Xerox Corporation

Conduent Business Services, LLC

Michael C Mongeon

Robert P Loce

Wencheng Wu

Matthew Adam Shreve

Edgar A Bernal

Howard A Mizes

Eric Michael Gross

Rakesh Suresh Kulkarni

Jinhui Yao

Jeffrey J Folkins

Michael Jon Levy

Joseph C Sheflin

Charles Donahue Rizzolo

Helen HaeKyung Shin

Daniel S Hann

Jagadeesh Chandra Bose Rantham Prabhakara

Isaiah Lorenzo Simmons, Jr

Jennifer Watts-Perotti

Madhavi Bangalore Shankara Narayana

David Allen Mantell

Dale Robert Mashtare

Nero R Lindblad

Daniel W Costanza

Yeqing Zhang

Roger Lee Triplett

Kenneth Russell Ossman

John Allott Moore

Robert E Grace

David Jordan Lieberman

Song-Feng Mo

Nancy Beth Goodman

Mark Sennett Jackson

Yasmine Charif

Krzysztof J Less

William A Blitz

Himanshu Madhu

Raymond D Wilcox

Michael J Severn

Tanvi Himanshubhai Shah

Hugh W Griffith

Tim D M Enskat

When monitoring a workspace to determine whether scheduled tasks or chores are completed according to a predetermined schedule, a video monitoring system monitors a region of interest (ROI) to identify employee-generated signals representing completion of a scheduled task. An employee makes a mark or gesture in the ROI monitored by the video monitoring system and the system analyzes pixels in each captured frame of the ROI to identify an employee signal, map the signal to a corresponding scheduled task, update the task as having been completed upon receipt of the employee signal, and alert a manager of the facility as to whether the task has been completed or not.

Employee task verification to video system

A system and method to identify the leader of a group in a retail, restaurant, or queue-type setting (or virtually any setting) through recognition of payment gestures. The method comprises acquiring initial video of a group, developing feature models for members of the group, acquiring video at a payment location, identifying a payment gesture in the acquired video, defining the person making the gesture as the leader of the group, and forwarding/backtracking through the video to identify timings associated with leader events (e.g., entering, exiting, ordering, etc.).

Queue group leader identification

Disclosed is a method and system for detecting an interaction event between two or more objects in a surveillance area, via the application of heuristics to trajectory representations of the static or dynamic movements associated with the objects. According to an exemplary embodiment, trajectory interaction features (TIFs) are extracted from the trajectory representations and heuristics are applied to the TIFs to determine if an interaction event has occurred, such as a potential illegal drug deal involving at least one pedestrian and at least one vehicle.

System and method for detecting potential drive-up drug deal activity via trajectory-based analysis

A system for recognizing processes performed by a call center agent during a session may receive input data from a screen recording system that includes a video signal representing a plurality of frames from a time-series video recording or video stream of a desktop of a user electronic device. The system processes the video signal to identify one or more frames of interest from the plurality of frames. Each frame of interest includes a change in a layout of the corresponding one or more screens as compared to a preceding frame in the time-series video recording. The system automatically identifies actions performed by the call center agent that represent an interaction that the call center agent had with one or more screens corresponding to the frame of interest. The system generates an event log that includes a timeline depicting a visual representation of the identified actions.

Methods and systems for automatically recognizing actions in a call center environment using video data

This disclosure provides a method and system for automatically recognizing facial expressions at variable resolutions of video. According to one exemplary method, facial expressions are detected, extracted and classified from a video sequence based on an automatic localization of the periocular region associated with a detected and extracted face.

Method and system for automatically recognizing facial expressions via algorithmic periocular localization

A system for recognizing processes performed by a call center agent during a session may collect input data by initiating a screen capture logging thread to capture screen shots of a desktop of the electronic device during a session. The system analyzes the input data to generate one or more events, generates a mid-level event log comprising one or more of the events, and performs action recognition on the mid-level event log to ascertain one or more actions that were performed within the one or more graphical user interfaces by the call center agent during the session.

