CONTEXT-BASED PRIORS FOR OBJECT DETECTION IN IMAGES

• US 20170011281A1
• Filed: 10/13/2015
• Published: 01/12/2017
• Est. Priority Date: 07/09/2015
• Status: Active Grant

• Current Assignee: Qualcomm, Inc.
• Original Assignee: Qualcomm, Inc.
• Inventors: DIJKMAN, Daniel Hendricus Franciscus, TOWAL, Regan Blythe, ANNAPUREDDY, Venkata Sreekanta Reddy
• Granted Patent: US 10,410,096 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 18/24 Classification techniques
• CPC Class Codes: G06N 3/02 Neural networks
• CPC Class Codes: G06V 10/255 Detecting or recognising potential candidate objects based on visual cues, e.g. shapes
• CPC Class Codes: G06V 10/454 Integrating the filters into a hierarchical structure, e.g. convolutional neural networks [CNN]
• CPC Class Codes: G06V 10/768 using context analysis, e.g. recognition aided by known co-occurring patterns
• CPC Class Codes: G06V 20/35 Categorising the entire scene, e.g. birthday party or wedding scene

Abstract

Context-based priors are utilized in machine learning networks (e.g., neural networks) for detecting objects in images. The likely locations of objects are estimated based on context labels. A machine learning network identifies a context label of an entire image. Based on the, the network selects a set of likely regions for detecting objects of interest in the image.

Claims

1. A method of object detection, comprising:

identifying a context label of an entire image; and

selecting a set of likely regions for detecting objects of interest in the image based at least in part on an identified context label.

2. The method of claim 1, further comprising training a neural network to refine the set of likely regions.

3. The method of claim 1, further comprising creating the context label based at least in part on user input.

4. The method of claim 1, further comprising creating the context label based at least in part on unsupervised learning.

5. The method of claim 1, further comprising generating the set of likely regions based at least in part on the context label.

6. The method of claim 1, further comprising:

identifying another context label; and

selecting another set of likely regions of detecting objects of interest in the image based at least in part on the other identified context label.

7. The method of claim 1, further comprising training a neural network to determine for each of the likely regions whether an object of interest is present.

8. The method of claim 1, further comprising training a neural network to classify each of the likely regions according to the context label.

9. An apparatus for object detection, comprising:

a memory; and

at least one processor coupled to the memory, the at least one processor configured;

to identify a context label of an entire image; and

to select a set of likely regions for detecting objects of interest in the image based at least in part on an identified context label.

10. The apparatus of claim 9, in which the at least one processor is further configured to train a neural network to refine the set of likely regions.

11. The apparatus of claim 9, in which the at least one processor is further configured to create the context label based at least in part on user input.

12. The apparatus of claim 9, in which the at least one processor is further configured to create the context label based at least in part on unsupervised learning.

13. The apparatus of claim 9, in which the at least one processor is further configured to generate the set of likely regions based at least in part on the context label.

14. The apparatus of claim 9, in which the at least one processor is further configured:

to identifying another context label; and

to select another set of likely regions of detecting objects of interest in the image based at least in part on the other identified context label.

15. The apparatus of claim 9, in which the at least one processor is further configured to train a neural network to determine for each of the likely regions whether an object of interest is present.

16. The apparatus of claim 9, in which the at least one processor is further configured to train a neural network to classify each of the likely regions according to the context label.

17. A non-transitory computer-readable medium for object detection having non-transitory program code recorded thereon, the program code comprising:

program code to identify a context label of an entire image; and

program code to select a set of likely regions for detecting objects of interest in the image based at least in part on an identified context label.

18. The computer-readable medium of claim 17, further comprising program code to train a neural network to refine the set of likely regions.

19. The a computer-readable medium of claim 17, further comprising program code to create the context label based at least in part on user input.

20. The computer-readable medium of claim 17, further comprising program code to create the context label based at least in part on unsupervised learning.

21. The computer-readable medium of claim 17, further comprising program code to generate the set of likely regions based at least in part on the context label.

22. The computer-readable medium of claim 17, further comprising:

program code to identifying another context label; and

program code to select another set of likely regions of detecting objects of interest in the image based at least in part on the other identified context label.

23. The computer-readable medium of claim 17, further comprising program code to train a neural network to determine for each of the likely regions whether an object of interest is present.

24. The computer-readable medium of claim 17, further comprising program code to train a neural network to classify each of the likely regions according to the context label.

25. An apparatus for wireless communication, comprising:

means for identifying a context label of an entire image; and

means for selecting a set of likely regions for detecting objects of interest in the image based at least in part on an identified context label.

26. The apparatus of claim 25, further comprising means for training a neural network to refine the set of likely regions.

27. The apparatus of claim 25, further comprising means for creating the context label based at least in part on unsupervised learning.

28. The apparatus of claim 25, further comprising:

means for identifying another context label; and

means for selecting another set of likely regions of detecting objects of interest in the image based at least in part on the other identified context label.