System and method for automated road identification in distant traffic camera images

• US 9,881,230 B2
• Filed: 05/11/2016
• Issued: 01/30/2018
• Est. Priority Date: 05/11/2016
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Katsuki, Takayuki, Tatsubori, Michiaki
• Primary Examiner(s): Hausmann, Michelle M
• Application Number:
  US15/152,058
• Publication Number:
  US 20170330051A1
• Time in Patent Office: 629 Days
• Field of Search: None
• CPC Class Codes: G06F 16/29 Geographical information databases
• CPC Class Codes: G06F 16/5866 using information manually generated, e.g. tags, keywords, comments, manually generated location and time information
• CPC Class Codes: G06V 10/44 Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
• CPC Class Codes: G06V 10/62 relating to a temporal dimension, e.g. time-based feature extraction; Pattern tracking
• CPC Class Codes: G06V 20/182 Network patterns, e.g. roads or rivers
• CPC Class Codes: G06V 20/52 Surveillance or monitoring of activities, e.g. for recognising suspicious objects recognising microscopic objects G06V20/69

Abstract

In embodiments the invention provides methods and systems for improved monitoring of roadways and related resources. The methods employ frugal devices such as remote webcams, and provide methods for improving the quality and usefulness of the data obtained from such devices.

Claims

1. A method for identifying features in an image, the method comprising:

determining a plurality of scaling ratios from average vehicle sizes in an image from a fixed-point traffic camera, wherein the scaling ratios are identified at two or more points in the image corresponding to different positions along a single roadway;

determining an ortho mapping function from the plurality of scaling ratios;

producing, using the ortho mapping function, an ortho projection of a road part extracted from the image;

identifying an identification label of a road part in a map corresponding to the road part in the ortho projection; and

producing a road-labeled image from the image and the identification label.

2. The method of claim 1, wherein the method further comprises determining narrative information from the map.

3. The method of claim 1, wherein the method further comprises receiving, by a server via a network, the image from the fixed-point traffic camera.

4. The method of claim 1, wherein the method further comprises transmitting the road-labeled image via a network.

5. The method of claim 1, wherein the image is an image comprising roadways and vehicles, and wherein the traffic camera is remote from the server.

6. The method of claim 1, wherein the method further comprises determining narrative information from the map and transmitting the identification label and the narrative information via a network.

7. The method of claim 1, wherein the method further comprises using keywords to identify the map from a database of maps.

8. The method of claim 1, further comprising advising a fixed-point camera annotator, and correlating a portion of the image to the road-labeled image.

9. The method of claim 1, wherein the method further comprises receiving, by a server via a network, the image from the fixed-point traffic camera, and wherein the method further comprises transmitting the road-labeled image via a network.

10. The method of claim 1, wherein the method further comprises determining narrative information from the GIS map and transmitting the identification label and the narrative information via a network.

11. The method of claim 1, wherein the method further comprises advising a fixed-point camera annotator, and correlating a portion of the image to the road-labeled image.

12. A computer system for identifying features in an image, comprising:

a processor;

a memory coupled to the processor, the memory configured to store program instructions executable by the processor to cause the computer system to;

determine a plurality of scaling ratios from average vehicle sizes in an image from a fixed point traffic camera, wherein the scaling ratios are identified at two or more points in the image corresponding to different positions along a single roadway;

determine an ortho mapping function from the plurality of scaling ratios;

produce, using the ortho mapping function, an ortho projection of a road part extracted from the image;

identify an identification label of a road part in a map corresponding to the road part in the ortho projection; and

produce a road-labeled image from the image and the identification label.

13. The computer system of claim 12, wherein the memory is further configured to store program instructions executable by the processor to cause the computer system to advise a fixed-point camera annotator, and correlate a portion of the image to the road-labeled image.

14. The computer system of claim 12, wherein the memory is further configured to store program instructions executable by the processor to cause the computer system to receive, by a server via a network, the image from the fixed-point traffic camera, and transmit the road-labeled image via a network.

15. The computer system of claim 12, wherein the memory is further configured to store program instructions executable by the processor to cause the computer system to determine narrative information from the map and transmit the identification label and the narrative information via a network.

16. The computer system of claim 12, wherein the memory is further configured to store program instructions executable by the processor to cause the computer system to advise a fixed-point camera annotator, and correlate a portion of the image to the road-labeled image.

17. A method for managing road use, the method comprising:

determining a plurality of scaling ratios from average vehicle sizes in an image from a fixed point traffic camera, wherein the scaling ratios are identified at two or more points in the image corresponding to different positions along a single roadway;

determining an ortho mapping function from the plurality of scaling ratios;

producing, using the ortho mapping function, an ortho projection of a road part extracted from the image;

identifying an identification label of a road part in a map corresponding to the road part in the ortho projection; and

producing a road-labeled image from the image and the identification label.

18. The method of claim 17, further comprising advising a fixed-point camera annotator, who specifies which part of camera view corresponds to which part of a road, based on the road-labeled image.

19. The method of claim 17, further comprising automatically generating an alert and transmitting the alert via a network when the road-labeled image surpasses a threshold traffic volume.