ADOPT: A system for Alerting Drivers to Occluded Pedestrian Traffic

TL;DR

ADOPT addresses occluded pedestrians by leveraging parked cars as a distributed sensing and alerting fabric. It introduces a low-power, infrastructure-free approach whereby pedestrians wear piezoelectric in-shoe transmitters and parked cars form a chain to detect crossing cohorts, compute remaining time to cross Δ(t) and propagate alerts. The core contributions include a binary sidewalk-vs-street classification using 1/RSS(L) - 1/RSS(R) = const, a tail-based estimate of remaining crossing time Δ(t) with Δ(t) = (W - y(t)) / v(t), and a safety-zone propagation model with D(t) = [Δ(t) + r] * v_max, plus a speed-adaptation rule for approaching cars via v_safe = min{ v_max, (L - C)/(e - s) }. Evaluation in SUMO shows high classification accuracy, precise localization and timing (RMSEs in the depicted ranges) and end-to-end protection with cars reducing speed smoothly rather than stopping. The work highlights practical impact for pedestrian safety with privacy-preserving, short-range V2V/V2P communications, and identifies future work on information overload, security, and all-clear signaling.

Abstract

Recent statistics reveal an alarming increase in accidents involving pedestrians (especially children) crossing the street. A common philosophy of existing pedestrian detection approaches is that this task should be undertaken by the moving cars themselves. In sharp departure from this philosophy, we propose to enlist the help of cars parked along the sidewalk to detect and protect crossing pedestrians. In support of this goal, we propose ADOPT: a system for Alerting Drivers to Occluded Pedestrian Traffic. ADOPT lays the theoretical foundations of a system that uses parked cars to: (1) detect the presence of a group of crossing pedestrians - a crossing cohort; (2) predict the time the last member of the cohort takes to clear the street; (3) send alert messages to those approaching cars that may reach the crossing area while pedestrians are still in the street; and, (4) show how approaching cars can adjust their speed, given several simultaneous crossing locations. Importantly, in ADOPT all communications occur over very short distances and at very low power. Our extensive simulations using SUMO-generated pedestrian and car traffic have shown the effectiveness of ADOPT in detecting and protecting crossing pedestrians.

Figures (20)

• Figure 1: Illustrating ADOPT: Parked cars detect occluded crossing pedestrians and alert approaching cars.
• Figure 2: Illustrating the proof of Theorem \ref{['thm:fundamental']}
• Figure 3: Illustrating the notation for the proof of Lemma \ref{['lem:y']}.
• Figure 4: Parked cars in the Safety Zone propagate alert messages within the estimated propagation distance to alert approaching cars.
• Figure 5: The Last car in the chain delivers the Caution message to the approaching car via DSRC if the chain length is less than $D(t)$.

Theorems & Definitions (2)

• Theorem 1
• Lemma 2