Fuji Jukogyo Kabushiki Kaisha

Subaru Corporation

Seisuke Kasaoki

Hiroyuki Sekiguchi

Meguru Ito

A vehicle exterior environment recognition apparatus includes a computer configured to serve as a vehicle identifier, a candidate identifier, a shift amount deriving unit, a candidate remover, and a lamp determiner. The vehicle identifier identifies, from respective captured images, a preceding vehicle and a vehicle region occupied by the preceding vehicle. The candidate identifier identifies, as a light-emission source candidate, a candidate determinable as a light-emission source in the identified vehicle region. The shift amount deriving unit derives a shift amount in a predetermined period of the light-emission source candidate in the vehicle region. The candidate remover removes, from the light-emission source candidate identified by the candidate identifier, the light-emission source candidate in which the shift amount is equal to or greater than a predetermined shift amount threshold. The lamp determiner determines whether the light-emission source candidate, unremoved by the candidate remover, is a lighted lamp.

Vehicle exterior environment recognition apparatus

A vehicle exterior environment recognition apparatus includes a computer configured to serve as a vehicle identifier, a candidate identifier, a cover identifier, and a lamp determiner. The vehicle identifier identifies, from an image captured by an image-capturing unit, a preceding vehicle and a vehicle region occupied by the preceding vehicle. The candidate identifier identifies, as a light-emission source candidate, a candidate determinable as a light-emission source in the identified vehicle region. The cover identifier identifies a cover in the identified vehicle region. The cover covers the light-emission source. The lamp determiner determines whether the light-emission source candidate is a lighted lamp, based on a lighted-state determination threshold and one of the number of pixels and pixel area of the identified light-emission source candidate. The lighted-state determination threshold is based on one of the number of pixels and pixel area of the cover identified by the cover identifier.

A vehicle exterior environment recognition apparatus includes a computer configured to serve as a vehicle identifier, a candidate identifier, an overexposure identifier, a movement amount deriving unit, a moving overexposure identifier, an overexposure range setting unit, and a lamp determiner. The candidate identifier identifies a light-emission source candidate. The overexposure identifier identifies an overexposed light-emission source candidate. The movement amount deriving unit derives an amount of movement of the overexposed light-emission source candidate. The moving overexposure identifier identifies a moving overexposed light-emission source, when the amount of movement is equal to or greater than a threshold. The overexposure range setting unit sets an overexposure range with respect to the moving overexposed light-emission source. The lamp determiner determines whether the identified light-emission source candidate is a lighted lamp, based on different conditions between the light-emission source candidate in the overexposure range and that in a range other than the overexposure range.

A vehicle external environment recognition device includes a three-dimensional position deriving module that derives three-dimensional positions in real space of subject parts in images that are obtained by imaging a detection area, an object identifying module that groups the subject parts of which differences in the three-dimensional position are within a predetermined range to identify an object, an edge intensity deriving module that horizontally divides an area containing the object to set divided areas, and derives an edge average that is an average value of edge intensities based on a luminance value of each pixel within each of the divided areas; and a floating matter identifying module that compares the edge average with a predetermined threshold, and identifies the object to be likely floating matters when the edge average is less than the threshold.

Vehicle external environment recognition device

There are provided an environment recognition device and an environment recognition method. An exterior environment recognition device obtains an image in a detection area, generates a block group by grouping, based on a first relative relationship between blocks, multiple blocks in an area extending from a plane corresponding to a road surface to a predetermined height in the obtained image, divides the block group into two in a horizontal direction of the image, and determines, based on a second relative relationship between two divided block groups, whether the block group is a first person candidate which is a candidate of a person.

Exterior environment recognition device and exterior environment recognition method

There is provided a driving support apparatus. A recognition controller determines whether an object detected by processing a captured image by an object detection unit is a smoke-like object or not in a smoke-like object determination unit. When the detected object is determined to be the smoke-like object, the recognition controller checks a range distribution in a region of the smoke-like object, adds the result as attribute information of 'density', and transmits the resultant to a controller. The controller decides in a support operation level decision unit whether a pre-crash brake control can be executed or not and an intensity of an operation based on the attribute information of the smoke-like object. Thus, even if the smoke-like object is detected, an appropriate driving support process according to the condition can be executed.

Driving support apparatus

There are provided an environment recognition device and an environment recognition method. The environment recognition device obtains a luminance of each of a plurality of blocks formed by dividing a detection area; derives an edge direction based on a direction in which an edge of the luminance of each block extends; associates the blocks with each other based on the edge direction so as to generate an edge trajectory; groups a region enclosed by the plurality of edge trajectories as a target object; and determines the target object as a specific object.

Environment recognition device and environment recognition method

There are provided an environment recognition device and an environment recognition method. The device obtains position information of a target portion in a detection area, including a relative distance from a subject vehicle; groups continuous target portions into a target object of which position differences in a width direction vertical to an advancing direction of the vehicle and in a depth direction parallel to the advancing direction fall within a first distance; determines that the target object is a candidate of a wall, when the target portions forming the target object forms a tilt surface tilting at a predetermined angle or more with respect to a plane vertical to the advancing direction; and determines that the continuous wall candidates of which position differences in the width and depth directions among the wall candidates fall within a second predetermined distance longer than the first predetermined distance are a wall.

Growing community of inventors

Tokyo, Japan

Seisuke Kasaoki