Abstract: A retrieval device includes one or more processors. The processors acquire trajectory information indicating a movement trajectory of a target in time-series images. The processors acquire situation information indicating a peripheral situation of the target in the time-series images. The processors acquire a retrieval query containing a movement trajectory and a peripheral situation. The processors retrieve an image matching with the retrieval query among images contained in the time-series images based on the trajectory information and the situation information.

Abstract: According to an embodiment, a transformation matrix deriving device includes a first trajectory generator, a second trajectory generator, a trajectory matcher, and a deriver. The first trajectory generator is configured to generate a first trajectory of a moving object, detected from a video, in a first coordinate system. The second trajectory generator is configured to generate a second trajectory of a moving object in a second coordinate system, from time-series data of positional information. The trajectory matcher is configured to associate the first trajectory with the second trajectory to be a motion trajectory of the same moving object based on a similarity between the first trajectory and the second trajectory. The deriver is configured to derive a transformation matrix that transforms the second coordinate system into the first coordinate system by using the first trajectory and the second trajectory associated with each other.

Abstract: According to an embodiment, an information processing device includes a memory and processing circuitry. The processing circuitry is configured to acquire a captured image; detect a plurality of targets included in the captured image; calculate target information representing at least one of a state or an attribute and reliability of the target information for each of the plurality of detected targets on the basic of the captured image; and estimate a distribution of the target information of the plurality of targets on the basis of a distribution of the target information of targets for which the reliability is higher than a set value.

Abstract: According to one embodiment, an information processing device includes a memory and a processor. The processor is configured to acquire an image, determine a likelihood of presence of an objected within the image, display information on a position of the object within the image based on the likelihood, identify the object within the image, and generate a recognition result based on the identified object.

Abstract: According to an embodiment, a transformation matrix deriving device includes a first trajectory generator, a second trajectory generator, a trajectory matcher, and a deriver. The first trajectory generator is configured to generate a first trajectory of a moving object, detected from a video, in a first coordinate system. The second trajectory generator is configured to generate a second trajectory of a moving object in a second coordinate system, from time-series data of positional information. The trajectory matcher is configured to associate the first trajectory with the second trajectory to be a motion trajectory of the same moving object based on a similarity between the first trajectory and the second trajectory. The deriver is configured to derive a transformation matrix that transforms the second coordinate system into the first coordinate system by using the first trajectory and the second trajectory associated with each other.

Abstract: According to one embodiment, an information processing device includes a memory and a processor. The processor is configured to acquire an image, determine a likelihood of presence of an objected within the image, display information on a position of the object within the image based on the likelihood, identify the object within the image, and generate a recognition result based on the identified object.

Abstract: According to an embodiment, an information processing device includes a memory and processing circuitry. The processing circuitry is configured to acquire a captured image; detect a plurality of targets included in the captured image; calculate target information representing at least one of a state or an attribute and reliability of the target information for each of the plurality of detected targets on the basic of the captured image; and estimate a distribution of the target information of the plurality of targets on the basis of a distribution of the target information of targets for which the reliability is higher than a set value.

Abstract: A retrieval device includes one or more processors. The processors acquire trajectory information indicating a movement trajectory of a target in time-series images. The processors acquire situation information indicating a peripheral situation of the target in the time-series images. The processors acquire a retrieval query containing a movement trajectory and a peripheral situation. The processors retrieve an image matching with the retrieval query among images contained in the time-series images based on the trajectory information and the situation information.

Abstract: A vital sign information collection system has a vital sign information measuring device that measures vital sign information, a vital sign information collecting device that performs authentication by attribute information of a measurement subject and collects the vital sign information measured by the vital sign information measuring device, and links the attribute information with the collected vital sign information, and a management device that acquires the attribute information and the vital sign information linked with each other, from the vital sign information collecting device, and retains the vital sign information linked with personal information to identify the measurement subject.

Abstract: The acquiring unit is configured to acquire positions of a particular part of a user in time series. The calculator is configured to calculate a feature value of a motion of the particular part from the positions acquired in time series. The comparing unit configured to compare the feature value and a first threshold. The recognizing unit is configured to recognize the motion of the particular part using a first recognition method and a second recognition method which is different from the first recognition method. The control unit configured to control the recognizing unit to select the first recognition method for recognizing a position or a motion of the particular part when the feature value is smaller than the first threshold, and select the second recognition method when the feature value is equal to or larger than the first threshold.

Abstract: According to one embodiment, a television apparatus includes a speech input unit, an indication input unit, a speech recognition unit, and a control unit. The speech input unit is configured to input a speech. The indication input unit is configured to input an indication to start speech recognition from a user. The speech recognition unit is configured to recognize the user's speech inputted after the indication is inputted. The control unit is configured to execute an operation command corresponding to a recognition result of the user's speech. The control unit, if a volume of the television apparatus at a timing when the indication is inputted is larger than or equal to a threshold, temporarily sets the volume to a value smaller than the threshold while the speech recognition unit is recognizing.

