The Pedestrian Patterns Dataset

TL;DR

This paper introduces a comprehensive pedestrian patterns dataset collected over multiple routes and times, including videos and GPS data, to aid autonomous driving research in risk assessment and long-term localization.

Contribution

The dataset uniquely captures social and pedestrian behavior patterns over time, combining video, GPS, and pedestrian detection data for autonomous vehicle applications.

Findings

Pedestrian density varies significantly across different times and routes.

The dataset enables improved risk prediction for autonomous navigation.

It facilitates research in long-term vision-based localization.

Abstract

We present the pedestrian patterns dataset for autonomous driving. The dataset was collected by repeatedly traversing the same three routes for one week starting at different specific timeslots. The purpose of the dataset is to capture the patterns of social and pedestrian behavior along the traversed routes at different times and to eventually use this information to make predictions about the risk associated with autonomously traveling along different routes. This dataset contains the Full HD videos and GPS data for each traversal. Fast R-CNN pedestrian detection method is applied to the captured videos to count the number of pedestrians at each video frame in order to assess the density of pedestrians along a route. By providing this large-scale dataset to researchers, we hope to accelerate autonomous driving research not only to estimate the risk, both to the public and to the autonomous vehicle but also accelerate research on long-term vision-based localization of mobile robots and autonomous vehicles of the future.