International Business Machines Corporation

Toshiba Global Commerce Solutions Holdings Corporation

Toshiba Global Commerce

Solutions Holdings Corporation

Russell Patrick Bobbitt

Yun Zhai

Sharathchandra UmapathiRao Pankanti

Arun Hampapur

Rogerio Schmidt Feris

Quanfu Fan

Akira Yanagawa

Florian Pinel

Frederik C Kjeldsen

Lisa Maire Brown

Sachiko Miyazawa

Chiao-Fe Shu

Ira L Allen

Peter Alan Coldicott

Myron Dale Flickner

Charles A Otto

Lei Ding

Frederik C M Kjeldsen

Frank Yeh, Jr

Unsang Park

Sharon Laquinta Cham

Shikhar Kwatra

Donna Karen Byron

Sharathchandra Umapathirao Pankanti

Zuoxuan Lu

Curtis Howard Brobst

Jiyan Pan

A method of calibrating a system including a camera, the method including detecting a robot navigating within an environment modeled as a geo-polygon space, including a transit of the robot through a scene of the environment captured by the camera, mapping a plurality of points occupied by the robot in images of the scene to the geo-polygon space, recording data about the mapping, and configuring at least one alert using the data recorded about the mapping, the alert executed by the computing system and configured to be triggered by an object transiting the scene.

Robotic geometric camera calibration and monitoring alert configuration and testing

Aspects of this disclosure relate to a system that uses images of a load handled by a crane as captured by cameras to monitor the load. The images may include different sets of outer perimeters of the load. The system may identify the outer perimeters and then define a safety zone that extends beyond these outer perimeters. In response to identifying an object within the safety zone, the system may execute a remedial action.

Camera-assisted crane safety

A method, system, and computer program product for automated collection of training data and training object detection models is provided. The method generates a set of reference images for a first set of products. Based on the set of reference images, the method identifies a subset of products within an image stream. Based on the subset of products, a second set of products is determined within the image stream. The method identifies a set of product gaps based on the subset of products and the second set of products. The method generates a product detection model based on the set of reference images, the subset of products, the second set of products, and the product gaps.

Automated training data collection for object detection

Selectively redacting an image by determining a set of attributes used by a machine learning model for an analysis, receiving image data detecting, by the one or more computer processors, a portion of the image data relevant to the analysis, the portion comprising at least some of the set of attributes, generating a synthetic portion from the portion, wherein the synthetic portion retains at least some of the attributes of the detected portion, replacing the portion with the synthetic portion, yielding redacted image data, and providing the redacted image data for analysis.

Selective redaction of images

In an approach for efficient data processing in a mesh network of computing devices, a processor receives data to be processed in the mesh network. A processor distributes a set of computational units to a set of computing devices in the mesh network. A processor creates a computational plan to construct a computational pipeline of the set of computational units. The computational plan considers cost and performance trade-offs by considering limitation of hardware resources, processing speed, accuracy and application requirements. A processor executes the computational plan by sending data to assigned computational units.

Efficient data processing in a mesh network of computing devices

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

A method includes activating a first object detector and a second object detector. The first object detector is operable to detect a first type of object in a set of image frames, and the second object detector is operable to detect a second type of object in the set of image frames. The method also includes activating a first set of attribute classifiers and a second set of attribute classifiers. The method also includes generating first statistics for the first object detector and second statistics for the second object detector. The method also includes modifying activation of at least the second set of attribute classifiers based on a comparison of the first statistics and the second statistics.

Attribute classifiers for image classification

Provided are techniques for optimized deployment of analytic models in an edge topology. A description of a multi-tiered edge topology with a plurality of nodes, a multimedia stream analytics composition, and performance objectives are received, where the multimedia stream analytics composition includes tasks that use analytic models. The analytic models are optimized and clustered to form clusters of optimized analytic models. A representative optimized analytic model is selected from each of the clusters. A configuration recommendation is determined that indicates deployment of the tasks and of each selected representative optimized analytic model on the plurality of nodes to meet the performance objectives. One or more workflows are generated from the configuration recommendation and executed on the plurality of nodes to generate output for the multimedia stream analytics composition.

Optimized deployment of analytic models in an edge topology

A computer-implemented method for assigning one or more conveyor belts to convey a plurality of items. The computer-implemented method determines an availability of one or more conveyor belts, determines a quantity of a plurality of items to be loaded onto the one or more conveyor belts, and assigns the one or more conveyor belts to convey the plurality of items, based on the determined quantity of the plurality of items to be loaded onto the one or more conveyor belts. The computer-implemented method further tracks a location of each of the plurality of items on the assigned one or more conveyor belts, associates each of the plurality of items with a user, and directs the user to the one or more conveyor belts based on the tracked location of each of the plurality of items associated with the user.

Optimized assignment of multiple conveyor belts

An approach is provided in which an information handling system trains a classifier using rated content segments that each has a first content type rating corresponding to a content type. Then, the information handling system uses the trained classifier to classify unrated content segments corresponding to an unrated content and generates second content type ratings for each of unrated content segments accordingly that identify a corresponding content type. In turn, the information handling system generates an overall content rating of the unrated content based on a combination of the second content type ratings.

Movie content rating

Methods and system are provided for monitoring a queue. A method includes receiving by sensors a non-visual identifier at predefined locations of a queue. Further, the method includes capturing by image capture devices images of an object possessing the non-visual identifier at the predefined locations of the queue. Further, the method includes visually tracking another object in the queue based on transformations of a predefined feature extracted from the images of the object possessing the non-visual identifier at the predefined locations.

Visual monitoring of queues using auxillary devices

Techniques are described for video redaction. In one aspect, techniques include receiving a video for redaction; analyzing the video to generate an appearance model for the video, providing a user interface (UI) allowing a user to modify the appearance model, and responsive to a user selecting an object from the appearance model, extending and completing a trajectory of the selected object with enhanced marking based on the user input.

Object-centric video redaction

Machine logic that pre-processes and post-processes images for visual object detection by performing the following steps: receiving a set of image(s); filtering the set of image(s) using a set of multimodal integral filter(s), thereby removing at least a portion of the set of image(s) and resulting in a filtered set of image(s); performing object detection on the filtered set of image(s) to generate a set of object-detected image(s); assembling a first plurality of object-detected image(s) from the set of object-detected image(s); and upon assembling the first plurality of object-detected image(s), performing non-maximum suppression on the assembled first plurality of object-detected image(s).

Growing community of inventors

New York, NY, United States of America

Russell Patrick Bobbitt