Detection of Lane-Change Events in Naturalistic Driving Videos

Global lessons learned from naturalistic driving studies to advance traffic safety and operation research: A systematic review

The state of practice of investigating traffic safety and operation is primarily based on traditional data sources, such as spot sensors, loop detectors, and historical crash data. Recently, researchers have utilized transportation data from instrumented vehicles, driving simulators, and microsimulation modeling. However, these data sources might not represent the actual driving environment at a trajectory level and might introduce bias due to their experimental control. The shortcomings of these data sources can be overcome via Naturalistic Driving Studies (NDSs) considering the fact that NDS provides detailed real-time driving data that would help investigate the safety and operational impacts of human behavior along with other factors related to weather, traffic, and roadway geometry in a naturalistic setting. With the enormous potential of the NDS data, this study leveraged the Preferred Reporting Items for Systematic Reviews and Meta-Analyzes (PRISMA) approach to shortlist the most relevant naturalistic studies out of 2304 initial studies around the world with a focus on traffic safety and operation over the past fifteen years (2005-2020). A total of 117 studies were systematically reviewed, which were grouped into seven relevant topics, including driver behavior and performance, crash/near-crash causation, driver distraction, pedestrian/bicycle safety, intersection/traffic signal related studies, detection and prediction using NDSs data, based on their frequency of appearance in the keywords of these studies. The proper deployment of Connected and Autonomous Vehicles (CAV) require an appropriate level of human behavior integration, especially at the intimal stages where both CAV and human-driven vehicles will interact and share the same roadways in a mixed traffic environment. In order to integrate the heterogeneous nature of human behavior through behavior cloning approach, real-time trajectory-level NDS data is essential. The insights from this study revealed that NDSs could be effectively leveraged to perfect the behavior cloning to facilitate rapid and safe implementation of CAV.

A Novel Intelligent Approach to Lane-Change Behavior Prediction for Intelligent and Connected Vehicles

The prediction of lane-change behavior is a challenging issue in intelligent and connected vehicles (ICVs), which can help vehicles predict in advance and change lanes safely. In this paper, a novel intelligent approach, which considering both the driving style-based lane-change environment and the driving trajectory-related parameters of the ICV and surrounding vehicles, is proposed to predict the lane-change behaviors for ICVs. By analyzing the characteristics of the lane-change behavior of the vehicle, a modified dataset for the prediction of lane-change behavior was established based on the Next-Generation Simulation (NGSIM) dataset, which is made up of real vehicle trajectories collected by camera. In the proposed approach, the hidden Markov model (HMM)-based model is designed to judge whether the current environment is suitable for lane change according to the driving environment parameters around the vehicle; then according to the driving state of the vehicle, a learning-based prediction-then-judgment model is proposed and designed to realize the prediction of the ICV's lane-change behavior. Experiments are implemented by using the modified dataset. From the experimental results, the lane-change probability value on the target lane in the truth of the lane-change behavior calculated by the designed HMM-based model is basically above 0.5, indicating that the model can make a more accurate judgment on the surrounding lane-change environment. The proposed learning-based prediction-then-judgment model has an accuracy of 99.32% for the prediction of lane-change behavior, and the accuracy of the lane-change detection algorithm in the model is 99.56%. The experimental results show that the proposed approach has a good performance in the prediction of lane-change behavior, which could effectively assist ICVs to change lanes safely.

