Infrared traffic sensor with feature curve generation

• US 5,995,900 A
• Filed: 01/24/1997
• Issued: 11/30/1999
• Est. Priority Date: 01/24/1997
• Status: Expired due to Fees

• Current Assignee: Northrop Grumman Systems Corporation (Northrop Grumman Corporation)
• Original Assignee: Grumman Corp. (Northrop Grumman Corporation)
• Inventors: Hsiao, Stephen, Farinaccio, Joseph, Hauck, Fred
• Primary Examiner(s): Cuchlinski, Jr., William A.
• Assistant Examiner(s): Donnelly, Arthur D.
• Application Number:
  US08/788,306
• Time in Patent Office: 1,040 Days
• Field of Search: 701/117, 701/118, 701/119, 340/907, 348/148, 348/149, 348/164, 364/572, 364/724.011
• US Class Current: 701/117
• CPC Class Codes: G08G 1/04 using optical or ultrasonic detectors

Abstract

The present invention is an infrared traffic sensor with feature curve generation to derive empirical information for determining traffic patterns. A real-time IR image camera is positioned over an automobile and truck traffic thoroughfare for collecting video image data of the traffic thoroughfare. Data in the form of a video signal taken by the infrared video camera is received by a signal processing unit for processing the data. The processed data is used to generate statistical feature curves from which the empirical traffic information such as the number of vehicles, the speed of the vehicles, and the classification of the vehicles are determined.

Claims

1. A traffic monitoring system for monitoring a thoroughfare with vehicles traveling on the thoroughfare, comprising:

a detector for capturing image data of the thoroughfare;

a processor in electrical communication with the detector for receiving the image data, the processor comprising;

1) a background generator operative to remove the effects of system noise, performance anomalies, and environmental parameters from the image data comprising;

(a) a first memory for storing a single frame captured from said detector as the reference frame;

(b) a second memory for storing a second single frame from said detector at a subsequent time;

(c) a third memory for storing a preselected value representing a frame without a vehicle;

(d) a first comparator for comparing said reference frame and said second single frame to determine a background frame;

(e) a second comparator for comparing said background frame to said predetermined value; and

(f) a fourth memory for storing the background frame with least value compared to the predetermined value to designate a vehicle free background;

2) a curve generator in electrical communication with the background generator for producing statistical feature curves representing a series of quantitative values; and

3) an information processor in electrical communication with the curve generator for receiving the feature curves and deriving empirical data representing movement patterns of the vehicles within the thoroughfare based on the feature curves;

means in electrical communication with the processor for receiving the empirical data and determining from the empirical data an amount of vehicles, speed assessment of the vehicles, and a classification of the vehicles within the thoroughfare captured by the image data.

2. The invention as set forth in claim 1, wherein the detector is an infrared camera and the image data is captured as infrared spectra and represents a region of interest.

3. The invention as set forth in claim 2, wherein the each feature curve provides a spatial distribution of energy in the infrared spectra in a vertical direction in the region of interest.

4. The invention as set forth in claim 3, further comprising:

means for calculating standard deviations of the image data over each region of interest on a line by line basis; and

means for comparing each standard deviation with a position number of the line from which the respective standard deviation is calculated.

5. The traffic monitoring system as set forth in claim 2, wherein the background generator includes a comparator for comparing the region of interest to a reference background set to remove the effects of differences in pixel sensitivities.

6. The traffic monitoring system as set forth in claim 2, wherein the background generator includes a comparator for comparing the region of interest to a reference background set to remove the effects of differences in lighting, shadows and weather.

7. The traffic monitoring system as set forth in claim 2, wherein the reference background comprises a two dimensional standard deviation of the difference between a first, reference frame of the region of interest and a next frame of the region of interest.

8. The invention as set forth in claim 1, wherein the processor is a signal processing unit.

9. The invention as set forth in claim 1, wherein the image data is received instantly by the processor and processed in real-time.

10. The invention as set forth in claim 1, wherein the image data is received by the processor and stored for future processing.

