A video-based security system for providing video security to cargo transport vehicle. The security system includes a camera support configured at the exterior of a cargo storage area; a camera system attached to the camera support for covering a top plane, front plane, left plane, right plane, and back plane of a cargo area; and a main unit connecting to the camera system for logging incident records.

A first device is detected within a geofenced area of an establishment. A second device is determined to be within the geofenced area. A first individual associated with the first device is instructed to enter the establishment and complete a first portion of opening security procedures associated with an opening of the establishment. Upon completion of the first portion, a second individual associated with the second device is instructed to enter the establishment for a second portion of the opening security procedures. The first individual and the second individual are monitored through video feeds during the first portion and the second portion of the opening security procedures for compliance with the opening security procedures.

Systems and techniques are provided for monitoring status of subjects in an area of real space. The system includes a display having access to memory storing a first data set identifying locations of subjects in the area of real space over time, a second data set identifying item put and take events in the area of real space and a third data set identifying accounts matched to the subjects in the first data set. The system includes a graphical user interface logic that renders a map on the display of at least part of the area of real space including avatars having locations on the map corresponding to locations in the area of real space according to the first data set, and identifying respective statuses assigned to the subjects based on one or more of the first data set, the second data set and the third data set.

Embodiments of the present invention describe receiving, by a first device, an information vector over a short-range communication network established between the first device and a second device. Additionally, embodiments comprise determining the first identifier does not match the second identifier, merging one or more smart maps from the two or more computing devices together, comparing a first set of devices represented in the first set of participants and a second set of devices represented in the second set of participants, identifying pairs of matching devices in the first set of devices and the second set of devices, generating a set of unique devices by discarding one device for each pair of matching devices identified, and outputting a smart map comprising a count of participants equal to the sum of participants associated with the set of unique devices.

Methods and systems for detecting and predicting anomalies include processing frames of a video stream to determine values of a feature corresponding to each frame. A feature time series is generated that corresponds to values of the identified feature over time. A matrix profile is generated that identifies similarities of sub-sequences of the time series to other sub-sequences of the feature time series. An anomaly is detected by determining that a value of the matrix profile exceeds a threshold value. An automatic action is performed responsive to the detected anomaly.

A management terminal manages a plurality of Self-Service Terminals (SSTs) for customer-assistance, transaction overrides, theft determinations, and transaction security audits. One or more overhead cameras stream real-time video of the transactions being processed at the SSTs to a server. Transaction data produced in real time at the SSTs are also provided to the server. The video is correlated with the transaction data and evaluated for security events. The video is also cached on the server. An operator of the management terminal can access a video review interface based on events and/or information visually gleaned by the operator during the transactions. The interface permits the operator to view a configured cached portion of the video captured for any given transaction to provide context to the operator for determining whether to perform or whether not to perform a transaction audit.

A management terminal manages a plurality of Self-Service Terminals (SSTs) for customer-assistance, transaction overrides, theft determinations, and transaction security audits. One or more overhead cameras stream real-time video of the transactions being processed at the SSTs to a server. Transaction data produced in real time at the SSTs are also provided to the server. The video is correlated with the transaction data and evaluated for security events. The video is also cached on the server. An operator of the management terminal can access a video review interface based on events and/or information visually gleaned by the operator during the transactions. The interface permits the operator to view a configured cached portion of the video captured for any given transaction to provide context to the operator for determining whether to perform or whether not to perform a transaction audit.

A monitoring information recording apparatus according to one aspect, includes a recording processing unit configured to record, in a case that monitoring information including-at least one of a captured image of a monitoring target and a measurement value calculated based on the captured image meets a predetermined criterion, the monitoring information in a first mode. The recording processing unit, records, in a case that the monitoring information has not been recorded in the first mode for a predetermined period of time or longer, the monitoring information in the first mode regardless of whether the above criterion is met or not.

A people-flow-estimation device includes a person-count-estimation unit for estimating the number of people included in a partial area of an image; a crowd-direction-estimation unit for estimating the direction of a crowd in the partial area; a movement-amount-estimation unit for estimating the amount of movement in the partial area; and a generation unit for extracting a partial area where people exist from a plurality of partial areas on the basis of the number of people and generating, on the basis of the number of people, the extracted partial area, and the direction and movement amount of a crowd associated with the partial area, people's flow information relating to a people's flow representing the flow of people in the partial area.

A people-flow-estimation device includes a person-count-estimation unit for estimating the number of people included in a partial area of an image; a crowd-direction-estimation unit for estimating the direction of a crowd in the partial area; a movement-amount-estimation unit for estimating the amount of movement in the partial area; and a generation unit for extracting a partial area where people exist from a plurality of partial areas on the basis of the number of people and generating, on the basis of the number of people, the extracted partial area, and the direction and movement amount of a crowd associated with the partial area, people's flow information relating to a people's flow representing the flow of people in the partial area.