Johnson Controls Tyco IP Holdings Llp

Tyco Fire + Security Gmbh

Lipphei Adam

David S Pinney

Jason M Ouellette

Brian Richard

Allen Houston

George Martinez

Disclosed herein are systems, methods, and non-transitory computer readable mediums directed to tracing a person of interest (POI) using video. As provided herein, images of a POI are obtained, such as from a data store, and then the POI is identified in one or more video frames of a monitored video feed by comparing the monitored video frames to the images of the POI using facial recognition techniques. If the POI is identified, additional persons within a prescribed distance threshold of the POI are determined and identified using facial recognition techniques. Thereafter, a list of each identified person within the distance threshold of the POI is generated and may be transmitted to a desired recipient.

Systems and methods of identifying persons-of-interest

Example implementations include a method, apparatus, and computer-readable medium for sharing analytical resources in a camera network, comprising capturing a video clip comprising a set of image frames via a first camera having only non-artificial intelligence (A.I) features, wherein the first camera is part of a camera network. The implementations further include identifying, in the camera network, a second camera that has an A.I feature. The implementations further include determining whether the second camera has bandwidth to analyze the video clip. The implementations include transmitting, via the first camera, the video clip to the second camera for analysis using the A.I feature, in response to determining that the second camera has bandwidth. The implementations include receiving, by the first camera from the second camera, metadata comprising results of the analysis using the A.I feature and generating, for display on a user interface, the video clip with the metadata.

Systems and methods for sharing analytical resources in a camera network

Disclosed herein are apparatuses and methods for verifying video authenticity using blockchain. An implementation may include receiving a video clip from a first source and generating a genesis block of a blockchain, wherein the genesis block includes the video clip, metadata of the video clip, and a first hash value of both the video clip and the metadata. The implementation includes distributing the blockchain to a plurality of nodes in a blockchain network. The implementation includes for each indication received of activity performed on the video clip to be recorded on the blockchain, verifying the activity and generating a new block on the blockchain recording the activity. The implementation includes receiving a modified version of the video clip, verifying an authenticity of the modified version based on each activity recorded in the blockchain, and in response to determining that the modified version is not authentic, generating an alert indicating inauthenticity.

Systems and methods for verifying video authenticity using blockchain

Example aspects include a method, apparatus, and computer-readable medium for surveillance data processing for sanitation verification, comprising determining, by a processor based on area identification information received by a surveillance system of a premises, that an area of the premises requires periodic sanitation. The aspects further include determining, by the processor based on data captured by one or more sensors of the surveillance system, whether one or more persons associated with the cleaning staff profile have visited the area within a threshold period of time. Additionally, the aspects further include sending, by the processor, a first notification to a facilities management device in response to the one or more persons associated with the cleaning staff profile not having visited the area within the threshold period of time.

Surveillance system for automatic sanitation verification

Example aspects include a method, apparatus, and computer-readable medium comprising identifying, by an access control system, an access attempt associated with an individual. The aspects further include confirming, by the access control system, an identity of the individual. Additionally, the aspects further include granting access to the individual by the access control system in response to confirming the identity of the individual. Additionally, the aspects further include building, by the access control system, a digital identity profile of the individual based on visual data of the individual captured contemporaneously with the access attempt.

Automatic creation and management of digital identity profiles for access control

Disclosed herein are apparatuses and methods for granting entry through a checkpoint. The implementations include receiving a request for entry of a person through a checkpoint. The implementations include estimating, via a thermal sensor, a body surface temperature of the person, and generating, via a user interface, a notification that prompts the person to answer at least one verification question. The implementations include receiving, via the user interface, at least one user response to the at least one verification question. The implementations include determining whether the at least one user response and the body surface temperature match criteria for gaining entry through the checkpoint. Additionally, the implementations include granting the request for entry in response to determining that the at least one user response and the body surface temperature match the criteria.

Enhanced entry authorization

Disclosed herein are systems, methods, and non-transitory computer readable mediums directed to identifying persons monitored on video frames of a video feed, determining if the number of people on a monitored video frame is above a prescribed group threshold, and if so, calculating distances between each respective person in the monitored video frame. The calculated distances between each respective person are then compared to a prescribed distance threshold and alerts are generated in response to any calculated distance not satisfying the prescribed threshold. Identification of persons in a monitored video frame may be performed by, for example, facial recognition software. Calculation of distance between persons in a monitored video frame may be performed, for example, by using bounding boxes, machine learning, or other classification techniques.

Growing community of inventors

Nolensville, TN, United States of America

Lipphei Adam