-
公开(公告)号：US11778162B2
公开(公告)日：2023-10-03
申请号：US17646330
申请日：2021-12-29
Applicant: Tata Consultancy Services Limited
Inventor： Lokender Tiwari , Brojeshwar Bhowmick
IPC: G06T7/60 , G06T7/73 , H04N13/275 , H04N13/282
CPC classification number: H04N13/275 , G06T7/60 , G06T7/75 , H04N13/282 , G06T2207/20081 , G06T2207/20084 , G06T2207/30196 , G06T2210/16 , G06T2210/21
Abstract: This disclosure relates generally to method and system for draping a 3D garment on a 3D human body. Dressing digital humans in 3D have gained much attention due to its use in online shopping and draping 3D garments over the 3D human body has immense applications in virtual try-on, animations, and accurate fitment of the 3D garment is the utmost importance. The proposed disclosure is a single unified garment deformation model that learns the shared space of variations for a body shape, a body pose, and a styling garment. The method receives a plurality of human body inputs to construct a 3D skinned garments for the subject. The deep draper network trained using a plurality of losses provides efficient deep neural network based method that predicts fast and accurate 3D garment images. The method couples the geometric and multi-view perceptual constraints that efficiently learn the garment deformation's high-frequency geometry.
-
公开(公告)号：US10475231B2
公开(公告)日：2019-11-12
申请号：US15898160
申请日：2018-02-15
Applicant: Tata Consultancy Services Limited
Inventor： Brojeshwar Bhowmick , Swapna Agarwal , Sanjana Sinha , Balamuralidhar Purushothaman , Apurbaa Mallik
Abstract: Methods and systems for change detection utilizing three dimensional (3D) point-cloud processing are provided. The method includes detecting changes in the surface based on a surface fitting approach with a locally weighted Moving Least Squares (MLS) approximation. The method includes acquiring and comparing surface geometry of a reference point-cloud defining a reference surface and a template point-cloud defining a template surface at local regions or local surfaces using the surface fitting approach. The method provides effective change detection for both, rigid as well as non-rigid changes, reducing false detections due to presence of noise and is independent of factors such as texture or illumination of an object or scene being tracked for changed detection.
-
公开(公告)号：US10130271B1
公开(公告)日：2018-11-20
申请号：US15900783
申请日：2018-02-20
Applicant: Tata Consultancy Services Limited
Inventor： Puneet Gupta , Brojeshwar Bhowmick , Arpan Pal
Abstract: Traditional electrocardiography (ECG) and photo-plethysmography (PPG) based HR estimation require human skin contact which is not only user uncomfortable, but also infeasible when multiple user monitoring is required or extreme sensitive conditions is a prime concern as in the case of monitoring neonates, sleeping human and skin damaged patients. Temporal signals depicting the motion or color variations in the frames across time, are estimated from a Region of Interest using Eulerian or Lagrangian approaches. However, the Eulerian approach fails under improper illumination, inappropriate camera focus or human factors like skin color. Likewise, Lagrangian approach is highly time-consuming and may fail when few or less discriminatory features are available for tracking. The present disclosure provides a poorness measure that is indicative of when an approach fails and facilitates serial fusion of the two approaches. Switching to an appropriate approach results in accurate heart rate estimation.
-
4.发明申请公开(公告)号：US20180047157A1
公开(公告)日：2018-02-15
申请号：US15466676
申请日：2017-03-22
Applicant: Tata Consultancy Services Limited
Inventor： Sanjana SINHA , Brojeshwar Bhowmick , Kingshuk Chakravarty , Aniruddha Sinha , Abhijit Das
CPC classification number: G06T7/0012 , A61B5/1121 , A61B5/1128 , A61B5/7271 , G06T7/143 , G06T7/593 , G06T7/70 , G06T7/75 , G06T2207/10016 , G06T2207/10024 , G06T2207/10028 , G06T2207/30008 , G06T2207/30241
Abstract: Systems and methods for identifying body joint location includes obtaining skeletal data, depth data and red, green, and blue (RGB) data pertaining to a user, obtaining, using input data, an estimate of body joint locations (BJLs) and body segment lengths (BSLs), iteratively identifying, based on the depth data and RGB data, probable correct BJLs in a bounded neighborhood around BJLs that are previously obtained, comparing a body segment length associated with the probable correct BJLs and a reference length, identifying candidate BJLs based on comparison, determining a physical orientation of each body segment by segmenting three dimensional (3D) coordinates of each body segment based on the depth data and performing an analysis on each segmented 3D coordinate. A corrected BJL is identified based on a minimal deviation in direction from the physical orientation of a corresponding body segment along with a feature descriptor of the RGB data and depth data.
-
公开(公告)号：US12174639B2
公开(公告)日：2024-12-24
申请号：US17813262
申请日：2022-07-18
Applicant: Tata Consultancy Services Limited
Inventor： Ruddra Dev Roychoudhury , Brojeshwar Bhowmick , Madhava Krishna Krishnan , Gulshan Kumar , Sai Shankar Narasimhan , Himansu Didwania
IPC: G05D1/00 , G06V10/22 , G06V10/764 , G06V10/774 , G06V10/82 , G06V20/70
Abstract: In state of the art methods for object goal navigation, scene understanding is implicit in their goal oriented exploration policies. Implicit scene understanding coupled with navigation is shown to be specific to tasks for which training is done and not generalizable to new tasks. Thus, embodiments of present disclosure propose a method of goal-conditioned exploration wherein scene understanding is decoupled from the exploration policies. Here, the scene understanding required for navigation is provided by a region classification network that is trained using semantic graphs representing the scene and agent can be navigated towards the goal either by using any state of the art pure exploration policies or by traversing through potential sub-goals identified based on a Co-occurrence Likelihood score calculated by using predictions from the region classification network. Hence, the method of present disclosure can be easily generalized to new tasks and new environments.
