Abstract: A first data group, which indicates reflection wave intensities from reflection points for radar directions indicating directions in which the corresponding reflection points exist relative to a radar apparatus and distances from the radar apparatus to the reflection points, and a second data group, which indicates Doppler velocities of the reflection points for the radar directions and the distances from the radar apparatus to the reflection points, are used to generate a third data group, which indicates the reflection wave intensities of the reflection points. A radar moving direction relative to a moving direction of the vehicle for each frame is generated based on the third data group. The radar moving direction when the moving direction of the vehicle is straight ahead is estimated using the radar moving direction in a predetermined number of frames, and the radar installation angle is calculated using the estimated radar moving direction.

Abstract: A vehicle movement estimation device has a radar that is provided in a vehicle and that performs transmission of a radar wave and reception of a reflected wave that is the radar wave reflected by an object, a radar movement estimator that estimates a radar movement velocity and a radar movement direction of the radar based on the received reflected wave, an angular velocity estimator that estimates a rotational angular velocity of the vehicle, and a vehicle movement estimator that estimates a movement velocity and a movement direction of a prescribed position of the vehicle based on the estimated radar movement velocity and radar movement direction, the estimated rotational angular velocity, and a spatial relationship between the radar and the prescribed position.

Abstract: A state calculation apparatus includes an receiver that receives azimuths of objects around a vehicle and their relative velocities to the vehicle, detected by a first sensor used for the vehicle, as target information, and a velocity and a travel direction of the vehicle, detected by a second sensor installed on the vehicle and having an error variance, as state information, and a controller that calculates velocities and travel directions of the vehicle, using the state information and based on a plurality of the azimuths and a plurality of the relative velocities extracted from the target information and that outputs at least either a velocity or a travel direction of the vehicle by using a specified filter to filter mean values of and error variances in the calculated velocities and travel directions and at least either the velocity or the travel direction detected by the second sensor.

Abstract: A radar apparatus includes an antenna that receives echo signals, each of the echo signals being a radar signal reflected by one or more objects; a Doppler-frequency acquirer that acquires Doppler frequencies at each range bin from the received echo signals; a direction correlation power-value calculator that calculates direction correlation power values for respective combinations of the Doppler frequencies and at least one of a distance to the one or more objects and an arrival direction of the echo signals, each direction correlation power value indicating a strength of a corresponding echo signal; and a normalized direction correlation-value calculator that calculates, for the respective combinations, normalized direction correlation values, each normalized direction correlation value indicating a probability of the arrival direction of the corresponding echo signal.

Abstract: A first data group, which indicates reflection wave intensities from reflection points for radar directions indicating directions in which the corresponding reflection points exist relative to a radar apparatus and distances from the radar apparatus to the reflection points, and a second data group, which indicates Doppler velocities of the reflection points for the radar directions and the distances from the radar apparatus to the reflection points, are used to generate a third data group, which indicates the reflection wave intensities of the reflection points. A radar moving direction relative to a moving direction of the vehicle for each frame is generated based on the third data group. The radar moving direction when the moving direction of the vehicle is straight ahead is estimated using the radar moving direction in a predetermined number of frames, and the radar installation angle is calculated using the estimated radar moving direction.

Abstract: A radar receiver of a radar apparatus includes a Doppler frequency acquirer which, in operation, acquires a Doppler frequency for each of range bins from an echo signal, received via at least one antenna, which is a radar signal reflected by an object, a direction correlation power value calculator which, in operation, calculates, for each of combinations of the range bins and the Doppler frequencies, a direction correlation power value indicating strength of the echo signal for each of directions, a normalized direction correlation value calculator which, in operation, calculates, for each of the combinations of the range bins and the Doppler frequencies, a normalized direction correlation value indicating likelihood of a direction of arrival of the echo signal for each of the directions, and a running vehicle detector which, in operation, determines, on a basis of the direction correlation power value and the normalized direction correlation value, whether the object is a running vehicle.

Abstract: A vehicle movement estimation device has a radar that is provided in a vehicle and that performs transmission of a radar wave and reception of a reflected wave that is the radar wave reflected by an object, a radar movement estimator that estimates a radar movement velocity and a radar movement direction of the radar based on the received reflected wave, an angular velocity estimator that estimates a rotational angular velocity of the vehicle, and a vehicle movement estimator that estimates a movement velocity and a movement direction of a prescribed position of the vehicle based on the estimated radar movement velocity and radar movement direction, the estimated rotational angular velocity, and a spatial relationship between the radar and the prescribed position.

Abstract: A radar receiver of a radar apparatus includes a Doppler frequency acquirer which, in operation, acquires a Doppler frequency for each of range bins from an echo signal, received via at least one antenna, which is a radar signal reflected by an object, a direction correlation power value calculator which, in operation, calculates, for each of combinations of the range bins and the Doppler frequencies, a direction correlation power value indicating strength of the echo signal for each of directions, a normalized direction correlation value calculator which, in operation, calculates, for each of the combinations of the range bins and the Doppler frequencies, a normalized direction correlation value indicating likelihood of a direction of arrival of the echo signal for each of the directions, and a running vehicle detector which, in operation, determines, on a basis of the direction correlation power value and the normalized direction correlation value, whether the object is a running vehicle.

