IP Library › Granted Patent US 12,657,862
Granted Patent B2
US 12,657,862 · App. 18/514,594 · Granted Jun 16, 2026

Auto-configuring a region of interest (ROI) associated with a camera

Inventors: Gopi Subramanian (Delray Beach, FL); Joseph Celi (Boca Raton, FL)
Assignee: Sensormatic Electronics, LLC
G06V10/255G06T7/248G06V20/52G06V40/10G06T2207/30196G06T2207/30241G06V10/62
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,657,862
App. No.
18/514,594
Granted
Jun 16, 2026
Kind
B2
Abstract

Disclosed herein are apparatuses and methods for auto-configuring a region of interest (ROI) associated with a camera. In one implementation, A method includes tracking, over a plurality of image frames spanning a first period of time, a plurality of objects moving in an environment, and determining a plurality of respective trajectories of the plurality of objects. The method includes identifying a common trajectory shared by more than one object of the plurality of objects based on comparing each of the plurality of respective trajectories to one another and identifying an ROI that encompasses the common trajectory. The method further includes tracking, over a plurality of new image frames spanning a second period of time, another plurality of objects moving in the environment, and generating an alert that the common trajectory has changed based on new trajectories of the another plurality of objects.

Claims (64)

1 . A method for auto-configuring a region of interest (ROI) associated with a camera, comprising:

tracking, over a plurality of image frames spanning a first period of time, a plurality of objects moving in an environment, wherein the plurality of image frames are received from a camera installed in the environment;

determining a plurality of respective trajectories including a respective trajectory of movement for each object of the plurality of objects;

identifying a common trajectory shared by more than one object of the plurality of objects based on comparing each of the plurality of respective trajectories to one another;

identifying an ROI that encompasses the common trajectory;

configuring the ROI to be associated with new image frames from the camera;

tracking, over a plurality of new image frames spanning a second period of time, another plurality of objects moving in the environment;

identifying a new common trajectory based on trajectories of movement by the another plurality of objects; and

generating, for output on a computing device, an alert that the common trajectory has changed in response to determining that the new common trajectory does not correspond to the common trajectory.

2 . The method of claim 1 , further comprising:

identifying a structural boundary of the environment and an inanimate object in the plurality of image frames from the first period of time; and

generating, for output on the computing device, an indication that a layout of the environment has changed in response to determining that the structural boundary has not changed position and the inanimate object has changed position in the plurality of new image frames from the second period of time.

3 . The method of claim 1 , further comprising:

identifying a structural boundary of the environment and an inanimate object in the plurality of image frames from the first period of time; and

generating, for output on the computing device, an indication that the camera has been moved in response to determining that both the structural boundary and the inanimate object have changed position or are not visible in the plurality of new image frames from the second period of time.

4 . The method of claim 1 , further comprising:

updating the ROI to encompass the new common trajectory; and

configuring the updated ROI to be associated with newer image frames from the camera, wherein the newer image frames are captured subsequent to the plurality of new image frames.

5 . The method of claim 4 , wherein updating the ROI comprises shifting the ROI from a first position to a second position that enables the updated ROI to encompass the new common trajectory.

6 . The method of claim 4 , wherein updating the ROI comprises scaling the ROI from a first size to a second size that enables the updated ROI to encompass the new common trajectory.

7 . The method of claim 4 , wherein the ROI is of a first shape, and wherein updating the ROI comprises reshaping the ROI from the first shape to a second shape that enables the updated ROI to encompass the new common trajectory.

8 . The method of claim 4 , wherein the ROI is a line, and wherein updating the ROI comprises shifting the ROI to a common start point and rotating the ROI to be perpendicular to the new common trajectory.

9 . The method of claim 1 , further comprising:

identifying a plurality of uncommon trajectories based on comparing each of the plurality of respective trajectories to one another, wherein the identified ROI does not encompass the plurality of uncommon trajectories.

10 . The method of claim 1 , wherein identifying the common trajectory comprises:

selecting a subset of the determined respective trajectories that have neighboring start points within a first threshold distance, neighboring end points within a second threshold distance, and neighboring slopes including the neighboring start points and the neighboring end points; and

calculating an average trajectory of the subset, wherein the average trajectory is the common trajectory.

11 . An apparatus for auto-configuring a region of interest (ROI) associated with

a camera, comprising:

at least one memory;

at least one hardware processor coupled with the at least one memory and configured, individually

or in combination, to:

track, over a plurality of image frames spanning a first period of time, a plurality of objects moving in an environment, wherein the plurality of image frames are received from a camera installed in the environment;

determine a plurality of respective trajectories including a respective trajectory of movement for each object of the plurality of objects;

identify a common trajectory shared by more than one object of the plurality of objects based on comparing each of the plurality of respective trajectories to one another;

identify an ROI that encompasses the common trajectory;

configure the ROI to be associated with new image frames from the camera;

track, over a plurality of new image frames spanning a second period of time, another plurality of objects moving in the environment;

identify a new common trajectory based on trajectories of movement by the another plurality of objects; and

generate, for output on a computing device, an alert that the common trajectory has changed in response to determining that the new common trajectory does not correspond to the common trajectory.

