International Business Machines Corporation

Virage, Incorporated

Chiao-Fe Shu

Arun Hampapur

Zuoxuan Lu

Christopher Scott Milite

Stephen R Russo

Andrew William Senior

Chek Keong Tan

Mojgan Monika Gorkani

Michael J Desimone

Amarnath Gupta

Carl P Mercier

Lisa Maire Brown

Ying-Li Tian

Yun Zhai

Ramesh Jain

Bradley Horowitz

Richard D Humphrey

Charles Fuller

Michael J Portuesi

Lisa Marie Brown

Jeffrey R Bach

Rogerio Schmidt Feris

Russell Patrick Bobbitt

Jonathan Hudson Connell, Ii

Sergio Borger

Frederik C M Kjeldsen

Senem Velipasalar

Raymond A Cooke

Christopher R Carlson

Sharathchandra UmapathiRao Pankanti

Florian Pinel

Lalit Agarwalla

Bruce Henry Hyre

Barry Gottlieb

Christopher A LoGiudice

Linda C Owen

Max Lu

A computer-implemented method for executing a composition of analytical models. In one embodiment, the computer-implemented method creates analytical model composition definitions for a plurality of analytical models. The computer-implemented method receives analytical model definitions and an analytical model composition. The computer-implemented method binds the analytical model composition to the analytical model definitions. The computer-implemented method deploys the analytical model composition using the analytical model composition definitions. The computer-implemented method executes the analytical model composition and returns a result of the analytical model composition.

Composition engine for analytical models

Embodiments are directed to an object detection system having at least one processor circuit configured to receive a series of image regions and apply to each image region in the series a detector, which is configured to determine a presence of a predetermined object in the image region. The object detection system performs a method of selecting and applying the detector from among a plurality of foreground detectors and a plurality of background detectors in a repeated pattern that includes sequentially selecting a selected one of the plurality of foreground detectors; sequentially applying the selected one of the plurality of foreground detectors to one of the series of image regions until all of the plurality of foreground detectors have been applied; selecting a selected one of the plurality of background detectors; and applying the selected one of the plurality of background detectors to one of the series of image regions.

Self-optimized object detection using online detector selection

A data indexing system and method includes acquiring activity data in a context and indexing the activity data in accordance with contextual conditions. The activity data is stored in accordance with indices. An event is correlated with the activity data by using the indices to review the activity data in the context.

People searches by multisensor event correlation

A system for detecting a change in object positioning by processing images by detecting a first entity tagged with a first visually unique identifier, and detecting a second entity tagged with a second visually unique identifier distinguishable from the first visually unique identifier. The system receives a first image, from a first image capturing device, containing the first visually unique identifier and the second visually unique identifier. The system analyzes the first image to determine a distance between the first visually unique identifier and the second visually unique identifier. The system receives a second image containing the first visually unique identifier. The system analyzes the second image to determine a location of the second visually unique identifier relative to the first visually unique identifier to form a distance assessment. Based on the distance assessment, the system determines a change in proximity between the first entity and the second entity.

Low-cost method to reliably determine relative object position

An approach for generating a coding schema for identifying a spatial location of an event within video image data is provided. In one embodiment, there is a spatial representation tool, including a compression component configured to receive trajectory data of a trajectory of an object for an event within video image data; generate a lossless compressed contour-coded blob to encode the trajectory data of the trajectory of the object for the event within video image data; generate a lossy searchable code of the trajectory of the object for the event within the video image data; convert a region of interest within the video image data to a lossy query code, the region of interest corresponding to a sub-section of a visual display output of the video image data; and compare the lossy query code to the lossy searchable code within a relational database to identify a corresponding lossless trajectory data of the trajectory of the object for the event within the video image data.

Coding scheme for identifying spatial locations of events within video image data

An invention for identifying a spatial location of an event within video image data is provided. Disclosed are embodiments for detecting an object and obtaining trajectory data of a trajectory of the object within the video image data from a sensor device; converting the trajectory data into a contour-coded compressed image; generating, based on the trajectory data, a searchable code that contains a set of locations traversed by the trajectory of the object within the video image; associating the searchable code with the contour-coded compressed image in a database; and returning, in response to a query having a selected location that corresponds a location of the set of locations in the searchable code, an image of the trajectory data corresponding to the object based on the contour-coded compressed image in the database.

Identifying spatial locations of events within video image data

An approach that indexes and searches according to a set of attributes of a person is provided. In one embodiment, there is an extensible indexing and search tool, including an extraction component configured to extract a set of attributes of a person monitored by a set of sensors in a zone of interest. An index component is configured to index each of the set of attributes of the person within an index of an extensible indexing and search tool. A search component is configured to enable a search of the index of the extensible indexing and search tool according to at least one of the set of attributes of the person.

Indexing and searching according to attributes of a person

An approach that manages moving surveillance cameras is described. In one embodiment, there is a system for managing images generated from a movable camera. In this embodiment, the system comprises a motion estimation component configured to determine camera motion. A camera motion alert component is configured to generate an alert in response to a determination that the camera has moved or the camera has ceased moving.

System and method for managing moving surveillance cameras

An invention for identifying a spatial location of an event within video image data is provided. Disclosed are embodiments for generating trajectory data of a trajectory of an object for a plurality of pixel regions of an area of interest within video image data, the generating comprising: identifying one or more pixel regions from the plurality of pixel regions containing trajectory data; performing a multi-point neighborhood scan within the one or more pixel regions from the plurality of pixel regions containing trajectory data; and generating a transition chain code based on the multi-point neighborhood scan. Embodiments further generate a set of compressed spatial representations of the trajectory data of the trajectory of the object for an event based on the transition chain code, and generate a lossless contour code of the trajectory data of the trajectory of the object for the event based on the transition chain code.

The present invention relates to the measurement of human activities through video, particularly in retail environments. A method for measuring retail display effectiveness in accordance with an embodiment of the present invention includes: detecting a moving object in a field of view of an imaging device, the imaging device obtaining image data of a product display; tracking the object in the field of view of the imaging device to obtain a track; and obtaining statistics for the track with regard to the product display.

System and method for the measurement of retail display effectiveness

Methods and apparatus are provided for example-based object retrieval that can retrieve objects from video images in real-time. An object of interest is identified in a sequence of images by obtaining an identification from a user of an example object having at least one attribute of interest; generating a query object based on the identified example object, wherein the query object has a substantially similar viewpoint as objects in the sequence of images and wherein the query object comprises a plurality of attributes that are substantially similar as the example object; and processing the sequence of images to identify the object of interest based on a similarity metric to the query object.

Example-based object retrieval for video surveillance

Growing community of inventors

Scarsdale, NY, United States of America

Chiao-Fe Shu