Operations monitoring in an area

• US 10,597,053 B2
• Filed: 05/08/2014
• Issued: 03/24/2020
• Est. Priority Date: 05/08/2013
• Status: Active Grant

• Current Assignee: International Electronic Machines Corp.
• Original Assignee: International Electronic Machines Corp.
• Inventors: Mian, Zahid F., Gamache, Ronald W.
• Primary Examiner(s): Truong, Nguyen T
• Application Number:
  US14/272,816
• Publication Number:
  US 20140333771A1
• Time in Patent Office: 2,147 Days
• Field of Search: 348149
• CPC Class Codes: B61L 17/00 Switching systems for classification yards
• CPC Class Codes: B61L 17/02 Details, e.g. indicating degree of track filling
• CPC Class Codes: B61L 23/00 Control, warning or like safety means along the route or between vehicles or trains
• CPC Class Codes: B61L 23/041 Obstacle detection
• CPC Class Codes: B61L 27/40 Handling position reports or trackside vehicle data
• CPC Class Codes: G06T 2207/10021 Stereoscopic video; Stereoscopic image sequence
• CPC Class Codes: G06T 2207/10048 Infrared image
• CPC Class Codes: G06T 2207/30232 Surveillance
• CPC Class Codes: G06T 2207/30236 Traffic on road, railway or crossing
• CPC Class Codes: G06T 7/55 from multiple images
• CPC Class Codes: G06V 20/54 of traffic, e.g. cars on the road, trains or boats
• CPC Class Codes: H04N 7/181 for receiving images from a plurality of remote sources

Abstract

A solution for monitoring an area including one or more restricted zones is provided. The solution can include one or more monitoring assemblies deployed to acquire image data of the area and independently monitor operations within the area at each monitoring assembly. A monitoring assembly can include one or more local alert components to generate an audible or visual alarm to local personnel. Data regarding static features present in the area can be used to create a registration map of the field of view, which can subsequently enable accurate determination of the three-dimensional location of a target using two-dimensional image data and/or identify an extent of a restricted zone even when one or more of the static features are obscured. Monitoring a target over a series of images can be used to determine whether an alert condition is present.

Claims

1. A system comprising:

a monitoring assembly including;

a set of cameras, wherein the set of cameras includes at least one near infrared camera;

a set of local alert components; and

a computer system configured to monitor operations in a region by performing a method including;

determining a location of a target at least partially visible in image data acquired by the set of cameras using data corresponding to a plurality of static features present in the region;

evaluating the location with respect to at least one restricted zone in the region;

in response to the evaluating indicating the target is at least partially located within a restricted zone, determining whether the target is being deliberately moved within the restricted zone, wherein the determining is based on at least one of;

a direction of movement of the target within the restricted zone or a cause of movement of the target into the restricted zone; and

activating at least one of the set of local alert components in response to determining the target is not being deliberately moved.

2. The system of claim 1, further comprising at least one additional monitoring assembly, wherein each monitoring assembly is configured to monitor operations in a unique sub-region of an area, and wherein each monitoring assembly further includes a wireless communications component configured to enable the computer system of each monitoring assembly to communicate with at least one computer system of another monitoring assembly.

3. The system of claim 2, further comprising a central system for managing operations in the area, wherein at least one computer system of the plurality of monitoring assemblies is configured to communicate with the central system.

4. The system of claim 1, the monitoring assembly further including a near infrared illuminator, wherein the method further includes operating the near infrared illuminator to provide sufficient light for the region.

5. The system of claim 1, wherein the monitoring assembly is mounted at a location providing a head-on oriented view with respect to a plurality of designated paths of travel of targets within the at least one restricted zone and at a height sufficient to prevent a line of sight of the set of cameras from being blocked due to normal operations in the region, wherein each target is located on one of a plurality of designated paths of travel, and wherein each of the designated paths of travel extends into the at least one restricted zone in the region.

6. The system of claim 1, wherein the region comprises a group of classification tracks in a railroad classification yard.

7. The system of claim 1, wherein the computer system is calibrated after deployment of the monitoring assembly to a location, wherein the calibration includes obtaining data regarding the plurality of static features in the region and identifying the plurality of static features in image data acquired by the set of cameras.

