Abstract:
A tracking apparatus which tracks a target includes a predilection unit, correction unit, and updating unit. The prediction unit predicts the state distribution of the target at a specific time. The correction unit, for at least one observation point of the target, that is observed at the specific time, uses a likelihood function to define a degree of certainty of the state distribution predicted by the prediction unit, and corrects the likelihood function depending on the number of observation points. The updating unit updates the state distribution at the specific time based on the likelihood function corrected by the correction unit.
Abstract:
In a dual-frequency CW radar apparatus, first/second beat signals that include reflection components of radar waves conforming to transmission signals of first/second frequencies are generated for each antenna element and the generated signals are Fourier transformed. A power spectrum average of the beat signals is used as a basis for the detection of a peak frequency fp corresponding to the frequency of the reflection components. A second eigenvalue λ2 of a correlation matrix: Ry=(½)·[y1,y2][y1,y2]H is calculated, the matrix being based on first received vector y1/second received vector y2 having elements that are Fourier transformed values of the peak frequency fp. Based on the magnitude of the eigenvalue λ2, whether or not the reflection components corresponding to the peak frequency fp are synthetic components of the reflected waves from a plurality of targets is decided.
Abstract:
An other lane monitoring device of the present disclosure includes an other vehicle acquisition section, a path acquisition section, a lane estimation section, and a position estimation section. The other vehicle acquisition section is configured to acquire other vehicle position information that indicates the current position of an other vehicle near the own vehicle. The path acquisition section is configured to acquire an own vehicle travel path that indicates a path along which the own vehicle has traveled. The lane estimation section is configured to use the own vehicle travel path as a basis for estimating an other lane area that is a lane where the other lane is present. The position estimation section is configured to estimate a future position of the other vehicle, assuming that the other vehicle moves along the own vehicle travel path or in the other lane area.
Abstract:
A radar apparatus includes a targeting unit that irradiates a radar wave and recognizes a detection subject using a reflected wave thereof. The targeting unit extracts, as a target, a peak that is confirmed to have historical connection over measurement cycles equal to or more than a predetermined targeting threshold, from peaks extracted from a power spectrum generated by frequency analysis. A rainy-weather determining unit determines that weather is rainy when a number of erroneous detections is greater than a predetermined rainy-weather determination threshold. The number of erroneous detections is a number of peaks that have been detected in a previous measurement cycle or earlier by the targeting unit and are not confirmed to have historical connection to a peak detected in a current measurement cycle. A parameter updating unit updates the targeting threshold so as to be a larger value as the number of erroneous detections increases when the rainy-weather determining unit determines that the weather is rainy.
Abstract:
An on-vehicle radar apparatus includes a radar sensor and a mounting angle calculation section that calculates a mounting angle of the radar sensor, and the radar sensor is mounted on a vehicle so that a sensing area includes a direction of 90 degrees relative to a front-back direction of the vehicle and detects a relative speed to an observation point at which the radar wave is reflected in the sensing area and an azimuth at which the observation point is located. The mounting angle calculation section calculates a mounting angle of the radar sensor from an azimuth of a speed zero observation point, the speed zero observation point being the observation point with a relative speed of zero.
Abstract:
An object model learning method includes: in an object identification model forming a convolutional neural network and a warp structure warping a feature map extracted in the convolutional neural network to a different coordinate system, preparing, in the warp structure, a warp parameter for relating a position in the different coordinate system to a position in a coordinate system before warp; and learning the warp parameter to input a capture image in which an object is captured to the object identification model and output a viewpoint conversion map in which the object is identified in the different coordinate system.
Abstract:
In a dual-frequency CW radar apparatus, first/second beat signals that include reflection components of radar waves conforming to transmission signals of first/second frequencies are generated for each antenna element and the generated signals are Fourier transformed. A power spectrum average of the beat signals is used as a basis for the detection of a peak frequency fp corresponding to the frequency of the reflection components. A second eigenvalue λ2 of a correlation matrix: Ry=(½)·[y1,y2][y1,y2]H is calculated, the matrix being based on first received vector y1/second received vector y2 having elements that are Fourier transformed values of the peak frequency fp. Based on the magnitude of the eigenvalue λ2, whether or not the reflection components corresponding to the peak frequency fp are synthetic components of the reflected waves from a plurality of targets is decided.
Abstract:
An estimation apparatus includes a distance estimator. The distance estimator performs regression analysis using, as samples, an observation of distance and an observation at each time within a predetermined period obtained by an observer. The estimation apparatus estimates that a value of the distance upon a value of a displacement calculated in accordance with a regression equation based on the regression analysis being zero shows a value of the distance to the forward object at a start time.
Abstract:
An estimation apparatus includes a distance estimator. The distance estimator performs regression analysis using, as samples, an observation of distance and an observation at each time within a predetermined period obtained by an observer. The estimation apparatus estimates that a value of the distance upon a value of a displacement calculated in accordance with a regression equation based on the regression analysis being zero shows a value of the distance to the forward object at a start time.
Abstract:
An on-vehicle radar apparatus includes a radar sensor and a mounting angle calculation section that calculates a mounting angle of the radar sensor, and the radar sensor is mounted on a vehicle so that a sensing area includes a direction of 90 degrees relative to a front-back direction of the vehicle and detects a relative speed to an observation point at which the radar wave is reflected in the sensing area and an azimuth at which the observation point is located. The mounting angle calculation section calculates a mounting angle of the radar sensor from an azimuth of a speed zero observation point, the speed zero observation point being the observation point with a relative speed of zero.