Semantic representation module of a machine-learning engine in a video analysis system

1. A computer-implemented method for processing data describing a scene depicted in a sequence of video frames, the method comprising:

receiving input data describing one or more objects detected in the scene, wherein the input data includes at least a classification for each of the one or more objects;

identifying one or more primitive events, wherein each primitive event provides a semantic value describing a behavior engaged in by a corresponding one of the objects depicted in the sequence of video frames, and wherein each primitive event has an assigned primitive event symbol;

generating, for one or more of the objects, a primitive event symbol stream which includes the primitive event symbols corresponding to the primitive events identified for a respective object;

generating, for one or more of the objects, a phase space symbol stream, wherein the phase space symbol stream describes a trajectory for a respective object through a phase space domain;

combining the primitive event symbol stream and the phase space symbol stream for each respective object to form a first vector representation of that object; and

passing the first vector representations to a machine learning engine configured to identify patterns of behavior for each object classification from the first vector representation.

2. The computer-implemented method of claim 1 , further comprising, applying a singular value decomposition (SVD) to the first vector representations to generate a second vector representations from the first vector representations, wherein the second vector representations reduce the dimensionality of the first vector representations.

3. The computer-implemented method of claim 1 , wherein the classification for an object specifies that the object depicted in the sequence of video frames depicts one of a vehicle object, a person object, or an unknown object.

4. The computer-implemented method of claim 3 , wherein the object is classified as a person, and wherein the input data further includes a posture of the person as depicted in the sequence of video frames.

5. The computer-implemented method of claim 1 , wherein the phase space domain specifies a three-dimensional position of the object as depicted within the scene.

6. The computer-implemented method of claim 1 , wherein input data further describes trajectories of one or more of the objects depicted within the scene.

7. The computer-implemented method of claim 1 , wherein the input data includes a trajectory of one or more of the objects depicted within the scene and includes a velocity determined for one or more of the objects depicted within the scene, and wherein the phase space symbol stream is generated from the trajectories and velocities of the one or more objects.

8. A non-transitory computer-readable medium containing a program, which, when executed on a processor is configured to perform an operation for processing data describing a scene depicted in a sequence of video frames, comprising:

receiving input data describing one or more objects detected in the scene, wherein the input data includes at least a classification for each of the one or more objects;

identifying one or more primitive events, wherein each primitive event provides a semantic value describing a behavior engaged in by a corresponding one of the objects depicted in the sequence of video frames, and wherein each primitive event has an assigned primitive event symbol;

generating, for one or more of the objects, a primitive event symbol stream which includes the primitive event symbols corresponding to the primitive events identified for a respective object;

generating, for one or more of the objects, a phase space symbol stream, wherein the phase space symbol stream describes a trajectory for a respective object through a phase space domain;

combining the primitive event symbol stream and the phase space symbol stream for each respective object to form a first vector representation of that object; and

passing the first vector representations to a machine learning engine configured to identify patterns of behavior for each object classification from the first vector representation.

9. The non-transitory computer-readable medium of claim 8 , wherein the operation further comprises, applying a singular value decomposition (SVD) to the first vector representations to generate a second vector representation from each first vector representation, wherein the second vector representations reduce the dimensionality of the corresponding first vector representation.

10. The non-transitory computer-readable medium of claim 9 , wherein the classification for an object specifies that the object depicted in the sequence of video frames depicts one of a vehicle object, a person object, or an unknown object.

11. The non-transitory computer-readable medium of claim 10 , wherein the object is classified as a person, and wherein the input data further includes a posture of the person as depicted in the sequence of video frames.

12. The non-transitory computer-readable medium of claim 9 , wherein the phase space domain specifies a three-dimensional position of the object as depicted within the scene.

13. The non-transitory computer-readable medium of claim 9 , wherein input data further describes trajectories of one or more of the objects depicted within the scene.

14. The non-transitory computer-readable medium of claim 9 , wherein the input data includes a trajectory of one or more of the objects depicted within the scene and includes a velocity determined for one or more of the objects depicted within the scene, and wherein the phase space symbol stream is generated from the trajectories and velocities of the one or more objects.

15. A system, comprising:

a video input source;

a processor; and

a memory storing a machine learning engine, wherein the machine learning engine is configured to:

receive input data describing one or more objects detected in the scene, wherein the input data includes at least a classification for each of the one or more objects;

identifying one or more primitive events, wherein each primitive event provides a semantic value describing a behavior engaged in by a corresponding one of the objects depicted in the sequence of video frames, and wherein each primitive event has an assigned primitive event symbol;

generate, for one or more of the objects, a primitive event symbol stream which includes the primitive event symbols corresponding to the primitive events identified for a respective object;

generate, for one or more of the objects, a phase space symbol stream, wherein the phase space symbol stream describes a trajectory for a respective object through a phase space domain;

combine the primitive event symbol stream and the phase space symbol stream for each respective object to form a first vector representation of that object; and

pass the first vector representations to a machine learning engine configured to identify patterns of behavior for each object classification from the first vector representation.

16. The system of claim 15 , wherein the machine learning engine is further configured to apply a singular value decomposition (SVD) to the first vector representations to generate a second vector representations from the first vector representations, wherein the second vector representations reduce the dimensionality of the first vector representations.

17. The system of claim 15 , wherein the classification for an object specifies that the object depicted in the sequence of video frames depicts one of a vehicle object, a person object, or an unknown object.

18. The system of claim 17 , wherein the object is classified as a person, and wherein the input data further includes a posture of the person as depicted in the sequence of video frames.

19. The system of claim 15 , wherein the phase space domain specifies a three-dimensional position of the object as depicted within the scene.

20. The system of claim 15 , wherein input data further describes trajectories of one or more of the objects depicted within the scene.

21. The system of claim 15 , wherein the input data includes a trajectory of one or more of the objects depicted within the scene and includes a velocity determined for one or more of the objects depicted within the scene, and wherein the phase space symbol stream is generated from the trajectories and velocities of the one or more objects.

22. A computer-implemented method for processing data describing a scene depicted in a sequence of video frames, the method comprising:

receiving input data describing one or more objects detected in the scene, wherein the input data includes at least a classification for each of the one or more objects;

identifying one or more primitive events, wherein each primitive event provides a semantic value describing a behavior engaged in by a first one of the objects depicted in the sequence of video frames and wherein each primitive event has an assigned primitive event symbol;

generating, for the first object, a primitive event symbol stream which includes the primitive event symbols corresponding to the primitive events identified for the first object; and

generating, for the first object, a phase space symbol stream, wherein the phase space symbol stream describes a trajectory for the first object through a phase space domain; and

outputting the primitive event symbol stream and the phase space symbol stream.

23. The computer-implemented method of claim 22 , wherein the classification for the first object specifies that the first object depicted in the sequence of video frames depicts one of a vehicle object, a person object, and an unknown object.

24. The computer-implemented method of claim 23 , wherein the first object is classified as a person, and wherein the input data further includes a posture of the person as depicted in the sequence of video frames.

25. The computer-implemented method of claim 22 , wherein the phase space domain specifies a position of the first object as depicted within the scene.