Noise2Weight: On detecting payload weight from drones acoustic emissions

The increasing popularity of autonomous and remotely-piloted drones has paved the way for several use-cases and application scenarios, including merchandise delivery, surveillance, and warfare, to cite a few. In many application scenarios, estimating with zero-touch the weight of the payload carried by a drone before it approaches could be of particular interest, e.g., to provide early tampering detection when the weight of the payload is sensitively different from the expected one. To the best of our knowledge, we are the first to investigate the possibility to remotely detect the weight of the payload carried by a commercial drone by analyzing its acoustic fingerprint. Rooted on a sound methodology and validated by an extensive experimental on-field campaign carried out on a reference 3DR Solo drone, we characterize how the differences in the thrust needed by a drone to carry different payloads affect the speed of the motors and the blades and, in turn, introduces significant variations in the resulting acoustic fingerprint. We applied the above findings to different use-cases and scenarios, characterized by different computational capabilities of the detection system. Results are striking: using the Mel-Frequency Cepstral Coefficients (MFCC) components of the audio signal and different Support Vector Machine (SVM) classifiers, we showed that it is possible to achieve a minimum classification accuracy of 98% in the detection of the specific payload class carried by the drone, using an acquisition time of only 0.25 s—performances improve when using longer time acquisitions. All the data used for our analysis have been released as open-source, to enable the community to validate our findings and use such data as a ready-to-use basis for further investigations.