Abstract: In an object recognition apparatus, a range point acquirer irradiates each of irradiation areas arranged in a horizontally and vertically extending grid and forming a detection area for detecting a target with laser light and receives the reflected light from the respective irradiation areas, thereby acquiring a plurality of range points representing per-irradiation area coordinates of the target. A noise remover is configured to, based on either or both of degrees of angle proximity and degrees of distance proximity between a plurality of subject range points to be determined whether to be a noise point, of the plurality of range points, as viewed from a reference point, determine whether or not each of the subject range points is a noise point, and remove the noise point from the plurality of range points. An object recognizer uses the plurality of range points other than the noise points to recognize the object.

Abstract: A corresponding point searching method searches corresponding points in plural images, acquired by in-vehicle cameras, for each pixel in a reference image by using a predetermined first method, for example, the Viterbi algorithm. The method searches corresponding points in the plural images for each pixel in the reference image by using a predetermined second method, for example, an optical flow method. The method detects whether or not a search accuracy of the corresponding points in each region divided in the reference image obtained by the predetermined first method is not less than a reference value. When not less than the reference value, the method selects the corresponding points obtained by the predetermined first method. When less than the reference value, the searching method selects the corresponding points obtained by the predetermined second method. The searching method provides the corresponding points between the plural images with a high accuracy.

Abstract: When a travel path is to be generated for a vehicle, road surface lines (white lines, etc.) delimiting the traffic lane of the vehicle, and also external objects in the vehicle environment, are detected and registered as respective obstacles. Specific points are defined at appropriate locations on each obstacle, and the travel path is generated by connecting respective mid-point positions between opposed pairs of specific points, each pair defined on respective ones of an opposed (left-side, right-side) pair of the registered obstacles.

Abstract: A range correction device includes an image acquiring unit, a collimating unit, a disparity calculating unit, and an updating unit. The image acquiring unit acquires stereo images formed of a plurality of simultaneously captured images. The collimating unit collimates the stereo images acquired by the image acquiring unit, using a correction parameter for correcting a vertical displacement between stereo images. The disparity calculating unit calculates a distribution of horizontal disparities between the stereo images from the stereo images collimated by the collimating unit. The updating unit calculates a distribution of vertical displacements between the stereo images on the basis of the stereo images and the distribution of horizontal disparities calculated by the disparity calculating unit and updates the correction parameter on the basis of the distribution of the calculated vertical displacements.

Abstract: A corresponding point searching method searches corresponding points in plural images, acquired by in-vehicle cameras, for each pixel in a reference image by using a predetermined first method, for example, the Viterbi algorithm. The method searches corresponding points in the plural images for each pixel in the reference image by using a predetermined second method, for example, an optical flow method. The method detects whether or not a search accuracy of the corresponding points in each region divided in the reference image obtained by the predetermined first method is not less than a reference value. When not less than the reference value, the method selects the corresponding points obtained by the predetermined first method. When less than the reference value, the searching method selects the corresponding points obtained by the predetermined second method. The searching method provides the corresponding points between the plural images with a high accuracy.

Abstract: In an object recognition apparatus, a range point acquirer irradiates each of irradiation areas arranged in a horizontally and vertically extending grid and forming a detection area for detecting a target with laser light and receives the reflected light from the respective irradiation areas, thereby acquiring a plurality of range points representing per-irradiation area coordinates of the target. A noise remover is configured to, based on either or both of degrees of angle proximity and degrees of distance proximity between a plurality of subject range points to be determined whether to be a noise point, of the plurality of range points, as viewed from a reference point, determine whether or not each of the subject range points is a noise point, and remove the noise point from the plurality of range points. An object recognizer uses the plurality of range points other than the noise points to recognize the object.

Abstract: In an object identification device, each score calculator extracts a feature quantity from the image, and calculates a score using the extracted feature quantity and a model of the specified object. The score represents a reliability that the specified object is displayed in the image. A score-vector generator generates a score vector having the scores as elements thereof. A cluster determiner determines, based on previously determined clusters in which the score vector is classifiable, one of the clusters to which the score vector belongs as a target cluster. An object identifier identifies whether the specified object is displayed in the image based on one of the identification conditions. The one of the identification conditions is previously determined for the target cluster determined by the cluster determiner.

Abstract: In an object identification device, each score calculator extracts a feature quantity from the image, and calculates a score using the extracted feature quantity and a model of the specified object. The score represents a reliability that the specified object is displayed in the image. A score-vector generator generates a score vector having the scores as elements thereof. A cluster determiner determines, based on previously determined clusters in which the score vector is classifiable, one of the clusters to which the score vector belongs as a target cluster. An object identifier identifies whether the specified object is displayed in the image based on one of the identification conditions. The one of the identification conditions is previously determined for the target cluster determined by the cluster determiner.

Abstract: When a travel path is to be generated for a vehicle, road surface lines (white lines, etc.) delimiting the traffic lane of the vehicle, and also external objects in the vehicle environment, are detected and registered as respective obstacles. Specific points are defined at appropriate locations on each obstacle, and the travel path is generated by connecting respective mid-point positions between opposed pairs of specific points, each pair defined on respective ones of an opposed (left-side, right-side) pair of the registered obstacles.