Defining Time-to-Collision Thresholds by the Type of Lead Vehicle in Non-Lane-Based Traffic Environments

Das, Sanhita; Maurya, Akhilesh Kumar

doi:10.1109/tits.2019.2946001

Cited by 49 publications

(17 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[27], [28] developed a framework to comprehensively assess traffic safety from video data by analyzing conflict risk and TTC on hourly basis, and found a significant correlation between the actual number of crashes and the traffic conflicts inferred through their proposed framework. Das and Maurya [29] utilized trajectory data extracted from an urban traffic environment to assess traffic safety based on the interactions of TTC, roadway center line separation, and leader-follower vehicle type pairing. Estimating TTC from video data is an ongoing research problem, recent studies have assessed TTC estimation from on-board [30] and UAV [31] cameras.…”

Section: B Vehicle Detection and Tracking For Traffic Safetymentioning

confidence: 99%

A Real-Time Safety-Based Optimal Velocity Model

Abdelhalim

Abbas

2022

IEEE Open J. Intell. Transp. Syst.

View full text Add to dashboard Cite

Modeling safety-critical driver behavior at signalized intersections needs to account for the driver's planned decision process, where a driver executes a plan to avoid collision in multiple time steps. Such a process can be embedded in the Optimal Velocity Model (OVM) that traditionally assumes that drivers base their "mental intention" on a distance gap only. We propose and evaluate a data-driven OVM based on real-time inference of roadside traffic video data. First, we extract vehicle trajectory data from roadside traffic footage through our advanced video processing algorithm (VT-Lane) for a study site in Blacksburg, VA, USA. Vehicles engaged in car-following episodes are then identified within the extracted vehicle trajectories database, and the real-time time-to-collision (TTC) is calculated for all car-following instances. Then, we analyze the driver behavior to predict the shape of the underlying TTC-based desired velocity function. A clustering approach is used to assess car-following behavior heterogeneity and understand the reasons behind outlying driving behaviors at the intersection to design our model accordingly. The results of this assessment show that the calibrated TTC-based OVM can replicate the observed driving behavior by capturing the acceleration pattern with an error 20% lower than the gap distance-based OVM.

show abstract

Section: B Vehicle Detection and Tracking For Traffic Safetymentioning

confidence: 99%

A Real-Time Safety-Based Optimal Velocity Model

Abdelhalim

Abbas

2022

IEEE Open J. Intell. Transp. Syst.

View full text Add to dashboard Cite

show abstract

“…Automated methods for surrogate safety analysis are experiencing increasing interest in the literature [32][33][34] as they provide insight into the failure mechanisms that can lead to collisions. Surrogate indicators are suitable for evaluating the risk of rear-end collisions as they incorporate both spatial proximity and speed [35]. Researchers argue that surrogate indicators, on one hand, indicate the possible causality of a collision.…”

Section: Surrogate Safety Indicatorsmentioning

confidence: 99%

Analysis of Child Traffic Safety near Primary School Areas Using UAV Technology

et al. 2022

View full text Add to dashboard Cite

Road safety in primary school areas is a delicate issue due to the vulnerability of children as road users. They are inexperienced traffic participants and sometimes their behavior in traffic situations is unpredictable. This paper reports a safety analysis conducted using video processing of conflict trajectories of vehicles and active transportation users (AT users). The videos were collected using unmanned aerial vehicles (UAVs) as this technology does not affect the actual behavior of traffic participants. Due to their airborne position, UAVs can conveniently gather information about driving behaviors and the exact positions of various participants. The safety analysis was conducted using surrogate indicators suitable for evaluating the risk of potential collisions as they incorporate both spatial proximity and speed. Three conflict indicators were used in the safety analysis: (i) time-to-collision, (ii) post-encroachment time, and (iii) heavy braking. The methodology was tested in a primary school area in the city of Zagreb. With the applied methodology, a total of 43 potential conflicts were identified in the school area (14 time-to-collision, 23 post-encroachment time, and 6 heavy braking). Based on the determined potential conflicts, safety measures were proposed to decrease the number and severity of potential conflicts and to increase traffic safety near school areas.

show abstract

“…The threshold of TTC has been studied heavily in literature. Brown et al [27] and Das et al [28] considered that 3 s as the threshold of TTC to warn rear-end collision. Bella et al [29] suggested using 2.5 s or 3 s as the threshold for abnormal car-following.…”

Section: ( ) ( ) Ttc( ) ( ) ( )mentioning

confidence: 99%

A Two-Layer Risky Driver Recognition Model With Context Awareness

Wang¹,

Lü

2021

IEEE Access

View full text Add to dashboard Cite

For autonomous vehicles and intelligent connected vehicles, the real-time recognition of risky drivers can play an important role in traffic accident prevention. However, the external environment substantially impacts driving behavior and driving risk and is usually costly to acquire. Existing risky driver recognition models often ignore external environment information or assume this information is given. We propose two hierarchical two-layer context-aware machine learning structures. The first layer can speculate external context, for example, traffic states. The second layer recognizes risky drivers based on the contextual information speculated from the first layer. The German Highway Drone Dataset is used to establish risky driver recognition and traffic state recognition models. Rear-end collision risk and side collision risk are evaluated for each vehicle. Drivers with high collision risk are labeled as risky drivers. By analyzing vehicle trajectory data from three traffic states: free-flow, saturated, and congested, we find that traffic states have a significant influence on vehicle's longitudinal speed, lateral speed, longitudinal acceleration/deceleration, and collision risk. Six classifiers, including SVM, KNN, RF, Adaboost, Extra trees, and XGBoost, are applied to train recognition models. Results show that the proposed structures can significantly improve model's ability to recognize risky drivers.

show abstract

Defining Time-to-Collision Thresholds by the Type of Lead Vehicle in Non-Lane-Based Traffic Environments

Cited by 49 publications

References 35 publications

A Real-Time Safety-Based Optimal Velocity Model

A Real-Time Safety-Based Optimal Velocity Model

Analysis of Child Traffic Safety near Primary School Areas Using UAV Technology

A Two-Layer Risky Driver Recognition Model With Context Awareness

Contact Info

Product

Resources

About