A Real-Time Bike-Pedestrian Safety System with Wide-Angle Perception and Evaluation Testbed for Urban Intersections

TL;DR

This paper introduces a real-time bike-pedestrian collision warning system using fisheye cameras, with a novel calibration pipeline, detection methods, and formalized decision testing, achieving high sensitivity and specificity.

Contribution

It presents a comprehensive pipeline for fisheye-based collision warnings, including calibration, detection, simulation, and formal decision testing, with open-source code available.

Findings

Achieves 93.3% sensitivity and 92.3% specificity in conformance testing.

Maintains warning latency above pedestrian reaction time across camera latencies.

Develops a calibration pipeline that overcomes fisheye lens challenges.

Abstract

Collisions between cyclists and pedestrians at urban intersections remain a persistent source of injuries, yet few systems attempt real-time warnings to unequipped road users using commodity hardware. We present a prototype collision warning system that runs on a single edge device with a wide-angle fisheye camera, producing audible and visual alerts at 30\,fps. The system makes four contributions. First, we develop a calibration pipeline for ultra-wide fisheye lenses that overcomes corner-detection failure and optimizer divergence through perspective remapping and direct bundle adjustment. Second, we combine fisheye-aware object detection with a closed-form ground-plane projection via a precomputed lookup table. Third, we introduce a design-time conformance simulation with 24 scripted hazard scenarios, stochastic size-aware detection failures, and a latency sweep showing that a first-order kinematic predictor maintains the mean warning budget above the distracted-pedestrian reaction time across realistic camera latencies. Fourth, we formalize the decision layer as a separable, auditable testbench with explicit deployment gates, contestability mechanisms, and a residual risk register. Under conformance testing with fisheye localization error, the selected pipeline configuration achieves 93.3\% sensitivity and 92.3\% specificity, with a mean warning budget of 3.3\,s. The system design was informed by community-aided design workshops. Code and replication scripts are available at https://github.com/mkturkcan/bikeped.