Abstract: An adhered-substance detecting apparatus capable of detecting adhered substances such as water droplets, mud, and dust, including those with ambiguous outlines, which adhere to, for example, a lens for an imaging apparatus, and a vehicle system equipped with the adhered-substance detecting apparatus are provided.

Abstract: A vehicle-mounted image processing device 1000 acquires an image around a host vehicle 10, senses a feature amount of a target object present on a road surface from the image, and relative position coordinates with respect to the host vehicle 10, acquires information of a three-dimensional object around the host vehicle 10 and relative position coordinates of the three-dimensional object, distinguishes whether the feature amount is a feature amount of a feature on the road surface or a feature amount of a feature on the three-dimensional object by using a positional relationship between the feature amount and the three-dimensional object, and recognizes the target object by using a feature on the road surface. As a result, a vehicle-mounted image processing device, which is capable of avoiding misrecognition of a part of a three-dimensional object as a target object when sensing the target object present on a road surface such as a parking bay by using a camera image, is provided.

Abstract: A parking assistance device for resetting a parking path when an obstacle is on the parking path includes a pull-out path computing unit that computes a pull-out path for pulling the vehicle out of the parking space based on parking space information and constraints regarding vehicle behavior, a candidate connection position setting unit that sets a plurality of candidate connection positions on the pull-out path, a reachable path computing unit that computes a reachable path for allowing the vehicle to reach at least one of the candidate connection positions from the initial position, a parking path setting unit that sets a parking path of from the initial position to the parking space by connecting the pull-out and reachable paths, and a path resetting unit that computes a parking path of from the stop position to the parking space, and sets the computed parking path as a new parking path.

Abstract: A parking assistance device includes a parking direction specification unit specifying a parking direction in a case where a subject vehicle is parked at a parking region, an obstacle detection unit detecting an obstacle, a detection range setting unit setting a detection range for detecting a bearing of the obstacle, a division unit dividing the detection range in a direction associated with the specified parking direction and generating plural divided ranges, a bearing calculation unit calculating a bearing of the detected obstacle, which is a bearing of a side surface of the obstacle which extends in the parking direction, for each of the divided ranges and calculating an average value of the bearings which are respectively calculated for the divided ranges, and a parking position setting unit setting a parking position where the subject vehicle is parked at the parking region based on the calculated average value.

Abstract: An apparatus for recognizing a division line on a road from an image captured by a camera includes: a processing area setting unit to set a processing area to the image; a statistics calculation unit to calculate statistics of the image in the processing area; a threshold value setting unit to set a plurality of threshold values on the basis of the statistics; a division line feature point extraction unit to classify a plurality of pixels contained in the image on the basis of the white line threshold value and the road surface threshold value and extracts feature points of the division line on the basis of classification results of the plurality of pixels; and a division line decision unit configured to decide the division line on the basis of the feature points extracted by the division line feature point extraction unit.

Abstract: A vehicle external recognition extracts a feature point from an image including an environment around a vehicle; measures a distance from the vehicle to the feature point based on a movement of the feature point; extracts, as a first road surface area, a local area judged as a road surface based on distance information to the feature point and a position of the feature point in the image from among a plurality of local areas in the image; calculates a multi-dimensional image feature amount including color information for each of the plurality of local areas, and similarity to the first road surface area using the image feature amount with respect to a no-road-surface-extracted area(s) from among the plurality of local areas; extracts a second road surface area from the no-road-surface-extracted area(s) based on the similarity; and recognizes a travelable area using the first and the second road surface areas.

Abstract: A parking assist apparatus 1 of the present invention assists parallel parking of an own vehicle 21. The parking assist apparatus 1 includes: a first route calculation unit 11 configured to calculate a first route for moving the own vehicle 21 from a target parking position P1 to a virtual departure position P3 based on a parking space and a constraint condition of own vehicle behavior; a second route calculation unit 12 configured to calculate a second route for moving the own vehicle 21 from an initial position P0 where parking assistance is started to the virtual departure position P3; and a parking route setting unit 13 configured to set a parking route of the own vehicle 21 with use of the first route and the second route.

Abstract: An in-vehicle processing device comprises a sensor input unit which acquires sensor information as an output of a sensor which acquires information around a vehicle, a movement information acquisition unit which acquires vehicle movement information as information related to a movement of the vehicle, a log recording unit which records information based on the vehicle movement information and the sensor information in a storage unit, a map generation unit which creates an environmental map including a drivable area where the vehicle can travel based on determination of static objects that do not move and mobile objects that can move by using information based on the vehicle movement information and the sensor information recorded in the storage unit, and a route calculation unit which calculates a travel route of the vehicle by using the environmental map, wherein the environmental map includes information of a parking position as a position of parking the vehicle.

Abstract: A subject of the present invention is to obtain an outside recognition apparatus for vehicle making it possible to improve accuracy of a distance measurement method based on tracking of a feature point on a camera image. An on-board outside recognition apparatus of the present invention extracts a feature point from an image including an environment around a user's own vehicle, measures a three-dimensional position of the feature point based on movement of the feature point tracked in time series on the image and calculates a foot position of the feature point on the image from the three-dimensional position of the feature point is performed. Then, the on-board outside recognition apparatus extracts a road surface area where the user's own vehicle can travel, from the image using a degree of similarity of a texture of the image, and judges a feature point the foot position of which is judged not to be included in the road surface area to be highly reliable.

Abstract: Provided is an on-vehicle processing device that can estimate the position of a vehicle with higher accuracy. A storage unit stores a parking lot point group including a plurality of coordinates of points of a part of an object in a parking lot coordinate system. A sensor input unit acquires peripheral information from a camera. A movement information acquisition unit acquires movement information. A local peripheral information creation unit generates local peripheral information expressing second point group data including a position of the vehicle in a local coordinate system and a plurality of coordinates of points of a part of the object in the local coordinate system on the basis of the peripheral information and the movement information.

