A Surrogate Video-Based Safety Methodology for Diagnosis and Evaluation of Low-Cost Pedestrian-Safety Countermeasures: The Case of Cochabamba, Bolivia

Lynn Scholl,Bismarck Ledezma-Navarro,Edgar Zamora,Mohamed Elagaty,Luis Miranda-Moreno

doi:10.3390/su11174737

Lynn Scholl, Bismarck Ledezma-Navarro + Show 3 more

Open Access

https://doi.org/10.3390/su11174737

Copy DOI

Abstract

Due to a lack of reliable data collection systems, traffic fatalities and injuries are often under-reported in developing countries. Recent developments in surrogate road safety methods and video analytics tools offer an alternative approach that can be both lower cost and more time efficient when crash data is incomplete or missing. However, very few studies investigating pedestrian road safety in developing countries using these approaches exist. This research uses an automated video analytics tool to develop and analyze surrogate traffic safety measures and to evaluate the effectiveness of temporary low-cost countermeasures at selected pedestrian crossings at risky intersections in the city of Cochabamba, Bolivia. Specialized computer vision software is used to process hundreds of hours of video data and generate data on road users’ speed and trajectories. We find that motorcycles, turning movements, and roundabouts, are among the key factors related to pedestrian crash risk, and that the implemented treatments were effective at four-legged intersections but not at traditional-design roundabouts. This study demonstrates the applicability of the surrogate methodology based on automated video analytics in the Latin American context, where traditional methods are challenging to implement. The methodology could serve as a tool to rapidly evaluate temporary treatments before they are permanently implemented and replicated.

Highlights

Each year approximately 1.3 million people die in traffic crashes around the world and between 20 and 50 million people are injured or disabled
This paper presents a proactive surrogate safety methodology for identifying pedestrian injury-risk factors and evaluating low-cost temporary countermeasures at intersections in the Latin American context
Using computer vision and deep-learning techniques, road-user trajectories, speeds and conflicts were automatically generated for thousands of vehicle–pedestrian interactions

Summary

Introduction

Each year approximately 1.3 million people die in traffic crashes around the world and between 20 and 50 million people are injured or disabled. Road traffic deaths account for 25% of all injury deaths worldwide, with traffic injuries being the 8th cause of death for people of all ages [1]. While all the regions of the world experience road traffic injuries, low-and middle-income countries (including Latin American countries) are disproportionately affected. These countries account only for 54% of vehicles registered world-wide, they account for 90% of road traffic fatalities [1]. The Latin America and the Caribbean region has one of the highest roadway fatality rates in the world, with approximately 17 traffic related fatalities per 100,000 inhabitants, compared to less than 10 fatalities per 100,000 inhabitants in high-income countries [2].

Objectives

Results

Conclusion