Abstract: Systems and methods to control operations of a camera based on one or more sensors attached to one or more actors. Sensor data collected from the sensors is analyzed to identify a state of an actor. The state of the actor is used to determine an operation parameter of the camera, such as the zoom level of the camera and/or the direction of the camera, and control the operation of the camera. For example, an actor who is in a state about to perform an interesting action can be selected from a plurality of actors; and the direction and the zoom level of the camera can be adjusted to focus on the selected actor in capture one or more subsequent images.

Abstract: Disclosed are systems and methods for improving image recognition by using information from sensor data. In one embodiment, the method comprises receiving one or more sensor records, the sensor records representing timestamped sensor data collected by a sensor recording device; selecting an event based on the sensor records; identifying a time associated with the event; retrieving a plurality of timestamped video frames; synchronizing the sensor records and the video frames, wherein synchronizing the sensor records and the video frames comprises synchronizing the timestamped sensor data with individual frames of the timestamped video frames according to a common timeframe; and selecting a subset of video frames from the plurality of timestamped video frames based on the selected event.

Abstract: Disclosed are systems and methods for improving image recognition by using information from sensor data. In one embodiment, the method comprises receiving one or more sensor records, the sensor records representing timestamped sensor data collected by a sensor recording device; selecting an event based on the sensor records; identifying a time associated with the event; retrieving a plurality of timestamped video frames; synchronizing the sensor records and the video frames, wherein synchronizing the sensor records and the video frames comprises synchronizing the timestamped sensor data with individual frames of the timestamped video frames according to a common timeframe; and selecting a subset of video frames from the plurality of timestamped video frames based on the selected event.

Abstract: Systems and methods to control operations of a camera based on one or more sensors attached to one or more actors. Sensor data collected from the sensors is analyzed to identify a state of an actor. The state of the actor is used to determine an operation parameter of the camera, such as the zoom level of the camera and/or the direction of the camera, and control the operation of the camera. For example, an actor who is in a state about to perform an interesting action can be selected from a plurality of actors; and the direction and the zoom level of the camera can be adjusted to focus on the selected actor in capture one or more subsequent images.

Abstract: Embodiments of the present disclosure help automatically identify athletic maneuvers performed by actors and/or their sports equipment using data from sensors. Among other things, various embodiments help judges and spectators of extreme sports to assess athletic maneuvers based on objective, empirical data and allow action sport participants to objectively compare tricks performed at different times and/or different locations. A computer-implemented method according to one embodiment of the present disclosure comprises receiving, by a computer system, sensor data related to motion by an actor over a time period; determining, by the computer system and based on the sensor data, a plurality of motion characteristics; and identifying, based on the plurality of motion characteristics, an athletic maneuver associated with the motion by the actor during the time period.

Abstract: Systems and methods to calibrate a gyroscope based on a motion of a predetermined characteristic. Data representing gyro sensor signals during a period of time is stored. A portion of the time period is identified, during which portion the gyroscope is subjected to a motion of the predetermined characteristic. Using the stored data the gyro signals are integrated with respect to time to calculate orientation of the gyroscope as a function of time. Deviation of a characteristic of the orientation of the gyroscope as the function of time during the portion of time period for the motion of the predetermined characteristic is determined to identify a component of bias in the gyro signals. The bias component is removed from the data to re-calculate the gyroscope orientation, and possible to further calculate the deviation in the re-calculated orientation and to identify a further bias component in the gyro signals.

Abstract: A method according to one embodiment includes: receiving, by a processing system, sensor data from a sensor device carried by a user or attached to the user's sports equipment during a sporting activity; identifying, by the processing system and based on the sensor data, an event engaged in by the user during a time period; determining, based on the sensor data, a position of the user during the event; identifying a camera that is operational and has the user in view during at least a portion of the time period; and selecting video footage of the event from the identified camera.

Abstract: Embodiments of the present disclosure help identify athletic maneuvers performed by actors and/or their sports equipment using data from sensors, including data from at least one gyroscopic sensor. Among other things, various embodiments can help judges and spectators of extreme sports to identify and assess athletic maneuvers more easily and accurately compared to conventional methods.

Abstract: Disclosed are systems and methods for improving image recognition by using information from sensor data. In one embodiment, the method comprises receiving one or more sensor records, the sensor records representing timestamped sensor data collected by a sensor recording device; selecting an event based on the sensor records; identifying a time associated with the event; retrieving a plurality of timestamped video frames; synchronizing the sensor records and the video frames, wherein synchronizing the sensor records and the video frames comprises synchronizing the timestamped sensor data with individual frames of the timestamped video frames according to a common timeframe; and selecting a subset of video frames from the plurality of timestamped video frames based on the selected event.

