Toyota Jidosha Kabushiki Kaisha

Kohei Shintani

Hiroaki Kawamura

Hisashi Matsuda

Yusuke Takeuchi

Daisuke Toyoda

The information processing device includes a processor, and the processor inputs information on a course on which the vehicle travels, setup information on a setup of the vehicle, and feedback information from a driver driving the vehicle into a learned model, and proposes an optimal setup when the vehicle travels on the course based on an output from the learned model.

Information processing device and information processing method

It is determined whether a traffic light is recognized in an image based on each of a result of a recognition operation by a traffic light first recognition unit (a recognition operation of the traffic light for an image acquired by a camera using a learned model based on pre-annotated data) and a result of a recognition operation by a traffic light second recognition unit (a recognition operation of the traffic light for an image acquired by the camera based on a feature amount of the traffic light). This makes it possible to sufficiently obtain the recognition accuracy of the traffic light, and to appropriately perform an instruction to a pedestrian according to the state of the traffic light.

Walking support system

When a frontmost white line of a crosswalk cannot be detected due to an obstacle existing on the crosswalk, an edge position of the obstacle closer to a pedestrian in an image acquired by a camera is set as the frontmost white line of the crosswalk. As a result, a vibration generation device vibrates in a pattern that urges the pedestrian to stop at the time when the pedestrian reaches a position before the edge position of the obstacle closer to the pedestrian, so that a stop notification for walking can be appropriately performed to the pedestrian even when the obstacle exists on the crosswalk.

An information processing device calculates an occupancy rate of a pedestrian crossing in an image obtained by capturing an image of a traveling direction of a target person, determines a crossing status of the target person for the pedestrian crossing based on the calculated occupancy rate, and generates support information for supporting the target person crossing the pedestrian crossing based on the crossing status.

When it is determined that a presence of a traffic light is not recognized in an image acquired by a first image acquisition operation by a camera, the presence of the traffic light is recognized in an image acquired by a second image acquisition operation in which a recognition accuracy of the presence of the traffic light is improved. In this second image acquisition operation, it is assumed that a pedestrian is stopped in front of a pedestrian crossing, and there is little demand for increasing a detection speed of objects such as moving objects present in a surrounding area. Thus, it is possible to sufficiently obtain the recognition accuracy of the traffic light by the second image acquisition operation that gives priority to the recognition accuracy of the presence of the traffic light.

An image area including a traffic light in an image taken by a camera is determined, and the determined image area including the traffic light is extracted and the extracted image area is subjected to enlargement processing to determine whether a status of the traffic light is red or green, and notice to start crossing is provided to a user under a condition that the status of the traffic light switches from red to green. Consequently, even with image information from a single camera alone, accuracy in recognition of the traffic light can sufficiently be enhanced. As a result, crossing start notice can properly be provided without an increase in configuration complexity and weight of the system.

Growing community of inventors

Nisshin, Japan

Kohei Shintani