Abstract: Device (10) comprises: a comparison object pixel acquisition unit (433) which acquires pixel values of a plurality of comparison object pixels which, when each pixel of an image is designated as a pixel of interest, and a ring-shaped region with the pixel of interest being designated as the center thereof being designated a vicinity region, said comparison object pixels are included in the vicinity region; a pixel difference calculation unit (434) which calculates the difference between the pixel value of the pixel of interest and the pixel values of each comparison object pixel; and a local binary pattern generation unit (435) which generates a local binary pattern for each pixel. A plurality of vicinity regions are present for each pixel of interest, and the distance of the vicinity regions are established on the basis of the spatial frequency characteristics of a lens with which the image is photographed.

Abstract: Provided is a feature extraction device including a sub region setting unit (433) which sets a plurality of sub regions with respect to a pixel of interest, and a binary pattern generation unit (434) which generates a local binary pattern indicating pixel value comparison results relative to each sub region with respect to each pixel of interest. The sub region setting unit (433) sets (436) a region constituted by a plurality of pixels including a pixel separated from the pixel of interest as a sub region, and the binary pattern generation unit (434) calculates (437) a representative value for each sub region and generates (439) a local binary pattern indicating whether or not the difference (438) between the representative value and the value of the pixel of interest is equal to or larger than a predetermined threshold value.

Abstract: A radar apparatus includes an antenna that receives echo signals, each of the echo signals being a radar signal reflected by one or more objects; a Doppler-frequency acquirer that acquires Doppler frequencies at each range bin from the received echo signals; a direction correlation power-value calculator that calculates direction correlation power values for respective combinations of the Doppler frequencies and at least one of a distance to the one or more objects and an arrival direction of the echo signals, each direction correlation power value indicating a strength of a corresponding echo signal; and a normalized direction correlation-value calculator that calculates, for the respective combinations, normalized direction correlation values, each normalized direction correlation value indicating a probability of the arrival direction of the corresponding echo signal.

Abstract: Provided is a feature extraction device whereby it is possible, while using local binary patterns, to extract image features with which object detection which is robust against disparities in a photographic environment is possible. A feature extraction unit (440) comprises: a binary pattern generation unit (443) which generates, for each of all pixels or partial pixels in an image, local binary patterns which denote, by bit values, whether the difference in pixel values between the pixel and the surrounding adjacent pixels is greater than or equal to a threshold value; a weighting generation unit (444) which determines, for each generated local binary pattern, a weighting according to the pixel value difference; and a histogram generation unit (445) which applies the determined weightings to the corresponding local binary patterns and generates a histogram which denotes the distribution of the local binary patterns which are generated from the image.

Abstract: Device (10) comprises: a comparison object pixel acquisition unit (433) which acquires pixel values of a plurality of comparison object pixels which, when each pixel of an image is designated as a pixel of interest, and a ring-shaped region with the pixel of interest being designated as the center thereof being designated a vicinity region, said comparison object pixels are included in the vicinity region; a pixel difference calculation unit (434) which calculates the difference between the pixel value of the pixel of interest and the pixel values of each comparison object pixel; and a local binary pattern generation unit (435) which generates a local binary pattern for each pixel. A plurality of vicinity regions are present for each pixel of interest, and the distance of the vicinity regions are established on the basis of the spatial frequency characteristics of a lens with which the image is photographed.

Abstract: Provided is a feature extraction device including a sub region setting unit (433) which sets a plurality of sub regions with respect to a pixel of interest, and a binary pattern generation unit (434) which generates a local binary pattern indicating pixel value comparison results relative to each sub region with respect to each pixel of interest. The sub region setting unit (433) sets (436) a region constituted by a plurality of pixels including a pixel separated from the pixel of interest as a sub region, and the binary pattern generation unit (434) calculates (437) a representative value for each sub region and generates (439) a local binary pattern indicating whether or not the difference (438) between the representative value and the value of the pixel of interest is equal to or larger than a predetermined threshold value.

Abstract: A feature calculator calculates the number of edge pixel pairs (three-dimensional histogram) defined by the edge direction of a predetermined pixel, the edge direction of an edge pixel present in a neighboring area of the predetermined pixel, and the spatial position relation between the predetermined pixel and the edge pixel present in the neighboring area of the predetermined pixel as a feature of an image. With this, the feature also represents the spatial relationship of the edges. Consequently, it is possible to also identify the difference of edge patterns due to the difference of the spatial relationships of the edges and increase the accuracy of identification of, for example, a portrait image.

Abstract: Provided is a feature extraction device whereby it is possible, while using local binary patterns, to extract image features with which object detection which is robust against disparities in a photographic environment is possible. A feature extraction unit (440) comprises: a binary pattern generation unit (443) which generates, for each of all pixels or partial pixels in an image, local binary patterns which denote, by bit values, whether the difference in pixel values between the pixel and the surrounding adjacent pixels is greater than or equal to a threshold value; a weighting generation unit (444) which determines, for each generated local binary pattern, a weighting according to the pixel value difference; and a histogram generation unit (445) which applies the determined weightings to the corresponding local binary patterns and generates a histogram which denotes the distribution of the local binary patterns which are generated from the image.

Abstract: A feature calculation unit (105) calculates the number of edge pixel pairs (three-dimensional histogram) defined by the edge direction of a predetermined pixel, the edge direction of an edge pixel present in a neighbor area of the predetermined pixel, and the spatial position relation between the predetermined pixel and the edge pixel present in the neighbor area of the predetermined pixel as a feature (S5) of an image. With this, the feature (S5) also represents the spatial relationship of the edges. Consequently, it is possible to also identify the difference of edge patterns due to the difference of the spatial relationships of the edges and increase the accuracy of identification of, for example, a portrait image.