Use of High-Resolution Signal Controller Data to Identify Red Light Running

Lavrenz, Steven; Day, Christopher M.; Grossman, Jay; Freije, Richard; Bullock, Darcy M.

doi:10.3141/2558-05

Cited by 11 publications

(4 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Overall, the amount of yellow time with a vehicle at the stop bar decreased at least 40% after the adjustment, from at least 337 seconds of yellow time in the before period to 203 seconds at most in the after period. The number of red light infractions are shown in Figure 11b for each of the 5 days studied (13). Overall, the number of red light infractions decreased 66% after the adjustment, from 5 per day in the before period to 1.6 per day in the after period.…”

Section: Evaluation Of Adjustmentsmentioning

confidence: 95%

Scalable Dashboard for Identifying Split Failures and Heuristic for Reallocating Split Times

Richardson

Day

et al. 2017

Transportation Research Record: Journal of the Transportation R

Self Cite

View full text Add to dashboard Cite

The three fundamental parameters of a traffic signal system are split, cycle, and offset. This paper describes the use of high-resolution data ( a) to identify time periods during which split parameters may be insufficient and ( b) to help practitioners identify opportunities for reallocating split time. A case study of seven corridors with 47 intersections is presented. A drill-down approach was developed to identify movements that could be improved by a reallocation of split times. A heuristic that can reallocate up to 5 seconds of underutilized green time on a competing phase was applied to those corridors. For the selected phase identified in this study, the adjustment reduced split failures by an average of 40% while also decreasing yellow occupancy an average of 40% and red light violations an average of 66%. The paper concludes by recommending that central systems implement drill-down dashboards. Such tools would enable easy identification and systemwide monitoring of split failures and would provide opportunities to reallocate slack time.

show abstract

Section: Evaluation Of Adjustmentsmentioning

confidence: 95%

Scalable Dashboard for Identifying Split Failures and Heuristic for Reallocating Split Times

Richardson

Day

et al. 2017

Transportation Research Record: Journal of the Transportation R

Self Cite

View full text Add to dashboard Cite

show abstract

“…Figure 3 also helps to understand the three variables. The figure shows a conceptual illustration of “detector on and off” events along with detector occupancy time and the respective signal phase information when vehicles arrive and leave the detection zone ( 23 ). Note that, depending on the variation in the detector occupancy time and signal phase information, one detection could account for the presence of one vehicle.…”

Section: Methodsmentioning

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

“…Many camera-based red light running detection systems are controversial, and there is relatively little published literature on the used methodologies. The recent study [25] proposes a system that combines high-resolution signal controller data with conventional stop bar loop detection to identify vehicles that enter the intersection after the start of red, when many of the most serious red light running crashes occur. The paper [35] presents a software-based methodology that monitors the underlying dataset of existing radar-based vehicle detection infrastructure to continuously monitor red light running incidents.…”

Section: Related Workmentioning

confidence: 99%