Cascading video object classification

• US 10,133,922 B2
• Filed: 12/05/2014
• Issued: 11/20/2018
• Est. Priority Date: 03/03/2008
• Status: Active Grant

• Current Assignee: Motorola Solutions, Inc.
• Original Assignee: Avigilon Analytics Corporation (Motorola Solutions, Inc.)
• Inventors: Saptharishi, Mahesh, Lisin, Dimitri A., Lipchin, Aleksey, Reyzin, Igor
• Primary Examiner(s): Hogue, Dennis
• Application Number:
  US14/562,552
• Publication Number:
  US 20150092054A1
• Time in Patent Office: 1,446 Days
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• CPC Class Codes: G06F 2218/12 Classification; Matching
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/30232 Surveillance
• CPC Class Codes: G06T 7/246 using feature-based methods, e.g. the tracking of corners or segments
• CPC Class Codes: G06T 7/73 using feature-based methods
• 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 20/52 Surveillance or monitoring of activities, e.g. for recognising suspicious objects recognising microscopic objects G06V20/69
• CPC Class Codes: H04N 23/611 where the recognised objects include parts of the human body
• CPC Class Codes: H04N 23/63 by using electronic viewfinders
• CPC Class Codes: H04N 23/631 Graphical user interfaces [GUI] specially adapted for controlling image capture or setting capture parameters
• CPC Class Codes: H04N 23/66 Remote control of cameras or camera parts, e.g. by remote control devices
• CPC Class Codes: H04N 23/661 Transmitting camera control signals through networks, e.g. control via the Internet
• CPC Class Codes: H04N 7/18 Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
• CPC Class Codes: H04N 7/181 for receiving images from a plurality of remote sources

Abstract

A camera system comprises an image capturing device and an object classification module connected to the image capturing device. The object classification module is operable to determine whether or not an object in an image is a member of an object class. The object classification module includes multiple decision steps configured in a cascade configuration, wherein at least one of the multiple decision steps is operable to (a) accept an object as a member of the object class, (b) reject an object as a member of the object class, and (c) call on a next step to determine whether or not an object is a member of the object class.

Claims

1. A method of constructing an object classifier in a camera system, comprising:

receiving image data including representations of objects, the objects being labeled as either members or non-members of an object class in an object classifier, and generating metadata related to the objects;

processing the image data to extract a set of features for each of the objects;

for each of the features of the set of features for each of the objects, searching a set of discriminant functions to select for a given feature a discriminant function that optimizes separation of the labeled objects, the selected discriminant function being associated with its given feature to form one of a group of multiple feature/transformation combinations, wherein each of the discriminant functions comprises a weight vector and a feature vector; and

selecting for inclusion in the object classifier a feature/transformation combination from the group, the selected feature/transformation combination maximizing object classification performance of the object classifier in comparison to non-selected ones of the multiple feature/transformation combinations.

2. A method according to claim 1, wherein the selected feature/transformation combination is a first feature/transformation combination corresponding to a first stage of the object classifier, further comprising selecting a second feature/transformation combination for a second stage, wherein object classification performance of the first stage is accounted for when the second feature/transformation combination is selected.

3. A method according to claim 2, wherein the first and second feature/transformation combinations include the same feature, the same discriminant function, or the same feature and the same discriminant function.

4. A method according to claim 1, wherein the object classifier includes an existing feature/transformation combination, and wherein the selected feature/transformation combination is used to replace the existing feature/transformation combination when the selected feature/transformation combination improves the object classification performance of the object classifier to thereby provide an improved object classifier.

5. A camera system, comprising:

a processor configured to receive image data including representations of objects, the objects being labeled as either members or non-members of an object class in an object classifier, to generate metadata related to the objects, and to process the image data to extract a set of features for each of the objects;

for each of the features of the set of features for each of the objects, the object classifier being configured to search a set of discriminant functions to select for a given feature a discriminant function that optimizes separation of the labeled objects, the selected discriminant function being associated with its given feature to form one of a group of multiple feature/transformation combinations, wherein each of the discriminant functions comprises a weight vector and a feature vector, and

the processor being further configured to select for inclusion in the object classifier a feature/transformation combination from the group, the selected feature/transformation combination maximizing object classification performance of the object classifier in comparison to non-selected ones of the multiple feature/transformation combinations.

6. A camera system according to claim 5, wherein the selected feature/transformation combination is a first feature/transformation combination corresponding to a first stage of the object classifier, the processor being further configured to select a second feature/transformation combination for a second stage, wherein object classification performance of the first stage is accounted for when the second feature/transformation combination is selected.

7. A camera system according to claim 6, wherein the first and second feature/transformation combinations include the same feature, the same discriminant function, or the same feature and the same discriminant function.

8. A method according to claim 5, wherein the object classifier includes an existing feature/transformation combination, and wherein the selected feature/transformation combination is used to replace the existing feature/transformation combination when the selected feature/transformation combination improves the object classification performance of the object classifier to thereby provide an improved object classifier.