Bayesian classifier system using a non-linear probability function and method thereof

• US 8,565,486 B2
• Filed: 01/05/2012
• Issued: 10/22/2013
• Est. Priority Date: 01/05/2012
• Status: Active Grant

• Current Assignee: Gentex Corporation
• Original Assignee: Gentex Corporation
• Inventors: Wright, David J., Bush, Gregory S., Falb, David M.
• Primary Examiner(s): AZARIAN, SEYED H
• Application Number:
  US13/343,952
• Publication Number:
  US 20130177212A1
• Time in Patent Office: 656 Days
• Field of Search: 382/100, 382103-107, 382120-123, 382/155, 382/162, 382/168, 382/173, 382/181, 382/199, 382/209, 382/219, 382/224, 382/232, 382/254, 382/274, 382/276, 382287-291, 382294-296, 382/305, 382/312, 340/12.25, 348/148, 706/12, 706/52
• US Class Current: 382/104
• CPC Class Codes: G06F 18/2415 based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G06V 10/764 using classification, e.g. of video objects
• CPC Class Codes: G06V 20/58 Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
• CPC Class Codes: G06V 20/584 of vehicle lights or traffic lights

Abstract

A classification system and method are provided, wherein the classification system includes a memory device, a processor communicatively connected to the memory device, and an input communicatively connected to the processor, wherein the input is configured to receive data comprising at least one object that is to be classified as one of an object of interest (OOI) and a nuisance of interest (NOI) based upon at least one non-Boolean attribute of the object, wherein the processor is configured as a Bayesian classifier to classify the object based upon the non-Boolean attribute using a non-linear probability function.

Claims

1. A classification system comprising:

a memory device;

a processor communicatively connected to said memory device; and

an input communicatively connected to said processor, wherein said input is configured to receive data comprising at least one object that is to be classified as one of an object of interest (OOI) and a nuisance of interest (NOI) based upon at least one non-Boolean attribute of said object;

wherein said at least one object that is to be classified is at least one of a headlight from an oncoming vehicle and a tail light of a leading vehicle;

wherein said OOI is said at least one object to be classified and said NOI is all other detected objects;

wherein said processor is configured as a Bayesian classifier to classify said object based upon said non-Boolean attribute using a non-linear probability function;

wherein said processor is further configured to determine a number of times said value of said non-Boolean attribute is within a threshold range for said OOI classification; and

wherein said processor is further configured to determine a number of times said value of said non-Boolean attribute is within a threshold range for said NOI classification.

2. The classification system of claim 1, wherein said processor is further configured to combine a plurality of said non-Boolean attributes through multiplication to produce a probability of said object'"'"'s classification.

3. The classification system of claim 1, wherein said processor is further configured to compute a likelihood that said non-Boolean attribute occurs in an OOI based upon a value of said non-Boolean attribute.

4. The classification system of claim 3, wherein said processor is further configured to compute a likelihood that said non-Boolean attribute occurs in a NOI based upon said value of said non-Boolean attribute.

5. The classification system of claim 4, wherein said processor is further configured to determine a function for said likelihood of said OOI.

6. The classification system of claim 5, wherein said processor is further configured to determine a function of said likelihood of said NOI.

7. The classification system of claim 6, wherein said processor is further configured to combine said OOI function and said NOI function to form a probability function.

8. The classification system of claim 7, wherein said processor is further configured to determine which attributes to use in an output probability equation.

9. The classification system of claim 1, wherein said processor is further configured to weight said probability function of one attribute with respect to a probability function of at least one other attribute of said object.

10. The classification system of claim 9, wherein said weighting of a probability function comprises scaling probability functions of other attributes.

11. The classification system of claim 1, wherein said input is an imager configured to image a scene forward of a vehicle.

12. The classification system of claim 11, wherein said object is classified as an OOI when it is determined said object is a headlight of an oncoming vehicle.

13. The classification system of claim 1, wherein said processor is further configured to classify said object using a second classifier.

14. A method of Bayesian classification, said method comprising the steps of:

receiving data comprising at least one object that is to be classified as one of an object of interest (OOI) and a nuisance of interest (NOI) based upon at least one non-Boolean attribute of said object;

wherein said at least one object that is to be classified is at least one of a headlight from an oncoming vehicle and a tail light of a leading vehicle;

wherein said OOI is said at least one object to be classified and said NOI is all other detected objects;

computing a likelihood that said non-Boolean attribute occurs in an OOI based upon a value of said non-Boolean attribute;

computing a likelihood that said non-Boolean attribute occurs in a NOI based upon said value of said non-Boolean attribute;

determining a number of times said value of said non-Boolean attribute is within a threshold range for said OOI classification;

determining a number of times said value of said non-Boolean attribute is within a threshold range for said NOI classification;

determining a function for said likelihood of said OOI;

determining a function for said likelihood of said NOI; and

combining said OOI and said NOI function to form a probability function.

15. The method of claim 14 further comprising the step of:

determining which attributes to use in an output probability equation.

16. A classification system comprising:

a memory device;

a processor communicatively connected to said memory device; and

an imager communicatively connected to said processor, said imager configured to image a scene forward of a vehicle and communicate image data to said processor, said image data comprising at least one object that is to be classified as one of an object of interest (OOI) and a nuisance of interest (NOI) based upon at least one non-Boolean attribute of said object, and said OOI being one of a headlight of an oncoming vehicle and a taillight of a leading vehicle;

wherein said at least one object that is to be classified is at least one of a headlight from an oncoming vehicle and a tail light of a leading vehicle;

wherein said OOI is said at least one object to be classified and said NOI is all other detected objects;

wherein said processor is configured as a Bayesian classifier to classify said object based upon said non-Boolean attribute using a non-linear probability function;

wherein said processor is further configured to determine a number of times said value of said non-Boolean attribute is within a threshold range for said OOI classification; and

wherein said processor is further configured to determine a number of times said value of said non-Boolean attribute is within a threshold range for said NOI classification.

17. The classification system of claim 16, wherein said processor is further configured to combine a plurality of said non-Boolean attributes through multiplication to produce a probability of said object'"'"'s classification.

18. The classification system of claim 16, wherein said processor is further configured to weight said probability function of one attribute with respect to a probability function of at least one other attribute of said object.