Automated Turning Movement Counts for Shared Lanes: Leveraging Vehicle Detection Data

Santiago-Chaparro, Kelvin R.; Chitturi, Madhav; Bill, Andrea R.; Noyce, David A.

doi:10.3141/2558-04

Cited by 8 publications

(5 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By this point, the dataset still contains some noise. Trajectory data were then cleaned and filtered using a previously-developed procedure ( 26 ).…”

Section: Methodsmentioning

confidence: 99%

“…Figure 1 shows a visualization of the northbound right turn and the eastbound through movement of the intersection; the two key approaches for the data analysis are presented below. Vehicle trajectory data were collected using a previously documented automated data collection procedure ( 26 ). The ground truth video recordings were obtained from a security camera installed by the intersection.…”

Section: Data Collection and Descriptionmentioning

confidence: 99%

See 1 more Smart Citation

Framework for Quantifying Right-Turn-on-Red Conflicts From Existing Radar-Based Vehicle Detection Infrastructure

Nassereddine

Santiago-Chaparro

Noyce

2022

Transportation Research Record: Journal of the Transportation R

Self Cite

View full text Add to dashboard Cite

Surrogate safety measures (SSMs) have been used as an alternative to crash-based methods to study road safety. This study proposes a framework to estimate SSMs, such as post encroachment time (PET) and time to collision (TTC) values between right-turn-on-red (RTOR) and through vehicles, and demonstrates the feasibility of using vehicle trajectories obtained from existing radar-based vehicle detection systems to calculate such measures. The framework was implemented by the research team using a software-based approach. The framework presented consists of three stages: first, noise removal and classification of vehicles per lane; second, pairing RTOR vehicles and conflicting-through vehicles; and third calculation of PET and TTC values for each interaction using the radar-based vehicle trajectory dataset. Using video recordings, the interactions between right-turning vehicles and conflicting-through vehicles were documented and key vehicle position timestamps were logged. Logged timestamps enabled the calculation of PET. Video recordings acted as a tool to verify the results of PET calculations based on radar-based vehicle trajectory data. Therefore, the validity of the automated calculation of PET based on radar-based vehicle trajectory data was confirmed using the video recordings from the data collection site. The proposed framework demonstrates the potential to expand the capabilities of existing vehicle detection infrastructure to support proactive safety evaluations at a system level and increase the return on investment on existing vehicle detection technology. The proposed framework can be used in the development of safety models using existing vehicle detection infrastructure based on radar technology without the need for image processing techniques or specialized hardware.

show abstract

“…By this point, the dataset still contains some noise. Trajectory data were then cleaned and filtered using a previously-developed procedure ( 26 ).…”

Section: Methodsmentioning

confidence: 99%

Section: Data Collection and Descriptionmentioning

confidence: 99%

Framework for Quantifying Right-Turn-on-Red Conflicts From Existing Radar-Based Vehicle Detection Infrastructure

Nassereddine

Santiago-Chaparro

Noyce

2022

Transportation Research Record: Journal of the Transportation R

Self Cite

View full text Add to dashboard Cite

show abstract

“…Moreover, the inclusion of such additional information adversely affects the performance of the clustering algorithms and makes the clustering stage more time consuming and cumbersome. To avoid these complications, the concept of the stopbar, which was introduced by Santiago-Chaparro et al [39] for radar-based vehicle trajectory analysis, has been adapted and applied in this study for vision-based stopbar identification.…”

Section: Stopbar Identificationmentioning

confidence: 99%

Automated Approach for Computer Vision-Based Vehicle Movement Classification at Traffic Intersections

Jana

Karmakar

Chakraborty

et al. 2023

Future Transportation

View full text Add to dashboard Cite

Movement-specific vehicle classification and counting at traffic intersections is a crucial component of various traffic management activities. In this context, with recent advancements in computer-vision-based techniques, cameras have emerged as a reliable data source for extracting vehicular trajectories from traffic scenes. However, classifying these trajectories by movement type is quite challenging, as characteristics of motion trajectories obtained this way vary depending on camera calibrations. Although some existing methods have addressed such classification tasks with decent accuracies, the performance of these methods significantly relied on the manual specification of several regions of interest. In this study, we proposed an automated classification method for movement-specific classification (such as right-turn, left-turn and through movements) of vision-based vehicle trajectories. Our classification framework identifies different movement patterns observed in a traffic scene using an unsupervised hierarchical clustering technique. Thereafter, a similarity-based assignment strategy is adopted to assign incoming vehicle trajectories to identified movement groups. A new similarity measure was designed to overcome the inherent shortcomings of vision-based trajectories. Experimental results demonstrated the effectiveness of the proposed classification approach and its ability to adapt to different traffic scenarios without any manual intervention.

show abstract

“…However, their method was based on one signalized intersection simulated in software without calibration. In a similar fashion, using vehicle trajectory data from a radar sensor, Santiago-Chaparro et al ( 14 ) developed a classification algorithm to predict intersection turning count for shared lanes. They claimed that their algorithm is capable of producing turning movement counts regardless of lane geometry and detection zone delineation at typical intersections but requires adjustment for large and unusual intersections.…”

Section: Existing Literaturementioning

confidence: 99%

Machine Learning Based Automated Left-Turn Vehicle Counts With Conventional Presence Mode Long-Loop Detectors: Alabama Case Studies

Biswas

Kang

Rahman

2022

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

Inductive-loop detectors are still used in many intersections because highway agencies have insufficient budget to replace them with new technologies or when accurate traffic monitoring is not necessary. Particularly, long-loop stop-bar detectors have been widely used for left-turning vehicles and are operated under “Presence” mode, which focuses only on detecting the presence of vehicles for signal operations, not for counting vehicles. As a result, a significant discrepancy exists between the number of vehicle detections and the actual vehicle observations. The present study developed machine learning (ML)-based methods to overcome this discrepancy so that conventional long-loop detectors can also be used for estimating hourly left-turn volume. Several ML classifiers were adopted to predict the difference (i.e., detection versus observation) for every vehicle detection event. Three predictors (detector occupancy time, left-turn phases when the detector is on and off) from high-resolution data were used as input of the ML models. Results showed that all the models are statistically significant with p-value <0.05. The developed models were then applied to estimate hourly left-turn volume, by adding its prediction result to left-turn detection counts by the detector. The hourly left-turn volume estimated with the proposed method accounts for 96% of the actual left turns for low left-turn traffic conditions, and 93% for heavy left-turn traffic conditions. This indicates that the proposed method can provide a good estimation of hourly left-turn volume for signalized intersections operated with long-loop detectors. The method is simple and based on data from existing vehicle detection technologies already in typical signalized intersections.

show abstract

Automated Turning Movement Counts for Shared Lanes: Leveraging Vehicle Detection Data

Cited by 8 publications

References 5 publications

Framework for Quantifying Right-Turn-on-Red Conflicts From Existing Radar-Based Vehicle Detection Infrastructure

Framework for Quantifying Right-Turn-on-Red Conflicts From Existing Radar-Based Vehicle Detection Infrastructure

Automated Approach for Computer Vision-Based Vehicle Movement Classification at Traffic Intersections

Machine Learning Based Automated Left-Turn Vehicle Counts With Conventional Presence Mode Long-Loop Detectors: Alabama Case Studies

Contact Info

Product

Resources

About