Systems and methods for road acoustics and road video-feed based traffic estimation and prediction

• US 8,723,690 B2
• Filed: 01/26/2011
• Issued: 05/13/2014
• Est. Priority Date: 01/26/2011
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Kalyanaraman, Shivkumar, Srivastava, Biplav, Tyagi, Vivek
• Primary Examiner(s): Wu, Daniel
• Assistant Examiner(s): Barakat, Mohamed
• Application Number:
  US13/014,169
• Publication Number:
  US 20120188102A1
• Time in Patent Office: 1,203 Days
• Field of Search: 340/932.934, 340/937, 340/943, 707/117, 707/118
• US Class Current: 340/937
• CPC Class Codes: G08G 1/0116 from roadside infrastructure, e.g. beacons
• CPC Class Codes: G08G 1/0133 for classifying traffic situation
• CPC Class Codes: G08G 1/0141 for traffic information dissemination

Abstract

Methods and arrangements for employing roadside acoustics sensing in ascertaining traffic density states. Traffic monitoring input is received from a road segment, the traffic monitoring input including traffic audio input. The traffic monitoring input is processed and the processed traffic monitoring input is classified with a predetermined traffic density state. The classified traffic monitoring input is combined with other classified traffic monitoring input.

Claims

1. A method comprising:

receiving traffic monitoring input from a road segment over a predetermined time period, the traffic monitoring input including traffic audio input;

processing the traffic monitoring input into a time-blocked signal;

classifying the processed traffic monitoring input into a predefined traffic density state, via applying a first statistical classifier;

combining the classified traffic monitoring input with other classified traffic monitoring input which is classified via at least one additional statistical classifier; and

thereupon determining a classification of the road segment over the predetermined time period into a predefined traffic density state.

2. The method according to claim 1, wherein the traffic monitoring input further includes traffic video input.

3. The method according to claim 1, wherein said processing comprises deriving spectral and temporal features from the traffic monitoring input.

4. The method according to claim 1, wherein:

said receiving comprises receiving individual readings of traffic monitoring input over the predetermined time period; and

said processing comprises bundling the readings of traffic monitoring input over the predetermined time period into the time-blocked signal.

5. The method according to claim 1, wherein said classifying comprises:

applying a plurality of statistical classifiers to the processed traffic monitoring input; and

fusing output from the plurality of statistical classifiers and classifying the fused output into a predefined traffic density state.

6. The method according to claim 1, wherein the predetermined traffic density state corresponds to a discrete range of traffic speeds.

7. The method according to claim 1, wherein the first statistical classifier and at least one additional statistical classifier employ at least one pre-trained statistical model.

8. The method according to claim 7, wherein the at least one pre-trained statistical model is trained on predetermined traffic density states.

9. The method according to claim 8, wherein each predetermined traffic density state corresponds to a discrete range of traffic speeds.

10. The method according to claim 8, wherein the at least one pre-trained statistical model is trained on varied climate conditions.

11. The method according to claim 8, wherein the at least one pre-trained statistical model is trained on road segments of similar surface.

12. The method according to claim 11, wherein:

each predetermined traffic density state corresponds to a discrete range of traffic speeds; and

the at least one pre-trained statistical model is trained on varied climate conditions.

13. An apparatus comprising:

at least one processor; and

a computer readable storage medium having computer readable program code embodied therewith and executable by the at least one processor, the computer readable program code comprising;

computer readable program code configured to receive traffic monitoring input from a road segment over a predetermined time period, the traffic monitoring input including traffic audio input;

computer readable program code configured to process the traffic monitoring input into a time-blocked signal;

computer readable program code configured to classify the processed traffic monitoring input into a predefined traffic density state, via applying a first statistical classifier;

computer readable program code configured to combine the classified traffic monitoring input with other classified traffic monitoring input which is classified via at least one additional statistical classifier; and

thereupon determining a classification of the road segment over the predetermined time period into a predefined traffic density state.

14. A computer program product comprising:

a non-transitory computer readable storage medium having computer readable program code embodied therewith, the computer readable program code comprising;

computer readable program code configured to receive traffic monitoring input from a road segment over a predetermined time period, the traffic monitoring input including traffic audio input;

computer readable program code configured to process the traffic monitoring input into a time-blocked signal;

computer readable program code configured to classify the processed traffic monitoring input into a predefined traffic density state, via applying a first statistical classifier;

computer readable program code configured to combine the classified traffic monitoring input with other classified traffic monitoring input which is classified via at least one additional statistical classifier; and

thereupon determining a classification of the road segment over the predetermined time period into a predefined traffic density state.

15. The computer program product according to claim 14, wherein the traffic monitoring input further includes traffic video input.

16. The computer program product according to claim 14, wherein the computer readable program code is configured to derive spectral and temporal features from the traffic monitoring input.

17. The computer program product according to claim 14, wherein:

the computer readable program code is configured to receive individual readings of traffic monitoring input over the predetermined time period; and

the computer readable program code is configured to bundle the readings of traffic monitoring input over the predetermined time period into the time-blocked signal.

18. The computer program product according to claim 14, wherein:

the computer readable program code is configured to apply a plurality of statistical classifiers to the processed traffic monitoring input; and

the computer readable program code is configured to fuse output from the plurality of statistical classifiers and classifying the fused output into a predefined traffic density state.

19. The computer program product according to claim 14, wherein the predetermined traffic density state corresponds to a discrete range of traffic speeds.

20. The computer program product according to claim 14, wherein the computer readable program code is configured to apply the first statistical classifier and at least one additional statistical classifier employ at least one pre-trained statistical model.

21. The computer program product according to claim 20, wherein the at least one pre-trained statistical model is trained on predetermined traffic density states.

22. The computer program product according to claim 21, wherein each predetermined traffic density state corresponds to a discrete range of traffic speeds.

23. The computer program product according to claim 21, wherein the at least one pre-trained statistical model is trained on varied climate conditions.

24. The computer program product according to claim 21, wherein the at least one pre-trained statistical model is trained on road segments of similar surface.

25. The computer program product according to claim 14, wherein:

each predetermined traffic density state corresponds to a discrete range of traffic speeds; and

the at least one pre-trained statistical model is trained on varied climate conditions.