system implementation. Furthermore, the authors also propose a speed detection process, based on classifier training, using RSSI input and speed calculations from the tunnel inductive loops as output, instead of the Friis equation with Kalman filtering steps. The proposed detector was experimentally placed at the Votonosi tunnel of the EGNATIA motorway in Greece, and its detection functionality was validated. Finally, the detector classification process accuracy is evaluated using feedback from the existing tunnel inductive loop detectors. According to the evaluation process, classifiers based on decision trees or random forests achieve the highest accuracy.

Controlling Mixed Connected and Non-Connected Vehicle Traffic Through a Diamond Interchange

Diamond interchanges (DIs) allow movement of vehicles between surface streets and freeways for all types of vehicles, including normal non-connected human-driven vehicle (NHDV) traffic and the connected vehicles (CVs). Unlike simple intersections, DIs consist of a pair of closely spaced intersections that are controlled together with complicated traffic movements and heavy demand fluctuations. This paper reviews the movements being controlled at DIs and presents a dynamic programming (DP)-based real-time proactive traffic control algorithm called MIDAS, to control both NHDVs and CVs. Like seminal cycle-free adaptive control methods such as OPAC and RHODES, MIDAS uses a forward recursion DP approach with efficient data structures for any large set of phase movements being controlled at DIs, over a finite-time horizon that rolls forward, and then uses a backward recursion to retrieve the optimal phase sequence and duration of phases. MIDAS captures Eulerian measurements from fixed loop detectors for all vehicles, and also captures Lagrangian measurements like in-vehicle GPS from CVs to estimate link travel times, arrival times, turning movements, etc. For every time horizon MIDAS predicts future arrivals, estimates queues at the interchange, and then minimizes a user-defined metric like delays, stops, or queues at an interchange. The paper compares performances of MIDAS with those of an optimal fixed cycle time signal control (OFTC) scheme and RHODES control on a simulated DI. The simulation is of Phoenix, AZ, DI (on I-17/19th Ave.) that uses the VISSIM micro-simulation platform. Performance is evaluated for various traffic loads and various CV market penetrations. Results show that MIDAS control outperforms RHODES and OFTC.

Parameter Estimation of the Macroscopic Fundamental Diagram: A Maximum Likelihood Approach

This paper extends the Stochastic Method of Cuts (SMoC) to approximate of the Macroscopic Fundamental Diagram (MFD) of urban networks and uses Maximum Likelihood Estimation (MLE) method to estimate the model parameters based on empirical data from a corridor and 30 cities around the world. For the corridor case, the estimated values are in good agreement with the measured values of the parameters. For the network datasets, the results indicate that the method yields satisfactory parameter estimates and graphical fits for roughly 50\% of the studied networks, where estimations fall within the expected range of the parameter values. The satisfactory estimates are mostly for the datasets which (i) cover a relatively wider range of densities and (ii) the average flow values at different densities are approximately normally distributed similar to the probability density function of the SMoC. The estimated parameter values are compared to the real or expected values and any discrepancies and their potential causes are discussed in depth to identify the challenges in the MFD estimation both analytically and empirically. In particular, we find that the most important issues needing further investigation are: (i) the distribution of loop detectors within the links, (ii) the distribution of loop detectors across the network, and (iii) the treatment of unsignalized intersections and their impact on the block length.

Video Based Vehicle Detection and Counting Using Digital Image Processing

Vehicle detection and counting is very much important for the purpose of upgrading and widening the road. The information obtained from the traffic monitoring can be used in planning the budget for road maintenance. The traffic monitoring can be done automatically or by detecting and counting the vehicles manually using human labors. In manual method of traffic monitoring the person records the data using tally sheet which may leads to the human errors and most of the automatic traffic census system used nowadays focuses on detecting and counting the vehicles by using devices called magnetic loop detectors. These devices are costly and once installed, cannot be removed. So, it is necessary to build the system that is capable of detecting and counting vehicles without involving persons for traffic monitoring and costlier devices to detect and count the vehicles. For that purpose in this work simple cameras are used for detection and counting of vehicles. Keywords: Detection, Counting, Background subtraction, Canny edge detection, Kalman filter.

Identifying Wrong-Way Driving Incidents from Regular Traffic Videos Using Unsupervised Trajectory-based Method

Currently, transportation agencies have implemented different wrong-way driving (WWD) detection systems based on loop detectors, radar detectors, or thermal cameras. Such systems are often deployed at fixed locations in urban areas or on toll roads. The majority of rural interchange terminals does not have real-time detection systems for WWD incidents. Portable traffic cameras are used to temporarily monitor WWD activities at rural interchange terminals. However, it has always been a time-consuming task to manually review those videos to identify WWD incidents. The objective of this study was to develop an unsupervised trajectory-based method to automatically detect WWD incidents from regular traffic videos (not limited by mounting height and angle). The principle of the method includes three primary steps: vehicle recognition and trajectory generation, trajectory clustering, and outlier detection. This study also developed a new subtrajectory-based metric that makes the algorithm more adaptable for vehicle trajectory classification in different road scenarios. Finally, the algorithm was tested by analyzing 357 h of traffic videos from 14 partial cloverleaf interchange terminals in seven U.S. states. The results suggested that the method could identify all the WWD incidents in the testing videos with an average precision of 80%. The method significantly reduced person-hours for reviewing the traffic videos. Furthermore, the new method could also be applied in detecting and extracting other kinds of abnormal traffic activities, such as illegal U-turns.

