Track prediction and identification via particle motion with intent
First Claim
Patent Images
1. A method of tracking a target executed by one or more processors, comprising:
- sensing, by a sensor, a target in an area of interest, the target having a type and the type having at least one mobility constraint associated therewith;
creating, by one or more processors, a set of particles to represent the sensed target;
attributing, by the one or more processors, to each particle a functional intent, wherein a probability density of the particles in the set of particles correlates to a probability the density of possible intents that guide movements of the sensed target, and wherein the functional intent of a specific particle is a combination of behavioral goals of a person guiding the sensed target and the mobility constraint of the type of the sensed target;
grouping, by the one or more processors, the set of particles based on attributed functional intents;
defining at least one vehicle type having predetermined vehicle characteristics;
identifying, by the one or more processors, objects within the area of interest with which the sensed target may interact;
allocating, by the one or more processors, to each object an attraction-repulsion factor for each functional intent;
correlating, by the one or more processors, functional intents, vehicle types, vehicle characteristics, and objects having attraction-repulsion factors with defined mobility constraints for the area of interest, to define a rule of behavior for each particle having a particular intent, wherein said rule of behavior defines a relationship between the functional intent of a particle and the objects within the area of interest;
applying, by the one or more processors, said rule of behavior to each particle to predict a movement and geographic location for each particle representing the sensed target; and
moving, by the one or more processors, each particle representing a predicted location of the target in accordance with the observed movements of the sensed target, said rule of behavior applied to each particle and geographic location for each particle.
1 Assignment
0 Petitions
Accused Products
Abstract
Provided is a system and method for tracking and identifying a target in an area of interest based on a comparison of predicted target behavior or movement and sensed target behavior or movement. Incorporating aspects of both particle diffusion and mobility constraint models with target intent derivations, the system may continuously track a target while simultaneously refining target identification information. Alternatively, the system and method are applied to reacquire a target track based on prioritized intents and predicted target location.
4 Citations
18 Claims
-
1. A method of tracking a target executed by one or more processors, comprising:
-
sensing, by a sensor, a target in an area of interest, the target having a type and the type having at least one mobility constraint associated therewith; creating, by one or more processors, a set of particles to represent the sensed target; attributing, by the one or more processors, to each particle a functional intent, wherein a probability density of the particles in the set of particles correlates to a probability the density of possible intents that guide movements of the sensed target, and wherein the functional intent of a specific particle is a combination of behavioral goals of a person guiding the sensed target and the mobility constraint of the type of the sensed target; grouping, by the one or more processors, the set of particles based on attributed functional intents; defining at least one vehicle type having predetermined vehicle characteristics; identifying, by the one or more processors, objects within the area of interest with which the sensed target may interact; allocating, by the one or more processors, to each object an attraction-repulsion factor for each functional intent; correlating, by the one or more processors, functional intents, vehicle types, vehicle characteristics, and objects having attraction-repulsion factors with defined mobility constraints for the area of interest, to define a rule of behavior for each particle having a particular intent, wherein said rule of behavior defines a relationship between the functional intent of a particle and the objects within the area of interest; applying, by the one or more processors, said rule of behavior to each particle to predict a movement and geographic location for each particle representing the sensed target; and moving, by the one or more processors, each particle representing a predicted location of the target in accordance with the observed movements of the sensed target, said rule of behavior applied to each particle and geographic location for each particle. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12)
-
-
13. A system for tracking and identifying a target, comprising:
-
at least one sensor for sensing the target in an area of interest, the target having a type and the type having at least one mobility constraint associated therewith; a first database residing on a first computer storage medium and including a plurality of vehicle types and corresponding vehicle characteristics; a second database residing on a second computer storage medium and including a set of particles to represent the sensed target and a plurality of functional intents attributed to each vehicle type, wherein the set of particles are grouped to represent the sensed target, and wherein a probability density of the particles in the set of particles correlates to a probability the density of possible intents that guide movements of the sensed target, and wherein the functional intent of a specific particle is a combination of behavioral goals of a person guiding the sensed target and the mobility constraint of the type of the sensed target; a third database residing on a third computer storage medium and populated with objects in the area of interest having a predetermined attraction-repulsion factor, wherein the attraction-repulsion factor is related to a relationship between a given functional intent and a given object; and a processor for correlating functional intents, vehicle types, vehicle characteristics, and objects having attraction-repulsion factors in the first, second, and third databases with pre-determined mobility constraints for the area of interest; for defining a rule of behavior for each particle having a particular intent, wherein said rule of behavior defines a relationship between the functional intent of a particle and the objects within the area of interest; for applying said rule of behavior to each particle to predict a movement and geographic location for each particle representing the sensed target; and for moving each particle representing a predicted location of the target in accordance with the observed movements of the sensed target, said rule of behavior applied to each particle and geographic location for each particle. - View Dependent Claims (14, 15, 16, 17, 18)
-
Specification