Tata Consultancy Services Limited

Chirabrata Bhaumik

Arpan Pal

Avik Ghose

Tapas Chakravarty

Amit Swain

Balamuralidhar Purushothaman

Aniruddha Sinha

Arijit Sinharay

Prateep Misra

Smriti Rani

Anirban Dutta Choudhury

Deepak N Swamy

Anwesha Khasnobish

Brojeshwar Bhowmick

Soma Bandyopadhyay

Priyanka Sinha

Amit Kumar Agrawal

Tanushyam Chattopadhyay

Vivek Chandel

Arindam Ray

Venkatramanan Siva Subrahmanian

Gitesh Kulkarni

Abhijeet Gorey

Arijit Chowdhury

Arijit Mukherjee

Arijit Ukil

Rohan Banerjee

Sunil Kumar Kopparapu

Ranjan Dasgupta

Swarnava Dey

Rajat Kumar Das

Raj Kumar Rakshit

Nasimuddin Ahmed

Devang Jagdishchandra Patel

Dhiman Chattopadhyay

Ishan Sahu

Soumitra Naskar

Shubhrangshu Ghosh

Prabhat Ranjan Mishra

Sumanta Ghosh

Jayeeta Mondal

Provat Biswas

Mohd Bilal Arif Syed

Dinesh Yadav

Anish Datta

Ankita Gupta

Ketkee Pandit

Suman Adak

Aakash Tyagi

Riddhi Panse

Abhijit Barman

Abhinav Kumar

Abhinav Jha

Kallol Ghosh

Debnarayan Kar

Deepak Swamy

Amit Kumar Agarwal

Jasma Shukla

Subrata Kolay

The present disclosure provides a method for surface wear inspection using millimeter wave radar. The system initially receives a plurality of uncompressed raw Synthetic Aperture Radar (SAR) images. Further, a plurality of reconstructed SAR images are generated based on the plurality of uncompressed raw SAR images using a variable focusing based Range Doppler Algorithm (RDA). Further, a master image and a slave image are selected from the reconstructed SAR images and corresponding anchor points are assigned. Further a plurality of fine level and coarse level shift coordinates are computed based on the corresponding anchor points. Further, a net shift value is computed based on the plurality of fine level and coarse level shift coordinates. The master and the slave images are aligned based on the net shift value and the interferogram is generated. The interferogram is further analyzed to profile the corresponding deformation pertaining to the surface under test.

Method and system for surface wear inspection using millimeter wave radar

Small and compact Deep Learning models are required for embedded AI in several domains. In many industrial use-cases, there are requirements to transform already trained models to ensemble embedded systems or re-train those for a given deployment scenario, with limited data for transfer learning. Moreover, the hardware platforms used in embedded application include FPGAs, AI hardware accelerators, System-on-Chips and on-premises computing elements (Fog/Network Edge). These are interconnected through heterogenous bus/network with different capacities. Method of the present disclosure finds how to automatically partition a given DNN into ensemble devices, considering the effect of accuracy—latency power—tradeoff, due to intermediate compression and effect of quantization due to conversion to AI accelerator SDKs. Method of the present disclosure is an iterative approach to obtain a set of partitions by repeatedly refining the partitions and generating a cascaded model for inference and training on ensemble hardware.

Combining compression, partitioning and quantization of DL models for fitment in hardware processors

This disclosure relates generally to system and method for ambient intelligence based user interaction. Prior methods for touchless user interaction are sensitive to ambient temperature in a lab environment, susceptible to noise from metallic surfaces and ambient radio waves and are dependent on ambient lighting. Embodiments of the present disclosure provides a multi-modal sensor fusion method which captures touchless gestures from a user or a group of users with their physical context information fused and tagged to these gestures for user interaction. Further pose graphs are generated for user interaction systems using a data association technique and Gaussian mixture model technique. The disclosed method provides a hands-free interface to operate instruments in a smart space, using principles of ambient intelligence.