12 . The apparatus of claim 11 , wherein the at least one hardware processor is further configured to:

identify a structural boundary of the environment and an inanimate object in the plurality of image frames from the first period of time; and

generate, for output on the computing device, an indication that a layout of the environment has changed in response to determining that the structural boundary has not changed position and the inanimate object has changed position in the plurality of new image frames from the second period of time.

13 . The apparatus of claim 11 , wherein the at least one hardware processor is further configured to:

identify a structural boundary of the environment and an inanimate object in the plurality of image frames from the first period of time; and

generate, for output on the computing device, an indication that the camera has been moved in response to determining that both the structural boundary and the inanimate object have changed position or are not visible in the plurality of new image frames from the second period of time.

14 . The apparatus of claim 11 , wherein the at least one hardware processor is further configured to:

update the ROI to encompass the new common trajectory; and

configure the updated ROI to be associated with newer image frames from the camera, wherein the newer image frames are captured subsequent to the plurality of new image frames.

15 . The apparatus of claim 14 , wherein updating the ROI comprises shifting the ROI from a first position to a second position that enables the updated ROI to encompass the new common trajectory.

16 . The apparatus of claim 14 , wherein updating the ROI comprises scaling the ROI from a first size to a second size that enables the updated ROI to encompass the new common trajectory.

17 . The apparatus of claim 14 , wherein the ROI is of a first shape, and wherein updating the ROI comprises reshaping the ROI from the first shape to a second shape that enables the updated ROI to encompass the new common trajectory.

18 . The apparatus of claim 14 , wherein the ROI is a line, and wherein updating the ROI comprises shifting the ROI to a common start point and rotating the ROI to be perpendicular to the new common trajectory.

19 . The apparatus of claim 11 , wherein the at least one hardware processor is further configured to:

identify a plurality of uncommon trajectories based on comparing each of the plurality of respective trajectories to one another, wherein the identified ROI does not encompass the plurality of uncommon trajectories.

20 . A non-transitory computer-readable medium for auto-configuring a region of interest (ROI) associated with a camera, including instructions executable by a processor to:

tracking, over a plurality of image frames spanning a first period of time, a plurality of objects moving in an environment, wherein the plurality of image frames are received from a camera installed in the environment;

determining a plurality of respective trajectories including a respective trajectory of movement for each object of the plurality of objects;

identifying a common trajectory shared by more than one object of the plurality of objects based on comparing each of the plurality of respective trajectories to one another;

identifying an ROI that encompasses the common trajectory;

configuring the ROI to be associated with new image frames from the camera;

tracking, over a plurality of new image frames spanning a second period of time, another plurality of objects moving in the environment;

identifying a new common trajectory based on trajectories of movement by the another plurality of objects; and

generating, for output on a computing device, an alert that the common trajectory has changed in response to determining that the new common trajectory does not correspond to the common trajectory.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 6, 2024
From: SUBRAMANIAN, GOPI; CELI, JOSEPH
To: SENSORMATIC ELECTRONICS, LLC
Reel/Frame 066389/0853 →
Continuity (3)
Continuation In Part 17977618 · Oct 31, 2022
Continuation 17067035 · Oct 9, 2020
Related Publication 20240087281A1 · Mar 14, 2024
References Cited (14)
US 9524028B2 · Dai et al. · 2016 [cited by applicant]
US 9566004B1 · Radwin et al. · 2017 [cited by applicant]
US 9965687B2 · Loce · 2018 [cited by examiner]
US 11354728B2 · Chachek et al. · 2022 [cited by applicant]
US 11373331B2 · Huelsdunk et al. · 2022 [cited by applicant]
US 11508140B2 · Subramanian et al. · 2022 [cited by applicant]
US 20090016610A1 · Ma · 2009 [cited by examiner]
US 20130335635A1 · Ghanem et al. · 2013 [cited by applicant]
US 20170169297A1 · Bernal · 2017 [cited by examiner]
US 20180315202A1 · Perry · 2018 [cited by examiner]
US 20180349710A1 · Houri et al. · 2018 [cited by applicant]
US 20190087661A1 · Lee et al. · 2019 [cited by applicant]
US 20190180597A1 · Wang et al. · 2019 [cited by applicant]
US 20210224615A1 · Winzell · 2021 [cited by applicant]