US-12626568-B2 - Tiered motion detection for video surveillance systems

Abstract

Systems, methods, and software to process tiered motion detection for video surveillance are provided herein. In one implementation, a video processing computing system is configured to identify a request for an object to enter a physical area and select a portion of the physical area available to the object based on the request. The video processing computing system is further configured to monitor movement of the object in the physical area using one or more video streams from one or more cameras and determine that the object moved outside the portion of the physical area available to the object based on the monitored movement. The computing system also generates an alert in response to the determination that the object moved outside the portion of the physical area available to the object.

Inventors

• Amit Kumar

Assignees

• DRAGONFRUIT AI, INC.

Dates

Publication Date

20260512

Application Date

20240305

Claims (20)

1. 1 . A method comprising: identifying a map of a physical area; obtaining user input identifying stationary objects in one or more video streams from one or more cameras and the map, wherein the user input for each stationary object of the stationary objects correlates a tag of said stationary object in at least one video stream of the one or more video streams to a representation of said stationary object in the map; identifying a request for an object to enter the physical area; obtaining second user input that defines a portion of the physical area available to the object relative to the stationary objects; selecting the portion of the physical area available to the object based on the request; monitoring movement of the object in the physical area using the one or more video streams; determining that the object moved outside the portion of the physical area available to the object based on the monitored movement; and generating an alert in response to the determination that the object moved outside the portion of the physical area available to the object.
2. 2 . The method of claim 1 further comprising: obtaining user input in the one or more video streams that defines the portion of the physical area available to the object.
3. 3 . The method of claim 1 , wherein determining that the object moved outside of the portion of the physical area available to the object comprises: determining the object exceeds the portion of the physical area available to the object for a user-configurable time threshold.
4. 4 . The method of claim 1 , wherein obtaining the second user input that defines the portion of the physical area available to the object relative to the stationary objects comprises obtaining user shading or highlighting of the portion of the physical area in the map or on at least one video stream of the one or more video streams.
5. 5 . The method of claim 1 , wherein obtaining the second user input that defines the portion of the physical area available to the object relative to the stationary objects: obtaining third user input that defines available traffic areas in the physical area; and wherein obtaining user shading or highlighting of the portion of the physical area in the map or on at least one video stream of the one or more video streams comprises receiving a selection of a subset of the available traffic areas as the portion of the physical area.
6. 6 . The method of claim 1 , wherein the physical area comprises a retail environment.
7. 7 . The method of claim 1 , wherein the object comprises a person, and wherein identifying the request for the object to enter the physical area comprises receiving a passcode from the person to enter the physical area.
8. 8 . The method of claim 1 further comprising: identifying a second request for a second object to enter the physical area; selecting the portion of the physical area available to the second object based on the second request; monitoring the movement of the object in the physical area using the one or more video streams; identifying an expiration event to prohibit the second object in the portion of the physical area; and in response to the expiration event, generating a second alert when movement is detected in the portion of the physical area.
9. 9 . A computing apparatus comprising: a storage system comprising non-transitory computer readable storage media; a processing system comprising at least one processor and operatively coupled to the storage system; and program instructions stored on the storage system that, when executed by the processing system, direct the computing apparatus to: identify a map of a physical area; obtain user input identifying stationary objects in one or more video streams from one or more cameras and the map, wherein the user input for each stationary object of the stationary objects correlates a tag of said stationary object in at least one video stream of the one or more video streams to a representation of said stationary object in the map; identify a request for an object to enter a physical area; obtain second user input that defines a portion of the physical area available to the object relative to the stationary objects; select the portion of the physical area available to the object based on the request; monitor movement of the object in the physical area using the one or more video streams; determine that the object moved outside the portion of the physical area available to the object based on the monitored movement; and generate an alert in response to the determination that the object moved outside the portion of the physical area available to the object.
10. 10 . The computing apparatus of claim 9 , wherein the program instructions further direct the computing apparatus to: obtain user input in the one or more video streams that defines the portion of the physical area available to the object.
11. 11 . The computing apparatus of claim 9 , wherein to determine that the object moved outside of the portion of the physical area available to the object, the program instructions direct the computing apparatus to: determine the object exceeds the portion of the physical area available to the object for a user-configurable time threshold.
12. 12 . The computing apparatus of claim 9 , wherein obtaining the second user input that defines the portion of the physical area available to the object relative to the stationary objects comprises obtaining user shading or highlighting of the portion of the physical area in the map or on at least one video stream of the one or more video streams.
13. 13 . The computing apparatus of claim 9 , wherein obtaining the second user input that defines the portion of the physical area available to the object relative to the stationary objects: obtaining third user input that defines available traffic areas in the physical area; and wherein obtaining user shading or highlighting of the portion of the physical area in the map or on at least one video stream of the one or more video streams comprises receiving a selection of a subset of the available traffic areas as the portion of the physical area.
14. 14 . The computing apparatus of claim 9 , wherein the physical area comprises a retail environment.
15. 15 . The computing apparatus of claim 9 , wherein the object comprises a person, and wherein identifying the request for the object to enter the physical area comprises receiving a passcode from the person to enter the physical area.
16. 16 . The computing apparatus of claim 9 , wherein the program instructions further direct the computing apparatus to: identify a second request for a second object to enter the physical area; select the portion of the physical area available to the second object based on the request; monitor the movement of the object in the physical area using one or more video streams from one or more cameras; identify an expiration event to prohibit the second object in the portion of the physical area; and in response to the expiration event, generate a second alert when movement is detected in the portion of the physical area.
17. 17 . An apparatus comprising: one or more non-transitory computer readable storage media; and program instructions stored on the one or more non-transitory computer readable storage media that, when executed by at least one processor, direct the at least one processor to: identify a map of a physical area; obtain user input identifying stationary objects in one or more video streams from one or more cameras and the map, wherein the user input for each stationary object of the stationary objects correlates a tag of said stationary object in at least one video stream of the one or more video streams to a representation of said stationary object in the map; identify a request for an object to enter a physical area; obtain second user input that defines a portion of the physical area available to the object relative to the stationary objects; select the portion of the physical area available to the object based on the request; monitor movement of the object in the physical area using the one or more video streams; determine that the object moved outside the portion of the physical area available to the object based on the monitored movement; and generate an alert in response to the determination that the object moved outside the portion of the physical area available to the object.
18. 18 . The apparatus of claim 17 , wherein the program instructions further direct the at least one processor to: obtain user input in the one or more video streams that defines the portion of the physical area available to the object.
19. 19 . The apparatus of claim 17 , wherein to determine that the object moved outside of the portion of the physical area available to the object, the program instructions direct the at least one processor to: determine the object exceeds the portion of the physical area available to the object for a user-configurable time threshold.
20. 20 . The apparatus of claim 17 , wherein obtaining the second user input that defines the portion of the physical area available to the object relative to the stationary objects comprises obtaining user shading or highlighting of the portion of the physical area in the map or on at least one video stream of the one or more video streams.

