摘要:
Provided is a reliability evaluation method and apparatus to evaluate the reliability of map information. The apparatus includes an evaluation object value acquisition unit that acquires an evaluation object value from map information stored in a storage medium. A measurement value acquisition unit acquires measurement values for the evaluation object value using a sensor installed in a vehicle. After acquiring the measurement values, a reliability evaluation unit that selects a reliability evaluation method to evaluate the reliability of the evaluation object value based on a current measured value and the dispersion of the measured values.
摘要:
Provided is a driving support device and method that specifies the reliability of information used in a driving support device. The driving support device includes a storage medium that stores one or more programs and accuracy information that specifies the reliability of information of various elements used by one of the programs to provide driving support. The driving support device also includes an execution target program specification unit that specifies what program from the one or more programs is to be executed as the execution target program. An element selection unit selects an element that corresponds to the specified execution target program from the various elements. The device also includes a reliability specification unit that specifies the reliability of information used in the target execution program based on the accuracy information of the selected element.
摘要:
Provided is a driving support system that includes an image recognition unit that performs image recognition processing to recognize if a recognition object associated with any of the support processes is included in image data captured by an on-vehicle camera and a recognition area information storage unit that stores information regarding a set recognition area in the image data that is set depending on a recognition accuracy of the recognition object set for execution of the support process. A candidate process extraction unit is also included for extracting at least one execution candidate support process from the plurality of support processes and a support process execution management unit that allows execution of the extracted execution candidate support process on a condition that a position in the image data of the recognition object recognized by the image recognition processing is included in the set recognition area.
摘要:
A vehicle stabilization control device includes: an actual turning state quantity acquisition unit that acquires an actual turning state quantity indicating an actual turning state of a vehicle; a curve information acquisition unit that acquires the shape of a curve ahead of the vehicle; a vehicle speed acquisition unit that acquires speed of the vehicle; and a curve traverse possibility determination unit that determines a possibility that the vehicle can stably traverse the curve, based on the curve shape and speed of the vehicle; a control quantity computation unit that, to control braking force on each wheel and suppress understeering, computes a target control quantity for each wheel, based on the actual turning state quantity and on the possibility that the vehicle can stably traverse the curve; and a control unit controlling the braking force for each wheel, based on the target control quantity for each wheel.
摘要:
A target vehicle speed for traveling a predetermined road section ahead of a host vehicle is obtained, and an acceleration gear ratio, which is a gear ratio for accelerating the host vehicle to a vehicle speed faster than the target vehicle speed after traveling through the predetermined road section, is also obtained. If a driving support control settings indicates that execution of a gear ratio control is permitted, a gear ratio of the host vehicle is set to the acceleration gear ratio before the host vehicle reaches a start point of the predetermined road section. If the driving support control settings indicate that execution of a deceleration control using the brake portion is permitted, a braking portion is controlled so as to decelerate a vehicle speed of the host vehicle to the target vehicle speed before the host vehicle reaches the start point of the predetermined road section.
摘要:
A target vehicle speed at a predetermined position ahead of a host vehicle is obtained, and a plurality of deceleration patterns with different deceleration schemes is obtained for decelerating the host vehicle to the target vehicle speed. Based on a driving operation for controlling speed of the host vehicle, a deceleration pattern is selected from the plurality of deceleration patterns. Using the selected deceleration pattern as a reference, the vehicle speed of the host vehicle is reduced to the target vehicle speed before the host vehicle reaches the predetermined position.
摘要:
An image processing system temporarily stores, as processing target captured images, captured images whose image-capturing positions are included in a predetermined region. The system calculates similarity degrees of the processing target captured images, selects the processing target captured images whose similarity degrees are different from each other as useful images, and extracts image feature points from each of the useful images. The system generates image feature point data that includes the extracted image feature points, generates reference data used when scenic image recognition is performed by associating the generated image feature point data with an image-capturing position at which the image is captured to obtain the captured image corresponding to the image feature point data, and creates a reference data database.
摘要:
An image processing system inputs a captured image of a scene viewed from a vehicle, extracts image feature points from the captured image, and obtains image-capturing situation information indicating a possibility that a specific subject is included in the captured image. The system determines importance degrees of the extracted image feature points based on the image-capturing situation information and generates image feature point data using the extracted image feature points based on the importance degrees. The system generates reference data by associating the image feature point data with image-capturing attribute information and creates a reference data database. The image-capturing attribute information includes an image-capturing position at which the image is captured to obtain the captured image corresponding to the image feature point data.
摘要:
An image processing system inputs a captured image of a scene viewed from a vehicle in a predetermined road section and an image-capturing position at which the image is captured. The system uses a given position in the predetermined road section as a specific position, and sets a target vehicle movement amount at the specific position, for passing through the predetermined road section. The system generates reference image data from the captured image obtained at the specific position. The system generates reference data that is used when scenic image recognition is performed, by associating the reference image data with the specific position and the target vehicle movement amount at the specific position, and generates a reference data database that is a database of the reference data.
摘要:
A scene matching reference data generation system inputs a set of probe data. The set of the probe data includes captured images sequentially obtained by a plurality of probe cars and the vehicle positions of the probe cars. The system temporarily stores the captured images, evaluates accuracy reliability degrees of the image-capturing positions of the captured images, and assigns the accuracy reliability degrees to the captured images. The system selects, as a plurality of processing target captured images, a plurality of the captured images having accuracy reliability degrees equal to or higher than a first predetermined degree, extracts image feature points from the selected processing target captured images, and generates image feature point data based on the extracted image feature points. The system generates reference data for scene matching by associating the generated image feature point data with a reference image-capturing position corresponding to the generated image feature point data.