Abstract: Computerized methods and systems obtain threat data generated from activity data using unsupervised learning. The activity data is collected from enterprises and describes activities performed on the enterprises. The threat data indicates likelihood that sequences of activities performed on the enterprises are indicative of malicious intent. A supervised ML model that processes sequential data is trained by providing a training set of sequential data to the supervised ML model. The training set includes at least some of the obtained threat data, and data derived from activity data collected from at least some of the enterprises. The trained supervised ML receives new data that describes a sequence of activities performed on an enterprise, and processes the received new data to produce a prediction of whether the sequence of activities performed on the enterprise will lead to a malicious action on the enterprise. In some embodiments, multiple supervised ML models are used.

Abstract: Computerized methods and systems obtain a plurality of first data sets associated with a plurality enterprises. Each first data set is associated with a corresponding one of the enterprises and has data indicative of activity performed in association with the corresponding enterprise. The plurality of first data sets is processed using a first LLM to produce, from each first data set, a second data set that provides a summary of a sequence of events that occurred on the enterprise corresponding to first data set. At least some of the second data sets, which are associated with a proper subset of the enterprises, are processed using a second LLM to identify patterns. For an enterprise not in the proper subset, a current security posture of the enterprise is processed together with the identified patterns to produce a recommended security posture for the enterprise.

Abstract: A method of ball trajectory tracking, the method comprising computer executable steps of: receiving a plurality of training frames, each one of the training frames showing a trajectory of a ball as a series of one or more elements, using the received training frames, training a first neuronal network to locate a trajectory of a ball in a frame, receiving a second frame, and using the first neuronal network, locating a trajectory of a ball in the second frame, the trajectory being shown in the second frame as a series of images of the ball having the located trajectory.

Abstract: A Smart-court system, adaptive to constrained sport environment, for enabling real time analysis and debriefing of sport activities is provided herein. The Smart-court system is comprised of: (i) an automatic recording system comprising a plurality of video cameras located in a court, arranged to real-time (RT) recording of a sport session and utilizing automatic calibration and stabilization module; and (ii) a data processing system comprising: (a) a capture module for grabbing a video stream; (b) an objects' detector module arranged to extract during the RT sport session, the objects from the foreground of each frame; (c) an event module for automatically analyzing, the motion and the activities of the tracked objects for automatically identifying and classifying events, creating a synchronized event log and calculating statistics that occurred during the RT sport session; and (d) a presentation module enabling to perform instant debriefing, combined biomechanical and tactical analysis of the video.

Abstract: A method for controlling cameras in a sport event, the method comprising steps executed by at least one computer, the steps comprising: during a sport event taking place in a constrained environment, receiving images of the sport event, the images being captured with a first pixels to time ratio, tracking a motion of a first object, using the images being captured with the first pixels to time ratio, detecting an arrival of the first object into a predefined positional relation to a second object during the tracked motion, and upon the detected arrival, initiating streaming of images being captured with a pixels to time ratio higher than the first pixels to time ratio by at least one selected camera.

Abstract: A method for ball game training, the method comprising steps executed by at least one computer, the steps comprising: receiving image data of a player and a ball, the image data being captured using at least two cameras, using the received image data, tracking motion of the player and motion of the ball in three dimensions, based on the tracked motions, predicting a position of the player and a trajectory of the ball, and based on the predicted position and trajectory, generating a control command for at least one ball throwing machine.

Abstract: A Smart-court system, adaptive to constrained sport environment, for enabling real time analysis and debriefing of sport activities is provided herein. The Smart-court system is comprised of: (i) an automatic recording system comprising a plurality of video cameras located in a court, arranged to real-time (RT) recording of a sport session and utilizing automatic calibration and stabilization module; and (ii) a data processing system comprising: (a) a capture module for grabbing a video stream; (b) an objects' detector module arranged to extract during the RT sport session, the objects from the foreground of each frame; (c) an event module for automatically analyzing, the motion and the activities of the tracked objects for automatically identifying and classifying events, creating a synchronized event log and calculating statistics that occurred during the RT sport session; and (d) a presentation module enabling to perform instant debriefing, combined biomechanical and tactical analysis of the video.

Abstract: A computer implemented method of event based video generation, comprising: on the device, receiving a feed of video captured by a camera, on a memory of the device, maintaining at least one buffer storing a most recent portion of the video feed being received, on a display of the device, presenting at least one GUI element, each one of the GUI elements being associated with a respective predefined video length, and upon actuation of one of the GUI elements by a user of the device, forwarding at least a sub-portion of the video feed portion stored in the buffer for further processing, the forwarded sub-portion having the predefined video length associated with the GUI element actuated by the user.

Abstract: A Smart-court system, adaptive to constrained sport environment, for enabling real time analysis and debriefing of sport activities is provided herein. The Smart-court system is comprised of: (i) an automatic recording system comprising a plurality of video cameras located in a court, arranged to real-time (RT) recording of a sport session and utilizing automatic calibration and stabilization module; and (ii) a data processing system comprising: (a) a capture module for grabbing a video stream; (b) an objects' detector module arranged to extract during the RT sport session, the objects from the foreground of each frame; (c) an event module for automatically analyzing, the motion and the activities of the tracked objects for automatically identifying and classifying events, creating a synchronized event log and calculating statistics that occurred during the RT sport session; and (d) a presentation module enabling to perform instant debriefing, combined biomechanical and tactical analysis of the video.

