%0 Generic %A Schulz, Yannick %A Kini Mattar, Avinash %A Hehn, Thomas %A Kooij, Julian %D 2024 %T OVAD - Occluded Vehicle Acoustic Detection dataset %U %R 10.4121/07c5956a-fd5f-411f-9b4e-ffe7eb7dec5f.v1 %K microphone array %K self driving %K robotics %K audio %K acoustics %K traffic sound %K vehicle sound %K beam forming %K machine learning %K multi-channel sound %X <p>Acoustic multi-microphone dataset (plus video) from the paper "Hearing What You Cannot See: Acoustic Vehicle Detection Around Corners" (IEEE Robotics and Automation Letters 2021, see DOI: <a href="https://doi.org/10.1109/LRA.2021.3062254" target="_blank">10.1109/LRA.2021.3062254</a> and <a href="https://arxiv.org/abs/2007.15739" target="_blank">arxiv</a>). For a short and intuitive introduction of our main ideas and online prediction results, we recommend to watch our supplementary video on <a href="http://www.youtube.com/watch?v=BXkeWf24MLg" target="_blank">Youtube: Hearing What You Cannot See</a>.</p><p><br></p><p>We present a data-driven acoustic detection method that can detect an approaching vehicle before it enters line-of-sight, e.g. while hidden behind a blind corner, in real-world outdoor conditions. The code can be found at <a href="https://github.com/tudelft-iv/occluded_vehicle_acoustic_detection" target="_blank">github.com/tudelft-iv/occluded_vehicle_acoustic_detection</a> .</p><p><br></p><p>As part of this publication, we provide a novel audio-visual dataset (OVAD - occluded vehicle acoustic detection) collected in outdoor urban environments with a 56-microphone array mounted on our research vehicle.</p> %I 4TU.ResearchData