Acoustic detection of disguised vehicles

A non-transitory computer-readable medium storing computer-executable instructions that when executed by at least a processor of a computer system cause the computer system to:

• record a target acoustic output of a target vehicle, wherein the target vehicle includes a vehicle type representing at least a make and model;
• generate a target acoustic fingerprint from the target acoustic output;
• retrieve, from a database, a reference acoustic fingerprint of a reference vehicle that is assigned to the vehicle type;
• acoustically detect whether the target vehicle matches the reference vehicle within a threshold based at least on an acoustic similarity between the target acoustic fingerprint and the reference acoustic fingerprint;
• compute a cumulative mean absolute error between the target acoustic fingerprint and the reference acoustic fingerprint, wherein the cumulative mean absolute error represents the acoustic similarity;
• and
• generate an electronic alert that the target vehicle is or is not similar to the reference vehicle based on the acoustic similarity to the reference acoustic fingerprint.

A computing system comprising:

• a processor;
• a memory operably connected to the processor;
• a non-transitory computer-readable medium operably connected to the processor and memory and storing computer-executable instructions that when executed by at least the processor cause the computing system to:
• record a first acoustic output of a target vehicle, wherein the target vehicle includes a vehicle type representing at least a make and model;
• generate a first acoustic fingerprint from the first acoustic output;
• retrieve, from a database, a second acoustic fingerprint of a reference vehicle associated to the vehicle type;
• wherein the second acoustic fingerprint is generated from a second acoustic output recorded from the reference vehicle;
• acoustically detect that the target vehicle has different audio characteristics than the reference vehicle based at least on an acoustic dissimilarity between the first acoustic fingerprint and the second acoustic fingerprint;
• compute a cumulative mean absolute error between the first acoustic fingerprint and the second acoustic fingerprint, wherein the cumulative mean absolute error represents the acoustic dissimilarity;
• and
• generate an electronic alert that the target vehicle is a modified version of the reference vehicle based on the acoustic dissimilarity.