Back to results
US 12,602,812 B2Granted
Mitigating effects caused by repeated and/or sporadic movement of objects in a field of view
AssigneeEvolon Technology, Inc.
InventorSteven Schramm
Life of this patent
Estimating the term…
Abstract
The present application describes a system and method for mitigating false alarms caused by repeated and/or sporadic movement of objects in a field of view of an image capture device.
Claims4
A method, comprising:
- receiving a series of captured images of a particular scene over a first time period;
- processing the particular scene with a detection system having detection parameters,
- detecting an object of interest in the particular scene using at least a portion of the captured images;
- identifying an area within and smaller than the particular scene, the area bounded by a bounding box, and a dimension of the area corresponding to a dimension of the object of interest;
- determining whether the object of interest is detected within the area over a threshold number of times within the first time period by comparing a first centroid pixel group of the object of interest to a second centroid pixel group of the bounding box;
- and
- based on determining whether the object of interest is detected within the area over the threshold number of times, causing the detection parameters to ignore the area until a resumption threshold has been met or exceeded;
- wherein the threshold number of times is greater than 1;
- and
- wherein the resumption threshold is a second time period.
7 more elements
A method, comprising:
- receiving a series of captured images of a particular scene over a first time period;
- processing the particular scene with a detection system having detection parameters,
- detecting an object of interest in the particular scene using at least a portion of the captured images;
- identifying an area within and smaller than the particular scene, the area bounded by a bounding box, and a dimension of the area corresponding to a dimension of the object of interest;
- determining whether the object of interest is detected within the area over a threshold number of times within the first time period by comparing a first centroid pixel group of the object of interest to a second centroid pixel group of the bounding box;
- and
- based on determining whether the object of interest is detected within the area over the threshold number of times, causing the detection parameters to ignore the area until a resumption threshold has been met or exceeded;
- wherein the threshold number of times is greater than 1;
- and
- wherein the resumption threshold is an area threshold.
7 more elements
A system, comprising:
- a processor;
- a memory coupled to the processor and storing computer executable instructions that, when executed by the processor, perform operations, comprising:
- selecting a series of captured images of a particular scene over a first time period;
- processing the particular scene with a detection system having detection parameters,
- detecting an object of interest in the particular scene using at least a portion of the captured images;
- identifying an area within and smaller than the particular scene, the area bounded by a bounding box, and a dimension of the area corresponding to a dimension of the object of interest;
- and
- determining whether the object of interest is detected within the area over a threshold number of times within the first time period by comparing a first centroid pixel group of the object of interest to a second centroid pixel group of the bounding box;
- and
- based on determining whether the object of interest is detected within the area over the threshold number of times, causing the detection parameters to ignore the area until a resumption threshold has been met or exceeded;
- wherein the threshold number of times is greater than 1;
- and
- wherein the resumption threshold is a second time period.
10 more elements
A system, comprising:
- a processor;
- a memory coupled to the processor and storing computer executable instructions that, when executed by the processor, perform operations, comprising:
- selecting a series of captured images of a particular scene over a first time period;
- processing the particular scene with a detection system having detection parameters,
- detecting an object of interest in the particular scene using at least a portion of the captured images;
- identifying an area within and smaller than the particular scene, the area bounded by a bounding box, and a dimension of the area corresponding to a dimension of the object of interest;
- and
- determining whether the object of interest is detected within the area over a threshold number of times within the first time period by comparing a first centroid pixel group of the object of interest to a second centroid pixel group of the bounding box;
- and
- based on determining whether the object of interest is detected within the area over the threshold number of times, causing the detection parameters to ignore the area until a resumption threshold has been met or exceeded;
- wherein the threshold number of times is greater than 1;
- and
- wherein the resumption threshold is an area threshold.
10 more elements
Dependencies are inferred from the claim text.