Abstract: A tracking device includes: an imaging unit that inputs an image into an image input unit; a first moving body detection unit that calculates an optical flow and detects a position and a direction of movement of a moving body based on the calculated optical flow; a second moving body detection unit that detects a position and a direction of movement based on a plurality of overhead images generated; a third moving body detection unit that detects a position and a direction of movement by integrating detection results from the first and second moving body detection units; a tracked moving body confirmation unit that determines a moving body to be tracked based on detection results from the first to third moving body detection units; an estimation unit that estimates a future position and direction of movement; and a tracking unit that tracks the tracked moving body and identifies a position.

Abstract: The objective of the present invention is to provide an object detection method such that an object such as a vehicle can be detected from an image captured by an on-board camera even when a lens of the on-board camera is dirty. In order to achieve the objective, in this object detection method for detecting an object included in a captured image, an original image including the object to be detected is prepared from the captured image, a processed image is generated from the prepared original image by applying predetermined processing to the original image, and learning regarding restoration of an image of the object to be detected is performed using the original image and the processed image.

Abstract: The present invention addresses the problem of enabling an accurate determination of line type using a plurality of cameras.

Abstract: It is an object of the present invention to obtain a parking support apparatus capable of calculating a parking route suited for the circumstances and the needs. A parking support apparatus 1 according to the present invention sets a plurality of candidate connection positions along a reverse direction route for a driver's own vehicle to leave from a target parking position, calculates a first connection route capable of reaching any one of the candidate connection positions, and calculates a first parking route by using the first connection route and the reverse direction route.

Abstract: An arithmetic apparatus includes: a sensor acquisition unit that collects sensor information about the surroundings of a vehicle; a feature point extraction unit that extracts a feature point of an object; a target point detection unit that expresses the position of the feature point with spatial coordinates and detects it as a target point; a road edge presumption unit that presumes a segment between the target points, which are continuously aligned, as a road edge; and a blockade judgment unit that judges whether or not to cancel the road edge, on the basis of information about an area behind the presumed road edge, which is obtained from the sensor information, where the area behind the road edge is an area opposite the sensor at the other side of the presumed road edge.

Abstract: A vehicle external recognition extracts a feature point from an image including an environment around a vehicle; measures a distance from the vehicle to the feature point based on a movement of the feature point; extracts, as a first road surface area, a local area judged as a road surface based on distance information to the feature point and a position of the feature point in the image from among a plurality of local areas in the image; calculates a multi-dimensional image feature amount including color information for each of the plurality of local areas, and similarity to the first road surface area using the image feature amount with respect to a no-road-surface-extracted area(s) from among the plurality of local areas; extracts a second road surface area from the no-road-surface-extracted area(s) based on the similarity; and recognizes a travelable area using the first and the second road surface areas.

Abstract: A section line recognition device is realized which can determine a line type of a section line in a road surface with high accuracy. In step 301, a feature amount is extracted from an image captured by each camera. This step corresponds to a process of a feature point extraction unit. In the next step 302, the extracted feature amount is transformed into bird's-eye view coordinates which is common coordinates. This step corresponds to a process of a coordinates transformation unit. Next, in step 303, a camera to be selected is determined. This step is a process of a camera determination unit. Next, in step 304, the state transition at the appearance position of the feature point on the bird's-eye view coordinates is determined using feature point coordinates of the camera selected in step 303. This step is a process of a state transition determination unit. Finally, in step 305, the line type is determined. This step is a process of a line type determination unit.

Abstract: A parking support apparatus includes: a first parking space setting unit that sets a first parking space including information of a parking position and a parking angle of a vehicle at a parking completion position; a second parking space setting unit that calculates a second parking space, which is obtained by correcting the parking angle of the first parking space, based on information of measurement of the first parking space by using a vehicle surrounding sensor which measures a surrounding area of the vehicle; a parking space determination unit that calculates reliability of the second parking space and determines to use the first parking space or the second parking space based on the calculated reliability; and a parking route generation unit that generates a parking route to the first parking space or the second parking space determined by the parking space determination unit.

Abstract: An autonomous driving control device and an autonomous driving path computation method capable of computing a driving path without extremely changing a movement of a steering wheel during autonomous driving. A parking control device computes a parking path for automatically parking a vehicle, and includes an acceleration section transition curve computing unit that computes an acceleration section transition curve based on a target steering speed set in advance and an acceleration section target vehicle speed, a deceleration section transition curve computing unit that computes a deceleration section transition curve based on the target steering speed and a deceleration target vehicle speed, and a parking path computing unit that computes a parking path using the acceleration section transition curve and the deceleration section transition curve. The parking path is computed by setting the deceleration section target vehicle speed faster than the acceleration section target vehicle speed.

Abstract: A vehicle-mounted image processing device 1000 acquires an image around a host vehicle 10, senses a feature amount of a target object present on a road surface from the image, and relative position coordinates with respect to the host vehicle 10, acquires information of a three-dimensional object around the host vehicle 10 and relative position coordinates of the three-dimensional object, distinguishes whether the feature amount is a feature amount of a feature on the road surface or a feature amount of a feature on the three-dimensional object by using a positional relationship between the feature amount and the three-dimensional object, and recognizes the target object by using a feature on the road surface. As a result, a vehicle-mounted image processing device, which is capable of avoiding misrecognition of a part of a three-dimensional object as a target object when sensing the target object present on a road surface such as a parking bay by using a camera image, is provided.