Abstract: A vehicle control device includes a recognizer configured to recognize a surrounding situation of a vehicle, a driving controller configured to control steering and acceleration/deceleration of the vehicle independently of an operation of a driver of the vehicle; and a mode decider configured to decide on any one of a plurality of driving modes including a first driving mode and a second driving mode as a driving mode of the vehicle. The recognizer recognizes a sign existing within a reference range of a route along which the vehicle travels. The mode decider changes the driving mode of the vehicle from the second driving mode to the first driving mode when the driving mode of the vehicle is the second driving mode and when the number of signs recognized by the recognizer exceeds a first reference value.

Abstract: An inference apparatus provides target data to multiple inference models to cause the inference models each derived from local learning data obtained in a different environment to perform predetermined inference to obtain an inference result from each of the inference models. The inference apparatus determines the value of each combining parameter using environment data, weights the inference result from each of the inference models using the determined value of each combining parameter, and combines the weighted inference result from each inference model together to generate an inference result in a target environment.

Abstract: A remote control manipulator system includes: a manipulator being controlled by an operator remotely to handle an object; a stereoscopic display device that displays a right-eye image and a left-eye image so as to be stereoscopically viewed; a model image generator that generates a model image being an image of an integrated three-dimensional model viewed from a viewpoint designated by the operator, the integrated three-dimensional model being a three-dimensional model obtained by integrating the manipulator model and a surrounding environment model being generated by performing image processing on the right-eye image and the left-eye image and being a three-dimensional model of the object and a surrounding environment thereof; and a model image display device that displays the model image and is configured to be able to be viewed by the operator switching between the stereoscopic display device and the model image display device through moving the head of the operator.

Abstract: The purpose of the present invention is to provide a gaze detector with which it is possible to detect a gaze (start point and gaze direction) by a simple configuration. The gaze detector detects a person's gaze, wherein the gaze detector is provided with a camera unit 10 for imaging the face of the person, a projector unit 20 for projecting a prescribed pattern light to the face of the person, a control unit 30 for controlling the presence of projection of the pattern light by the camera unit 10 and the projector unit 20, and a gaze detection processing unit 40 for detecting a gaze from the image of the face of the person imaged by the camera unit.

Abstract: An integrated analysis method according to one or more embodiments may include: a step of each client apparatus executing computation for obtaining correlation between elements in local samples included in the local learning data; a step of a server apparatus acquiring results of the computation by the client apparatuses; a step of the server apparatus calculating an integration result indicating the correlation between elements of all of the local samples of all of the local learning data, by integrating the results of computation acquired from the client apparatuses; a step of the server apparatus deriving one or more principal components from the calculated integration result by performing principal component analysis; and a step of the server apparatus outputting information regarding the one or more derived principal components.

Abstract: An inference apparatus provides target data to multiple inference models to cause the inference models each derived from local learning data obtained in a different environment to perform predetermined inference to obtain an inference result from each of the inference models. The inference apparatus determines the value of each combining parameter using environment data, weights the inference result from each of the inference models using the determined value of each combining parameter, and combines the weighted inference result from each inference model together to generate an inference result in a target environment.

Abstract: It is provided a method (and corresponding apparatuses, computer programs, and medium) for determining whether an item being processed is defective or non-defective, the method including a step of determining, by a local neural network and on the basis of sensing measurements performed on an item while the item is being processed, a local classification result indicating whether the item is defective or non-defective. It is determined a confidence index indicating a level of confidence that the local classification result is correct. Then, in response to the confidence index being below a given threshold, it is determined, by a central neural network and on the basis of the sensing measurements, a central classification result indicating whether the item is defective or non-defective, wherein the local neural network has less computational resources than the central neural network.

Abstract: A model integration apparatus according to one or more embodiments may include a model collecting unit that collects trained learning models from a plurality of learning apparatuses, an integration processing unit that executes integration processing of integrating the results of machine learning reflected in an integration range set in the common portion, with respect to the trained learning models, and a model updating unit that transmits a result of the integration processing to the learning apparatuses. The model updating unit may further update the trained learning models retained by the learning apparatuses by causing the learning apparatuses to each apply the result of the integration processing to the integration range in the trained learning model.

Abstract: This invention provides a resin composition for preparing an allylphenol-maleimide copolymer used for a protective film for an electronic component including: (A) an allyl group-containing phenol compound having a rigid structure; (B) an N-aromatic maleimide group-containing compound having a rigid structure; and (C) an N-aliphatic maleimide group-containing compound having a flexible structure.

Abstract: A control device assumes that observation light observed by an imaging device is composite light of primary reflection light and secondary reflection light. The control device acquires three or more samples of a brightness amplitude value of the observation light, calculates a phase error caused by the secondary reflection light using these samples, calculates a corrected phase value by correcting a phase value of the observation light using the phase error, and calculates a three-dimensional position of the measurement point on the measurement object based on the corrected phase value.

