Patents by Inventor Subarna Tripathi
Subarna Tripathi has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Publication number: 20240104915Abstract: Machine learning models can process a video and generate outputs such as action segmentation assigning portions of the video to a particular action, or action classification assigning an action class for each frame of the video. Some machine learning models can accurately make predictions for short videos but may not be particularly suited for performing action segmentation for long duration, structured videos. An effective machine learning model may include a hybrid architecture involving a temporal convolutional network and a bi-directional graph neural network. The machine learning model can process long duration structured videos by using a temporal convolutional network as a first pass action segmentation model to generate rich, frame-wise features. The frame-wise features can be converted into a graph having forward edges and backward edges. A graph neural network can process the graph to refine a final fine-grain per-frame action prediction.Type: ApplicationFiled: September 1, 2023Publication date: March 28, 2024Applicant: Intel CorporationInventors: Anthony Daniel Rhodes, Byungsu Min, Subarna Tripathi, Giuseppe Raffa, Sovan Biswas
-
Patent number: 10178396Abstract: A video compression framework based on parametric object and background compression is proposed. At the encoder, an object is detected and frames are segmented into regions corresponding to the foreground object and the background. The encoder generates object motion and appearance parameters. The motion or warping parameters may include at least two parameters for object translation; two parameters for object scaling in two primary axes and one object orientation parameter indicating a rotation of the object. Particle filtering may be employed to generate the object motion parameters. The proposed methodology is the formalization of the concept and usability for perceptual quality scalability layer for Region(s) of Interest. A coded video sequence format is proposed which aims at “network friendly” video representation supporting appearance and generalized motion of object(s).Type: GrantFiled: December 30, 2011Date of Patent: January 8, 2019Assignee: STMICROELECTRONICS INTERNATIONAL N.V.Inventors: Santanu Chaudhury, Subarna Tripathi, Sumantra Dutta Roy
-
Publication number: 20180204076Abstract: A method for moving objection detection in an image analysis system is provided. The method includes analyzing consecutive video frames from a single camera to extract box properties and exclude objects that are not of interest based upon the box properties. Motion and structure data are obtained for boxes not excluded. The motion and structure data are sent to a trained classifier. Moving object boxes are determined by the trained classifier. The moving object box identifications are provided to a vehicle system. The data sent to the classifier can consist of the motion and structure data, and no deep learning methods are applied to the video frame data. Driver assistance vehicle systems and autonomous driving systems are also provided based upon the moving object box detection.Type: ApplicationFiled: January 16, 2018Publication date: July 19, 2018Inventors: Subarna Tripathi, Kunyao Chen, Truong Nguyen, Youngbae Hwang
-
Patent number: 9813731Abstract: A video compression framework based on parametric object and background compression is proposed. At the encoder, an embodiment detects objects and segments frames into regions corresponding to the foreground object and the background. The object and the background are individually encoded using separate parametric coding techniques. While the object is encoded using the projection of coefficients to the orthonormal basis of the learnt subspace (used for appearance based object tracking), the background is characterized using an auto-regressive (AR) process model. An advantage of the proposed schemes is that the decoder structure allows for simultaneous reconstruction of object and background, thus making it amenable to the new multi-thread/multi-processor architectures.Type: GrantFiled: August 6, 2014Date of Patent: November 7, 2017Assignee: STMICROELECTONICS INTERNATIONAL N.V.Inventors: Santanu Chaudhury, Mona Mathur, Aditya Khandelia, Subarna Tripathi, Brejesh Lall, Sumantra Dutta Roy, Saurabh Gorecha
-
Patent number: 9626769Abstract: A video compression framework based on parametric object and background compression is proposed. At the encoder, an object is detected and frames are segmented into regions corresponding to the foreground object and the background. The encoder generates object motion and appearance parameters. The motion or warping parameters may include at least two parameters for object translation; two parameters for object scaling in two primary axes and one object orientation parameter indicating a rotation of the object. Particle filtering may be employed to generate the object motion parameters. The proposed methodology is the formalization of the concept and usability for perceptual quality scalability layer for Region(s) of Interest. A coded video sequence format is proposed which aims at “network friendly” video representation supporting appearance and generalized motion of object(s).Type: GrantFiled: December 30, 2011Date of Patent: April 18, 2017Assignee: STMicroelectronics International N.V.Inventors: Subarna Tripathi, Mona Mathur, Santanu Chaudhury
