Citing¶
How to cite the paper, the dataset and the starter kit. All three use the same reference.
Paper¶
Mehmet Kerem Turkcan. A Real-Time Bike-Pedestrian Safety System with Wide-Angle Perception and Evaluation Testbed for Urban Intersections. arXiv:2604.17046 [cs.CV], submitted 18 April 2026. https://arxiv.org/abs/2604.17046
@misc{turkcan2026realtimebikepedestriansafetywideangle,
title = {A Real-Time Bike-Pedestrian Safety System with Wide-Angle Perception and Evaluation Testbed for Urban Intersections},
author = {Mehmet Kerem Turkcan},
year = {2026},
eprint = {2604.17046},
archivePrefix = {arXiv},
primaryClass = {cs.CV},
url = {https://arxiv.org/abs/2604.17046}
}
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.
Where each contribution lives in this repository:
| Contribution | Code | Documentation |
|---|---|---|
| Fisheye calibration by perspective remapping and bundle adjustment | calibration/ |
Calibration |
| Ground-plane projection | FisheyeCamera in decision_testbench.py |
Perception |
| Conformance simulation, detection failures, latency sweep | decision_testbench.py |
Testbench, uncertainty, latency |
| Decision layer | decision_pipeline.py |
Decision pipeline |
The sensitivity and specificity in the abstract are the default row of python decision_testbench.py --compare. The quickstart shows that run.
Dataset¶
The scenario dataset is at https://huggingface.co/datasets/mehmetkeremturkcan/bikeped under CC BY 4.0. Its card asks for the paper citation above. See dataset for the contents.
Starter kit¶
If the bridge starter kit informs published work, cite the paper with the same entry.