Methods and systems for automatically recognizing actions in a call center environment using screen capture technology

Disclosed is a method and system for detecting an interaction event between two or more objects in a surveillance area, via the application of heuristics to trajectory representations of the static or dynamic movements associated with the objects. According to an exemplary embodiment, trajectory interaction features (TIFs) are extracted from the trajectory representations and heuristics are applied to the TIFs to determine if an interaction event has occurred, such as a potential illegal drug deal involving two or more pedestrians.

Method and system for detecting the occurrence of an interaction event via trajectory-based analysis

Disclosed is a method and system for detecting an interaction event between two or more objects in a surveillance area via the application of heuristics to trajectory representations of the static or dynamic movements associated with the objects. According to an exemplary embodiment, trajectory interaction features (TIFs) are extracted from the trajectory representations and heuristics are applied to the TIFs to determine if an interaction event has occurred, such as a potential mugging involving two or more pedestrians.

System and method for detecting potential mugging event via trajectory-based analysis

A system for recognizing processes performed by a call center agent during a session collects from one or more input devices in communication with the electronic device, input data that includes data pertaining to one or more interactions that a call center agent has with one or more programs running on the electronic device that cause one or more graphical user interfaces to be displayed on a desktop of the electronic device during a session. The system analyzes the input data to generate one or more events and a mid-level event log having one or more of the events, and performs action recognition on the mid-level event log to ascertain one or more actions that were performed within the one or more graphical user interfaces by the call center agent during the session.

A computer vision system () operates to monitor an environment (e.g., such as a restaurant, store or other retail establishment) including a resource located therein (e.g., such as a restroom, a dining table, a drink, condiment or supply dispenser, a trash receptacle or a tray collection rack). The system includes: an image source or camera () that supplies image data () representative of at least a portion of the environment monitored by the system, the portion including the resource therein; and an event detection device () including a data processor () and operative to detect an event involving the resource. Suitably, the event detection device is arranged to: (i) be selectively configurable by a user to define the event involving the resource; (ii) receive the image data supplied by the image source; (iii) analyze the received image data to detect the defined event; and (iv) output a notification in response to detecting the defined event.

Store resource event detection

This disclosure provides a video-based method and system for busyness detection and notification. Specifically, according to an exemplary embodiment, multiple overhead image capturing devices are used to acquire video including multiple non-overlapping ROIs (regions of interest) and the video is processed to count the number of people included within the ROIs. A busyness metric is calculated based on the number of people counted and notification of the busyness metric or changes in the busyness metric is communicated to appropriate personnel, e.g., a manager of a retail store.

Busyness defection and notification method and system

A system for delivering one of a good and service to a customer in a retail environment includes a computer located at an order station. The computer is configured to receive an order for the one good and service. The system includes a first image capture device in communication with the computer. The first image capture device captures a first image of a customer ordering the one good and service in response to the order being submitted. The system further includes a wearable computer peripheral device configured to acquire the first image from the first image capture device and electronically display the first image to a user tasked with delivering the one good and service while carrying the second wearable computer peripheral device. In this manner, an identity of the customer can be compared against the first image upon a delivery of the one good and service.

Using head mountable displays to provide real-time assistance to employees in a retail environment

Disclosed are methods and systems to automatically detect and optionally classify when a recipient receives goods in surveillance video. According to one exemplary embodiment, a computer implemented method determines a customer has received goods which are associated with a retail environment.

Methods and systems for goods received gesture recognition

What is disclosed is a system and method for enhancing a spatio-temporal resolution of a depth data stream. In one embodiment, time-sequential reflectance frames and time-sequential depth frames of a scene are received. If a temporal resolution of the reflectance frames is greater than the depth frames then a new depth frame is generated based on correlations determined between motion patterns in the sequence of reflectance frames and the sequence of depth frames. The new depth frame is inserted into the sequence of depth frames at a selected time point. If a spatial resolution of the reflectance frames is greater than the depth frames then the spatial resolution of a selected depth frame is enhanced by generating new pixel depth values which are added to the selected depth frame. The spatially enhanced depth frame is then inserted back into the sequence of depth frames.

Enhancing a spatio-temporal resolution of a depth data stream

Growing community of inventors

Walworth, NY, United States of America

Michael C Mongeon