Method for combining boosted classifiers for efficient multi-class object detection

• US 20050249401A1
• Filed: 04/21/2005
• Published: 11/10/2005
• Est. Priority Date: 05/10/2004
• Status: Active Grant

• Current Assignee: IP3 2017, Series 200 of Allied Security Trust I (Allied Security Trust)
• Original Assignee: Siemens Corp. (Siemens AG)
• Inventors: Zhu, Ying, Comaniciu, Dorin, Bahlmann, Claus, Kohler, Thorsten, Pellkofer, Martin
• Granted Patent: US 7,769,228 B2
• Time in Patent Office: Days
• US Class Current: 382/159
• CPC Class Codes: G06F 18/211 Selection of the most significant subset of features
• CPC Class Codes: G06F 18/214 Generating training patterns; Bootstrap methods, e.g. bagging or boosting
• CPC Class Codes: G06V 10/771 Feature selection, e.g. selecting representative features from a multi-dimensional feature space
• CPC Class Codes: G06V 10/7747 Organisation of the process, e.g. bagging or boosting

Abstract

A method for training a system for detecting multi-class objects in an image or a video sequence is described. A common ensemble of weak classifiers for a set of object classes is identified. For each object class, a separate weighting scheme is adapted for the ensemble of weak classifiers. A method for detecting objects of multiple classes in an image or a video sequence is also disclosed. Each class is assigned a detector that is implemented by a weighted combination of weak classifiers such that all of the detectors are based on a common ensemble of weak classifiers. Then weights are individually set for each class.

Claims

1. A method for training a system for detecting multi-class objects in an image or a video sequence comprising the steps of:

identifying a common ensemble of weak classifiers for a set of object classes; and

for each object class, adapting a separate weighting scheme for the ensemble of weak classifiers.

2. The method of claim 1 wherein one of the object classes is a distinguished class and the ensemble of weak classifiers are selected from the distinguished class.

3. The method of claim 2 wherein the distinguished class has a high occurrence of at least one object in the image or the video sequence.

4. The method of claim 1 wherein the ensemble of weak classifiers is learned from a data set comprising all of the object classes.

5. The method of claim 4 wherein the ensemble of weak classifiers is optimized to discriminate positive objects from negative objects.

6. The method of claim 1 wherein the ensemble of weak classifiers is a combination of weak classifier ensembles, each of which is individually learned from a single object class.

7. The method of claim 6 wherein the combination is a mathematical union of the ensembles of weak classifiers.

8. The method of claim 6 wherein the combination is a mathematical intersection of the ensembles of weak classifiers.

9. The method of claim 6 wherein the combination of weak classifier ensembles is a subset determined by voting.

10. A method for detecting objects of multiple classes in an image or a video sequence, the method comprising the steps of:

assigned each class a detector that is implemented by a weighted combination of weak classifiers wherein all of the detectors are based on a common ensemble of weak classifiers, and

individually setting weights for each class.

11. The method of claim 10 wherein the scores of the detectors are utilized to classify the detected object into one of the object classes.