11. A traffic monitoring method for monitoring a thoroughfare with vehicles traveling on the thoroughfare, the method comprising;

capturing image data as infrared spectra of the thoroughfare represented by a region of interest defined by a vertical and horizontal axis with a plurality of rows of pixels;

processing said image data through a background generator operative to remove the effects of system noise, performance anomalies, and environmental parameters from the image data by completing the steps of;

(a) storing a single frame captured from said detector as the reference frame;

(b) storing a second single frame at a subsequent time;

(c) storing a predetermined value representing a frame without a vehicle;

(d) comparing said reference frame and said second single frame to determine a background frame;

(e) comparing said background frame to said predetermined value;

(f) storing the background frame with the least value compared to the predetermined value to indicate a vehicle free background;

(g) repeating said steps periodically to produce subsequent representative background frames to be used as a reference with respect to the dynamic conditions of the thoroughfare;

determining a spatial distribution of energy in the infrared spectra in a vertical direction in the region of interest by generating a feature curve for each region of interest;

deriving empirical data representing movement patterns of the vehicles within the thoroughfare based on the feature curves; and

calculating from the empirical data an amount of vehicles, speed assessment of the vehicles, and a classification of the vehicles within the thoroughfare captured by the image data.

12. The invention as set forth in claim 11, wherein the spatial distribution is determined by:

calculating standard deviations of the image data over each region of interest on a line by line basis; and

comparing each standard deviation with a position number of the line from which the respective standard deviation is calculated.

13. The invention as set forth in claim 12, wherein the standard deviations are calculated with the following expression:

##EQU3## across each row of pixels in the region of interest, wherein n varies from 1 up to a width of the region of interest in pixels, i is the row number, x is the pixel value in the i^th row, and x is the mean value of the i^th row of pixels.

14. The invention as set forth in claim 11, wherein the empirical data is determined by:

comparing each standard deviation of the respective row of pixels with the vertical axis;

associating the compared standard deviations and vertical axis with infrared views of vehicle attributes.

15. A traffic monitoring system for monitoring a thoroughfare with vehicles traveling on the thoroughfare, comprising:

a detector for capturing image data of the thoroughfare, said data defined by a vertical and horizontal axis with a plurality of rows of pixels;

a processor in electrical communication with the detector for receiving the image data, the processor comprising;

1) a background generator operative to remove the effects of system noise, performance anomalies, and environmental parameters from the image data comprising;

(a) a first memory for storing a single frame captured from said detector as the reference frame;

(b) a second memory for storing a second single frame from said detector at a subsequent time;

(c) a third memory for storing a preselected value representing a frame without a vehicle;

(d) a first comparator for comparing said reference frame and said second single frame to determine a background frame;

(e) a second comparator for comparing said background frame to said predetermined value; and

(f) a fourth memory for storing the background frame with least value compared to the predetermined value to designate a vehicle free background;

2) a curve generator in electrical communication with the background generator for producing statistical feature curves representing a series of quantitative values; and

3) an information processor in electrical communication with the curve generator for receiving the feature curves and deriving empirical data representing movement patterns of the vehicles within the thoroughfare based on the feature curves;

a computer program operating in electrical communication with said processor for producing statistical feature curves representing a series of quantitative values and for deriving empirical data representing movement patterns of the vehicles within the thoroughfare based on the feature curves; and

means in electrical communication with the processor for receiving the empirical data and determining from the empirical data an amount of vehicles, speed assessment of the vehicles, and a classification of the vehicles within the thoroughfare captured by the image data.

16. The invention as set forth in claim 15, wherein the detector is an infrared camera and the image data is captured as infrared spectra.

17. The invention as set forth in claim 16, wherein each feature curve provides a spatial distribution of energy in the infrared spectra in a vertical direction in the region of interest.

18. The invention as set forth in claim 17, further comprising:

means for calculating standard deviations of the image data over each region of interest on a line by line basis; and

means for comparing each standard deviation with a position number of the line from which the respective standard deviation is calculated.

19. The invention as set forth in claim 18, further comprising means for calculating the standard deviations with the following expression:

##EQU4## across each row of pixels in the region of interest, wherein n varies from 1 up to a width of the region of interest in pixels, i is the row number, x is the pixel value in the i^th row, and x is the mean value of the i^th row of pixels.

20. The invention as set forth in claim 16, further comprising:

means for comparing each standard deviation of the respective row of pixels with the vertical axis; and

means for associating the compared standard deviations and vertical axis with infrared views of vehicle attributes.

21. The traffic monitoring system as set forth in claim 15, wherein the background generator includes a comparator for comparing the region of interest to a reference background set to remove the effects of differences in pixel sensitivities.

22. The traffic monitoring system as set forth in claim 15, wherein the background generator includes a comparator for comparing the region of interest to a reference background set to remove the effects of differences in lighting, shadows and weather.

23. The traffic monitoring system as set forth in claim 15, wherein the reference background comprises a two dimensional standard deviation of the difference between a first, reference frame of the region of interest and a next frame of the region of interest.