Abstract:
The learning device learns the target detection model used in the radar device. The learning device includes an acquisition unit, a learning data generation unit, and a learning processing unit. The acquisition unit acquires a reception signal generated based on the received wave and a tracking signal generated based on the reception signal from the radar device. The learning data generation unit generates learning data using the reception signal and the tracking signal. The learning processing unit learns a target detection model that detects a target from the reception signal, using the learning data.
Abstract:
The learning device includes an acquisition unit, a learning data generation unit, and a learning processing unit. The acquisition unit acquires operation data generated during an operation of a radar device and the operation history data indicating operations performed by an operator on the radar device from the radar device. The learning data generation unit generates the learning data using the operation data and the operation history data. The learning processing unit learns an operation determination model that determines an operation to be performed on the radar device based on the operation data, using the learning data.
Abstract:
In order to achieve object detection that does not detect an object moving at a speed within a prescribed speed range, the present invention comprises at least two cross-correlation calculation units which each calculate a cross correlation function between a waveform of a reflection signal obtained when a transmission signal having changing frequencies is reflected by a target object, and a different correlation waveform generated from the waveform of the transmission signal, and a synthesis unit that synthesizes at least two cross-correlation functions from at least the two cross-correlation calculation units so as to make detection of a target object moving at a speed within the prescribed speed range less likely, and that outputs the synthesis results to a post-processing unit.
Abstract:
A reception signal demodulation device which converts a modulated reception signal into a digital signal and performs signal reconstruction includes a demodulator which demodulates the received signal, a matched filter which improves a signal-to-noise power ratio of the signal from the demodulator, a threshold value discriminator which determines a compression rate based on the signal from the matched filter, and a reconstruction circuit which compresses the signal from the matched filter, converts it into the digital signal, and performs signal reconstruction from the signal converted into the digital signal based on the compression rate.
Abstract:
The learning device learns a tracking model used for a radar device. A first acquisition unit acquires, from a radar device, a target detection information indicating a position of a target detected based on a received wave, and a track of the target calculated based on the target detection information. A second acquisition unit acquires a target position information indicating a position of the target. A learning data generation unit generates learning data using the target detection information, the track, and the target position information. A learning processing unit learns a tracking model for performing tracking processing of the target based on the target detection information, using the learning data.
Abstract:
The present invention relates to a signal processing device for accurately detecting a moving object without being influenced by the speed of the moving object. This signal processing device is provided with: at least two cross-correlation calculation units for calculating cross-correlation functions for the waveform of a reflection signal obtained through the reflection, by an object, of a transmission signal having a varying frequency and different correlation waveforms generated from the waveform of the transmission signal; a combination unit for combining the at least two cross-correlation functions from the at least two cross-correlation calculation units so as not to be separated in the frequency shift direction; and a detection unit for detecting the object on the basis of the cross-correlation function resulting from the combination.
Abstract:
A distributed-cooperative-information-processing device according to the present invention is allocated in a distributed manner within a predetermined field. The device measures an environment by using a sensor device; generates estimate determination information being information indicating a probability of a hypothetical set of states in the environment, based on a measurement result of the environment; receives the estimate determination information generated by another distributed-cooperative-information-processing device within the field; manages information of the another distributed-cooperative-information-processing device; and integrates the estimate determination information generated by own device and the estimate determination information received from the another distributed-cooperative-information-processing device.