Face and license plate detection in street level images with 3-D road width features estimated from laser data

• US 8,971,646 B1
• Filed: 06/06/2014
• Issued: 03/03/2015
• Est. Priority Date: 01/26/2012
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Wu, Bo
• Primary Examiner(s): Bhatnagar, Anand
• Assistant Examiner(s): PARK, SOO JIN
• Application Number:
  US14/297,949
• Time in Patent Office: 270 Days
• Field of Search: None
• US Class Current: 382/224
• CPC Class Codes: G06V 20/10 Terrestrial scenes scenes under surveillance with static cameras G06V20/52; scenes perceived from the exterior of a vehicle G06V20/56; scenes perceived from the interior of a vehicle G06V20/59
• CPC Class Codes: G06V 20/176 Urban or other man-made structures
• CPC Class Codes: G06V 20/54 of traffic, e.g. cars on the road, trains or boats
• CPC Class Codes: G06V 20/63 Scene text, e.g. street names

Abstract

A computer implemented system for identifying license plates and faces in street-level images is disclosed. The system includes an object detector configured to determine a set of candidate objects in the image, a feature vector module configured to generate a set of feature vectors using the object detector to generate a feature vector for each candidate object in the set of candidate objects, a composite feature vector module to generate a set of composite feature vectors by combining each generated feature vector with a corresponding road or street description of the object in question, and an identifier module configured to identify objects of a particular type using a classifier that takes a set of composite feature vectors as input and returns a list of candidate objects that are classified as being of the particular type as output.

Claims

1. A computer-implemented method for generating a classifier for detecting objects in a digital image, the method comprising:

providing, for each object in a set of objects in one or more digital images, a description of a roadway or a street in which or near which each object appears, the description including a corresponding road or street width estimate;

generating, by one or more processors, a set of composite feature vectors by combining one or more selected feature vectors with the corresponding roadway or street description including the width estimate, each composite feature vector including attributes of a given one of the set of objects; and

generating, by the one or more processors, an object classifier that filters out false positives using the composite feature vectors.

2. The method of claim 1, wherein each selected feature vector includes a detection score indicating a likelihood that a given object in the set of objects is of a predetermined type of interest.

3. The method of claim 2, wherein the predetermined type of interest is either a license plate type or a face type.

4. The method of claim 1, wherein the generating the object classifier comprises using a Support Vector Machine (SVD) algorithm to generate the object classifier.

5. The method of claim 1, wherein the width estimate represents an effective road or street width associated with a given object.

6. The method of claim 5, wherein the effective road or street width varies with position of the given object in each image.

7. The method of claim 1, wherein the width estimate is a three-dimensional width estimate.

8. A computer-implemented method for identifying objects in a digital image, wherein the objects appear near or in a street or roadway, the method comprising:

generating, by one or more processors, a set of feature vectors using an object detector to generate a feature vector for each candidate object in a set of candidate objects, each candidate object having a description of a roadway or street in which or near which the candidate object appears, the description including a corresponding roadway or street width estimate;

generating, by the one or more processors, a set of composite feature vectors by combining each generated feature vector with the corresponding roadway or street description; and

identifying, by the one or more processors, objects of a particular type.

9. The method of claim 8, wherein each generated feature vector includes a detection score indicating a likelihood that a given object in the set of objects is of a predetermined type of interest.

10. The method of claim 9, wherein the predetermined type of interest is either a license plate type or a face type.

11. The method of claim 8, wherein the width estimate represents an effective road or street width associated with a given object.

12. The method of claim 11, wherein the effective road or street width varies with position of the given object in each image.

13. The method of claim 8, wherein the width estimate is a three-dimensional width estimate.

14. A computer-implemented system for generating a classifier for detecting objects in a digital image, the system comprising:

a feature vector module configured to generate a set of feature vectors for each object in a set of objects, each object having a description of a roadway or street in which or near which the object appears, the description including a corresponding roadway or street width estimate;

a composite feature vector module configured to generate a set of composite feature vectors by combining each generated feature vector with the corresponding road or street description; and

an object classifier module configured to generate an object classifier used to identify objects of a particular type.

15. The system of claim 14, wherein the feature vector module is further configured to detect one or both of license plates or faces.

16. The system of claim 14, wherein each generated feature vector includes a detection score indicating a likelihood that a given object in the set of objects is of a predetermined type of interest.

17. The system of claim 16, wherein the predetermined type of interest is either a license plate type or a face type.

18. The system of claim 14, wherein the width estimate represents an effective road or street width associated with a given object.

19. The system of claim 18, wherein the effective road or street width varies with position of the given object in each image.

20. The system of claim 14, wherein the width estimate is a three-dimensional width estimate.