IP Library › Granted Patent US 12,165,413
Granted Patent B2
US 12,165,413 · App. 17/523,516 · Granted Dec 10, 2024

Methods and apparatuses for occlusion detection

Inventors: Yash Chaturvedi (Panathur, IN); Joseph Celi (Boca Raton, FL)
Assignee: Sensormatic Electronics, LLC
G06V20/52G06T7/20G06V10/22G06V40/10
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 12,165,413
App. No.
17/523,516
Granted
Dec 10, 2024
Kind
B2
Abstract

Aspects of the present disclosure include methods, systems, and non-transitory computer readable media for receiving an initial image of the area, receiving an updated image of the area, detecting at least one of a person in the area or a movement in the area based on the updated image, comparing the updated image and the initial image to identify a change in the area, and determining a presence or an absence of the occlusion based on the change in the area and the at least one of the person or the movement in the area.

Claims (66)

1. A method for detecting an occlusion of an area, comprising:

receiving an initial image of the area;

receiving an updated image of the area;

detecting at least one of a person in the area or a movement in the area based on at least the updated image;

comparing the updated image and the initial image to identify a change in the area;

determining a presence of the occlusion based on the change in the area and the at least one of the person or the movement in the area without using machine learning algorithms; and

in response to determining the presence of the occlusion, the method further comprises:

detecting the person or the movement;

generating a first bounding box around the person or the movement;

generating a second bounding box around the change in the area;

merging the first bounding box and the second bounding box into a merged bounding box;

calculating an intersection over union value based on at least one of the first bounding box, the second bounding box, or the merged bounding box;

comparing the intersection over union value to a threshold value; and

detecting the occlusion in response to the intersection over union value being greater than the threshold value.

2. The method of claim 1 , further comprising: refraining from calculating an available space in the area until a removal of the occlusion occurs.

3. The method of claim 2 , further comprising, after the removal of the occlusion, calculating an available space in the area.

4. The method of claim 3 , further comprising transmitting a message indicating the available space in the area.

5. The method of claim 4 , wherein:

the area is a shelf in a store; and

further comprising determining an amount of merchandise to replenish the shelf based on the available space in the shelf, wherein the message comprises an indication indicating the amount of merchandise to be replenished.

6. The method of claim 1 , wherein the area is one of a shelf, a line in a store, a waiting area, or a compartment of a transportation vehicle.

7. A system for detecting an occlusion of an area, comprising:

a memory including instructions; and

a processor communicatively coupled to the memory and configured to execute the instructions to:

capture an initial image of the area;

capture an updated image of the area;

detect at least one of a person in the area or a movement in the area based at least on the updated image;

compare the updated image and the initial image to identify a change in the area;

determine a presence of the occlusion based on the change in the area and the at least one of the person or the movement in the area without using machine learning algorithms; and

in response to determining the presence of the occlusion, the processor is further configured to:

detect the person or the movement;

generate a first bounding box around the person or the movement;

generate a second bounding box around the change in the area;

merge the first bounding box and the second bounding box into a merged bounding box;

calculate an intersection over union value based on at least one of the first bounding box, the second bounding box, or the merged bounding box;

compare the intersection over union value to a threshold value; and

detect the occlusion in response to the intersection over union value being greater than the threshold value.

8. The system of claim 7 , wherein the processor is further configured to:

refrain from calculating an available space in the area until a removal of the occlusion.

9. The system of claim 8 , wherein the processor is further configured to, after the removal of the occlusion, calculate an available space in the area.

10. The system of claim 9 , wherein the processor is further configured to transmit a message indicating the available space in the area.

11. The system of claim 10 , wherein:

the area is a shelf in a store; and

the processor is further configured to determine an amount of merchandise to replenish the shelf based on the available space in the shelf, wherein the message comprises an indication indicating the amount of merchandise to be replenished.

12. The system of claim 7 , wherein the area is one of a shelf, a line in a store, a waiting area, or a compartment of a transportation vehicle.

13. A non-transitory computer readable medium including instructions that, when executed by a processor of a system for detecting an occlusion of an area, cause the processor to:

capture an initial image of the area;

capture an updated image of the area;

detect at least one of a person in the area or a movement in the area based at least on the updated image;

compare the updated image and the initial image to identify a change in the area;

determine a presence of the occlusion based on the change in the area and the at least one of the person or the movement in the area without using machine learning algorithms; and

in response to determining the presence of the occlusion, the non-transitory computer readable medium further comprises instructions to:

detect the person or the movement;

generate a first bounding box around the person or the movement;

generate a second bounding box around the change in the area;

merge the first bounding box and the second bounding box into a merged bounding box;

calculate an intersection over union value based on at least one of the first bounding box, the second bounding box, or the merged bounding box;

compare the intersection over union value to a threshold value; and

detect the occlusion in response to the intersection over union value being greater than the threshold value.

14. The non-transitory computer readable medium of claim 13 , further comprising instructions that, when executed by the processor, cause the processor to: refrain from calculating an available space in the area until a removal of the occlusion.

15. The non-transitory computer readable medium of claim 14 , further comprising instructions that, when executed by the processor, cause the processor to, after the removal of the occlusion, calculate an available space in the area.

16. The non-transitory computer readable medium of claim 15 , further comprising instructions that, when executed by the processor, cause the processor to transmit a message indicating the available space in the area.

17. The non-transitory computer readable medium of claim 16 , wherein:

the area is a shelf in a store; and

further comprising instructions that, when executed by the processor, cause the processor to determine an amount of merchandise to replenish the shelf based on the available space in the shelf, wherein the message comprises an indication indicating the amount of merchandise to be replenished.

18. The non-transitory computer readable medium of claim 13 , wherein the area is one of a shelf, a line in a store, a waiting area, or a compartment of a transportation vehicle.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 16, 2021
From: CHATURVEDI, YASH; CELI, JOSEPH
To: SENSORMATIC ELECTRONICS, LLC
Reel/Frame 058128/0764 →
Continuity (1)
Related Publication 20230145016A1 · May 11, 2023