International Business Machines Corporation

Nvidia Corporation

Cisco Technology, Inc.

Milind R Naphade

Sambit Sahu

John Richard Smith

Ming Li

Younghun Kim

Farzin Aghdasi

Parthasarathy Sriram

Apostol Ivanov Natsev

Chung-Sheng Li

Ching-Yung Lin

Anshul Sheopuri

Arman Toorians

Stephen Eric Levy

Parijat Dube

Rahul Jain

Hongliang Fei

Matthew Leon Hill

Carlos M Pignataro

Rong Yan

Charu Chandra Aggarwal

Kun-Lung Wu

Philip Shilung Yu

Sriram Kolinjivadi Padmanabhan

Ming-Yu Liu

Yuan-Chi Chang

Min Wang

Chitra Dorai

Belle L Tseng

Feng Chen

Xiaodong Yang

Jing Dai

Sujit Biswas

Tian-Jy Chao

Jelena Tesic

Aaron Bartholomew

Bhanu Nagendra Pisupati

Vinay Kolar

Ratnesh Kumar

Shahram Ebadollahi

Murray Scott Campbell

Lexing Xie

Richard John Nash

Duncan A Ashby

So Yeon Chun

Todd M Appel

Anders Thornqvist

Martin Vuyk

John Hutchinson

Sanjay K Mamidipalli

Shuo Wang

Ioana Roxana Stanoi

John Ronald Kender

Pavankumar Murali

Feng Cheng

Sankar Basu

Gyana Ranjan Dash

Manjula Shivanna

Alexander Haubold

Srinivas Ruddaraju

En Cheng

Brian Michael Landry

Evan McLaughlin

Arihant Jain

Tingting Huang

Calibration of various sensors may be difficult without specialized software to process intrinsic and extrinsic information about the sensors. Certain types of input files, such as image files, may also lack certain information, like depth information, to effectively translate regions of interest between images taken from a different perspective. Landmarks can be used to establish points for associating regions of interest between images taken from a different perspective and provided as an overlay to verify sensor calibration.

Sensor calibration for space translation

The present disclosure provides various approaches for smart area monitoring suitable for parking garages or other areas. These approaches may include ROI-based occupancy detection to determine whether particular parking spots are occupied by leveraging image data from image sensors, such as cameras. These approaches may also include multi-sensor object tracking using multiple sensors that are distributed across an area that leverage both image data and spatial information regarding the area, to provide precise object tracking across the sensors. Further approaches relate to various architectures and configurations for smart area monitoring systems, as well as visualization and processing techniques. For example, as opposed to presenting video of an area captured by cameras, 3D renderings may be generated and played from metadata extracted from sensors around the area.

Scenario recreation through object detection and 3D visualization in a multi-sensor environment

In various examples, cloud computing systems may store frames of video streams and metadata generated from the frames in separate data stores, with each type of data being indexed using shared timestamps. Thus, the frames of a video stream may be stored and/or processed and corresponding metadata of the frames may be stored and/or generated across any number of devices of the cloud computing system (e.g., edge and/or core devices) while being linked by the timestamps. A client device may provide a request or query to dynamically annotate the video stream using a particular subset of the metadata. In processing the request or query, the timestamps may be used to retrieve video data representing frames of the video stream and metadata extracted from those frames across the data stores. The retrieved metadata and video data may be used to annotate the frames for display on the client device.

Overlaying metadata on video streams on demand for intelligent video analysis

In various examples, a set of object trajectories may be determined based at least in part on sensor data representative of a field of view of a sensor. The set of object trajectories may be applied to a long short-term memory (LSTM) network to train the LSTM network. An expected object trajectory for an object in the field of view of the sensor may be computed by the LSTM network based at least in part an observed object trajectory. By comparing the observed object trajectory to the expected object trajectory, a determination may be made that the observed object trajectory is indicative of an anomaly.