Abstract: Embodiments of the present disclosure help to synchronize multiple video segments of an actor or actors performing athletic maneuvers. Among other things, various embodiments help provide a side-by-side visual comparison of athletic maneuvers.

Abstract: Systems and methods to control operations of a camera based on one or more sensors attached to one or more actors. Sensor data collected from the sensors is analyzed to identify a state of an actor. The state of the actor is used to determine an operation parameter of the camera, such as the zoom level of the camera and/or the direction of the camera, and control the operation of the camera. For example, an actor who is in a state about to perform an interesting action can be selected from a plurality of actors; and the direction and the zoom level of the camera can be adjusted to focus on the selected actor in capture one or more subsequent images.

Abstract: Embodiments of the present disclosure help to automatically generate video selected from multiple video sources using intelligent sensor processing, thereby providing viewers with a unique and rich viewing experience quickly and inexpensively.

Abstract: Embodiments of the present disclosure help to synchronize multiple video segments of an actor or actors performing athletic maneuvers. Among other things, various embodiments help provide a side-by-side visual comparison of athletic maneuvers.

Abstract: A method according to one embodiment includes: receiving, by a processing system, sensor data from a sensor device carried by a user or attached to the user's sports equipment during a sporting activity; identifying, by the processing system and based on the sensor data, an event engaged in by the user during a time period; determining, based on the sensor data, a position of the user during the event; identifying a camera that is operational and has the user in view during at least a portion of the time period; and selecting video footage of the event from the identified camera.

Abstract: A method and apparatus for detecting a jump of a moving sportsman and separating the jump from other sportsman motion is described. Accelerometer data generated by a sportsman's motion is received in a computing device. The computing device is used to apply fuzzy logic membership functions to a plurality of parameters associated with the accelerometer data to detect a pattern associated with jumps. A subset of the data is identified as representing a jump based upon the detection of the pattern. The determination is used in the computing device to transform data, whereby jumps are separated from other sportsman motion.

Abstract: Embodiments of the present disclosure are directed to a method and apparatus for calibration of gyro sensors by using magnetic sensor measurements and background computation during normal product operation. In one embodiment, magnetic sensor measurements are used to adjust gyro gain by comparing measured magnetic vector orientation with its expected orientation computed from gyro integration. The background process constantly compares this discrepancy for various values of gyro gain and selects the one that minimizes such error on average. In one embodiment, device orientation obtained by gyro integration is improved by using magnetic sensor measurements.

Abstract: A distributed, multi-stage, intelligent system is configured to determine user action performance characteristics parameters in action sports. Ruggedness, complexity, and cost are unevenly distributed among components across the stages for improved overall performance and reduced cost. The system includes stage-one, wearable devices configured to use sensors to collect initial data and transfer the initial data to stage-two devices which may temporally store the initial data and/or perform further data processing to generate intermediate data for communication to one or more stage-three devices configured for long term data storage, further processing and presentation.

Abstract: A system and method for automatic digital curation, annotation, and tagging of action videos receives, in a processing system, GPS data, and in some embodiments inertial data, from a sensor-based device carried by a sportsman during a sporting activity. The processing system processes the GPS data and the inertial data, if present to identify at least one sportsman event, and stores data identifying the sportsman event in a performance database. Video data from a video camera is stored in a video database, the video data including location, time, and direction information associated with frames of video. Timecode data in the video database is synchronized with timecode data in the performance database, and the data identifying the sportsman event is used to automatically select, annotate, tag or edit said video data.

Abstract: Embodiments of the present disclosure help to synchronize multiple video segments of an actor or actors performing athletic maneuvers. Among other things, various embodiments help provide a side-by-side visual comparison of athletic maneuvers.

Abstract: A distributed, multi-stage, intelligent system is configured to determine user action performance characteristics parameters in action sports. Raggedness, complexity, and cost are unevenly distributed among components across the stages for improved overall performance and reduced cost. The system includes stage-one, wearable devices configured to use sensors to collect initial data and transfer the initial data to stage-two devices which may temporally store the initial data and/or perform further data processing to generate intermediate data for communication to one or more stage-three devices configured for long term data storage, further processing and presentation.