Naturalistic driving study of rear seat child occupants: Quantification of head position using a Kinect™ sensor

OBJECTIVE

Restraint performance is evaluated using anthropomorphic test devices (ATDs) positioned in prescribed, optimal seating positions. Anecdotally, humans-children in particular-assume a variety of positions that may affect restraint performance. Naturalistic driving studies (NDSs), where cameras and other data acquisition systems are placed in a vehicle used by participants during their regular transportation, offer means to collect these data. To date, these studies have used conventional video and analysis methods and, thus, analyses have largely been qualitative. This article describes a recently completed NDS of child occupants in which their position was monitored using a Kinect sensor to quantify their head position throughout normal, everyday driving trips.

METHODS

A study vehicle was instrumented with a data acquisition system to measure vehicle dynamics, a set of video cameras, and a Kinect sensor providing 3D motion capture at 1 Hz of the rear seat occupants. Participant families used the vehicle for all driving trips over 2 weeks. The child occupants' head position was manually identified via custom software from each Kinect color image. The 3D head position was then extracted and its distribution summarized by seat position (left, rear, center) and restraint type (forward-facing child restraint system [FFCRS], booster seat, seat belt).

RESULTS

Data from 18 families (37 child occupants) resulted in 582 trips (with children) for analysis. The average age of the child occupants was 45.6 months and 51% were male. Twenty-five child occupants were restrained in FFCRS, 9 in booster seats, and 3 in seat belts. As restraint type moved from more to less restraint (FFCRS to booster seat to seat belt), the range of fore-aft head position increased: 218, 244, and 340 mm on average, respectively. This observation was also true for left-right movement for every seat position. In general, those in the center seat position demonstrated a smaller range of head positions.

CONCLUSIONS

For the first time in a naturalistic setting, the range of head positions for child occupants was quantified. More variability was observed for those restrained in booster seats and seat belts than for those in FFCRS. The role of activities, in particular interactions with electronic devices, on head position was notable; this will be the subject of further analysis in other components of the broader study. These data can lead to solutions for optimal protection for occupants who assume positions that differ from prescribed, optimal testing positions.

Modeling Driving Performance Using In-Vehicle Speech Data From a Naturalistic Driving Study

OBJECTIVE

We aimed to (a) describe the development and application of an automated approach for processing in-vehicle speech data from a naturalistic driving study (NDS), (b) examine the influence of child passenger presence on driving performance, and (c) model this relationship using in-vehicle speech data.

BACKGROUND

Parent drivers frequently engage in child-related secondary behaviors, but the impact on driving performance is unknown. Applying automated speech-processing techniques to NDS audio data would facilitate the analysis of in-vehicle driver-child interactions and their influence on driving performance.

METHOD

Speech activity detection and speaker diarization algorithms were applied to audio data from a Melbourne-based NDS involving 42 families. Multilevel models were developed to evaluate the effect of speech activity and the presence of child passengers on driving performance.

RESULTS

Speech activity was significantly associated with velocity and steering angle variability. Child passenger presence alone was not associated with changes in driving performance. However, speech activity in the presence of two child passengers was associated with the most variability in driving performance.

CONCLUSION

The effects of in-vehicle speech on driving performance in the presence of child passengers appear to be heterogeneous, and multiple factors may need to be considered in evaluating their impact. This goal can potentially be achieved within large-scale NDS through the automated processing of observational data, including speech.

APPLICATION

Speech-processing algorithms enable new perspectives on driving performance to be gained from existing NDS data, and variables that were once labor-intensive to process can be readily utilized in future research.

Viscoelastic shear properties of porcine temporomandibular joint disc

OBJECTIVES

To investigate the intrinsic viscoelastic shear properties in porcine TMJ discs.

MATERIALS AND METHODS

Twelve fresh porcine TMJ discs from young adult pigs (6-8 months) were used. Cylindrical samples (5 mm diameter) with uniform thickness (~1.2 mm) were prepared from five regions of the TMJ disc. Torsional shear tests were performed under 10% compressive strain. Dynamic shear was applied in two methods: 1) a frequency sweep test over the frequency range of 0.1-10 rad/s with a constant shear strain amplitude of 0.05 rad and 2) a strain sweep test over the range of 0.005-0.15 rad at a constant frequency of 10 rad/s. Transient stress relaxation tests were also performed to determine the equilibrium shear properties.

RESULTS

As the frequency increased in the frequency sweep test, the dynamic shear complex modulus increased, with values ranging from 7 to 17 kPa. The phase angle, ranging from 11 to 15 degrees, displayed no pattern of regional variation as the frequency increased. The dynamic shear modulus decreased as the shear strain increased. The equilibrium shear modulus had values ranging from 2.6 to 4 kPa. The posterior region had significantly higher values for dynamic shear modulus than those in the anterior region, while no significant regional difference was found for equilibrium shear modulus.

CONCLUSION

Our results suggest that the intrinsic region-dependent viscoelastic shear characteristics of TMJ disc may play a crucial role in determining the local strain of the TMJ disc under mechanical loading.

Evaluation of a video-based measure of driver heart rate

INTRODUCTION

Internal driver events such as emotional arousal do not consistently elicit observable behaviors. However, heart rate (HR) offers promise as a surrogate measure for predicting these states in drivers. Imaging photoplethysmography (IPPG) can measure HR from face video recorded in static, indoor settings, but has yet to be examined in an in-vehicle driving environment.

METHODS

Participants (N=10) completed an on-road driving task whilst wearing a commercial, chest-strap style heart rate monitor ("baseline"). IPPG was applied to driver face video to estimate HR and the two measures of HR were compared.

