Invariant-based dimensional reduction of object recognition features, systems and methods

Patent metadata

Field	Value
Publication number	US-10410088-B2
Application number	US-201715706600-A
Country	US
Kind code	B2
Filing date	Sep 15, 2017
Priority date	Feb 19, 2014
Publication date	Sep 10, 2019
Grant date	Sep 10, 2019

Abstract

A sensor data processing system and method is described. Contemplated systems and methods derive a first recognition trait of an object from a first data set that represents the object in a first environmental state. A second recognition trait of the object is then derived from a second data set that represents the object in a second environmental state. The sensor data processing systems and methods then identifies a mapping of elements of the first and second recognition traits in a new representation space. The mapping of elements satisfies a variance criterion for corresponding elements, which allows the mapping to be used for object recognition. The sensor data processing systems and methods described herein provide new object recognition techniques that are computationally efficient and can be performed in real-time by the mobile phone technology that is currently available.

First claim

What is claimed is:

1. A biometric sensor data processing system comprising:
a memory; and
one or more image processing computers in communication with the memory, the one or more image processing computers configured to:
obtain a first sensor data set representative of at least one object, the sensor data set comprising at least one of medical image data and biometric data obtained from sensing the at least one object under a first environmental state within an environment having one or more environmental parameters that correspond to one or more environmental attributes;
generate a trait vocabulary as a function of descriptors derived from at least the first training data set;
derive a first recognition trait comprising a first plurality of elements from the first training data set according to a trait extraction algorithm, wherein the first recognition trait is derived using the trait vocabulary;
obtain a second sensor data set representative of the at least one object, the sensor data set comprising at least one of medical image data and biometric data obtained from sensing the at least one object under a second environmental state within the environment, wherein at least one environmental parameter corresponding to one or more of the environmental attributes is modified within the second environmental state;
derive a second recognition trait comprising a second plurality of elements from the second training data set according to the trait extraction algorithm; and
identify a mapping that maps one or more elements of the first recognition trait and the second recognition trait in a new representation space, wherein the mapping comprises calculating at least one variance between the first recognition trait and the second recognition trait.

2. The system of claim 1 , wherein the one or more of elements in the new representation space satisfy trait element variance criteria among corresponding elements in the first recognition trait and the second recognition trait.

3. The system of claim 1 , wherein the trait vocabulary is generated as a function of descriptor clusters derived from at least the first sensory data set.

4. The system of claim 1 , wherein a plurality of environmental parameters corresponding to one or more of the environmental attributes is modified within the second environmental state.

5. The system of claim 4 , wherein the plurality of environmental parameters is modified one environmental parameter at a time.

6. The system of claim 1 , wherein the one or more environmental parameters include at least one of a duration or length of time, a sampling or analysis frequency, and a distortion of time via slowing down or speeding up sensor data playback.

7. The system of claim 1 , wherein the one or more environmental parameters include one or more lighting properties.

8. The system of claim 7 , wherein the one or more lighting properties include one or more of light color and background color.

9. The system of claim 1 , wherein the one or more environmental parameters include one or more object properties.

10. The system of claim 9 , wherein the object properties comprise object color.

11. The system of claim 1 , wherein the one or more environmental parameters include at least one of object movement, object direction or object phase.

12. The system of claim 1 , wherein at least one of the first sensor data set and the second sensor data set comprises medical image data.

13. The system of claim 12 , wherein the medical image data includes image data of a heart beating.

14. The system of claim 1 , wherein at least one of the first sensor data set and the second sensor set comprises accelerometer data.

15. The system of claim 1 , wherein at least one of the first sensor data set and the second sensor data set comprises video data.

16. The system of claim 15 , wherein the one or more environmental parameters include a video frame rate.

17. The system of claim 1 , wherein the at least one object comprises a person.

18. The system of claim 1 , further comprising classifying the object as a type of object based on at least one of the first recognition trait and the second recognition trait.

19. The system of claim 1 , wherein the second recognition trait has a correspondence to the first recognition trait.

20. The system of claim 19 , wherein the correspondence between the first recognition trait and the second recognition trait is based on a probability.

21. The system of claim 19 , wherein the correspondence relates to at least one of a physical geometry, logical geometry, a scaling factor, and a correspondence between RGB image data.

22. The system of claim 1 , further comprising tracking a location of at least one of the first recognition trait and the second recognition trait across multiple environmental states.

23. The system of claim 1 , wherein the environment comprises a virtual or simulated environment.

24. The system of claim 1 , wherein the second recognition trait is derived using the trait vocabulary.

25. The system of claim 1 , wherein the trait extraction algorithm comprises at least one of an image processing algorithm, a classification algorithm, an object recognition algorithm, and an edge-based recognition technique.

26. The system of claim 25 , wherein the image processing algorithm comprises at least one of a SIFT, FAST, FREAK, BRIEF, ORB, BRISK, GLOH, SURF, vSLAM, SLAM, BURST, and DAISY image processing algorithm.

27. The system of claim 1 wherein the first recognition trait comprises an image descriptor.

28. The system of claim 27 , wherein the first plurality of elements comprises dimensions of the image descriptor.

29. The system of claim 1 , wherein the first recognition trait comprises a cluster of descriptors.

30. The system of claim 1 , further comprising one or more object categorization computers configured to classify the at least one object as a type of object related to medical information based on at least one of the first recognition trait and the second recognition trait.

31. The system of claim 1 , wherein at least one of the first sensor data set and the second sensor data set is related to medical imaging.

32. The system of claim 1 , wherein the identification of the mapping defines a new trait vocabulary.

33. The system of claim 1 , wherein the mapping represents a variant property as a recognition property with respect to the at least one environmental parameter adjusted as exhibited by at least some of the first plurality of elements.

34. The system of claim 1 , wherein the mapping includes a dimensionality reduction of the one or more elements.

35. The system of claim 1 , wherein the mapping comprises a non-linear mapping from the first plurality of elements and the second plurality of elements to a third plurality of elements in a new multi-dimensional space.

36. The system of claim 1 , wherein the mapping comprises a linear mapping from the first plurality of elements and the second plurality of elements to a third plurality of elements in a new invariant space.

37. The system of claim 1 , wherein trait element variance criteria identify a low variance among the corresponding elements in the traits across the first sens

Assignees

• Nant Holdings Ip Llc

Inventors

• Wnuk Kamil
• Sudol Jeremi
• Song Bing
• Siddiqui Matheen
• Mckinnon David

Classifications

• G06V10/771

  Feature selection, e.g. selecting representative features from a multi-dimensional feature space · CPC title

• G06F18/2113

  by ranking or filtering the set of features, e.g. using a measure of variance or of feature cross-correlation · CPC title

• G06K9/4671

  Physics · mapped topic

• G06K9/6232 Primary

  Physics · mapped topic

• G06K9/623

  Physics · mapped topic