Scene understanding using a neurosynaptic system

• US 9,536,179 B2
• Filed: 04/19/2016
• Issued: 01/03/2017
• Est. Priority Date: 05/29/2014
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Andreopoulos, Alexander, Appuswamy, Rathinakumar, Datta, Pallab, Esser, Steven K., Modha, Dharmendra S.
• Primary Examiner(s): AHMED, SAMIR ANWAR
• Application Number:
  US15/133,102
• Publication Number:
  US 20160232430A1
• Time in Patent Office: 259 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 18/214 Generating training patterns; Bootstrap methods, e.g. bagging or boosting
• CPC Class Codes: G06F 18/24 Classification techniques
• CPC Class Codes: G06N 3/065 Analogue means
• CPC Class Codes: G06N 3/08 Learning methods
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/20081 Training; Learning
• CPC Class Codes: G06T 7/246 using feature-based methods, e.g. the tracking of corners or segments
• CPC Class Codes: G06V 10/451 with interaction between the filter responses, e.g. cortical complex cells
• CPC Class Codes: G06V 10/955 using specific electronic processors
• CPC Class Codes: G06V 20/41 Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items segmenting video sequences G06V20/49
• CPC Class Codes: G06V 30/194 References adjustable by an adaptive method, e.g. learning
• CPC Class Codes: H04N 19/136 Incoming video signal characteristics or properties
• CPC Class Codes: H04N 9/67 for matrixing camera processing pipelines for matrixing of colour signals H04N23/85

Abstract

Embodiments of the invention provide a method for scene understanding based on a sequence of image frames. The method comprises converting each pixel of each image frame to neural spikes, and extracting features from the sequence of image frames by processing neural spikes corresponding to pixels of the sequence of image frames. The method further comprises encoding the extracted features as neural spikes, and classifying the extracted features.

Claims

1. A method, comprising:

for an image frame of a sequence of image frames;

converting, utilizing a first neurosynaptic core circuit, at least one pixel of the image frame to at least one neural spike;

processing, utilizing a second neurosynaptic core circuit, the at least one neural spike to extract at least one salient feature from the image frame;

generating, utilizing a third neurosynaptic core circuit, a map representing the at least one salient feature; and

detecting, utilizing a fourth neurosynaptic core circuit, presence of an object of interest in the image frame based on the map;

wherein each neurosynaptic core circuit comprises a plurality of electronic synapse devices interconnecting a plurality of electronic neurons to a plurality of electronic axons.

2. The method of claim 1, wherein the detecting comprises:

determining a region of the image frame that the at least one salient feature is extracted from; and

classifying the at least one salient feature to classify the object of interest.

3. The method of claim 2, wherein the detecting further comprises:

determining whether the at least one salient feature comprises at least one motion saliency feature; and

classifying the object of interest as an object of interest that is in motion in response to determining the at least one salient feature comprises at least one motion saliency feature.

4. The method of claim 2, wherein the detecting further comprises:

determining whether the at least one salient feature comprises at least one spatial saliency feature; and

classifying the object of interest as an object of interest that is motionless in response to determining the at least one salient feature comprises at least one spatial saliency feature.

5. The method of claim 1, wherein the sequence of image frames comprise a video.

6. A system, comprising:

at least one processor; and

a non-transitory processor-readable memory device storing instructions that when executed by the at least one processor causes the at least one processor to perform operations including;

for an image frame of a sequence of image frames;

converting, utilizing a first neurosynaptic core circuit, at least one pixel of the image frame to at least one neural spike;

processing, utilizing a second neurosynaptic core circuit, the at least one neural spike to extract at least one salient feature from the image frame;

generating, utilizing a third neurosynaptic core circuit, a map representing the at least one salient feature; and

detecting, utilizing a fourth neurosynaptic core circuit, presence of an object of interest in the image frame based on the map;

wherein each neurosynaptic core circuit comprises a plurality of electronic synapse devices interconnecting a plurality of electronic neurons to a plurality of electronic axons.

7. The system of claim 6, wherein the detecting comprises:

determining a region of the image frame that the at least one salient feature is extracted from; and

classifying the at least one salient feature to classify the object of interest.

8. The system of claim 7, wherein the detecting further comprises:

determining whether the at least one salient feature comprises at least one motion saliency feature; and

classifying the object of interest as an object of interest that is in motion in response to determining the at least one salient feature comprises at least one motion saliency feature.

9. The system of claim 7, wherein the detecting further comprises:

determining whether the at least one salient feature comprises at least one spatial saliency feature; and

classifying the object of interest as an object of interest that is motionless in response to determining the at least one salient feature comprises at least one spatial saliency feature.

10. The system of claim 6, wherein the sequence of image frames comprise a video.

11. A non-transitory computer-readable medium storing instructions that, when executed by at least one processor of a machine, cause the machine to perform operations comprising:

for an image frame of a sequence of image frames;

converting, utilizing a first neurosynaptic core circuit, at least one pixel of the image frame to at least one neural spike;

processing, utilizing a second neurosynaptic core circuit, the at least one neural spike to extract at least one salient feature from the image frame;

generating, utilizing a third neurosynaptic core circuit, a map representing the at least one salient feature; and

detecting, utilizing a fourth neurosynaptic core circuit, presence of an object of interest in the image frame based on the map;

wherein each neurosynaptic core circuit comprises a plurality of electronic synapse devices interconnecting a plurality of electronic neurons to a plurality of electronic axons.

12. The computer-readable medium of claim 11, wherein the detecting comprises:

determining a region of the image frame that the at least one salient feature is extracted from; and

classifying the at least one salient feature to classify the object of interest.

13. The computer-readable medium of claim 12, wherein the detecting further comprises:

determining whether the at least one salient feature comprises at least one motion saliency feature; and

classifying the object of interest as an object of interest that is in motion in response to determining the at least one salient feature comprises at least one motion saliency feature.

14. The computer-readable medium of claim 12, wherein the detecting further comprises:

determining whether the at least one salient feature comprises at least one spatial saliency feature; and

classifying the object of interest as an object of interest that is motionless in response to determining the at least one salient feature comprises at least one spatial saliency feature.

15. The computer-readable medium of claim 11, wherein the sequence of image frames comprise a video.