Tata Consultancy Services Limited

Arindam Saha

Aniruddha Sinha

Brojeshwar Bhowmick

Arpan Pal

Soumyadip Maity

Gautam Shroff

Rohan Banerjee

Ranjan Dasgupta

Hiranmay Ghosh

Mohan Bhaskara

Mahesha Gunmi

Apurbaa Mallik

Anupam Basu

Lokesh Kumar

This disclosure relates generally to method and system to detect and estimate dynamic obstacles using Red Green Blue-Depth RGB-D sensors for robot navigation. Obstacle detection and tracking tasks with efficient processing of depth images becomes complex in dynamic and cluttered environments. The method detects one or more obstacles being identified in the one or more depth images in two dimensional space using the depth map captured using a Red Green Blue-Depth RGB-D sensor configured to a mobile robot. Further, a restricted v-depth map is computed between specified columns taken from the width of each dynamic obstacle of the u-depth map and within the depth range derived from the u-depth map. The one or more dynamic obstacles are tracked by matching segments of subsequent depth images to predict future position in the region of the monitoring environment by computing a closeness signature. The method evaluates correctness with open data sequence and real world data.

Method and system to detect and estimate dynamic obstacles using RGB-D sensors for robot navigation

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.

System and method for stitching images using non-linear optimization and multi-constraint cost function minimization

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.

Systems and methods for edge points based monocular visual SLAM

The present subject matter discloses a system and a method for constructing a 3D structure. A stream of images having timestamps associated is received at first. A plurality of image sub-groups is created using the stream of images. The plurality of image sub-groups are used for extracting features of the images present in the image sub-groups. The features are used for generating point correspondences between the images. Epipolar geometries for the image sub-groups are calculated for filtering of the point correspondences, and generating filtered point correspondences. Further, 3D points representing one or more 3D point structures are generated using the filtered point correspondences. A registered 3D structure is constructed using the one or more 3D structures upon considering a scale correction and transformation between the one or more 3D structures. Further, the registered 3D structure is dense reconstructed for improving the pixel density of the 3D structure.

Constructing a 3D structure

The present invention provides a method and system for broadcast of additional content such as metadata required for client specific interactive application in an analog domain along with conventional audio, video and PSI or SI data. The present invention enables transmission of encoded audio data or EPG data, timestamp information required for audio video synchronization referred to as metadata by embedding such metadata in the pixels of video pixels and then encoding by the standard video encoder to generate an encoded stream. The encoded stream is decoded using the standard video decoder at the receiving station to generate a Composite Video Blanking and Sync (CVBS) analog video signal. From the CVBS signal, the RGB or YUV pixels of the videos are extracted. Finally a data extractor module retrieves the embedded metadata from the RGB or YUV pixels.

Method and system for embedding metadata in multiplexed analog videos broadcasted through digital broadcasting medium

Disclosed is a method and system for constructing a 3D structure. The system of the present disclosure comprises an image capturing unit for capturing images of an object. The system comprises of a gyroscope, a magnetometer, and an accelerometer for determining extrinsic camera parameters, wherein the extrinsic camera parameters comprise a rotation and a translation of the images. Further the system determines an internal calibration matrix once. The system uses the extrinsic camera parameters and the internal calibration matrix for determining a fundamental matrix. The system extracts features of the images for establishing point correspondences between the images. Further, the point correspondences are filtered using the fundamental matrix for generating filtered point correspondences. The filtered point correspondences are triangulated for determining 3D points representing the 3D structure. Further, the 3D structure may be optimized for eliminating reprojection errors associated with the 3D structure.

Disclosed is a method and system enabling power effective participatory sensing. The hand held device of the system is equipped with plurality of sensors, and is configured to enable the power effective sensor to monitor operation of the power intensive sensors. In one embodiment, a participatory sensing approach is used for traffic condition. A methodology for triggering power hungry sensors (audio) with the help of low power sensors (accelerometer) is presented which is able to reduce the overall power consumption of the mobile device. Further, a decision tree based approach is used to classify the level of congestion by measuring the horn density in a particular location.

System and method for power effective participatory sensing

A method for embedding, multiplexing and broadcasting of multiple audio metadata in an analog video stream and thereby generating output analog video containing multiple separable audio-video tuples of optimum quality. Further, a user study is performed on a sample tutorial video for various frame rates and resolution to calculate the mean opinion score for deriving the degree of multiplexing that may be provided without deteriorating the quality of video.

Method for embedding and multiplexing audio metadata in a broadcasted analog video stream

A method and system for multiplexing of multiple channels of video data through a single analog broadcasting channel is disclosed. The method enables a spatial and temporal multiplexing of videos of each of the multiple channels. The multiplexed content is created as a result of multiplexing that is encoded to generate digital transport stream that is transmitted through analog medium. The system enables a STB receiver to decode each of the videos from the stream. At least one video from the multiple videos is played on the television based on user selection.

Growing community of inventors

Kolkata, India

Arindam Saha