Abstract: A wearable information input device according to an embodiment is worn on an upper limb of a user. The wearable information input device includes a contact detecting unit, a position detecting unit, and a trajectory generating unit. The contact detecting unit detects contact with the upper limb by an input unit. The input unit is used by the user to input information. The position detecting unit detects a position of the input unit while the input unit is in contact with the upper limb. The trajectory generating unit generates a trajectory of motion of the input unit based on information about the position detected by the position detecting unit.

Abstract: According to an embodiment, a recognition device includes an obtaining unit, a selection action recognizing unit, and an output unit. The obtaining unit is configured to obtain a measured value according to an action of a target for measurement. The measured value is measured by a measuring device attached to a specific body part of the target for measurement. The selection action recognizing unit is configured to, based on an acceleration of the specific body part as obtained from the measured value, recognize that a selection action has been performed for selecting any one target for operations included in a screen area. The output unit is configured to, in a state in which the selection action has been performed, output information about an operation state of the target for operations based on an amount of change in a tilt of the specific body part as obtained from the measured value.

Abstract: A pulse wave measuring device includes: a connector that is disposed on a main unit; an external sensor that includes an external light-emitting module radiating light to a human body to be measured and an external light-receiving module receiving at least one of reflected light and transmitted light originating from the external light-emitting module and the human body so as to measure a pulse wave; an first controller that switches the external light-emitting module ON and OFF; an second controller that switches the external light-receiving module ON and OFF; and an external sensor connection determination section that determines a connection between the external sensor and the connector in accordance with a transient response of the external light-receiving module, wherein, after the external sensor connection determination section determines that the external sensor is connected to the connector, a measurement of the pulse wave by using the external sensor is started.

Abstract: According to an embodiment, a display control device includes a selector and a controller. The selector is configured to acquire display condition information in which combinations of pieces of position-time information of a user and pieces of activity-time information are associated with pieces of display information to be displayed on a display device, respectively, specify a combination of a piece of position information and a piece of activity information associated with the time corresponding to the piece of position information, from among the combinations of the pieces of position information and the pieces of activity information in the display condition information, and select the piece of display information corresponding to the specified combination. The controller is configured to control to display the selected piece of display information on the display device.

Abstract: According to the invention, a pulse wave measuring device includes: a connector that is disposed on a main unit; an external sensor that includes an external light-emitting module radiating light to a human body to be measured and an external light-receiving module receiving at least one of reflected light and transmitted light originating from the external light-emitting module and the human body so as to measure a pulse wave; an first controller that switches the external light-emitting module ON and OFF; an second controller that switches the external light-receiving module ON and OFF; and an external sensor connection determination section that determines a connection between the external sensor and the connector in accordance with a transient response of the external light-receiving module, wherein, after the external sensor connection determination section determines that the external sensor is connected to the connector, a measurement of the pulse wave by using the external sensor is started.

Abstract: A device for speech input includes a speech input unit configured to convert a speech of a user to a speech signal; an angle detection unit configured to detect an angle of the speech input unit; a distance detection unit configured to detect a distance between the speech input unit and the user; and an input switch unit configured to control on and off of the speech input unit based on the angle and the distance.

Abstract: According to one embodiment, a monitoring apparatus includes an acquisition unit, an analysis unit, a calculation unit, a storage, a determination unit. The acquisition unit acquires an environmental sound. The analysis unit performs frequency analysis to extract characteristic frequency components. The calculation unit calculates first values of metrics. The storage stores contour data generated by second values of the metrics. The determination unit determines whether or not there is a first measurement point in which a first value and a second value match, if there is no first measurement point or the change is not less than the threshold value, determines that the machines is abnormal.

Abstract: According to one embodiment, a voice recognition apparatus includes a determination unit, an estimating unit, and a voice recognition unit. The determination unit determines whether a component with a frequency of not less than 1000 Hz and with a level not lower than a predetermined level is included in a sound input from a plurality of microphones. The estimating unit estimates a sound source direction of the sound when the determination unit determines that the component is included in the sound. The voice recognition unit recognizes whether the sound obtained in the sound source direction coincides with a voice model registered beforehand.

Abstract: According to one embodiment, a display device includes: a display; an audio output module; a recognition module configured to recognize a time-series motion of a user; an issuing module configured to issue an operating instruction when the recognized time-series motion is a predetermined time-series motion; and a notification module configured to, when the time-series motion is recognized, notify the user of the recognized time-series motion by at least one of outputting of audio and displaying of an image on the display, regardless of whether the operating instruction is issued based on the recognized time-series motion.