Abstract: A captured image including a preferential calibration index arranged in an exclusive region in a first plane and a non-preferential calibration index arranged in a common region is obtained. First, the coordinate position of the preferential calibration index is detected, and then the coordinate position of the non-preferential calibration index is calculated based on the positional relationship with the detected preferential calibration index. A homography between a captured-image surface of the image surface and the first plane is calculated based on the actual coordinate positions and the calculated coordinate positions representing the coordinates of at least four points, and camera calibration is performed using the homography.

Abstract: Planar calibration indices (c1) including coordinate information of at least four points are placed on a first plane (S1), and an image plane of the camera image including the calibration indices is input as a second plane (S2). Points (c2) existing on the second plane and corresponding to predetermined portions of the calibration indices are specified, and homography between the first plane and the second plane is computed, on the basis of the corresponding relationship of the at least four points included commonly in the first plane and the second plane, so that the camera image is calibrated. For example, a device is mounted on a vehicle, and four points, whose arrangement on a plane in 3D space is known, are used as calibration indices, and corresponding four points on the camera image, which correspond to them respectively, is achieved automatically.

Abstract: A captured image including a preferential calibration index arranged in an exclusive region in a first plane and a non-preferential calibration index arranged in a common region is obtained. First, the coordinate position of the preferential calibration index is detected, and then the coordinate position of the non-preferential calibration index is calculated based on the positional relationship with the detected preferential calibration index. A homography between a captured-image surface of the image surface and the first plane is calculated based on the actual coordinate positions and the calculated coordinate positions representing the coordinates of at least four points, and camera calibration is performed using the homography.

Abstract: An object recognition apparatus that processes images, as acquired by an imaging means (10) mounted on a moving object, in a first image plane and a second image plane of different points of view, and recognizes an object in the vicinity of the moving object. The object recognition apparatus comprises: a feature point detection means (42) that detects feature points in first and second image planes of an object image; a fundamental matrix determination means (43a) that determines, based on calculation of an epipole through the auto-epipolar property, a fundamental matrix that expresses a geometrically corresponding relationship based on translational camera movement, with not less than two pairs of feature points corresponding between the first and second image planes; and a three-dimensional position calculation means (43b) that calculates a three-dimensional position of an object based on the coordinates of the object in the first and second image planes and the determined fundamental matrix.

Abstract: There is provided an object recognizing apparatus capable of recognizing a shape of an object in a stable manner with a small amount of calculation, even when data of non-target object is mixedly contained. The object recognizing apparatus includes an object detecting section, a shape model setting section 3, a conformance degree calculating section 4 and a profile shape determining section 5. The shape model setting section 3 extract arbitrarily samples of a group of samples detected by the object detecting section 1 and constituting surface shape information and then sets shape models. The conformance degree calculating section 4 calculates the conformance degree of each shape model. The setting of the shape model and calculation of conformance degree are effected up to a predetermined maximum number of times.

Abstract: There is provided an obstacle detection apparatus for detecting an obstacle based on an image of periphery of a vehicle and a distance to an obstacle present in the vehicle's periphery.

Abstract: A calibration device for calibrating a range image sensor, detecting a distance of each direction within a detection range and generating a range image data, in a state where the range image sensor is attached at a mobile body, the calibration device includes a data receiving portion for receiving a calibration-subject data including a calibration target, which is set within the detection range and includes a first plane surface and a second plane surface, from the range image sensor, a plane surface specifying portion for specifying each of the first and second plane surfaces in a three-dimensional reference coordinate system, a normal vector calculating portion for three-dimensionally calculating a normal vector of each of the first and second plane surfaces, and a rotation calculating portion for three-dimensionally calculating a rotation of the range image sensor on the basis of an already-recognized posture information and the normal vector.

Abstract: An obstruction detecting apparatus includes a camera capturing a surrounding of a vehicle, a projective transformation means projection-transforming one frame of captured images, captured by means of the camera, respectively on at least two imaginary planes, so as to generate transformed images, viewed downwardly from an above viewpoint, the imaginary planes having a first imaginary plane being set at the same level as a road surface and/or at least one second imaginary plane being set at a different level from the road surface to be in parallel with the road surface, and a three-dimensional object area extracting means extracting image areas from the transformed images, and extracting an area, at which the image areas overlap when the transformed images are superimposed, and which extends along a radially outward direction from an optical center, as a three-dimensional object area, at which an image of a three-dimensional object exists.

Abstract: A bird's-eye image generating apparatus includes a first image receiving portion for receiving a first image, a second image receiving portion for receiving a second image at a second position, a first projective transforming portion for executing a projective transformation to the first image so as to be a first transformed image and for correcting the first transformed image so as to be a first corrected image at the second position, a second projective transforming portion for executing the projective transformation to the second image so as to be in a second transformed image, a three-dimensional object range extracting portion for extracting a three-dimensional object range in which a three-dimensional object exists, and a projective distortion correcting portion for correcting the three-dimensional object range by compressing so as to be a second corrected image.

Abstract: A parking assist device detecting a parking stall line from an image, which is captured by a capturing portion; setting a parking target position on the basis of the parking stall line; and assisting the vehicle to travel to the parking target position; the parking assist device includes a vehicle detecting portion for detecting a movement of the vehicle, a memorizing portion for memorizing the movement detected by the vehicle detecting portion, as a vehicle moving trajectory, a temporary parking target position estimating portion for assuming a temporary parking target position on the basis of variations of the vehicle moving trajectory, which has been memorized by the memorizing portion, and a parking stall line searching area setting portion for setting a parking stall line searching area, within which a parking stall line is searched on the basis of the temporary parking target position.

