Back to results
US 2004/0165478 A1Published application
Biomimetic sonar system and method
AssigneeNeptune Technologies, Inc.
InventorsJohn B. Harmon JR., Whitlow Au, Paul Eugene Nachtigall, Herbert Lawrence Roitblat
Life of this patent
Estimating the term…
Abstract
The Biomimetic Sonar invention ensonifies submerged objects, digitizes acoustic images reflected from the ensonified objects, and classifies and stores the digitized images using electronic processing derived from that believed to be used by Tursiops truncatus, the bottlenose dolphin. The invention also provides a probable identification of an ensonified object based on comparison of an ensonified object with templates in a library of acoustic images.
Claims26
A sonar system, comprising:
- a transmitter and receiver that use acoustic signal waveforms and processing similar to those used by dolphins for echolocation in which acoustic pulse are radiated by the transmitter, two or more channels of pulse echoes are received by the receiver and processed to generate acoustic images and probable identification of objects in the ensonified field.
A sonar system, comprising:
- a transmitter and receiver that use acoustic signal waveforms and processing similar to those used by dolphins for echolocation in which acoustic pulses are radiated by the transmitter, two or more channels of pulse echoes are received by the receiver and each channel processed through a cochlear processor and an envelope processor, and the outputs of such channels are further processed by a shape from latency processor, a stereausis processor, and an object recognition processor to generate acoustic images and probable identification of objects in the ensonified field.
A sonar system, comprising:
- a transmitter and receiver that use acoustic signal waveforms and processing similar to those used by dolphins for echolocation in which acoustic pulses are radiated by the transmitter, two or more channels of pulse echoes from one or more ensonified objects are received by the receiver and each channel is processed through a cochlear processor and then an envelope processor, the output of each envelope processor is further processed by a shape from latency processor, a second output of each cochlear processor is processed by a stereausis processor, a third output of each cochlear processor is processed by an object recognition processor that contains a library of object templates, a template comparator, an end user interface, and a neural network, and in which object recognition processor the echolocation data describing one or more ensonified objects that is output from the shape from latency processor, the two or more cochlear processors, and the stereausis processor are processed by the neural network to generate acoustic images, the generated images are compared by the template comparator with object templates in the object template library for identification, and probable identifications of the one or more ensonified objects are provided through the neural network to the end user interface.
Dependencies are inferred from the claim text.