Abstract: A driving monitoring device (100) decides an applicable collision pattern that applies to a collision pattern of a case where a vehicle (200) collides with a mobile object, based on a velocity vector of the vehicle, a velocity vector of the mobile object, and so on. Subsequently, the driving monitoring device calculates a time until collision, which is a time taken until the vehicle collides with the mobile object, in the applicable collision pattern. Then, the driving monitoring device calculates a danger level of an accident in which the vehicle collides with the mobile object, based on the applicable collision pattern and the time until collision.

Abstract: In a data synchronization device (20), a first estimation unit (51) estimates as a first data range, a data range in which a vehicle is turning right or left, in moving image data (33). A second estimation unit (52) estimates as a second data range, a data range in which the vehicle is turning right or left, in acceleration data (34). A synchronization unit (53) performs a time-synchronization between the moving image data (33) and the acceleration data (34) based on a time range corresponding to the first data range estimated by the first estimation unit (51) and a time range corresponding to the second data range estimated by the second estimation unit (52).

Abstract: A reception unit (101) receives from each moving body among a plurality of moving bodies, moving body data indicating a measured position of each moving body which is a position of each moving body measured at each moving body and may include an error, and indicating a measured position of a surrounding object of each moving body which is a position of the surrounding object of each moving body measured at each moving body and may include an error. A correction data generation unit (102) generates for each moving body, correction data for correcting the error that may be included in the measured position of each moving body, with using measured positions of the plurality of moving bodies and measured positions of surrounding objects of the plurality of moving bodies indicated in a plurality of moving body data received from the plurality of moving bodies. A transmission unit (103) transmits to each moving body, the correction data for each moving body generated by the correction data generation unit (102).

Abstract: An information processing device includes a processor to execute a program; and a memory to store the program which, when executed by the processor, performs processes of, calculating braking time of a host vehicle; detecting reaction time of the driver of the host vehicle; specifying longer prediction time as the sum of the braking time and the reaction time becomes longer, the prediction time being a range of a time at which a collision between the host vehicle and a surrounding vehicle is predicted in the future; making a prediction of the position and speed of the host vehicle and the position and speed of the surrounding vehicle at a time point included in the prediction time; and predicting, from a result of the prediction, whether or not the host vehicle and surrounding vehicle will collide.

Abstract: In a data synchronization device (20), a first estimation unit (51) estimates as a first data range, a data range in which a vehicle is turning right or left, in moving image data (33). A second estimation unit (52) estimates as a second data range, a data range in which the vehicle is turning right or left, in acceleration data (34). A synchronization unit (53) performs a time-synchronization between the moving image data (33) and the acceleration data (34) based on a time range corresponding to the first data range estimated by the first estimation unit (51) and a time range corresponding to the second data range estimated by the second estimation unit (52).

Abstract: An action selection device (10) includes an action selection unit (22). The action selection unit (22) acquires from a memory (30), an action list (31) in which a requirement recognition area is associated with each action of a plurality of actions, the requirement recognition area indicating an area for which recognition by a sensor is required. The action selection unit (22) acquires from a peripheral recognition device (53), a recognition area (53a) recognized by sensors (53-1) that the peripheral recognition device (53) has. The action selection unit (22) selects from the action list (31), an action associated with the requirement recognition area included in the recognition area (53a).

Abstract: A driving monitoring device (100) decides an applicable collision pattern that applies to a collision pattern of a case where a vehicle (200) collides with a mobile object, based on a velocity vector of the vehicle, a velocity vector of the mobile object, and so on. Subsequently, the driving monitoring device calculates a time until collision, which is a time taken until the vehicle collides with the mobile object, in the applicable collision pattern. Then, the driving monitoring device calculates a danger level of an accident in which the vehicle collides with the mobile object, based on the applicable collision pattern and the time until collision.

Abstract: A blind spot identification unit (21) identifies a plurality of obstacles causing a blind spot in an area around a vehicle. An individual calculation part (231) calculates, as an individual probability, a probability of occurrence of a traffic accident at a target position with respect to the position of a target object which is each of the obstacles identified by the blind spot identification unit (21). A combined calculation part (232) calculates, as a combined probability, a probability of occurrence of a traffic accident at the target position with respect to each of the plurality of obstacles from the individual probability calculated by the individual calculation part (231).

Abstract: A blind spot identification unit (21) identifies a plurality of obstacles causing a blind spot in an area around a vehicle. An individual calculation part (231) calculates, as an individual probability, a probability of occurrence of a traffic accident at a target position with respect to the position of a target object which is each of the obstacles identified by the blind spot identification unit (21). A combined calculation part (232) calculates, as a combined probability, a probability of occurrence of a traffic accident at the target position with respect to each of the plurality of obstacles from the individual probability calculated by the individual calculation part (231).

Abstract: It is an object to obtain a high-resolution image generation apparatus that can generate a high-quality image by sorting out good portions from faulty portions in optical flow. The present invention includes: a hard disk that stores multi-viewpoint image information and parameter information of a base image and a plurality of reference images; an optical flow computation unit that extracts a plurality of pairs of the base image and a reference image, the plurality of pairs each including a different reference image, and computes optical flow for each pair; a depth information computation unit that computes depth information which indicates depth of each pixel of the base image for each pair, based on optical flow and the parameter information; and an optical flow sorting unit that determines whether or not each piece of pixel-based correspondence information included in the optical flow of each pair is to be used for improving a resolution of the base image, based on two pieces of the depth information.

Abstract: It is an object to obtain a high-resolution image generation apparatus that can generate a high-quality image by sorting out good portions from faulty portions in optical flow. The present invention includes: a hard disk that stores multi-viewpoint image information and parameter information of a base image and a plurality of reference images; an optical flow computation unit that extracts a plurality of pairs of the base image and a reference image, the plurality of pairs each including a different reference image, and computes optical flow for each pair; a depth information computation unit that computes depth information which indicates depth of each pixel of the base image for each pair, based on optical flow and the parameter information; and an optical flow sorting unit that determines whether or not each piece of pixel-based correspondence information included in the optical flow of each pair is to be used for improving a resolution of the base image, based on two pieces of the depth information.