Method and system for ambient intelligence based user interaction

Lighting conditions affect quality of images being captured. In traditional systems, illuminators (light sources) are used to illuminate the objects without considering illumination levels at different zones/sides of an object being photographed. As a result, all illuminators may run at maximum capacity, resulting in wastage of power and compromising efficiency of the system. The disclosure herein generally relates to illumination of objects, and, more particularly, to a method and system for adaptive illumination of objects. The system determines illumination at different zones of the object, and further identifies zones that are not illuminated properly in comparison with a threshold of illumination. Further the system controls intensity of only the illuminators which are responsible for illumination of the zones in which measured illumination is below a threshold of illumination, and increases the intensity by a value determined based on difference between measured illumination and the threshold of illumination, for each zone.

Method and system for zone-wise adaptive illumination of objects

Ultra Wide Band (UWB) based Real Time Location Systems (RTLS) that are being used for location tracking suffer from environment specific errors that are introduced due to factors such as difference in reflection and propagation. In order to address this challenge, present invention discloses performing error modelling for object localization using Ultra Wide Band (UWB) sensors. The error modelling allows to correct a determined location of an object being tracked, to determine a corrected location. Based on an obtained distance value of a tag node with reference to position of a plurality of anchor nodes, location of an object in a 2-Dimensional space is determined. The determined location is corrected to obtain the corrected location, and in this process the error modelling and related error correction is done.

Method and system of error modelling for object localization using ultra wide band (UWB) sensors

This disclosure relates generally to method and system for determining label value for labels in unstructured documents. Typical systems have challenge in understanding variations in layout of unstructured documents and extract information therefrom. The disclosed method and system facilitate systematically identifying sections and bounding boxes in the page images, taking image portion of the bounding boxes and extracting labels and label values therefrom. In case the label values are not present in the same bounding box having the label, the neighboring labels are examined for the matching label values. The system also obtains label-label value pairs from the document by utilizing a trained deep learning model, and compares the output with the label-label value pairs extracted earlier. An aggregated confidence score is assigned to the text in the bounding box.

System and method for determination of label values in unstructured documents

This disclosure relates generally to a method and system for determining viscosity information of fluids. The present disclosure utilizes an intensity modulated continuous wave (CW) laser diode-based PA sensing method to obtain a continuous wave photoacoustic (CWPA) spectra. Through this CWPA spectra, a full width half maximum (FWHM) and a spectral area is determined to obtain the information about the viscosity of fluids. Although, the CWPA based sensing technique is used for distinguishing different types of abnormalities in tissues, so far it is not used for measuring viscosity which is an important thermo-physical property. The viscosity information of the fluids from the normalized Gaussian fitted CWPA spectra is based on a viscosity feature computed from a FWHM, and a spectral area. The viscosity feature improves the good of fit parameter (R) significantly to 0.98 as compared to the traditional only FWHM based viscosity determination for which Ris 0.91.

Method and system for determining viscosity information of fluids

Fluids are normally transported from one place to another through pipelines. It is essential to monitor the pipeline to avoid leakage or theft. It is expensive and not feasible to install cameras and sensors along the whole length of the pipeline. A system and method for inspecting and detecting fluid leakage in a pipeline has been provided. The system is using vibration sensors along with pressure sensors to detect the leakage or theft along with the exact location of the leakage or theft. The pressure sensors are mounted on the pipeline so that the fluid touches the diaphragm of the pressure sensors to sense the wave generated due to leakage. The vibration sensors are mounted on top of the pipeline surface and on the nearby ground to eliminate general noise conditions. Moreover, two pressure sensors are also installed at opposite sides to pinpoint the leakage location.

