Nippon Telegraph and Telephone Corporation

Ntt Corporation

Yuki Yokohata

Manabu Yoshida

Ippei Shake

Atsuhiko Maeda

Takahiro Hata

Kohei Mori

Kouhei Mori

Kazuaki Obana

Aki Hayashi

Satoshi Fukada

A driving assistance device includes a hardware processor and a memory, in which the hardware processor is configured to execute: acquiring image data captured in a vehicle and sensor data relating to a driving operation; converting an image in each frame included in the image data into an image feature amount indicated by the image; combining the image feature amount and the acquired sensor data; performing, based on the combined data, a learning process for a driving assistance information learning model used when a target value relating to the driving operation by a driver of the vehicle is generated from the image feature amount included in the combined data; and generating, when new image data captured in the running vehicle is acquired, the target value relating to the driving operation based on the image feature amount converted from the acquired new image data and the driving assistance information learning model.

Driving assistance device and method, and storage medium in which program is stored

An estimation method includes acquiring sensor information acquired by a sensor mounted on a first vehicle belonging to a vehicle line, acquiring position information on a location of the first vehicle, and estimating a cause of the vehicle line by using the sensor information and the position information. The estimating of the cause includes estimating the cause by using information on a facility or a feature present near the first vehicle, information indicating a state of the first vehicle, information on an object present ahead of the first vehicle included in the sensor information, or information on a road that affects traveling. The information on the facility or the feature is searched based on the position information, the information on the object is estimated based on the sensor information, and the information on the road is searched based on the position information.

Estimation method, estimation apparatus and estimation program of cause of line of vehicles

A position estimation unitestimates, for each movement in a predetermined section, a plurality of position candidates of a position estimation target on the basis of position information and sensor information. A position determination unitevaluates, for each movement in the predetermined section, on the basis of the plurality of position candidates of the position estimation target obtained by the movement in the predetermined section, whether the position information used to estimate the position candidates has an error caused by any of a position of a GPS satellite, a position of a mobile body in a real space, or the mobile body or does not have any error caused thereby. The position determination unitdetermines a final output value of the position of the position estimation target on the basis of a result obtained by removing, from the plurality of estimated position candidates of the position estimation target in the plurality of times of the movement in the predetermined section, a position candidate of the position estimation target estimated in the movement in the predetermined section that has been evaluated to have the error.

Position estimation method, position estimation device, and position estimation program

A technique of estimating, based on a camera image captured from a mobile object, the position coordinates of an ambient object or the mobile object itself is offered. A plurality of camera images that are captured at different geographical locations and contain at least one identical stationary object are acquired; position coordinates of the imaging locations of the corresponding camera images are acquired; and the position coordinates of the stationary object are estimated based on the position coordinates of the imaging locations and gaze vectors oriented from a camera to the stationary object in each of the camera images. Alternatively, a camera image that contains at least two stationary objects having position coordinates that are known is acquired; and the position coordinates of a location at which the camera image is captured are estimated based on the position coordinates of each of the stationary objects and a gaze vector oriented from the camera to each of the stationary objects in the camera image.

Position coordinates estimation device, position coordinates estimation method, and program

A lane pricing technique for charging a mobile body traveling on a road for use of a lane is provided. A lane pricing device according to one embodiment is configured to: acquire from a mobile body traveling on a road, at least one of position information of a mobile body measured based on a positioning signal, and/or a camera image that is acquired by capturing an image from the mobile body and includes a part of a lane in which the mobile body is moving; specify, based on at least one of the position information and/or the camera image, a lane in which the mobile body is moving; acquire lane identification information for identifying a specified lane along with time information indicative of time when the mobile body is moving; and determine and output a toll to be charged to the mobile body in units of lanes based on the lane identification information and the time information.

Lane pricing system, lane pricing device, method, and program

A sidewalk information generation device includes a thinning unit configured to perform thinning processing for extracting, from image data indicating an area of a sidewalk, a centerline in a width direction of the area of the sidewalk, a segmentation unit configured to perform segmentation processing for dividing the centerline extracted by the thinning unit in a longitudinal direction to generate a plurality of lines, and a vectorization unit configured to convert each of the plurality of lines generated by the segmentation unit to vector data indicating a coordinate sequence of a plurality of line segments.

Sidewalk information generation device, method and program

A sidewalk network information generation device in an embodiment includes a sidewalk centerline data storage device configured to store sidewalk centerline data indicating a plurality of sidewalk centerlines, a detection unit configured to detect an end point and a corner point of each of the plurality of sidewalk centerlines from the sidewalk centerline data stored in the sidewalk centerline data storage unit, and a link information generation unit configured to select, from among the end points and the corner points of the plurality of sidewalk centerlines detected by the detection unit, first coordinates indicating an end point or a corner point of a first sidewalk centerline and second coordinates indicating an end point or a corner point of a second sidewalk centerline within a certain distance from the first coordinates, and generate link information for linking the plurality of sidewalk centerlines on the basis of the selected first and second coordinates.

Sidewalk network information generation device, method and program

A technology is provided whereby a lane can be correctly estimated without relying on lane markers. A shape indicating a road region is extracted from image data obtained by capturing images in the progression direction of a vehicleand, on the basis of information indicating the shape, the angle of inclination for one contour line, the center-of-gravity coordinates for a diagram indicating the shape of the road region, the angle between two consecutive contour lines across one vertex of the diagram indicating the shape, and the area of the diagram indicating the shape are calculated as feature values for the shape of the road region. In addition, the lane in which the vehicleis traveling can be estimated by determining whether or not the calculated feature values are included in a threshold value range preset for each lane.

Lane estimation device, method, and program

The traffic flow estimation apparatus acquires images and position information and speed information, the images being captured at different timings by a first moving object that is in motion in a target area and including a second moving object around the first moving object, the position information and speed information being of the first moving object at the timings; estimates a lane in which the second moving object is in motion; and estimates a traffic flow for each lane in the target area based on the speed information of the first moving object, the information indicative of a change over time of positions of the second moving object, and the lanes in which the first moving object and the second moving object are in motion.

Traffic flow estimation apparatus, traffic flow estimation method, traffic flow estimation program, and storage medium storing traffic flow estimation program

A crosswalk detection device according to an embodiment includes a processor, and the processor configured to perform image scanning processing for scanning aerial image data in unit of window, multiple line segment creation processing for creating a plurality of line segments corresponding to a distance based on a dimension of a crosswalk in any direction within a region scanned in the aerial image data, first calculation processing for calculating an absolute value of a first derivative value indicating a difference in brightness between both ends of the line segment and calculating an average value of the absolute value of the first derivative value for each angle, second calculation processing for calculating an absolute value of a second derivative value indicating a difference between a difference in brightness between a first end and an intermediate point of the line segment and a difference in brightness between the intermediate point and a second end of the line segment and calculating an average value of the absolute value of the second derivative value for each angle, and crosswalk determination processing for determining that coordinates of each of the line segments are coordinates of the crosswalk based on a calculation result.

Growing community of inventors

Musashino, Japan

Yuki Yokohata