ASPED: An Audio Dataset for Detecting Pedestrians

TL;DR

This paper introduces ASPED, a large-scale audio dataset for pedestrian detection, demonstrating the potential of audio-based methods while highlighting the task's complexity.

Contribution

The paper presents a new dataset for audio pedestrian detection and explores its viability, marking a novel contribution in audio analysis for this application.

Findings

Audio approaches show promise for pedestrian detection

Standard methods are insufficient for this challenging task

The dataset enables future research in audio-based pedestrian detection

Abstract

We introduce the new audio analysis task of pedestrian detection and present a new large-scale dataset for this task. While the preliminary results prove the viability of using audio approaches for pedestrian detection, they also show that this challenging task cannot be easily solved with standard approaches.