Visual attention measures predict pedestrian detection in central field loss: a pilot study

Abstract

Purpose: The ability of visually impaired people to deploy attention effectively to maximize use of their residual vision in dynamic situations is fundamental to safe mobility. We conducted a pilot study to evaluate whether tests of dynamic attention (multiple object tracking; MOT) and static attention (Useful Field of View; UFOV) were predictive of the ability of people with central field loss (CFL) to detect pedestrian hazards in simulated driving.

Methods: 11 people with bilateral CFL (visual acuity 20/30-20/200) and 11 age-similar normally-sighted drivers participated. Dynamic and static attention were evaluated with brief, computer-based MOT and UFOV tasks, respectively. Dependent variables were the log speed threshold for 60% correct identification of targets (MOT) and the increase in the presentation duration for 75% correct identification of a central target when a concurrent peripheral task was added (UFOV divided and selective attention subtests). Participants drove in a simulator and pressed the horn whenever they detected pedestrians that walked or ran toward the road. The dependent variable was the proportion of timely reactions (could have stopped in time to avoid a collision).

Results: UFOV and MOT performance of CFL participants was poorer than that of controls, and the proportion of timely reactions was also lower (worse) (84% and 97%, respectively; p = 0.001). For CFL participants, higher proportions of timely reactions correlated significantly with higher (better) MOT speed thresholds (r = 0.73, p = 0.01), with better performance on the UFOV divided and selective attention subtests (r = -0.66 and -0.62, respectively, p<0.04), with better contrast sensitivity scores (r = 0.54, p = 0.08) and smaller scotomas (r = -0.60, p = 0.05).

Conclusions: Our results suggest that brief laboratory-based tests of visual attention may provide useful measures of functional visual ability of individuals with CFL relevant to more complex mobility tasks.

Figure 1. The car and truck targets from the UFOV central identification task.

The targets differed only in whether two thin lines were present in the top left area of each outline, making this task difficult for participants with CFL.

Figure 2. Relationship between proportion of timely reactions and attention measures for CFL participants.

(a) UFOV divided attention threshold duration, (b) UFOV selective attention threshold duration, (c) UFOV divided attention difference score, (d) UFOV selective attention difference score, and (e) the MOT task. Better performance on the pedestrian detection task was associated with better performance on each of the attention tests. UFOV scores are plotted on reversed axes so that better performance is at the right hand side of the x-axis for all figures. Thick black line shows the linear trend.