Motion-Validating Remote Monitoring System

• US 20090010493A1
• Filed: 07/03/2008
• Published: 01/08/2009
• Est. Priority Date: 07/03/2007
• Status: Active Grant

• Current Assignee: Pivotal Vision, LLC
• Original Assignee: Pivotal Vision, LLC
• Inventors: Gornick, John R., Moksnes, Craig B.
• Granted Patent: US 8,542,872 B2
• Time in Patent Office: Days
• US Class Current: 382/103
• CPC Class Codes: G06T 17/05 Geographic models
• CPC Class Codes: G06T 2207/30232 Surveillance
• CPC Class Codes: G06T 7/20 Analysis of motion motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51
• CPC Class Codes: G06T 7/292 Multi-camera tracking
• CPC Class Codes: G06T 7/70 Determining position or orientation of objects or cameras camera calibration G06T7/80
• CPC Class Codes: G06V 10/24 Aligning, centring, orientation detection or correction of the image
• CPC Class Codes: G06V 20/52 Surveillance or monitoring of activities, e.g. for recognising suspicious objects recognising microscopic objects G06V20/69
• CPC Class Codes: G08B 13/194 using image scanning and comparing systems
• CPC Class Codes: G08B 13/19602 Image analysis to detect motion of the intruder, e.g. by frame subtraction
• CPC Class Codes: G08B 13/19604 involving reference image or background adaptation with time to compensate for changing conditions, e.g. reference image update on detection of light level change
• CPC Class Codes: G08B 13/19608 Tracking movement of a target, e.g. by detecting an object predefined as a target, using target direction and or velocity to predict its new position
• CPC Class Codes: G08B 13/1961 Movement detection not involving frame subtraction, e.g. motion detection on the basis of luminance changes in the image
• CPC Class Codes: G08B 13/1963 Arrangements allowing camera rotation to change view, e.g. pivoting camera, pan-tilt and zoom [PTZ]
• CPC Class Codes: G08B 13/19641 Multiple cameras having overlapping views on a single scene
• CPC Class Codes: G08B 13/19645 Multiple cameras, each having view on one of a plurality of scenes, e.g. multiple cameras for multi-room surveillance or for tracking an object by view hand-over
• CPC Class Codes: H04N 5/144 Movement detection for video coding H04N19/503; analysis of motion in general G06T7/20

Abstract

A method of autonomously monitoring a remote site, including the steps of locating a primary detector at a site to be monitored; creating one or more geospatial maps of the site using an overhead image of the site; calibrating the primary detector to the geospatial map using a detector-specific model; detecting an object in motion at the site; tracking the moving object on the geospatial map; and alerting a user to the presence of motion at the site. In addition thermal image data from a infrared cameras, rather than optical/visual image data, is used to create detector-specific models and geospatial maps in substantially the same way that optical cameras and optical image data would be used.

Claims

1. A motion-validating monitoring system for detecting objects in motion comprising:

a primary detector for monitoring a remote site and transmitting primary detector image data;

a secondary detector for monitoring a remote site and transmitting secondary detector image data; and

a detector controller adapted to receive the primary and secondary detector image data from the primary detector and the secondary detector, and to use the primary and secondary image data to create one or more detector-specific, three-dimensional models of an image viewed by the detector, the detector-specific three-dimensional model adapted to determine a location of a detected object in motion and project the location of the detected object in motion to a geospatial map.

2. A method of autonomously monitoring a remote site, including:

locating a plurality of detectors at a site to be monitored;

creating a geospatial map of the site based on an overhead image of the site and a distance between two site points depicted on the overhead image;

calibrating the plurality of detectors to the geospatial map using an intermediate detector-specific models of the views of the plurality of detectors; and

detecting an object in motion at the site by analyzing digital pixel data transmitted from the plurality of detectors.

3. The method of claim 2, further comprising tracking the object in motion on the geospatial map by projecting locations of the object in motion to the geospatial map such that the location of the object in motion as identified on the spatial map remains known as long as at least one of the plurality of detectors is able to detect the object in motion and whether the object in motion moves out of a detection range of one detector and into the detection range of another detector.

4. A method of autonomously tracking an object in motion at a remote site, including:

providing a first detector for a site to be monitored, wherein the first detector is adapted to capture images of a first portion of the site;

providing a second detector for a site to be monitored, wherein the second detector is adapted to capture images of a second portion of the site;

defining a first detector model corresponding to an image captured by the first detector, wherein the first detector model is adapted to define a geographical location of an object in motion appearing in the image captured by the first detector in terms of three-dimensional coordinates specific to the first detector model;

defining a second detector model corresponding to an image captured by the second detector, wherein the second detector model is adapted to define a geographical location of an object in motion in the image captured by the second detector in terms of three-dimensional coordinates specific to the second detector model;

projecting the first and second geographical locations of the first and second objects in motion to a common geographical map of the site;

determining whether the first object in motion appearing in the first image is the same as the second object in motion appearing in the second image; and

seamlessly tracking objects in motion projected to the common geographical map without regard to whether an object is no longer detectable by either the first or second detector.

5. A method of detecting motion at a remote site having a changing background, comprising:

capturing a plurality of sequential images of a remote site using a detector located at the remote site, wherein each image is defined by a plurality of image pixels, each pixel defining portions of an image and including pixel image data;

establishing a plurality of background history arrays, each corresponding to one of the plurality of pixels, and each comprising sequential pixel image data;

defining a background based on the plurality of background history arrays;

updating the background by analyzing changes in pixel data, such that false motion is not represented in an updated background; and

comparing a current image to the background to identify motion pixels, wherein comparing the current image to the background includes comparing individual pixel data of the current image to corresponding background pixel data, and wherein the presence of motion pixels indicates motion.

6. A method of validating motion at a remote site, comprising:

capturing a series of images of a portion of a remote site using a detector, wherein the series of images includes background and current pixel data;

comparing the background and current pixel data to identify regions of interest, wherein the regions of interest define a pre-validated location of an object in motion;

validating the regions of interest, wherein validating the regions of interest includes projecting the regions of interest to a geospatial map and defining the location of the regions of interest in geospatial coordinates.