Agency: Department of Transportation | Branch: | Program: SBIR | Phase: Phase I | Award Amount: 149.97K | Year: 2015
The rapid development of automated vehicles has attracted a lot of attentions from the public in recent years. Current studies on automated vehicles mainly focus on microscopic simulations with simple network topologies and driver behaviors, and few has considered to incorporate automated vehicles into macroscopic travel demand models for the analysis in a regional network. In this project, we propose a multiple-resolution approach that allows us to model the impacts of automated vehicles for both transportation and traffic operation analysis. The approach hinges on the development of a capacity adjustment factor (CAF) for automated vehicles, similar to the heavy vehicles adjustment factor used in highway capacity analysis. CAF will be linked to input variables such as roadway facility types, traffic demand levels, and market penetration rates of automated vehicles. CAF will be derived from a microsimulation study, which involves the development of an integrated car-following model for both human drivers and automated vehicles, calibration of the model using NGSIM data, implementation of the model as a plugin in microsimulation. The proposed modeling approach can then be used to analyze the impact of automated vehicles in a regional network through additional traffic assignment runs using the adjusted capacity based on CAF.
Agency: Department of Transportation | Branch: | Program: SBIR | Phase: Phase I | Award Amount: 125.00K | Year: 2014
Continued population growth and expanded commercial development have already push the daily traffic on National Park Service(NPS) Parkways exceeds design capacity especially around the urban area. The Parkways around urban areas usually serve as commuting routes for commuters and as scenic routes for visitors. Heavy traffic in rush hours, high travel speeds during non-peak periods, and condition of the road surface in bad weather have made the Parkways more vulnerable to traffic accidents. It is important to collect and utilize the traffic data to fulfill the needs of improving safety and mobility of the Parkways. Therefore, we propose to develop a visually unobtrusive and self-powered traffic monitoring system, NPS Traffic Monitor HD, for vehicle detection and tracking with heterogeneous detection technologies for the NPS Parkways, while ensuring the long-term preservation of the Parkways' scenic values, recreational opportunities, and rich natural and cultural resources. The proposed system will be able to utilize data collected from inductive loop signature detectors and from at least one alternative detection technology to generate traffic performance measures. We will demonstrate the proof of concept of the proposed system and also identify its potential applications using the George Washington Memorial Parkway (GWMP) facility.
Agency: Department of Transportation | Branch: | Program: SBIR | Phase: Phase I | Award Amount: 99.97K | Year: 2011
We propose a Smartphone based system that can integrate information commonly available on a mobile phone and real time traffic signal phasing data to provide assistance to pedestrians and cyclists for safer intersection crossing. GPS accelerometer and digital compass information from a smart phone together with digital maps will be integrated to determine the location and orientation of a user. Real time traffic signal phasing data can be obtained through wireless communication with either a local signal controller or a central traffic management system. The information together can then inform pedestrians and cyclists particularly those with vision or hearing or walking impairment as to when to cross through audible or haptic feedback.An automated ‘pedestrian call’ request can also be sent to the traffic controller wirelessly from the smart phone of registered users after confirming the direction and orientation that the pedestrian is intending to cross. The proposed system will eliminate the need of physically locating and pressing a pushbutton at the intersection crossing and provide supportive information to the pedestrians and cyclists while traveling along the crosswalk.
Jeng S.-T.,CLR Analytics Inc. |
Chu L.,CLR Analytics Inc. |
Chu L.,University of California at Irvine
IEEE Transactions on Intelligent Transportation Systems | Year: 2015
Weigh-in-motion (WIM) has been employed as a major technology to collect heavy vehicles' data on the freeways. Because WIM is one of the most costly and sophisticated data collection systems, how to effectively utilize the valuable WIM data and monitor the performance of WIM stations are particularly important. In this paper, we proposed an innovative and yet practical approach for heavy vehicle tracking that combines the use of both WIM data and the inductive loop signature data. The proposed multilevel vehicle reidentification approach was able to generate promising tracking performance with both inductive loop signatures and WIM data applied. © 2000-2011 IEEE. Source
Jeng S.-T.,CLR Analytics Inc. |
Chu L.,CLR Analytics Inc. |
Hernandez S.,University of California at Irvine
Transportation Research Record | Year: 2013
In this study, a new vehicle classification algorithm was developed with inductive loop signature technology. There were two steps to the proposed algorithm. The first step was to use the Haar wavelet to transform and reconstruct inductive vehicle signatures, and the second step was to group vehicles into FHWA vehicle types through the use of the k nearest neighbor (KNN) approach with a Euclidean distance classifier. To determine the proper proportion of the wavelet to apply for reconstruction and feature extraction, transformed signatures were examined with percentages of large components of their corresponding wavelets. To implement the KNN approach, a library of vehicle signature templates for each FHWA vehicle class was composed. The proposed vehicle classification algorithm demonstrated promising classification results, with a 92.4% overall accuracy. The algorithm can be applied to the real world without the concerns about recalibration and transferability that arise with the use of signature data from single loops. Two additional vehicle classification schemes were applied for performance evaluation. For the inductive signature performance evaluation classification scheme, which aimed to facilitate emission analysis and easy interpretation, the overall accuracy was 94.1%. For the axle-based vehicle classification scheme proposed in this project, which aimed to group vehicles by use and the number of axles, the overall accuracy was 93.8%. Future research will focus on refinement of the signature template library for each FHWA vehicle type to further improve the performance of the proposed vehicle classification algorithm. The selection of the value of k for the KNN approach will be investigated also. Source