EP-4742190-A1 - SYSTEM AND METHOD FOR PROXIMITY SEARCHING

EP4742190A1EP 4742190 A1EP4742190 A1EP 4742190A1EP-4742190-A1

Abstract

A method for proximity searching in a surveillance system comprises receiving a request to perform, over a period of interest, a proximity search related to a first object depicted in a first image captured by a selected media device, the request received as a result of user input, obtaining media data captured by one or more media devices during the period of interest, identifying, based on the media data, one or more second objects exhibiting a spatial proximity and a temporal proximity with the first object during the period of interest, and, for each of the one or more second objects, obtaining, based on the media data, a second image depicting the second object, the second image captured at a time at which the second object exhibited the spatial proximity and the temporal proximity with the first object, and outputting the second image.

Inventors

ROONEY, Christopher
KODAGODA, Neesha
KIMBER, Helen

Assignees

Genetec Inc.

Dates

Publication Date: 20260513
Application Date: 20251112

Claims (15)

A method for proximity searching in a surveillance system, the surveillance system comprising a plurality of media devices deployed at a monitored location, the method comprising: receiving a request to perform, over a period of interest, a proximity search related to a first object depicted in a first image captured by a selected one of the plurality of media devices, the request received as a result of user input; obtaining media data captured by one or more of the plurality of media devices during the period of interest; identifying, based on the media data, one or more second objects exhibiting a spatial proximity and a temporal proximity with the first object during the period of interest; and for each of the one or more second objects, obtaining, based on the media data, a second image depicting the second object, the second image captured at a time at which the second object exhibited the spatial proximity and the temporal proximity with the first object, and outputting the second image.
The method of claim 1, wherein the proximity search relates to a first person, and wherein the one or more second objects are one or more second persons.
The method of claim 1 or 2, further comprising, prior to receiving the request to perform the proximity search: receiving a demand to display selected media data captured by the selected media device; displaying the selected media data and an indication of a plurality of potential objects of interest depicted in the selected media data; and receiving the user input comprising a selection of the first object among the plurality of potential objects of interest.
The method of any one of claims 1 to 3, wherein obtaining the media data comprises one of: obtaining the media data captured by the selected media device; obtaining the media data captured by ones of the plurality of media devices other than the selected media device; and obtaining the media data captured by at least some of the plurality of media devices.
The method of any one of claims 1 to 4, wherein identifying the one or more second objects comprises: tracking the first object within a plurality of images associated with the media data, thereby generating first metadata; tracking a plurality of objects within the plurality of images, thereby generating second metadata; comparing the first metadata to the second metadata to determine a degree of the spatial proximity and the temporal proximity that each of the plurality of objects exhibits with the first object; and identifying the one or more second objects among the plurality of objects based on the comparing.
The method of any one of claims 1 to 5, further comprising: implementing an object segmentation technique to detect the first object in the first image based on the request; and tracking the first object within additional images associated with the media data.
The method of claim 6, further comprising associating a first representation with the first object, wherein the first object is tracked within the additional images using the first representation, preferably wherein identifying the one or more second objects comprises: querying at least one database having stored therein, for each object depicted in the additional images, a second representation, time metadata indicative of a time at which the object was detected, and location metadata indicative of a location of the object when detected; and identifying the one or more second objects based on the second representation, the time metadata, and the location metadata.
The method of any one of claims 1 to 7, further comprising: generating, based on the media data, an indication of the spatial proximity between the second object and the first object; and outputting the indication of the spatial proximity along with the second image.
The method of any one of claims 1 to 8, further comprising: generating, based on the media data, an indication of the temporal proximity between the second object and the first object; and outputting the indication of the temporal proximity along with the second image.
The method of any one of claims 1 to 9, further comprising generating and outputting an indication of at least one of an elapsed time since the second object exhibited the spatial proximity and the temporal proximity with the first object, a duration for which the second object exhibited the spatial proximity and the temporal proximity with the first object, a location of the second object when the second object exhibited the spatial proximity and the temporal proximity with the first object, and a distance between the second object and the first object when the second object exhibited the spatial proximity and the temporal proximity with the first object.
The method of any one of claims 1 to 10, further comprising selecting one of a plurality of colours for a visual indicator, each colour of the plurality of colours associated with a respective level of a plurality of levels representative of the spatial proximity and the temporal proximity, and displaying the visual indicator as an indication of the spatial proximity and the temporal proximity.
The method of any one of claims 1 to 11, wherein the second image is output for each of the one or more second objects to obtain a plurality of second images arranged in chronological order based on the temporal proximity.