-
Patent Agency Ranking
6.发明授权公开(公告)号：US11551394B2
公开(公告)日：2023-01-10
申请号：US17199149
申请日：2021-03-11
Applicant: Tata Consultancy Services Limited
Inventor： Sandika Biswas , Dipanjan Das , Sanjana Sinha , Brojeshwar Bhowmick
Abstract: Conventional state-of-the-art methods are limited in their ability to generate realistic animation from audio on any unknown faces and cannot be easily generalized to different facial characteristics and voice accents. Further, these methods fail to produce realistic facial animation for subjects which are quite different than that of distribution of facial characteristics network has seen during training. Embodiments of the present disclosure provide systems and methods that generate audio-speech driven animated talking face using a cascaded generative adversarial network (CGAN), wherein a first GAN is used to transfer lip motion from canonical face to person-specific face. A second GAN based texture generator network is conditioned on person-specific landmark to generate high-fidelity face corresponding to the motion. Texture generator GAN is made more flexible using meta learning to adapt to unknown subject's traits and orientation of face during inference. Finally, eye-blinks are induced in the final animation face being generated.
-
公开(公告)号：US11288769B2
公开(公告)日：2022-03-29
申请号：US16830328
申请日：2020-03-26
Applicant: Tata Consultancy Services Limited
Inventor： Arindam Saha , Soumyadip Maity , Brojeshwar Bhowmick
Abstract: The present disclosure provides a system and a method for stitching images using non-linear optimization and multi-constraint cost function minimization. Most of conventional homography based transformation approaches for image alignment, calculate transformations based on linear algorithms which ignore parameters such as lens distortion and unable to handle parallax for non-planar images resulting in improper image stitching with misalignments. The disclosed system and the method generates initial stitched image by estimating a global homography for each image using estimated pairwise homography matrix and feature point correspondences for each pair of images, based on a non-linear optimization. Local warping based image alignment is applied on the initial stitched image, using multi-constraint cost function minimization to mitigate aberrations caused by noises in the global homography estimation to generate the refined stitched image. The refined stitched image is accurate and free from misalignments and poor intensities.
-
公开(公告)号：US10980447B2
公开(公告)日：2021-04-20
申请号：US15908731
申请日：2018-02-28
Applicant: Tata Consultancy Services Limited
Inventor： Sanjana Sinha , Brojeshwar Bhowmick , Aniruddha Sinha , Abhijit Das
Abstract: Body joint tracking is applied in various industries and medical field. In body joint tracking, marker less devices plays an important role. However, the marker less devices are facing some challenges in providing optimal tracking due to occlusion, ambiguity, lighting conditions, dynamic objects etc. System and method of the present disclosure provides an optimized body joint tracking. Here, motion data pertaining to a first set of motion frames from a motion sensor are received. Further, the motion data are processed to obtain a plurality of 3 dimensional cylindrical models. Here, every cylindrical model among the plurality of 3 dimensional cylindrical model represents a body segment. The coefficients associated with the plurality of 3 dimensional cylindrical models are initialized to obtain a set of initialized cylindrical models. A set of dynamic coefficients associated with the initialized cylindrical models are utilized to track joint motion trajectories of a set of subsequent frames.
-
公开(公告)号：US10360665B2
公开(公告)日：2019-07-23
申请号：US15898144
申请日：2018-02-15
Applicant: Tata Consultancy Services Limited
Inventor： Kavya Gupta , Brojeshwar Bhowmick , Angshul Majumdar
Abstract: Motion blur occur when acquiring images and videos with cameras fitted to the high speed motion devices, for example, drones. Distorted images intervene with the mapping of the visual points, hence the pose estimation and tracking may get corrupted. System and method for solving inverse problems using a coupled autoencoder is disclosed. In an embodiment, solving inverse problems, for example, generating a clean sample from an unknown corrupted sample is disclosed. The coupled autoencoder learns the autoencoder weights and coupling map (between source and target) simultaneously. The technique is applicable to any transfer learning problem. The embodiments of the present disclosure implements/proposes a new formulation that recasts deblurring as a transfer learning problem which is solved using the proposed coupled autoencoder.
-
公开(公告)号：US20190114777A1
公开(公告)日：2019-04-18
申请号：US15913800
申请日：2018-03-06
Applicant: Tata Consultancy Services Limited
Inventor： Soumyadip Maity , Arindam Saha , Brojeshwar Bhowmick
Abstract: Feature based visual simultaneous localization and mapping (SLAM) do not produce reliable camera and structure estimates due to insufficient features in a low-textured environment. Moreover, existing visual SLAMs produce partial reconstruction when the number of 3D-2D correspondences is insufficient for incremental camera estimation using bundle adjustment. Systems and methods of the present disclosure provide edge points based monocular visual SLAM that mitigates these problems. The SLAM is initialized through a validation process. A local optimization process is provided for stable pose estimation in situations where camera tracking becomes unreliable in a very low-textured challenging environment. An efficient and reliable loop closing process that uses structural properties of edges in the frames is also provided.
-
-
-
-
-
-
-
-
-
Search Results
40
records
(took 0.02 seconds)
