Audio-Based Pedestrian Detection in the Presence of Vehicular Noise
This work addresses pedestrian detection for safety applications in real-world noisy settings, but it is incremental as it builds on existing methods with new data and analysis.
The paper tackles the problem of audio-based pedestrian detection in noisy environments by introducing a new 1321-hour roadside dataset with traffic-rich soundscapes, and finds that vehicular noise significantly impacts model performance, highlighting the influence of acoustic context.
Audio-based pedestrian detection is a challenging task and has, thus far, only been explored in noise-limited environments. We present a new dataset, results, and a detailed analysis of the state-of-the-art in audio-based pedestrian detection in the presence of vehicular noise. In our study, we conduct three analyses: (i) cross-dataset evaluation between noisy and noise-limited environments, (ii) an assessment of the impact of noisy data on model performance, highlighting the influence of acoustic context, and (iii) an evaluation of the model's predictive robustness on out-of-domain sounds. The new dataset is a comprehensive 1321-hour roadside dataset. It incorporates traffic-rich soundscapes. Each recording includes 16kHz audio synchronized with frame-level pedestrian annotations and 1fps video thumbnails.