Fitting Volume Delay Functions under interrupted and uninterrupted flow conditions at Greek urban roads

This paper presents the calibration of the most commonly used Volume Delay Functions (VDF): BPR, Conical, Akcelik and Modified Davidson, for an urban area populated by over 1 million inhabitants, the city of Thessaloniki in Greece. The estimation of the unknown coefficients was carried out for a typical freeway, the ring road of the city, and selected arterial and collected roads of the city center, through recent data of hourly observed vehicle speeds and volumes obtained from video recordings and loop detectors. The BPR function yielded the highest accuracy across all the examined road sections and was characterized as the most suitable to simulate and interpret the existing traffic conditions. The estimated coefficients differed significantly from the values proposed in the pertinent literature, which highlights the importance of using locally derived data for the calibration of the VDFs.

Overcoming Challenges of Distributed Fiber-Optic Sensing for Highway Traffic Monitoring

This work presents a wide-area highway monitoring system based on distributed fiber-optic sensing (DFOS) as a cost-effective way of gathering traffic information at numerous sensing points along a fiber cable. The primary advantage of our proposed DFOS system is that it utilizes an existing fiber cable buried beneath the highway to detect and localize the vibrations of passing vehicles. Each section along the fiber cable acts as a sensing point and registers the vibration of nearby vehicles. The amplitude and location of vibrations as measured by DFOS can supplement the information obtained from existing point sensor systems (traffic camera, inductive loop detector) which are typically installed hundreds of meters apart. We trained a neural network for speed estimation ( SpeedNet) and also proposed novel solutions to some of the challenges posed when using DFOS to monitor traffic. To demonstrate the potential of DFOS, we conducted a field test for two days on a 45-km section of the Tomei expressway in Japan. Our proposed SpeedNet model estimated average traffic speeds every minute for an overall accuracy of over 90% as compared with existing loop detector-based sensors. As cameras suffer from weather and intensity changes, and loop detectors can be difficult to install at multiple locations, monitoring traffic using DFOS over an existing fiber-optic cable shows tremendous potential.

Extracting Densely Covered Areas Within Floating Car Datasets Using Inductive Loop Detector Data

We present an approach to use static traffic count data to find relatively representative areas within Floating Car Data (FCD) datasets. We perform a case study within the state of Nordrhein-Westfalen, Germany using enviroCar FCD and traffic count data obtained from Inductive Loop Detectors (ILD). Findings indicate that our approach combining FCD and traffic count data is capable of assessing suitable subsets within FCD datasets that contain a relatively high ratio of FCD records and ILD readings. We face challenges concerning the correct choice of traffic count data, counting individual FCD trajectories and defining a threshold by which an area can be considered as representative.

Probability of Secondary Crash Occurrence on Freeways with the Use of Private-Sector Speed Data

A percentage of crashes on freeways are suspected to be caused in part by the congestion or distraction from earlier incidents. Identifying and preventing these secondary crashes are major goals of transportation agencies, yet the characteristics of secondary crashes—in particular the probability of their occurrence—are poorly understood. Many secondary crashes occur when a vehicle encounters non-recurring congestion, yet previous efforts to identify incident queues and their secondary crashes have relied either on deterministic queuing theory, or on data from uniformly-spaced, dense loop detectors. This study is the first analysis of secondary crash occurrence integrating incident timelines and traffic volumes with widely-available (and legally obtained) private sector speed data. Analysis found that 9.2% of all vehicle crashes were secondary to another incident, and that 6.2% of these crashes were tertiary to another primary incident. Secondary crashes occurred on average once every 10 crashes and 54 disabled vehicles. The findings support a fast incident response, as the probability of secondary crash occurrence increases approximately one percentage point for every additional 2–3 minutes spent on-scene in high volume scenarios.

Real-Time Incident Detection and Capacity Estimation Using Loop Detector Data

Given the fact that the existing literature lacks the real-time estimation of road capacity and incident location using data from inductance loop detectors, a data-driven framework is proposed in this study for real-time incident detection, as well as road capacity and incident location estimation. The proposed algorithm for incident detection is developed based on the variation in traffic flow parameters acquired from inductance loop detectors. Threshold values of speed and occupancy are determined for incident detection based on the PeMS database. The detection of the incident is followed by the real-time road capacity and incident location estimation using a Cell Transmission Model (CTM) based approach. The data of several incidents were downloaded from PeMS and used for the development of the proposed framework presented in this study. Results show that the developed framework detects the incident and estimates the reduced capacity accurately. The location of the incident is estimated with an overall accuracy of 92.5%. The performance of the proposed framework can be further improved by incorporating the effect of the on-ramps, off-ramps, and high-occupancy lanes, as well as by modeling each lane separately.