Nec Corporation

Kenji Sobata

Yasunori Futatsugi

Atsushi Fukuzato

Jun Nakayamada

Yoshihiro Mishima

Yuki Chiba

Yusuke Koitabashi

Asako Fujii

Takuroh Kashima

A dangerous scene prediction devicefor predicting a dangerous scene occurring during driving of a vehicle includes a learning model selection/synthesis unitand a dangerous scene prediction unit. The learning model selection/synthesis unitselects, from two or more learning models, a learning model used for predicting the dangerous scene, depending on a scene determined based on information obtained during the driving of the vehicle. The dangerous scene prediction unitpredicts the dangerous scene occurring during the driving of the vehicle, using the selected learning model.

Dangerous scene prediction device, dangerous scene prediction method, and dangerous scene prediction program

A comfort determination model learning unitlearns a comfort determination model, by using comfortable activity data where a comfort indicator, which is an indicator measuring whether an individual is comfortable or not when an activity classified as a comfortable activity is performed, is associated with a teacher label indicating comfort, and uncomfortable activity data where the comfort indicator when an activity classified as an uncomfortable activity is performed, is associated with a teacher label indicating discomfort, as first training data, taking an objective variable for a comfort value indicating a degree of comfort, and taking an explanatory variable for each of the comfort indicators. An individual data generation unitgenerates individual data including explanatory variables, which are used in the comfort determination model, generated based on the comfort indicators of the subject during riding on a vehicle, and driving situations of the vehicle when the comfort indicators are obtained. A driving data generation unitgenerates comfortable driving data and uncomfortable driving data according to a comfort value calculated by applying the individual data to the comfort determination model.

Comfort driving data collection system, driving control device, method, and program

An object recognition systemincludes: a recognition devicethat recognizes an object in an image; and a serverthat generates a learning model. The recognition deviceincludes: a first object recognition unitthat determines a type of the object in the image using the learning model; and an image transmission unitthat transmits a type-indeterminable image, which is an image in which the type has not been determined, to the serverwhen an object included in the type-indeterminable image is an object detected as a three-dimensional object. The serverincludes: a learning devicethat generates the learning model based on training data in which a teacher label is assigned to the type-indeterminable image; and a learning model transmission unitthat transmits the generated learning model to the recognition device. The first object recognition unitdetermines the type of the object in the image using the transmitted learning model.

Object recognition system, recognition device, object recognition method, and object recognition program

An object recognition deviceincludes a scene determination unit, a learning-model selection unit, and an object recognition unit. The scene determination unitdetermines, based on information obtained during driving of a vehicle, a scene of the vehicle. The learning-model selection unitselects, in accordance with the determined scene, a learning model to be used for object recognition from two or more learning models. The object recognition unitrecognizes, using the selected learning model, an object in an image to be photographed during driving of the vehicle.

Growing community of inventors

Tokyo, Japan

Kenji Sobata