Implementations generally perform robust multi-view multi-target action recognition using reconstructed 3-dimensional (3D) poses. In some implementations, a method includes obtaining a plurality of videos of a plurality of subjects in an environment, where at least one target subject of the plurality of subjects performs one or more actions in the environment. The method further includes tracking the at least one target subject across at least two cameras. The method further includes reconstructing a 3-dimensional (3D) model of the at least one target subject based on the plurality of videos and the tracking of the at least one target subject. The method further includes recognizing the one or more actions of the at least one target subject based on the reconstructing of the 3D model.

Implementations generally perform robust multi-view multi-target action recognition using reconstructed 3-dimensional (3D) poses. In some implementations, a method includes obtaining a plurality of videos of a plurality of subjects in an environment, where at least one target subject of the plurality of subjects performs one or more actions in the environment. The method further includes tracking the at least one target subject across at least two cameras. The method further includes reconstructing a 3-dimensional (3D) model of the at least one target subject based on the plurality of videos and the tracking of the at least one target subject. The method further includes recognizing the one or more actions of the at least one target subject based on the reconstructing of the 3D model.

A system, method, and computer-readable medium for associating a person’s gestures with specific features of objects is disclosed. Using one or more image capture devices, a person’s gestures and the location of that person in an environment is determined. Using determined distances between the person and objects in the environment and scales associated with features of those objects, the list of specific features in the person’s field-of-view may be determined. Further, a facial expression of the person may be scored and that score associated with one or more specific features.

A system, method, and computer-readable medium for associating a person’s gestures with specific features of objects is disclosed. Using one or more image capture devices, a person’s gestures and the location of that person in an environment is determined. Using determined distances between the person and objects in the environment and scales associated with features of those objects, the list of specific features in the person’s field-of-view may be determined. Further, a facial expression of the person may be scored and that score associated with one or more specific features.

An information processing apparatus includes a processor configured to: obtain a video and an instruction to generate a still image from the video, the video being a video in which a work target is photographed, the work target being a target on which to work; generate the still image in response to the instruction, the still image being cut from the video including the work target; specify the work target in the video, position information, and a superimposition area by using the still image, the position information describing a position of the work target, the superimposition area being an area in which an image is superimposed, the image being obtained by using the position of the work target as a reference; receive instruction information indicating an instruction for work on the work target; and superimpose and display an instruction image in the superimposition area in the video, the instruction image being an image according to the instruction information.

In one example, a method performed by a processing system including at least one processor includes obtaining video footage of a first subject, creating a profile for the first subject, based on features extracted from the video footage, obtaining video footage of a second subject different from the first subject, adjusting movements of the second subject in the video footage of the second subject to mimic movements of the first subject as embodied in the profile for the first subject, to create video footage of a modified second subject, verifying that the video footage of the modified second subject is consistent with a policy specified in the profile for the first subject, and rendering a media including the video footage of the modified second subject when the video footage of the modified second subject is consistent with the policy specified in the profile for the first subject.

This application relates to systems, methods, devices, and other techniques that can be utilized to simulate and analyze behaviors of customers in a retail environment.

A new approach is proposed that supports protocol compliance by a person in various workplace applications and environments. The proposed approach determines if a person is following a set of protocols/procedures created and defined to ensure safety and efficiency of the workers/employees in his/her workplace environment. This proposed approach focuses on specifying one or more zones of interest, identifying presence of the person and/or an object associated with the person in the one or more zones of interest, classifying a sequence of activities and/or postures of the person, and determining the durations of the activities. A is notified if it is determined that the person is not in compliance with the set of protocols in the workplace environment. In addition, data collected from the one or more zones of interest is stored securely in a local site to protect confidentiality of production processes as well as privacy of the person.

Commercial interactions with non-discretized items such as liquids in carafes or other dispensers are detected and associated with actors using images captured by one or more digital cameras including the carafes or dispensers within their fields of view. The images are processed to detect body parts of actors and other aspects therein, and to not only determine that a commercial interaction has occurred but also identify an actor that performed the commercial interaction. Based on information or data determined from such images, movements of body parts associated with raising, lowering or rotating one or more carafes or other dispensers may be detected, and a commercial interaction involving such carafes or dispensers may be detected and associated with a specific actor accordingly.

A method implemented on a visual computing device to authenticate one or more users includes receiving a first three-dimensional pattern from a user. The first three-dimensional pattern is sent to a server computer. At a time of user authentication, a second three-dimensional pattern is received from the user. The second three-dimensional pattern is sent to the server computer. An indication is received from the server computer as to whether the first three-dimensional pattern matches the second three-dimensional pattern within a margin of error. When the first three-dimensional pattern matches the second three-dimensional pattern within the margin of error, the user is authenticated at the server computer. When the first three-dimensional pattern does not match the second three-dimensional pattern within the margin of error, user is prevented from being authenticated at the server computer.