Research
OccluNet — acoustic detection of occluded objects
Neural audio method that detects both the occluder and the object hidden behind it using a 16-channel microphone array.
PyTorchMicrophone arraysTSP / impulse responseSignal processingPython
Problem
Cameras and LiDAR cannot see objects hidden behind a barrier. OccluNet uses sound to detect both the occluder and the hidden object under direct occlusion — without the relay-wall setup that prior non-line-of-sight methods require.
Approach
- Emit a chirp (frequency sweep) into the scene and record it with a 16-channel microphone array.
- Extract room impulse responses via TSP deconvolution.
- Feed multi-channel spectrogram features into a dual-branch CNN (temporal + spectral) — the AudioIR encoder.
- Classify the occluded object and regress distance/direction from the acoustic features.
Result
- Journal paper "Neural Audio-based Detection of Occluding and Occluded Objects" submitted to Applied Acoustics (Elsevier), through reviewer revision rounds.
- [CONFIRM CURRENT STATUS: under review / accepted / published + DOI]
- [ADD KEY QUANTITATIVE RESULTS]
System breakdown
Hardware
- 16-channel circular microphone array
- Loudspeaker chirp source
- Anechoic-room access for controlled baselines
- Occluder panels and target object set
Firmware / embedded
- Multi-channel synchronous audio capture
- TSP (time-stretched pulse) excitation and deconvolution
- Calibration of channel gain and latency offsets
Software
- PyTorch dual-branch CNN (AudioIR encoder)
- Spectrogram and impulse-response feature pipeline
- Classification head + distance/direction regression head
- Experiment tracking and ablation tooling
Project demo video slot