The present technology relates to a controller and a control method capable of providing an imaging system which achieves cost reduction. A control unit controls a first imaging direction of a first imaging unit and a second imaging direction of a second imaging unit as a direction different from the first imaging direction in accordance with a situation of an object associated with a first image captured by the first imaging unit or a second image captured by the second imaging unit. For example, the present technology is applicable to a lecture capture system.

A method for real-time semantic image segmentation using a monocular event-based sensor includes capturing a scene using a red, green, blue (RGB) sensor to obtain a plurality of RGB frames and an event sensor to obtain event data corresponding to each of the plurality of RGB frames, performing object labeling for objects in a first RGB frame among the plurality of RGB frames by identifying one or more object classes, obtaining an event velocity of the scene by fusing the event data corresponding to the first RGB frame and at least one subsequent RGB frame among the plurality of RGB frames, determining whether the event velocity is greater than a predefined threshold, and performing object labeling for objects in the at least one subsequent RGB frame based on the determination.

A method, apparatus and system for human skeleton pose estimation includes synchronously capturing images of a human moving through an area from a plurality of different points of view, for each of the plurality of captured images, determining a bounding box that bounds the human in the captured image and identifying pixel locations of the bounding box in the image, for each of the plurality of captured images, determining 2D and single-view 3D skeletons from the pixel locations of the bounding box, determining a first, multi-view 3D skeleton using a combination of the 2D and single-view 3D skeletons, and optimizing the first, multi-view 3D skeleton to determine a final 3D skeleton pose for the human. The method, apparatus and system can further include illuminating the area with structured light during the capturing of the images of the human moving through the area.

Methods and systems for processing of voice input to identify intents and mapped standard terminologies are provided. Using natural language processing, an intent of a voice input is identified. The intent is utilized to identify a standard terminology that maps to the intent. The standard terminology is utilized to identify information relevant to the standard terminology in a patient's electronic health record.

A computer-implemented method, computerized apparatus and computer program product for activity recognition using adaptive window size segmentation of sensor data stream. A data stream generated by one or more sensors is obtained. A frequency analysis of the data in a first segment of the data stream is performed. A size of a second segment is determined based on the frequency analysis. Activity recognition is performed for the second segment by extracting one or more features of the data therein and applying a machine learning process on the extracted features to obtain a classification of the data into an activity class.

A system and method includes detecting motion in a space; capturing images of a scene in a direction of the motion within the space by peripheral image capturing devices and detecting a body of a person within the images of the scene; extracting an image of the body from the images of the scene; identifying a head of the body based on the extracted at least one image of the body and extracting an image of a head from the extracted the one image of the body; transmitting the one image of the body to a body tracking module; transmitting the extracted image of the head to a face detection module; in parallel, tracking the body within the space and performing by a facial recognition module facial recognition of the extracted image of the head of the body; and determining an identity of a user associated with the body.

In one embodiment, a method includes receiving a user input at a client system, wherein the user input is associated with one or more intents and one or more slots, generating one or more first dialog acts based on the user input, calculating a task-confidence score based on one or more intent-confidence scores associated with the one or more intents, respectively, and one or more slot-confidence scores associated with the one or more slots, respectively, generating one or more second dialog acts modifying the one or more first dialog acts responsive to the task-confidence score being less than a threshold score, and presenting a response to the user input at the client system, wherein the response is based on one or more of the first dialog acts or the second dialog acts.

A state recognition apparatus includes circuitry configured to: recognize a monitoring target based on a captured image; recognize a motion of each part of the recognized monitoring target; recognize a state of the monitoring target based on the recognized motion of each part; and output a state recognition result indicating the recognized state of the monitoring target.

An apparatus, system and process for tracking and analyzing target person movements, captured while the target person is performing ordinary tasks outside of a medical context, for medical diagnosis and treatment review are described. The method may include constructing a model of a target person from three-dimensional (3D) image data of the target person performing an activity over a period of time. The method may also include tracking movement of the model of the target person in the 3D image data over the period of time, and detecting one or more motion features in the movement of the model of the target person that are relevant to diagnosis, treatment, care, or a combination thereof, of a potential chronic neurodegenerative or musculoskeletal medical condition. The method may also include computing a risk score associated with likelihood of the target person having the medical condition based on the detected motion features.

A system to generate an adapted workout plan includes an input reception device to receive input data from a user and a workout routine modeling engine coupled to the input reception device. The workout routine modeling engine is configured to analyze the input data from a user and generate an adapted workout routine for the user based on the input data.