Provided are a device and a method which enable easy analysis and evaluation of work efficiency of a worker without burdensome tasks and easy determination of a worker's skill level by comparing the worker's work efficiency status with that of another worker or a past record of the same worker, wherein analytical information is produced by estimating the worker's joint positions based on a video; acquiring time series data on joint positions; determining work efficiency based on the time series data; acquiring a target range (part of a work process with low work efficiency); output an image of the target range overlaid on a graph of the time series data; and output a posture image of the worker overlaid on the video. The analytical information may include information on a working activity to be analyzed and information on a chosen model working activity with high work efficiency.

Systems and methods for machine learning assisted intent determination are disclosed. In some embodiments, a system comprises at least one processor and memory storing instructions executable by the at least one processor, the instructions when executed cause the system to obtain user information, the user information comprising a behavioral information of the user; obtain control access information for the user, the control access information indicating whether the user accessed a controlled area; train, using the obtained user information and control access information, an intent model of a machine learning system, the intent model configured to determine a user intent, the user intent indicting whether the user intends to access the controlled area; and use the trained intent model to determine the user intent based on the obtained user information.

A method and an apparatus for early warning of climbing behaviors, an electronic device, and a storage medium are disclosed. The method includes: acquiring video image data including a monitored target and at least one object (11); acquiring behavior information of the at least one object when it is determined that the at least one object enters a target area corresponding to the monitored target (12); marking video frames in which the at least one object is included when it is determined that the behavior information indicates that the at least one object climbs the monitored target (13). By marking the video frames in the video image data, the behavior of the object climbing the monitored target can be found in time, and the management efficiency can be improved.

The present invention relates to a method for deriving a 3D data from image data comprising: receiving, from at least one camera, image data representing an environment; detecting, from the image data, at least one object within the environment; classifying the at least one detected object, wherein the method comprises, for each classified object of the classified at least one objects: determining a 2D skeleton of the classified object by implementing a neural network to identify features of the classified object in the image data corresponding to the classified object; and constructing a 3D skeleton for the classified object, comprising mapping the determined 2D skeleton to 3D.

A shelf space allocation management device manages products allocated on shelves in a store by use of an imaging device. The shelf space allocation management device acquires an image including a position assumed to be changed in allocation status of each product on each shelf; it determines whether each product reflected in the image matches one of pre-recorded images, thus executing a product allocation inspection. Herein, the shelf space allocation management device specifies a position at which a person causes any change in the allocation status of each product on each shelf, and therefore it may control the imaging device to capture an image including the position. It is possible to carry out a product allocation inspection for each period determined in advance depending on the type of each product, or it is possible to carry out a product allocation inspection being triggered by a customer purchasing each product.

An Internet of Thing (IoT) sport device includes a body with a processor, a camera and a wireless transceiver coupled to the processor.

A situation identification method includes acquiring a plurality of images; identifying, for each of the plurality of images, a first area including a bed area where a place to sleep appears in an image, and a second area where an area in a predetermined range around the place to sleep appears in the image; detecting a state of a subject to be monitored for each of the plurality of images based on a result of detection of a head area indicating an area of a head of the subject in the first area and a result of detection of a living object in the second area; when the state of the subject changes from a first state to a second state, identifying a situation of the subject based on a combination of the first state and the second state; and outputting information that indicates the identified situation.

Biometric identification methods and apparatuses (including devices and systems) for uniquely identifying one an individual based on wearable garments including a plurality of sensors, including but not limited to sensors having multiple sensing modalities (e.g., movement, respiratory movements, heart rate, ECG, EEG, etc.).

Systems and methods are described for navigating through a data space. The navigating comprises detecting a gesture of a body from gesture data received via a detector. The gesture data is absolute three-space location data of an instantaneous state of the body at a point in time and physical space. The detecting comprises identifying the gesture using the gesture data. The navigating comprises translating the gesture to a gesture signal, and navigating through the data space in response to the gesture signal. The data space is a data-representational space comprising a dataset represented in the physical space.

Techniques for detecting attributes and/or gestures associated with pedestrians in an environment are described herein. The techniques may include receiving sensor data associated with a pedestrian in an environment of a vehicle and inputting the sensor data into a machine-learned model that is configured to determine a gesture and/or an attribute of the pedestrian. Based on the input data, an output may be received from the machine-learned model that indicates the gesture and/or the attribute of the pedestrian and the vehicle may be controlled based at least in part on the gesture and/or the attribute of the pedestrian. The techniques may also include training the machine-learned model to detect the attribute and/or the gesture of the pedestrian.