Vehicle Sound Source Recognition and Locolization Research Project



Almost every moving vehicle makes some kind of noise; the noise can come from the vibrations of the running engine, bumping and friction of the vehicle tires with the ground, wind effects, etc. Vehicles of the same kind and working in similar conditions ("class") will generate similar noises, or have some kind of noise signature. This noise pattern gives a clue for military reconnaissance or a surveillance mission robot to detect a vehicle and recognize its class. Our research goal is to characterize noise patterns and use them to recognize whether a new detected sound is from a vehicle of known type, and if so to classify its type.

In our CyberRAVE research project, each robot has a camera and a pair of stereo microphones set apart about 20 centimaters away, with the vehicle sound signature being detected we use this stereo sound information to initialize the process of finding an interesting object and a tracking its movement in field.

For more detailed information please see my paper "Vehicle Sound Signature Recognition by Frequency Principle Component Analysis" in postscript or pdf format.

 


Return to Huadong's homepage