Description

BACKGROUND Video surveillance involves the use of cameras to monitor and record activities in a specific area. These cameras capture live footage, which can be viewed in real-time or stored for later analysis. Video surveillance is commonly employed for security purposes, such as monitoring public spaces, businesses, and homes to deter and detect criminal activities. Advances in technology have led to the integration of features like facial recognition and remote access to enhance the effectiveness of video surveillance systems. In addition to video surveillance, many organizations and businesses employ motion detector to identify desirable (or undesirable) movement in a physical area. The basic principle behind motion detection is to monitor changes in the environment and trigger an alert or response when movement is detected. However, while motions sensors can be useful in monitoring a physical area, difficulties arise in managing the location and placement of the sensors. Further, difficulties arise in configuring different sensors for different situations and preferences. OVERVIEW Provided herein are systems, methods, and software to provide tiered motion detection for video surveillance systems. In one implementation, a method of operating a video processing computing device includes identifying a request for an object to enter a physical area and selecting a portion of the physical area available to the object based on the request. The method further includes monitoring movement of the object in the physical area using one or more video streams from one or more cameras and determining that the object moved outside the portion of the physical area available to the object. The method also provides generating an alert in response to the determination that the object moved outside the portion of the physical area available to the object. In one implementation, the method further includes identifying a map of the physical area and obtaining user input identifying stationary objects in the one or more video streams and the map, wherein the user input for each stationary object of the stationary objects correlates a tag of said stationary object in at least one video stream of the one or more video streams to a representation of said object stationary object in the map. The method further provides obtaining second user input that defines the portion of the physical area available to the object relative to the stationary objects. BRIEF DESCRIPTION OF THE DRAWINGS Many aspects of the disclosure can be better understood with reference to the following drawings. While several implementations are described in connection with these drawings, the disclosure is not limited to the implementations disclosed herein. On the contrary, the intent is to cover all alternatives, modifications, and equivalents. FIG. 1 illustrates a computing environment to provide tiered motion detection for video surveillance according to an implementation. FIG. 2 illustrates an operation of a video processing computing device to provide tiered motion detection for video surveillance according to an implementation. FIG. 3 illustrates a user interface to provide input regarding available traffic areas in a physical area according to an implementation. FIG. 4 illustrates a user interface to provide input regarding landmarks in a physical area according to an implementation. FIG. 5 illustrates a user interface to select the portion of the physical area available to an object according to an implementation. FIG. 6 illustrates a timing diagram of generating an alert associated with improper movement in a physical area according to an implementation. FIG. 7 illustrates a timing diagram of making a portion of a physical area available to an object for a defined period according to an implementation. FIG. 8 illustrates a computing system to provide tiered motion detection for video surveillance according to an implementation. DETAILED DESCRIPTION FIG. 1 illustrates a computing environment 100 to provide tiered motion detection for video surveillance according to an implementation. Computing environment 100 includes physical area 105, video processing computing device 110, and streams 130-132. Physical area 105 further includes cameras 120-122 that provide video streams 130-132, aisles 180-182, door 190, available portion 192, and entry symbol 194. Video processing computing device 110 includes data store 112 and provides alert operation 200 that is described below with respect to FIG. 2. In computing environment 100, cameras 120-122 provide video streams 130-132 to video processing computing device 110. Cameras 120-122 are each representative of a surveillance camera that is a device equipped with a lens and sensor to capture video footage of a specific area or location. It is commonly used for security purposes to monitor activities and deter potential threats. Video processing computing device 110 is communicatively coupled to cameras 120-122 and