Subaru Corporation

Akitaka Oko

A camera unit calibrating apparatus performs a predetermined measurement based on images acquired by imaging the same object from different viewpoints using cameras. The apparatus includes a collimator unit and a control unit that controls the collimator unit. The collimator unit includes collimators corresponding to the cameras respectively, collimator driving devices corresponding to the collimators respectively, a support unit that supports the collimators to allow the collimators to be translated individually within a predetermined plane, and a collimator control unit that controls the collimators and the collimator driving devices. The control unit controls each of the collimator driving devices to individually set a corresponding one of the collimators to a predetermined position and orientation, and cause each of collimated images produced by the collimators to be formed at a desired position within a range of an imaging area of a corresponding one of the cameras.

Camera unit calibrating apparatus and calibrating method

An image processing apparatus includes a first distance calculation unit, a second distance calculation unit, a correction amount calculation unit, and an image correction unit. The first distance calculation unit calculates a first distance to an imaging target based on first images which are generated by a first camera and included in stereo images. The second distance calculation unit calculates a second distance to the imaging target based on at least one of the stereo images. The correction amount calculation unit calculates, if a difference between pixel positions, each corresponding to the imaging target, in the respective first images is within a predetermined amount, a correction amount of a pixel position corresponding to the imaging target in an image based on the first and second distances. The image correction unit causes a position of a pixel value included in the image to move laterally based on the correction amount.

Image processing apparatus and image processing method

A camera unit calibrating apparatus performs measurement based on images of an object acquired from different viewpoints by cameras. The apparatus includes a collimator unit including collimators each corresponding to a camera, collimator driving devices corresponding to the collimators, plane mirrors reflecting collimated beams from the collimators in predetermined directions, mirror driving devices corresponding to the plane mirrors, a support unit supporting the collimators to allow the collimators to be translated individually within a predetermined plane and also supporting the plane mirrors swingably, and a collimator control unit controlling the collimators and the collimator and mirror driving devices; and a control unit controlling the collimator unit. The control unit controls the collimator and mirror driving devices to individually set the collimators and the plane mirrors to predetermined positions and orientations, and causes each collimated image to be formed at a desired position within a range of a camera's imaging area.

An image processing apparatus includes a sub-image generation unit, a luminance ratio map generation unit, and an electric heating wire pattern estimation unit. The sub-image generation unit generates sub-images by dividing a first image in a lateral direction. The first image is one of a left image and a right image that are captured by a stereo camera through a windshield provided with an electric heating wire. The luminance ratio map generation unit sequentially selects one of the sub-images and generates map data based on the selected sub-image and a second image. The map data indicates a ratio between luminance values. The second image is another of the left image and the right image. The electric heating wire pattern estimation unit performs an estimation of a wiring pattern of the electric heating wire based on the map data regarding each of the sub-images.

Image processing apparatus

An image processing apparatus includes a corresponding point calculator and a determination unit. The corresponding point calculator identifies corresponding points relating to an object based on left and right images in each stereo image. The corresponding points include a right image point in the right image and a left image point in the left image. The determination unit predicts a first position of the left image point in a second stereo image, and a second position of the right image point in a second stereo image, based on a position of the left image point in a first stereo image and a position of the right image point in the first stereo image, and determines whether the object is a mobile body based on a difference between the first position predicted and the first position identified, and a difference between the second position predicted and the second position identified.

A stereo camera apparatus includes a stereo camera, a speed sensor, and a control device. The control device includes one or more processors and one or more storage media. The one or more processors are configured to: detect corresponding points from a first image pair and a second image pair to be captured at different times by the stereo camera; divide each of images of the first image pair and the second image pair into regions; calculate, for each of the regions, a movement speed based on an external parameter by using one or more of the corresponding points included in the each of the regions; and calculate, for the each of the regions, a parallax correction value to cause a difference between the movement speed based on the external parameter and a movement speed detectable by the speed sensor to fall below a predetermined threshold.

Stereo camera apparatus and control device

An image processing device includes a rotation processor, a parallax image generator, and a rotation controller. The rotation processor makes rotation processing including rotating first left and right images in a stereo image, to generate second left and right images. The parallax image generator calculates corresponding left and right image points in the second left and right images, to generate a parallax image. The rotation controller obtains a coordinate point to calculate an amount of angular change in a rotation angle in the rotation processing. The coordinate point indicates relation of a first positional difference in a horizontal direction and a second positional difference in a vertical direction, between first and second positions. The first and second positions are respective positions of the left and right image points in the second left and right images.

Image processing device

A vehicle detection apparatus includes circuitry configured to cut out a region of interest in an image, calculate a composite feature quantity of the region of interest as a whole by dividing the region of interest into a plurality of divided regions, calculating a feature quantity of each of the divided regions, and combining the calculated feature quantities of the respective divided regions together, and perform, on the basis of the calculated composite feature quantity, filtering that discards the region of interest that is determinable as not being a wheel of a vehicle.

Growing community of inventors

Tokyo, Japan

Akitaka Oko