Object behavior anomaly detection using neural networks

Smart area monitoring with artificial intelligence

In one embodiment, a computing device scans a plurality of available data sources associated with a profiled identity for an individual, and categorizes instances of the data sources according to recognized terms within the data sources. Once determining whether the profiled identity contributed positively to each categorized instance, categorized instances that have a positive contribution by the profiled identity may be clustered into clusters. The computing device may then rank the clusters based on size of the clusters and frequency of recognized terms within the clusters, and can then infer an expertise of the profiled identity based on one or more best-ranked clusters. The inferred expertise of the profiled identity may then be stored.

Dynamically inferred expertise

Providing an end-to-end citizen engagement, in one aspect, may comprise obtaining data of multiple disintegrated sources from one or more of communication and social computing channels via one or more adapters. Data refactoring and management, integration and process orchestration of the data according to a data model as data attributes of the data model may be provided. One or more analytics may be performed based on the data attributes stored according to the data model and input specified to the one or more analytics. One or more results computed by performing the one or more analytics may be provided. One or more application logics supporting one or more front-end applications may be produced. One or more front-end applications for automated sensing of user activities and sensor-based individual assistant capability may be provided.

End-to-end effective citizen engagement via advanced analytics and sensor-based personal assistant capability (EECEASPA)

A GPS-enabled cellular electronic device is operated in an indoor mode. An increase in strength of a cellular signal is detected at the GPS-enabled cellular electronic device. Responsive at least to the increase in cellular signal strength, the GPS-enabled cellular electronic device is transitioned to an outdoor testing mode. Detecting is carried out to determine whether movement of the GPS-enabled cellular electronic device occurs during the outdoor testing mode. If so, the GPS-enabled cellular electronic device is transitioned to an outdoor mode.

Energy efficient location tracking on smart phones

Providing an end-to-end citizen engagement, in one aspect, may comprise obtaining data of multiple disintegrated sources from one or more of communication and social computing channels via one or more adapters. Data refactoring and management, integration and process orchestration of the data according to a data model as data attributes of the data model may be provided. One or more analytics may be performed based on the data attributes stored according to the data model and input specified to the one or more analytics. One or more results computed by performing the one or more analytics may be provided. One or more application logics supporting one or more front-end applications may be produced. One or more front-end applications for automated sensing of user activities and sensor-based personal assistant capability may be provided.

A method for freight vehicle monitoring includes obtaining historical telecommunications data, performing vehicle location identification using the historical telecommunications data, wherein performing the vehicle location identification comprises using a machine learning based algorithm to determine one or more meaningful vehicle locations, identifying, based on the one or more meaningful vehicle locations, if one or more telecommunications devices are those of a freight vehicle occupant, and tracking a location of the one or more telecommunications devices identified as those of a freight vehicle occupant.

Freight vehicle monitoring using telecommunications data

A computer readable medium embodies a program of machine-readable instructions executable by a processing apparatus to perform operations including determining information corresponding to a number of differences in distances between ending points of journeys taken by a vehicle and starting points of consecutive journeys taken by the vehicle, and transmitting one or more representations of the information. Another computer readable medium tangibly includes instructions for, for each of a number of vehicles, receiving one or more scores corresponding to a vehicle, and determining a ranked list containing at least a portion of the scores, and outputting the ranked list. Another computer readable medium includes instructions for, for each of a number of vehicles, receiving information corresponding to a vehicle, using one or more metrics, calculating one or more values from the received information, and communicating one or more representations of the one or more value to one or more entities.

Anomaly detection for road user charging systems

Detecting appliance in a building, in one aspect, may comprise receiving meter data associated with energy consumption, the meter data comprising at least energy consumption data associated with usage of the appliance, receiving customer data associated with the meter data, extracting features for training a model for detecting the appliance, based on at least the meter data and the customer data, and constructing the model based on the features.

Detecting appliances in a building from coarse grained meter data with partial label

Growing community of inventors

Fishkill, NY, United States of America

Milind R Naphade