Detecting and Tracking Unsafe Lane Departure Events for Predicting Driver Safety in Challenging Naturalistic Driving Data

Our goal is to improve driver safety predictions in at-risk medical or aging populations from naturalistic driving video data. To meet this goal, we developed a novel model capable of detecting and tracking unsafe lane departure events (e.g., changes and incursions), which may occur more frequently in at-risk driver populations. The model detects and tracks roadway lane markings in challenging, low-resolution driving videos using a semantic lane detection pre-processor (Mask R-CNN) utilizing the driver's forward lane region, demarking the convex hull that represents the driver's lane. The hull centroid is tracked over time, improving lane tracking over approaches which detect lane markers from single video frames. The lane time series was denoised using a Fix-lag Kalman filter. Preliminary results show promise for robust lane departure event detection. Overall recall for detecting lane departure events was 81.82%. The F1 score was 75% (precision 69.23%) and 70.59% (precision 62.07%) for left and right lane departures, respectively. Future investigations include exploring (1) horizontal offset as a means to detect lead vehicle proximity, even when image perspectives are known to have a chirp effect and (2) Long Short Term Memory (LSTM) models to detect peaks instead of a peak detection algorithm.

Evaluation of the Driving Safety of Visually Impaired Bioptic Drivers Based on Critical Events in Naturalistic Driving

Purpose

Visually impaired people may be allowed to drive if they wear bioptic telescopes. Bioptic driving safety is debatable, especially given that the telescopes are seldom used by most bioptic drivers. This preliminary study examined bioptic safety based on critical events that occurred in naturalistic daily driving.

Methods

Daily driving activities were recorded using in-car video recorders in 20 bioptic drivers (median age 55, visual acuity, 20/60-160) and 19 control subjects (median age 74) for two to eight weeks. In a secondary analysis, these subjects were compared with 44 cognitively impaired drivers with normal vision (median age 75).

Results

In 292 hours of driving by bioptic drivers and 169 hours by control drivers, seven bioptic drivers and three control drivers had eight and four near-collisions, respectively. Near-collision survival times were not significantly different between the two groups (hazard ratio [HR] = 1.93, P = 0.591) according to Cox hazards regression. Even without compensation for bioptic drivers' longer driving exposure, their odds ratio (OR) was not statistically significant (OR = 2.88, P = 0.18). When including cognitively impaired drivers with normal vision, cognition was a significant predictor of near collisions (HR = 3.86, P = 0.036), but vision loss was not (HR = 0.47, P = 0.317).

Conclusions

This preliminary study failed to find any evidence suggesting that bioptic drivers were more prone to near-collision than healthy drivers. Vision might be a less-significant factor than cognition.

Translational Relevance

Given that bioptic drivers use the telescope for less than 2% of the driving time, this study suggests that driving safety might not be substantially affected even when visual acuity is in the low vision range.

Driving Safety of Cognitively-Impaired Drivers Based on Near Collisions in Naturalistic Driving

Background

Controlled naturalistic driving for examining impacts of cognitive impairment on driving safety is rare.

Objective

Evaluating the safety among drivers with mild cognitive impairment based on near collision incidents using naturalistic driving, and investigating its correlation with cognitive measures.

Methods

Frequency of near collisions of 44 cognitively impaired [Age = 75.1(±6.7), MMSE = 25.5(±2.5)] and 19 control group drivers [Age = 72.5(±7.8), MMSE = 29.3(±0.8)] were obtained from two weeks of recorded driving. Survival time free of predicted collision based on a previously established near-collision to collision estimate ratio of 11 : 1, for 140 hours of driving exposure was calculated. Participants were also tested using Mini-Mental Status Examination (MMSE), Trail A, and Trail B. Spearman correlation and Cox survival analysis were conducted.

Results

Near collision frequency per driving hour was correlated with MMSE (r = -0.258, p = 0.041). Survival analyses showed that cognitively impaired drivers might be prone to higher probability of having collision (p = 0.056) with a hazard ratio of 5.78 (p = 0.092). When all participants were combined, there was a significant difference (p < 0.017) in all the three cognitive measures between drivers with and without predicted collision, which were not significant within patient or control group alone (p > 0.186). Cox regression analysis showed MMSE as the only significant factor (p < 0.025) for survival time of predicted collision, but not age, gender, or driving experience.

Conclusion

The association between driving critical events and cognitive measures suggests that some drivers with mild cognitive impairment might have an elevated driving collision risk compared to control drivers. Standard clinical cognitive measures may be reasonable predictors.