Method and system for inspecting and detecting fluid in a pipeline

Radar based HR and BR measurements by simultaneous decoding is a technical problem due to presence of intermodulation of BR and HR harmonics, which degrades simultaneous decoding. Embodiments herein provide a method and system for unobtrusive liveliness detection and monitoring of a subject using a Dual Frequency Radar (DFR) in an IOT network. The system has the capability to completely process the captured raw signals onboard to by applying required signal conditioning and extraction of relevant information using unique signal processing techniques for determining the HR and the BR of the subject accurately. The intermodulation of BR and HR harmonics is eliminated by the system by performing frequency spectrum averaging of both radars signals, which improves the accuracy. Further, the system is configured with a light MQTT protocol and encoding modules for any data to be shared for off board processing, ensuring data security and privacy compliance.

Method and system for unobtrusive liveliness detection and monitoring using DFR in an IOT network

Any sensing system is faced with triangle of dilemma between accuracy, latency and energy. High energy and high latency sensing systems are often very accurate but less useful. Embodiments herein provide a method and system for edge based sensor controlling in the IoT network for event monitoring. The system disclosed herein applies a hierarchical sensor selection process and adaptively chooses sensors among multiple sensors deployed in the IoT network. Further, on-the-fly changes operation modes of the sensors to automatically produce the best possible inference from the selected sensor data, in time, power and latency at the edge. Further, sensors of the system include a waveform and diversity control mechanism that enables controlling of an excitation signal of the sensor.

Edge based sensor actuation and control in IoT network for event monitoring

This disclosure relates generally to surveillance, and more particularly to perform entry and exit monitoring of a user. In an embodiment, the system identifies an entry event (during which a user enters a room being surveilled) and/or an exit event (during which a user leaves a room being surveilled), based on a Bluetooth Low Energy (BLE) based system. This system uses two receivers one positioned outside and the other positioned inside the room being surveilled, to receive BLE beacon transmitted by a user who is in motion. Based on relative change in Received Signal Strength Indicator (RSSI) values of this beacon with respect to the first and second receivers, the system identifies direction of movement of the user, and in turn, determines one of the entry or exit events.

Method and system for entry and exit monitoring using bluetooth low energy (BLE) beacons

A mobile device and a method for estimation of direction of motion of a user are described. The mobile device comprises an inertial sensor to capture acceleration signals based on motion of the user and a direction estimation module. The direction estimation module determines direction of gravity based on filtering acceleration values obtained from captured the acceleration signals using a low-pass filter to identify a plane orthogonal to the direction of gravity. The plane orthogonal to the gravity comprises two orthogonal axes orthogonal to the direction of gravity. Further, displacement values are evaluated based on a user input for placement of the mobile device with respect to user's body, and integration of the acceleration values across the two orthogonal axes with respect to time. A direction of motion of the user is estimated based on a ratio of the displacement values along the two orthogonal axes.

Estimation of direction of motion of users on mobile devices

A method and system for real-time analytics of sensor-based data is disclosed. Also disclosed is a Cloud-based Paltform-as-a-Service (PaaS) offering for sensor driven applications with services and features for their complete life-cycle management including prompt development, testing, deployment and so forth. The method of the present disclosure enables real-time tracking of various physical parameters and attributes related to smart-spaces using sensor devices implemented in the premises of the smart-space environment and using crowd-sourced user input data. Further, the parameters obtained are sent to the cloud-computing server, wherein the analytics are performed in real-time based on the obtained parameters.

Computer platform for development and deployment of sensor data based applications and services

A computing platform for intelligent development, deployment and management of vehicle telemetry applications is disclosed herein. Further, the present disclosure provides a method and system that enables provision of Intelligent Transportation Service on the Cloud-based Platform that facilitates creation and deployment of vehicle telemetry applications configured for enabling traffic measurements, traffic shaping, vehicle surveillance and other vehicle related services.

Computer platform for development and deployment of sensor-driven vehicle telemetry applications and services

The application provides a method and system for automatically recommending television program to a user. The application provides a method and system for recommending related television programs while viewing video on internet based, using context of the said video. Further, the application provides a method and system for extracting electronic program guide information for all the channels available on the television and correlating them for recommending related television programs.

Method and system for television program recommendation

Growing community of inventors

Kolkata, India

Chirabrata Bhaumik