8. A method comprising:

at each of a plurality of monitoring assemblies located within an area;

acquiring image data for a region of the area using a set of cameras of the monitoring assembly;

processing the image data using a computer system of the monitoring assembly to determine a location of each of a set of targets at least partially visible in the image data;

the computer system evaluating the location with respect to at least one restricted zone in the region;

in response to the evaluating indicating the target is at least partially located within a restricted zone, the computer system determining whether the target is being deliberately moved within the restricted zone, wherein the determining is based on at least one of;

a direction of movement of the target within the restricted zone or a cause of movement of the target into the restricted zone; and

the computer system activating at least one of the set of local alert components in response to determining the target is not being deliberately moved.

9. The method of claim 8, further comprising deploying the plurality of monitoring assemblies within the area, wherein the deploying includes mounting the set of cameras at a location providing a head-on oriented view with respect to a path of travel of targets within the at least one restricted zone and at a height sufficient to prevent a line of sight of the set of cameras from being blocked due to normal operations in the region.

10. The method of claim 8, further comprising calibrating the computer system of each of the plurality of monitoring assemblies, wherein the calibrating includes obtaining data regarding a plurality of static features in the region and identifying the plurality of static features in image data acquired by the set of cameras, wherein the computer system uses the data regarding the plurality of static features during the evaluating.

11. The method of claim 10, wherein the calibrating further includes creating a registration map of the region in the image data using the plurality of static features identified in the image data, wherein the computer system uses the registration map during the evaluating.

12. The method of claim 11, wherein the registration map includes a mask for a set of paths of travel for targets in the region.

13. The method of claim 8, wherein the region comprises a group of classification tracks in a railroad classification yard.

14. The method of claim 8, the method further comprising, in response to determining the target is not being deliberately moved, the computer system providing information regarding an alert condition for processing by at least one of:

the computer system of another monitoring assembly or a central system managing the operations in the area.

15. A classification yard comprising:

a plurality of classification tracks having a first side from which rail vehicles enter for assembly in a consist and a second side from which consists exit the plurality of classification tracks, wherein each classification track includes a foul region defined by a mechanism located between the first and second sides for halting movement of a rail vehicle and a switch for merging the classification track with another classification track on the second side;

a monitoring assembly including;

a set of cameras, each camera having a field of view that includes the mechanism and the switch for each of the plurality of classification tracks; and

a computer system configured to monitor the foul region of each of the plurality of classification tracks by performing a method including;

determining a location of a rail vehicle at least partially visible in image data acquired by the set of cameras using data corresponding to a plurality of static features present in the classification yard;

evaluating the location with respect to the foul region for a classification track on which the rail vehicle is located; and

in response to the evaluating indicating the rail vehicle is at least partially located within the foul region, determining a presence of an alert condition using a series of images including the rail vehicle, wherein the alert condition is present when the rail vehicle is not being deliberately operated, wherein the determining is based on at least one of;

a direction of movement of the rail vehicle within the foul region or a cause of movement of the rail vehicle into the foul region.

16. The yard of claim 15, wherein the classification yard includes multiple groups of classification tracks, each group of classification tracks including a subset of the plurality of classification tracks and having at least one monitoring assembly configured to monitor the foul region of each classification track in the group.

17. The yard of claim 15, wherein the classification yard includes a plurality of monitoring assemblies, each monitoring assembly including a computer system configured for wireless communication with at least one other computer system of another monitoring assembly.

18. The yard of claim 17, further comprising a central system for managing operations of the rail vehicles on the plurality of classification tracks, wherein at least one computer system of the plurality of monitoring assemblies is configured to communicate with the central system.

19. The yard of claim 15, wherein the monitoring assembly is mounted at a location providing a head-on oriented view with respect to the plurality of classification tracks in the foul regions and at a height sufficient to prevent a line of sight of the set of cameras from being blocked due to normal operations in the classification yard.

20. The yard of claim 15, wherein the set of cameras includes a near infrared camera.

21. The yard of claim 15, further comprising a set of local alert components, wherein the method further includes activating at least one of the set of local alert components in response to determining the presence of an alert condition.