Abstract: A parking assist device detecting a parking stall line from an image, which is captured by a capturing portion; setting a parking target position on the basis of the parking stall line; and assisting the vehicle to travel to the parking target position; the parking assist device includes a vehicle detecting portion for detecting a movement of the vehicle, a memorizing portion for memorizing the movement detected by the vehicle detecting portion, as a vehicle moving trajectory, a temporary parking target position estimating portion for assuming a temporary parking target position on the basis of variations of the vehicle moving trajectory, which has been memorized by the memorizing portion, and a parking stall line searching area setting portion for setting a parking stall line searching area, within which a parking stall line is searched on the basis of the temporary parking target position.

Abstract: There is provided an obstacle detection apparatus for detecting an obstacle based on an image of periphery of a vehicle and a distance to an obstacle present in the vehicle's periphery.

Abstract: To provide a vehicle vicinity monitoring system enabling an obstacle border to be extracted, even under dark conditions, without any adverse effect caused by an obstacle shadow created by the illuminating of vehicle illumination devices. The vehicle vicinity monitoring system captures images of the vicinity of the vehicle using an image-capturing device 3, and uses a notification device 6 to provide vehicle occupants with information concerning obstacles in the vicinity of the vehicle. A primary lighting device 4 and/or a secondary lighting device 4 are provided to the vehicle. The primary lighting device 4 directs light upon shadows cast within the imaging field of the image-capturing device 3 as a result of the illumination device being illuminated. The secondary lighting device 4 is a lighting device for projecting light in a prescribed pattern within the imaging field of the image-capturing device in order to confirm the existence of an obstacle.

Abstract: A calibration device for calibrating a range image sensor, detecting a distance of each direction within a detection range and generating a range image data, in a state where the range image sensor is attached at a mobile body, the calibration device includes a data receiving portion for receiving a calibration-subject data including a calibration target, which is set within the detection range and includes a first plane surface and a second plane surface, from the range image sensor, a plane surface specifying portion for specifying each of the first and second plane surfaces in a three-dimensional reference coordinate system, a normal vector calculating portion for three-dimensionally calculating a normal vector of each of the first and second plane surfaces, and a rotation calculating portion for three-dimensionally calculating a rotation of the range image sensor on the basis of an already-recognized posture information and the normal vector.

Abstract: A device for detecting a road traveling lane, which is capable of stably defining a position of a boundary of a traveling lane. The device has edge point detection means (ED) for detecting a plurality of edge points in a contour on an image, edge histogram producing means (HD) for producing a vertical edge histogram for horizontal elements of the plurality of edge points, block marking line determination means (BD) for determining presence and absence of a block-like marking line on the basis of periodicity of distribution and a combination of distributions of plus edges and minus edges in the vertical edge histogram, and lane boundary edge detection means (MD) for detecting vertical edge points present outside (relative to the center of the traveling lane) of a region where the block-like marking line is present.

Abstract: An object recognition apparatus that is capable of consistently recognizing the shape of an object in the periphery of a moving body using a small amount of computation even when data for an extraneous object are introduced, and of calculating the positional relationship of both objects and satisfactorily reporting the positional relationship. The object recognition apparatus for recognizing an object in the periphery of a moving object is configured as described below.

Abstract: To provide a parking assistance device for accurately detecting obstacles in the periphery of a parking zone; for detecting a parking space in which a vehicle can be parked without coming into contact with the obstacles; and for satisfactorily assisting a driving operation. The parking assistance device detects a stationary object present in the periphery of a vehicle, and assists in parking the vehicle.

Abstract: There is provided an object recognizing apparatus capable of recognizing a shape of an object in a stable manner with a small amount of calculation, even when data of non-target object is mixedly contained. The object recognizing apparatus includes an object detecting section , a shape model setting section 3, a conformance degree calculating section 4 and a profile shape determining section 5. The shape model setting section 3 extract arbitrarily samples of a group of samples detected by the object detecting section 1 and constituting surface shape information and then sets shape models. The conformance degree calculating section 4 calculates the conformance degree of each shape model. The setting of the shape model and calculation of conformance degree are effected up to a predetermined maximum number of times.

Abstract: An object recognition apparatus that processes images, as acquired by an imaging means (10) mounted on a moving object, in a first image plane and a second image plane of different points of view, and recognizes an object in the vicinity of the moving object. The object recognition apparatus comprises: a feature point detection means (42) that detects feature points in first and second image planes of an object image; a fundamental matrix determination means (43a) that determines, based on calculation of an epipole through the auto-epipolar property, a fundamental matrix that expresses a geometrically corresponding relationship based on translational camera movement, with not less than two pairs of feature points corresponding between the first and second image planes; and a three-dimensional position calculation means (43b) that calculates a three-dimensional position of an object based on the coordinates of the object in the first and second image planes and the determined fundamental matrix.

Abstract: A movable body circumstance monitoring apparatus includes element for capturing an image of a surrounding of a movable body depending upon movement of the movable body, deriving at least four feature points in a specified flat at the image, tracking the feature points in response to movement of the movable body from a first state to a second state, and specifying relative position and posture of the element for capturing the image at the first and second states in response to first flat coordinates of the feature points at the first state and second flat coordinates of the feature points at the second state based upon a tracking result.