Trajectory classification and response

A computer-readable storage device storing instructions that are executable by one or more processors to cause the one or more processors to perform operations comprising:

• obtaining multiple sets of trajectory data, each set of trajectory data descriptive of trajectories of two or more objects, the two or more objects including a first object and a second object;
• generating multiple sets of transformed trajectory data based on the multiple sets of trajectory data, each set of transformed trajectory data corresponding to a set of the trajectory data and descriptive of the trajectories of the two or more objects in a normalized reference frame in which a movement path of the first object is constrained;
• generating feature data based on the sets of transformed trajectory data;
• performing a clustering operation based on the feature data to generate a set of trajectory clusters;
• generating training data based on the set of trajectory clusters;
• and
• using the training data to train a machine learning classifier to classify particular trajectory patterns.

A system comprising:

• one or more processors;
• and
• one or more memory devices coupled to the one or more processors and storing instructions that are executable by the one or more processors to cause the one or more processors to:
• obtain multiple sets of trajectory data, each set of trajectory data descriptive of trajectories of two or more objects, the two or more objects including a first object and a second object;
• generate multiple sets of transformed trajectory data based on the multiple sets of trajectory data, each set of transformed trajectory data corresponding to a set of the trajectory data and descriptive of the trajectories of the two or more objects in a normalized reference frame in which a movement path of the first object is constrained;
• generate feature data based on the sets of transformed trajectory data;
• perform a clustering operation based on the feature data to generate a set of trajectory clusters;
• generate training data based on the set of trajectory clusters;
• and
• use the training data to train a machine learning classifier to classify particular trajectory patterns.

A method comprising:

• obtaining trajectory data descriptive of trajectories of two or more objects, the two or more objects including a first object and a second object;
• generating transformed trajectory data based on the trajectory data, the transformed trajectory data descriptive of the trajectories of the two or more objects in a normalized reference frame in which a movement path of the first object is constrained;
• generating feature data based on the transformed trajectory data;
• providing the feature data as input to a machine learning classifier to determine a trajectory pattern associated with the trajectory data;
• and
• initiating a response action based on the trajectory pattern.

A computer-readable storage device storing instructions that are executable by one or more processors to cause the one or more processors to perform operations comprising:

• obtaining trajectory data descriptive of trajectories of two or more objects, the two or more objects including a first object and a second object;
• generating transformed trajectory data based on the trajectory data, the transformed trajectory data descriptive of the trajectories of the two or more objects in a normalized reference frame in which a movement path of the first object is constrained;
• generating feature data based on the transformed trajectory data;
• providing the feature data as input to a machine learning classifier to determine a trajectory pattern associated with the trajectory data;
• and
• initiating a response action based on the trajectory pattern.

A system comprising:

• one or more processors;
• and
• one or more memory devices coupled to the one or more processors and storing instructions that are executable by the one or more processors to cause the one or more processors to:
• obtain trajectory data descriptive of trajectories of two or more objects, the two or more objects including a first object and a second object;
• generate transformed trajectory data based on the trajectory data, the transformed trajectory data descriptive of the trajectories of the two or more objects in a normalized reference frame in which a movement path of the first object is constrained;
• generate feature data based on the transformed trajectory data;
• provide the feature data as input to a machine learning classifier to determine a trajectory pattern associated with the trajectory data;
• and
• initiate a response action based on the trajectory pattern.