Abstract: A motion prediction system for predicting the motion of a random animate subject. A first neural network is a markerless motion capture network, trained to receive video data of the subject and to process the video data to generate a time sequence of musculoskeletal motion capture data. A second neural network is a motion prediction network, trained to receive the musculoskeletal motion capture data and to process the data to generate a prediction of the subject's location based on position change in position of joints and/or muscles.

Abstract: A motion prediction system for predicting the motion of a random animate subject. A first neural network is a markerless motion capture network, trained to receive video data of the subject and to process the video data to generate a time sequence of musculoskeletal motion capture data. A second neural network is a motion prediction network, trained to receive the musculoskeletal motion capture data and to process the data to generate a prediction of the subject's location based on position change in position of joints and/or muscles.

Abstract: A method of patrolling a perimeter of a geographic area, using two or more unmanned vehicles having means for locomotion along a perimeter path. Each vehicle is equipped with at least the following systems: a navigation system operable to autonomously navigate the unmanned vehicle, an anomaly detection system, a communications system, an anomaly tracking system, operable to track, visually or by following, a detected anomaly, and an alert evaluation system. Each vehicle travels the path on a predetermined route, and is operable to broadcast an alert message to all other vehicles if that vehicle detects an anomaly, to perform an evaluation of any received alert message to determine if it will travel to an anomaly based on stored evaluation rules, and to respond to an alert message based on the evaluation.

Abstract: A method of patrolling a perimeter of a geographic area, using two or more unmanned vehicles having means for locomotion along a perimeter path. Each vehicle is equipped with at least the following systems: a navigation system operable to autonomously navigate the unmanned vehicle, an anomaly detection system, a communications system, an anomaly tracking system, operable to track, visually or by following, a detected anomaly, and an alert evaluation system. Each vehicle travels the path on a predetermined route, and is operable to broadcast an alert message to all other vehicles if that vehicle detects an anomaly, to perform an evaluation of any received alert message to determine if it will travel to an anomaly based on stored evaluation rules, and to respond to an alert message based on the evaluation.

Abstract: A system and method for estimating location and motion of an object. An image of a ground surface is obtained and a first set of features is extracted from the image. A map database is searched for a second set of features that match the first set of features and a geo-location is retrieved from the map database, wherein the geo-location is associated with the second set of features. The location is estimated based on the retrieved geo-location. The motion of the object, such as distance travelled, path travelled and/or speed may be estimated in a similar manner by comparing the location of extracted features that are present in two or more images over a selected time period.

Abstract: A system and method for estimating location and motion of an object. An image of a ground surface is obtained and a first set of features is extracted from the image. A map database is searched for a second set of features that match the first set of features and a geo-location is retrieved from the map database, wherein the geo-location is associated with the second set of features. The location is estimated based on the retrieved geo-location. The motion of the object, such as distance travelled, path travelled and/or speed may be estimated in a similar manner by comparing the location of extracted features that are present in two or more images over a selected time period.