Datacentric analysis to reduce pedestrians accidents: A case study in Colombia

TL;DR

This study uses system-dynamics and deep learning to analyze pedestrian accidents in Bucaramanga, Colombia, proposing safety policies like speed bumps that could reduce accidents by 80%.

Contribution

It introduces a novel approach combining video analysis, deep learning, and system-dynamics to identify causes and suggest effective safety interventions.

Findings

Speed bumps could reduce accidents by 80%.

Deep learning effectively segments objects in traffic scenes.

Simulation-based policies can significantly improve pedestrian safety.

Abstract

Since 2012, in a case-study in Bucaramanga-Colombia, 179 pedestrians died in car accidents, and another 2873 pedestrians were injured. Each day, at least one passerby is involved in a tragedy. Knowing the causes to decrease accidents is crucial, and using system-dynamics to reproduce the collisions' events is critical to prevent further accidents. This work implements simulations to save lives by reducing the city's accidental rate and suggesting new safety policies to implement. Simulation's inputs are video recordings in some areas of the city. Deep Learning analysis of the images results in the segmentation of the different objects in the scene, and an interaction model identifies the primary reasons which prevail in the pedestrians or vehicles' behaviours. The first and most efficient safety policy to implement-validated by our simulations-would be to build speed bumps in specific places before the crossings reducing the accident rate by 80%.