Abstract: A Smart-court system, adaptive to constrained sport environment, for enabling real time analysis and debriefing of sport activities is provided herein. The Smart-court system is comprised of: (i) an automatic recording system comprising a plurality of video cameras located in a court, arranged to real-time (RT) recording of a sport session and utilizing automatic calibration and stabilization module; and (ii) a data processing system comprising: (a) a capture module for grabbing a video stream; (b) an objects' detector module arranged to extract during the RT sport session, the objects from the foreground of each frame; (c) an event module for automatically analyzing, the motion and the activities of the tracked objects for automatically identifying and classifying events, creating a synchronized event log and calculating statistics that occurred during the RT sport session; and (d) a presentation module enabling to perform instant debriefing, combined biomechanical and tactical analysis of the video.

Abstract: A Smart-court system, adaptive to constrained sport environment, for enabling real time analysis and debriefing of sport activities is provided herein. The Smart-court system is comprised of: (i) an automatic recording system comprising a plurality of video cameras located in a court, arranged to real-time (RT) recording of a sport session and utilizing automatic calibration and stabilization module; and (ii) a data processing system comprising: (a) a capture module for grabbing a video stream; (b) an objects' detector module arranged to extract during the RT sport session, the objects from the foreground of each frame; (c) an event module for automatically analyzing, the motion and the activities of the tracked objects for automatically identifying and classifying events, creating a synchronized event log and calculating statistics that occurred during the RT sport session; and (d) a presentation module enabling to perform instant debriefing, combined biomechanical and tactical analysis of the video.

Abstract: A method for ball game training, the method comprising steps executed by at least one computer, the steps comprising: receiving image data of a player and a ball, the image data being captured using at least two cameras, using the received image data, tracking motion of the player and motion of the ball in three dimensions, based on the tracked motions, predicting a position of the player and a trajectory of the ball, and based on the predicted position and trajectory, generating a control command for at least one ball throwing machine.

Abstract: A method for ball game training, the method comprising steps executed by at least one computer, the steps comprising: receiving image data of a player and a ball, the image data being captured using at least two cameras, using the received image data, tracking motion of the player and motion of the ball in three dimensions, based on the tracked motions, predicting a position of the player and a trajectory of the ball, and based on the predicted position and trajectory, generating a control command for at least one ball throwing machine.

Abstract: A Smart-court system, adaptive to constrained sport environment, for enabling real time analysis and debriefing of sport activities is provided herein. The Smart-court system is comprised of: (i) an automatic recording system comprising a plurality of video cameras located in a court, arranged to real-time (RT) recording of a sport session and utilizing automatic calibration and stabilization module; and (ii) a data processing system comprising: (a) a capture module for grabbing a video stream; (b) an objects' detector module arranged to extract during the RT sport session, the objects from the foreground of each frame; (c) an event module for automatically analyzing, the motion and the activities of the tracked objects for automatically identifying and classifying events, creating a synchronized event log and calculating statistics that occurred during the RT sport session; and (d) a presentation module enabling to perform instant debriefing, combined biomechanical and tactical analysis of the video.

Abstract: A computer implemented method of object extraction from video images, the method comprising steps a computer is programmed to perform, the steps comprising: receiving a plurality of video images, deriving a plurality of background templates from at least one of the received video images, calculating a plurality of differences from an individual one of the received video images, each one of the differences being calculated between the individual video image and a respective and different one of the background templates, and extracting an object of interest from the individual video image, using a rule applied on the calculated differences.

Abstract: A Smart-court system, adaptive to constrained sport environment, for enabling real time analysis and debriefing of sport activities is provided herein. The Smart-court system is comprised of: (i) an automatic recording system comprising a plurality of video cameras located in a court, arranged to real-time (RT) recording of a sport session and utilizing automatic calibration and stabilization module; and (ii) a data processing system comprising: (a) a capture module for grabbing a video stream; (b) an objects' detector module arranged to extract during the RT sport session, the objects from the foreground of each frame; (c) an event module for automatically analyzing, the motion and the activities of the tracked objects for automatically identifying and classifying events, creating a synchronized event log and calculating statistics that occurred during the RT sport session; and (d) a presentation module enabling to perform instant debriefing, combined biomechanical and tactical analysis of the video.

Abstract: A computer implemented method of crowd-sourced video generation, comprising: by a server computer in communication with a plurality of remote client devices, receiving a feed of video captured by a camera, on a memory of the server computer, storing at least a portion of the video feed being received, receiving at least one tag from a respective one of the client devices, determining an occurrence of an event type, based on an at least one of the received tags, and forwarding a sub-portion of the video feed portion stored on the memory for further processing, the forwarded sub-portion having a video length predefined for the event type of the determined occurrence.

Abstract: A computer implemented method of object extraction from video images, the method comprising steps a computer is programmed to perform, the steps comprising: receiving a plurality of video images, deriving a plurality of background templates from at least one of the received video images, calculating a plurality of differences from an individual one of the received video images, each one of the differences being calculated between the individual video image and a respective and different one of the background templates, and extracting an object of interest from the individual video image, using a rule applied on the calculated differences.

Abstract: A computer implemented method of event based video generation, comprising: on the device, receiving a feed of video captured by a camera, on a memory of the device, maintaining at least one buffer storing a most recent portion of the video feed being received, on a display of the device, presenting at least one GUI element, each one of the GUI elements being associated with a respective predefined video length, and upon actuation of one of the GUI elements by a user of the device, forwarding at least a sub-portion of the video feed portion stored in the buffer for further processing, the forwarded sub-portion having the predefined video length associated with the GUI element actuated by the user.

Abstract: A method for ball game training, the method comprising steps executed by at least one computer, the steps comprising: receiving image data of a player and a ball, the image data being captured using at least two cameras, using the received image data, tracking motion of the player and motion of the ball in three dimensions, based on the tracked motions, predicting a position of the player and a trajectory of the ball, and based on the predicted position and trajectory, generating a control command for at least one ball throwing machine.