Abstract: The purpose of the present invention is to provide a gaze detector with which it is possible to detect a gaze (start point and gaze direction) by a simple configuration. The gaze detector detects a person's gaze, wherein the gaze detector is provided with a camera unit 10 for imaging the face of the person, a projector unit 20 for projecting a prescribed pattern light to the face of the person, a control unit 30 for controlling the presence of projection of the pattern light by the camera unit 10 and the projector unit 20, and a gaze detection processing unit 40 for detecting a gaze from the image of the face of the person imaged by the camera unit.

Abstract: A three-dimensional measurement apparatus includes: projecting means for projecting, onto a measurement target, patterned light having a two-dimensionally coded pattern in which a plurality of types of words each having a different two-dimensional structure and being distinguishable from each other are two-dimensionally arranged; capturing means for capturing the measurement target onto which the patterned light is projected; and calculating means for calculating a three-dimensional position of a target pixel of the image from an image captured by the capturing means, and the two-dimensionally coded pattern is two-fold symmetrical. The two-dimensionally coded pattern is a pattern in which a predetermined word is repeated in the column direction for each column.

Abstract: Three-dimensional measurement is performed by projecting patterned light having a hybrid pattern Ph onto a measurement target. The hybrid pattern Ph is a pattern in which a random pattern Pr is superimposed on a structured light pattern Ps, and is arranged in pattern such that the random pattern Pr and the structured light pattern Ps do not interfere mutually.

Abstract: A driver state estimation device which can estimate a distance to a head position of a driver without detecting a center position of a face area of the driver in an image, comprises a monocular camera 11 which can pick up an image of a driver sitting in a driver's seat, a storage section 15 and a CPU 12, the storage section 15 comprising an image storing part 15a for storing the image picked up by the monocular camera 11, and the CPU 12 comprising a head detecting section 23 for detecting a head of the driver in the image read from the image storing part 15a, a defocus amount detecting section 24 for detecting a defocus amount of the head of the driver in the image detected by the head detecting section 23 and a distance estimating section 25 for estimating a distance from the head of the driver sitting in the driver's seat to the monocular camera 11 with use of the defocus amount detected by the defocus amount detecting section 24.

Abstract: A control device assumes that observation light observed by an imaging device is composite light of primary reflection light and secondary reflection light. The control device acquires three or more samples of a brightness amplitude value of the observation light, calculates a phase error caused by the secondary reflection light using these samples, calculates a corrected phase value by correcting a phase value of the observation light using the phase error, and calculates a three-dimensional position of the measurement point on the measurement object based on the corrected phase value.

Abstract: A driver state estimation device which can estimate a distance to a driver's head position without detecting a center position of the driver's face area in an image, includes a camera, a lighting part, and a CPU including a face detecting section for detecting the driver's face in a first image picked up at the time of light irradiation from the lighting part and in a second image picked up at the time of no light irradiation from the lighting part, a face brightness ratio calculating section for calculating a brightness ratio between the driver's face in the first image and that in the second image, and a distance estimating section for estimating a distance from the driver's head to the camera using the calculated face brightness ratio.

Abstract: A three-dimensional measurement apparatus includes: projecting means for projecting, onto a measurement target, patterned light having a two-dimensionally coded pattern in which a plurality of types of words each having a different two-dimensional structure and being distinguishable from each other are two-dimensionally arranged; capturing means for capturing the measurement target onto which the patterned light is projected; and calculating means for calculating a three-dimensional position of a target pixel of the image from an image captured by the capturing means, and the two-dimensionally coded pattern is two-fold symmetrical. The two-dimensionally coded pattern is a pattern in which a predetermined word is repeated in the column direction for each column.

Abstract: Three-dimensional measurement is performed by projecting patterned light having a hybrid pattern Ph onto a measurement target. The hybrid pattern Ph is a pattern in which a random pattern Pr is superimposed on a structured light pattern Ps, and is arranged in pattern such that the random pattern Pr and the structured light pattern Ps do not interfere mutually.

Abstract: An observing apparatus includes a lighting device for irradiating a surface of a measuring target with light having a first light source distribution, and an imaging section for imaging the surface of the measuring target. Considering a first plane passing through a measurement point, the first light source distribution is set such that: (1) a radiance L11(?) changes in a continuous or stepwise manner according to an angle ?, and (2) the radiance L11(?) is not zero in a local region of a predetermined range of ±? having a point located at a predetermined angle ?c as a center on the first plane when viewed from the measurement point, and the following equation substantially holds for arbitrary a satisfying 0<a??; L11(?c?a)+L11(?c+a)=2×L11(?c).

Abstract: The present invention provides a digital image processing enhancing system and method with denoising function. The collected digital image is input; the obtained digital image is decomposed into an illumination image and a reflection image, and then the decomposed illumination image and the reflection image is processed, at last, the processed illumination image and the reflection image are composed into an output image, which is output to an output device. The present invention can improve the image quality, remove the noises of the image, remain details features of an object and obtain the natural visual effect.