Avigilon Corporation

Motorola Solutions, Inc.

Kevin Piette

Pietro Russo

Bo Yang Yu

Yanyan Hu

Mahesh Saptharishi

Moussa Doumbouya

Peter L Venetianer

Peter Anderholm

Jehan Wickramasuriya

Shaun P Marlatt

Nicholas John Alcock

Brenna Randlett

Quan Pan

Liia Fadeeva

Eric Peterson

Hugo Fitzpatrick

Obtaining potential match results for a reference image across a plurality of system sites is disclosed. A computing device of one of the system sites includes a signature generator identifiable as a first version amongst a plurality of versions of a respective plurality of possible signature generators. The computing device is configured to generate, within the first signature generator, a first signature corresponding to a cropped object portion of a larger image. The first signature is distinctive to the first version. The computing device is further configured to determine that the cropped object portion being processed within the computing device is a match result for a similar images search. A server is configured to receive the cropped object portion and the first signature from the computing device.

Obtaining potential match results for a reference image across a plurality of system sites

Alias capture to support searching for an object-of-interest is disclosed. A method includes capturing, using a camera with a defined field of view, video image frames that include a moving object-of-interest. The method also includes tracking the object-of-interest over a period of time starting when the object-of-interest enters the field of view and ending when the object-of-interest exits the field of view. The method also includes detecting, at a point in time in-between the start and end of the period of time of the tracking, a threshold exceeding change in an appearance of the object-of-interest. The method also includes creating, before the end of the period of time of the tracking, a new object profile for the object-of-interest in response to the detecting of the threshold exceeding change.

Alias capture to support searching for an object-of-interest

A method, system and computer program product for emulating depth data of a three-dimensional camera device is disclosed. The method includes concurrently operating the radar device and the 3D camera device to generate training radar data and training depth data respectively. Each of the radar device and the 3D camera device has a respective field of view. The field of view of the radar device overlaps the field of view of the 3D camera device. The method also includes inputting the training radar and depth data to the neural network. The method also includes employing the training radar and depth data to train the neural network. Once trained, the neural network is configured to receive real radar data as input and to output substitute depth data.

Method, system and computer program product for emulating depth data of a three-dimensional camera device

Methods, systems, and techniques for monitoring an object-of-interest within a region involve receiving at least data from two sources monitoring a region and correlating that data to determine that an object-of-interest depicted or represented in data from one of the sources is the same object-of-interest depicted or represented in data from the other source. Metadata identifying that the object-of-interest from the two sources is the same object-of-interest is then stored for later use in, for example, object tracking.

Sensor fusion for monitoring an object-of-interest in a region

Methods, systems, and techniques for classifying and/or detecting objects using visible and invisible light images. A visible light image and an invisible light image are received at a convolutional neural network (CNN). The visible light image depicts a region-of-interest imaged using visible light. The invisible light image depicts at least a portion of the region-of-interest imaged using invisible light, and at least one of the images depicts an object-of-interest within the portion of the region-of-interest shared between the images. The CNN then classifies and/or detects the object-of-interest using the images. The CNN may be trained to perform this classification and/or detection using pairs of visible and invisible light training images.

Method and system for object classification using visible and invisible light images

A computer-implemented method comprises detecting, with a presence detector such as a radar device, a presence of a person at a location such as an ATM vestibule. In response thereto, a timer is initiated. After initiating the timer, a portal sensor is used to detect a change in a status of a portal permitting access to the location. In response thereto, the timer is adjusted (for example the timer is reset). Thus, multiple consecutive normal usages of the vestibule do not unnecessarily trigger an alarm.

Presence detection and uses thereof

A system is provided, including: a radar sensor configured to transmit and receive a radar signal from a person; a depth camera configured to receive a depth image of the person; one or more processors communicative with memory having stored thereon computer program code configured when executed by the one or more processors to cause the one or more processors to perform a method comprising: detect the person; determine depth information relating to the person using the depth image; determine a correlation between the depth information of the person and the radar signal received from the person; and in response to the correlation not within a range of expected values, generating an alert. The depth information may be a volume or surface area of the person.

Human profile and anomaly detection

A process for adjusting an amount of video analytics data reported by video capturing devices deployed in a given location. In operation, an electronic computing device detects occurrence of an incident at an incident location based on processing video data or sensor data that are captured corresponding to the incident location. When it is determined that a video capturing device that is deployed within a predetermined distance from the incident location is currently configured with a second video analytics data reporting threshold that is greater than the first video analytics data reporting threshold, the electronic computing device transmits an instruction to the video capturing device to lower the second video analytics data reporting threshold to the first video analytics data reporting threshold and further report video analytics data corresponding to a video stream captured by the video capturing device as a function of the first video analytics data reporting threshold.

Device and method for adjusting an amount of video analytics data reported by video capturing devices deployed in a given location

An electronic movement-controlled apparatus that includes a camera and a movable arm is disclosed. The movable arm has both a stationary end and a movable end with the camera being attached to the movable end so as to be movable therewith. The stationary end is configured to be coupled to a rigid support structure. The movable arm includes a plurality of arm segments connected in series to form the movable arm. The arm segments are configured to have cooperating segment regions in terms of each of the arm segments being compressible and expandable in unison to move the movable end and effect a pan and tilt movement of the camera.

Camera on movable arm

A surveillance drone is disclosed. The surveillance drone includes a gas-filled container and propellers for aerial mobility. The surveillance drone also includes an electronic surveillance sensing device positioned below the gas-filled container. The gas-filled container may be filled with a lighter than air gas such as, for example, helium.

Surveillance drone including gas-filled container and propellers for aerial mobility

A computer-implemented method for detecting a person in a room using a sensor, such as a radar sensor or depth cameras is provided. The method can be used to detect sleeping persons in a publically accessible location to prevent loitering. Furthermore, the method can be used to identify which rooms amongst a plurality of rooms are occupied, for example changing rooms.

Growing community of inventors

Carlisle, MA, United States of America

Kevin Piette