Passive sound source classification and localization
A method for processing audible sounds using ultrasonic sensors. The method includes passively monitoring, via ultrasonic sensors, an external environment for a audible sounds. An audible sound may be detected and used to produce a sound signal. The sound signal may be filtered to determine one or more features corresponding thereto, including a class, a position, and a velocity. A priority may be assigned to the sound signal based on the sound signal to determine an appropriate response. A corresponding system and computer program product are also disclosed and claimed herein.
1. A method comprising:
passively monitoring, with at least one ultrasonic sensor, an outdoor environment for audible sounds;
converting, by the at least one ultrasonic sensor, an audible sound into an electrical signal;
processing, by a neural network trained to perform classification with respect to a plurality of classes, the electrical signal in order to classify a source of the audible sound as pertaining to a first class of the plurality of classes;
analyzing, by a computer system, the electrical signal to estimate at least one of a relative position and a relative velocity corresponding to the source; and
assigning, by the computer system, a priority to the source based on at least one of the first class, the relative position, and the relative velocity.
2. The method of claim 1 , wherein the at least one ultrasonic sensor is carried onboard a first vehicle.
3. The method of claim 2 , further comprising tracking the source when the priority is above a threshold and not tracking the source when the priority is below the threshold.
4. The method of claim 3 , wherein tracking comprises monitoring the relative position of the source with respect to the first vehicle.
5. The method of claim 1 , wherein assigning the priority to the source further comprises assigning the priority based on at least one of current traffic conditions, behavior policies, and expectations of objects.
6. The method of claim 5 , wherein the priority assigned by the computer system to the source changes over time.
7. The method of claim 2 , further comprising communicating at least one of the first class, the relative position, and the relative velocity to a second vehicle.
8. The method of claim 7 , wherein the communicating comprises sending the at least one of the first class, the relative position, and the relative velocity directly from the first vehicle to the second vehicle via wireless communication.
9. The method of claim 1 , further comprising generating a confidence score for at least one of the relative position and the relative velocity.
10. The method of claim 9 , wherein the confidence score is based at least partially on information received from at least one of another sensor type and a remotely-located ultrasonic sensor.
11. A system comprising:
an ultrasonic sensor;
at least one processor; and
at least one memory device operably connected to the at least one processor and storing instructions for execution by the at least one processor, the instructions causing the at least one processor to:
receive an electrical signal from the ultrasonic sensor, wherein the electrical signal is generated by the ultrasonic sensor in response to the ultrasonic sensor receiving an audible sound emanating from a source,
process, using a neural network trained to perform classification with respect to a plurality of classes, the electrical signal in order to classify the source as pertaining to a first class of the plurality of classes,
analyze the electrical signal to estimate at least one of a relative position and a relative velocity corresponding to the source, and
assign a priority to the source based on at least one of the first class, the relative position, and the relative velocity.
12. The system of claim 11 , wherein the at least one ultrasonic sensor is carried onboard a first vehicle.
13. The system of claim 11 , wherein the instructions further cause the at least one processor to track the source when the priority is above a threshold and not track the source when the priority is below the threshold.
14. The system of claim 13 , wherein to track the source is to monitor the relative position of the source with respect to the first vehicle.
15. The system of claim 11 , wherein to assign the priority to the source is to assign the priority based on at least one of current traffic conditions, behavior policies, and expectations of objects.
16. The system of claim 15 , wherein the priority assigned to the source changes over time.
17. The system of claim 12 , wherein the instructions further cause the processor to communicate at least one of the first class, the relative position, and the relative velocity to a second vehicle.
18. The system of claim 11 , wherein to communicate the at least one of the first class, the relative position, and the relative velocity to the second vehicle is to communicate the at least one of the first class, the relative position, and the relative velocity directly to the second vehicle via wireless communication.