The method of any one of claims 1 to 12, wherein the user input comprises one of: a delineation of at least one bounding box circumscribing the first object in the first image; a click interaction selecting the first object in the first image; and an actuation of an interface element configured to initiate the proximity search when actuated.
The method of any one of claims 1 to 13, wherein each of the first image and the second image is one of an entire frame from a video feed, a portion of a frame from the video feed, and a portion of the video feed, preferably wherein the video feed is a live video feed captured in real-time or an archived video feed retrieved from memory.
A system for proximity searching in a surveillance system, the surveillance system comprising a plurality of media devices deployed at a monitored location, the system comprising: a processing unit; and a non-transitory computer-readable medium having stored thereon program instructions executable by the processing unit for: receiving a request to perform, over a period of interest, a proximity search related to first object depicted in a first image captured by a selected one of the plurality of media devices, the request received as a result of user input; obtaining media data captured by one or more of the plurality of media devices during the period of interest; identifying, based on the media data, one or more second objects exhibiting a spatial proximity and a temporal proximity with the first object during the period of interest; and for each of the one or more second objects, obtaining, based on the media data, a second image depicting the second object, the second image captured at a time at which the second object exhibited the spatial proximity and the temporal proximity with the first object, and outputting the second image.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS The present application claims the benefit of United States Provisional Patent Applications No. 63/719,473, filed on November 12, 2024, No. 63/882,922, filed on September 16, 2025, No. 63/719,314, filed on November 12, 2024, and No. 63/883,233, filed on September 17, 2025. Field The present disclosure relates generally to physical security and surveillance, and more specifically to proximity detection and searching in a surveillance system. Background A surveillance system is a network of various devices employed to monitor activities and behaviours of persons or other objects in a particular area being surveilled. A surveillance system may collect information from a variety of sources, centralize that information, and make the information available to surveillance personnel to aid them in making decisions relating to the safety of persons or other objects within the area being surveilled. A surveillance network may include any suitable number of devices for collecting information, including cameras, microphones, access card readers, and the like, as well as any number of monitors or other interfaces for presenting information to operators of the surveillance system. However, due to the large number of devices involved in the surveillance network, it may prove complex and time-consuming to provide surveillance personnel with information in a clear, concise, and actionable manner. Therefore, there is a need for improvement. Summary The following presents a simplified summary of one or more implementations in accordance with aspects of the present disclosure in order to provide a basic understanding of such implementations, without limiting the embodiments presented within the present disclosure. To facilitate contextual awareness and forensic investigations by, for instance, security personnel, the present disclosure describes techniques for identifying objects (whether persons or otherwise) which were present within temporal and/or geographical proximity (also referred to herein as spatial proximity) of an object of interest. After the object of interest is identified, for instance based on user input from security personnel, the system identifies one or more proximate objects which were temporally and/or spatially collocated with the object of interest and presents information relating to the proximate objects via a graphical user interface. In accordance with a broad aspect, there is provided a method for proximity searching in a surveillance system, the surveillance system comprising a plurality of media devices deployed at a monitored location, the method comprising receiving a request to perform, over a period of interest, a proximity search related to a first object depicted in a first image captured by a selected one of the plurality of media devices, the request received as a result of user input; obtaining media data captured by one or more of the plurality of media devices during the period of interest; identifying, based on the media data, one or more second objects exhibiting a spatial proximity and a temporal proximity with the first object during the period of interest; and, for each of the one or more second objects, obtaining, based on the media data, a second image depicting the second object, the second image captured at a time at which the second object exhibited the spatial proximity and the temporal proximity with the first object, and outputting the second image. In at least one embodiment in accordance with any previous/other embodiment described herein, the method further comprises, prior to receiving the request to perform the proximity search, receiving a demand to display selected media data captured by the selected media device; displaying the selected media data and an indication of a plurality of potential objects of interest depicted in the selected media data; and receiving the user input comprising a selection of the first object among the plurality of potential objects of interest. In at least one embodiment in accordance with any previous/other embodiment described herein, obtaining the media data comprises one of obtaining the media data captured by the selected media device; obtaining the media data captured by ones of the plurality of media devices other than the selected media device; and obtaining the media data captured by at least some of the plurality of media devices. In at least one embodiment in accordance with any previous/other embodiment described herein, identifying the one or more second objects comprises tracking the first object within a plurality of images associated with the media data, thereby generating first metadata; tracking a plurality of objects within the plurality of images, thereby generating second metadata; comparing the first metadata to the second metadata to determine a degree of the spatial proximity and the temporal proximity that each of the plurality of objects exhibits with the first object; an