Abstract:
A system includes a processor configured to provide an immersive virtual environment wherein first and second users can view and edit interaction data corresponding to interactive motion capture for first and second performers who interact with one another in a performance corresponding to the interaction between first and second characters, so as to edit the interaction between the first and second characters and thereby provide edited data corresponding to the performance.
Abstract:
A system and method detects the intent and/or motivation of two or more persons or other animate objects in a video scene. In one embodiment, the system forms a blob of the two or more persons, draws a bounding box around said blob, calculates an entropy value for said blob, and compares that entropy value to a threshold to determine if the two or more persons are involved in a fight or other altercation.
Abstract:
A method and apparatus for predicting hospital bed exit events from video camera systems is disclosed. The system processes video data with a deep convolutional neural network consisting of five main layers: a 1 × 1 3D convolutional layer used for generating feature maps from raw video data, a context-aware pooling layer used for rectifying data from different camera angles, two fully connected layers used for applying pre-trained deep features, and an output layer used to provide a likelihood of a bed exit event.
Abstract:
Die Erfindung betrifft ein Arbeitsplatzanalysesystem (1) in einem Arbeitsbereich (10) zur Erfassung und Analyse der Anwesenheit einer zu überwachenden Person (P) in mehreren unterschiedlich definierten Zonen (A, B, C) des Arbeitsbereichs (10) und wenigstens der zeitlichen Aufenthaltsdauer (t A , t B , t C ) der zu überwachenden Person (P) innerhalb der Zonen (A, B, C), wobei in dem Arbeitsplatzanalysesystem (1) wenigstens eine Erfassungseinrichtung (20) vorgesehen ist, die ausgebildet ist die Anwesenheit und die Aufenthaltsdauer (t A , t B , t C ) der zu überwachenden Person (P) in den jeweiligen Zonen (A, B, C) zu detektieren und zu erfassen, und eine Analyseeinrichtung (30) vorgesehen ist, die ausgebildet ist die Anwesenheit und die Aufenthaltsdauer(t A , t B , t C ) der zu überwachenden Person (P) in den jeweiligen Zonen (A, B, C) zu analysieren und auszuwerten.
Abstract:
A solution is provided to enhance motion detection and recognition of moving objects associated with various sports by embedding motion sensors into sports instruments such as tennis rackets, badminton rackets, baseball bats and golf clubs, that are swung in a three-dimensional (3D) space. A motion sensor device inserted and locked inside a sports instrument is configured to detect motions associated with movements associated with the sports instrument. The device is shaped to be inserted into a sensor housing attached to a selected location inside the sports instrument. The device includes a motion sensor for detecting motion associated with the movement of the sports instrument, a cover for protecting the motion sensor, and a locking mechanism attached to the sensor housing for locking the motion sensor inside the sensor housing.
Abstract:
Systems and methods are provided for controlling industrial equipment in the performance of various industrial activities based on the detected body movement of a user in an industrial automation environment. The method includes employing a time-of-flight sensor to detect movement of a body part of the user, ascertaining whether or not the movement of the body part conforms to a recognized movement of the body part, interpreting the recognized movement of the body part as a performable action, and thereafter actuating industrial machinery to perform the performable action.
Abstract:
A method is for movement in a physically configurable space. The space includes one or more physically configurable elements. A first user is in a first location and in a first position in the physically configurable space. The method includes providing the physically configurable space with at least one sensor, connecting the at least one sensor to a control unit, and sensing at least the first user's first location in the physically configurable space by the at least one sensor. The method further includes configuring the at least one configurable element by the control unit on the basis of sensed information from the at least one sensor so that the first user's allowed moving space is altered. A configurable space is for use with the method.
Abstract:
An apparatus and method for determining a user activity include or define a plurality of baseline signatures, each baseline signature corresponding to a type of user activity and having data formed from a first data representing a varying static electric field and a second data representing motion. Data responsive to a varying static electric field is obtained from a first sensor, and data responsive to motion is obtained from a second sensor. The first data is combined with the second data, and the user activity is identified based on a comparison of the combined first and second data with the plurality of baseline signatures.
Abstract:
The invention consists of a codification and cueing system for the optimization of adversarial or cooperative interactions between human actors engaged in sports and other activities. The system uses measurements from motion sensors to identify key events in the activity and participant's behavior to provide real-time cues to help the actors perform as well as train. The system is illustrated for a tennis application. The codification describes the players' interactions based on court events, such as the ball's trajectory relative to the court, and player behavioral events, such as the stroke phases and court movements. The cueing method can be implemented using different subsets of such events. In its simplest implementation, timing cues are obtained from the stroke backswing initiation, forward swing initiation and impact of the ball on the racket. Following the detection of these events, a signal is transmitted to the adversary where it is used to generate auditory, visual and/or haptic stimuli. These stimuli encode information that help the players anticipate the type of oncoming ball and hence the cue helps select, prepare for and execute the appropriate stroke. The anticipatory cue also primes the players' perceptual processes, directing attention to relevant aspects of the performance.
Abstract:
A play segment extraction method or a play segment extraction device extracts a play segment of sports recorded in a sports video using a processor. The processor identifies a referee in a sports video, estimates a posture of the identified referee, estimates an operation of the referee from the estimated posture, and extracts a play segment, based on the estimated operation of the referee. Thereby, it is possible to accurately extract the play segment.