RESULTS

For 4 of 10 participants, IPPG produced a valid HR signal (±5 BPM of baseline) between 48 and 75% of trip duration. For the remaining participants, IPPG accuracy was poor (<20%).

CONCLUSIONS

In-vehicle IPPG is achievable, but significant challenges remain.

PRACTICAL APPLICATIONS

The relationship between IPPG accuracy and various confounding factors was quantified for future refinement.

Examining physiological responses across different driving maneuvers during an on-road driving task: a pilot study comparing older and younger drivers

OBJECTIVE

This pilot study aimed to investigate physiological responses during an on-road driving task for older and younger drivers.

METHODS

Five older drivers (mean age = 74.60 years [2.97]) and 5 younger drivers (mean age = 30.00 years [3.08]) completed a series of cognitive assessments (Montreal Cognitive Assessment [MoCA], Mini Mental Status Examination [MMSE]; Trail Making Test [Trails A and Trails B]) and an on-road driving task along a predetermined, standardized urban route in their own vehicle. Driving performance was observed and scored by a single trained observer using a standardized procedure, where driving behaviors (appropriate and inappropriate) were scored for intersection negotiation, lane changing, and merging. During the on-road driving task, participants' heart rate (HR) was monitored with an unobtrusive physiological monitor.

RESULTS

Younger drivers performed significantly better on all cognitive assessments compared to older drivers (MoCA: t(8) = 3.882, P <.01; MMSE: t(8) = 2.954, P <.05; Trails A: t(8) = -2.499, P <.05; Trails B: t(8) = -3.262, P <.05). Analyses of participants' performance during the on-road driving task revealed a high level of appropriate overall driving behavior (M = 87%, SD = 7.62, range = 73-95%), including intersection negotiation (M = 89%, SD = 8.37%), lane changing (M = 100%), and merging (M = 53%, SD = 28.28%). The overall proportion of appropriate driving behavior did not significantly differ across age groups (younger drivers: M = 87.6%, SD = 9.04; older drivers: M = 87.0%, SD = 6.96; t(8) = 0.118, P =.91).

CONCLUSIONS

Although older drivers scored lower than younger drivers on the cognitive assessments, there was no indication of cognitive overload among older drivers based on HR response to the on-road driving task. The results provide preliminary evidence that mild age-related cognitive impairment may not pose a motor vehicle crash hazard for the wider older driver population. To maintain safe mobility of the aging population, further research into the specific crash risk factors in the older driver population is warranted.

Computer vision and driver distraction: developing a behaviour-flagging protocol for naturalistic driving data

Naturalistic driving studies (NDS) allow researchers to discreetly observe everyday, real-world driving to better understand the risk factors that contribute to hazardous situations. In particular, NDS designs provide high ecological validity in the study of driver distraction. With increasing dataset sizes, current best practice of manually reviewing videos to classify the occurrence of driving behaviours, including those that are indicative of distraction, is becoming increasingly impractical. Current statistical solutions underutilise available data and create further epistemic problems. Similarly, technical solutions such as eye-tracking often require dedicated hardware that is not readily accessible or feasible to use. A computer vision solution based on open-source software was developed and tested to improve the accuracy and speed of processing NDS video data for the purpose of quantifying the occurrence of driver distraction. Using classifier cascades, manually-reviewed video data from a previously published NDS was reanalysed and used as a benchmark of current best practice for performance comparison. Two software coding systems were developed - one based on hierarchical clustering (HC), and one based on gender differences (MF). Compared to manual video coding, HC achieved 86 percent concordance, 55 percent reduction in processing time, and classified an additional 69 percent of target behaviour not previously identified through manual review. MF achieved 67 percent concordance, a 75 percent reduction in processing time, and classified an additional 35 percent of target behaviour not identified through manual review. The findings highlight the improvements in processing speed and correctly classifying target behaviours achievable through the use of custom developed computer vision solutions. Suggestions for improved system performance and wider implementation are discussed.

SU-E-J-108: Quantitative Analysis of Longitudinal Cognitive Impairment Due to Radiation Therapy Based on Automatic Segmentation of Hippocampus and Subcortical Structure

PURPOSE

In this study, we developed a quantitative analysis tool based on patient's longitudinal MR images to 1) measure the radiation dose received by each subcortical structure, 2) follow the change of volume and shape of each structure longitudinally. This tool provides a systematic approach to study the radiation therapy (and subsequent chemotherapy) associated with cognitive impairments.

METHODS

MRI scans of one patient taken before and after radiation therapy are demonstrated in this study. 3D Conformal radiation therapy was performed on RapidArc™. An open source MRI analysis tool, FMRIB's Integrated Registration and Segmentation Tool (FIRST), was used for segmentation. The images are registered to a standard template with expert-defined labeling for all sub-cortical structures, and the labeling of each structure is mapped back to the individual MRI space for segmentation. After the segmentation, the radiation dose map was coregistered to the MRI space to calculate the dose received by each structure.

RESULTS

For the structure that is contained within the radiation zone, we can calculate the total dose based on the volumetric distribution of radiation dose. For the structure that is outside the radiation field, we can calculate the distance from the radiation zone. We have demonstrated in this work that the analysis can be done for all segmented sub-cortical structures. The change of volume before and after radiation treatment can be analyzed, and the results can be correlated with the change of cognitive performance over time.

CONCLUSIONS

We presented an automated tool for efficient, quantitative and user-independent measurements of radiation dose in subcortical structures. The obtained results can be correlated with the cognitive test score and the clinical outcome to evaluate radiation and the subsequent chemotherapy induced changes in brain structures and functions.