-
Patent number: 9497464Abstract: A GOP-independent dynamic bit-rate controller system includes a user interface to receive one or more input parameters, a bit-rate controller and an encoder. The bit-rate controller regulates a bit-rate of an output bit-stream. The bit-rate controller includes multiple bit-rate modules to determine a bit-estimate and a quantization parameter, and a control module to calculate a convergence period based on the received input parameters and a frame rate. The control module selects a bit rate module based on the convergence period and the encoder generates the output bit-stream using the quantization parameter determined by the bit rate module.Type: GrantFiled: March 14, 2013Date of Patent: November 15, 2016Assignees: STMICROELECTRONICS INTERNATIONAL N.V., STMICROELECTRONICS S.R.L.Inventors: Subarna Tripathi, Emiliano Piccinelli
-
Patent number: 9245200Abstract: An embodiment is a computer-implemented method for detecting a straight line in a digital image comprising a plurality of pixels comprising the steps: detecting an edge in the digital image, generating a first straight line which passes through a first pixel of the detected edge, generating a second straight line which passes through a second pixel of the detected edge, which is different from the first pixel, determining at least two intersections with a boundary of the digital image for each generated straight line, determining a set of two parameter values for each generated straight line based on the respective determined at least two intersections, wherein the set of two parameter values uniquely determines the respective generated straight line, and detecting the straight line in the digital image based on the determined sets of two parameter values.Type: GrantFiled: October 31, 2013Date of Patent: January 26, 2016Assignees: STMicroelectronics S.r.l., STMicroelectronics International N.V.Inventors: Luca Magri, Beatrice Rossi, Subarna Tripathi, Pasqualina Fragneto, Emiliano Mario Piccinelli
-
Patent number: 9197903Abstract: A system and corresponding method determines a macroblock partition to transcode digital data from a first video standard to a second video standard with any spatial resolution. The system includes a processing module and an encoding module. The processing module processes digital data to determine a macroblock partition. The encoding module is coupled to the processing module for encoding the digital data based on the macroblock partition. The system is further coupled to a decoding module for receiving the digital data. The method determines the partition of a macroblock for transcoding digital data with any spatial resolution and without any motion estimation.Type: GrantFiled: October 16, 2008Date of Patent: November 24, 2015Assignees: STMICROELECTRONICS S.R.L., STMICROELECTRONICS INTERNATIONAL N.V.Inventors: Subarna Tripathi, Kaushik Saha, Emiliana Mario Picinelli
-
Patent number: 8913658Abstract: A GOP-independent dynamic bit-rate controller system includes a user interface to receive one or more input parameters, a bit-rate controller and an encoder. The bit-rate controller regulates a bit-rate of an output bit-stream. The bit-rate controller includes multiple bit-rate modules to determine a bit-estimate and a quantization parameter, and a control module to calculate a convergence period based on the received input parameters and a frame rate. The control module selects a bit rate module based on the convergence period and the encoder generates the output bit-stream using the quantization parameter determined by the bit rate module.Type: GrantFiled: June 21, 2010Date of Patent: December 16, 2014Assignees: STMicroelectronics International N.V., STMicroelectronics S.r.l.Inventors: Subarna Tripathi, Emiliano Mario Piccinelli
-
Publication number: 20140348231Abstract: A video compression framework based on parametric object and background compression is proposed. At the encoder, an embodiment detects objects and segments frames into regions corresponding to the foreground object and the background. The object and the background are individually encoded using separate parametric coding techniques. While the object is encoded using the projection of coefficients to the orthonormal basis of the learnt subspace (used for appearance based object tracking), the background is characterized using an auto-regressive (AR) process model. An advantage of the proposed schemes is that the decoder structure allows for simultaneous reconstruction of object and background, thus making it amenable to the new multi-thread/multi-processor architectures.Type: ApplicationFiled: August 6, 2014Publication date: November 27, 2014Inventors: Santanu Chaudhury, Mona Mathur, Aditya Khandelia, Subarna Tripathi, Brejesh Lall, Sumantra Dutta Roy, Saurabh Gorecha
-
Patent number: 8848802Abstract: A video compression framework based on parametric object and background compression is proposed. At the encoder, an embodiment detects objects and segments frames into regions corresponding to the foreground object and the background. The object and the background are individually encoded using separate parametric coding techniques. While the object is encoded using the projection coefficients to the orthonormal basis of the learnt subspace (used for appearance based object tracking), the background is characterized using an auto-regressive (AR) process model. An advantage of the proposed schemes is that the decoder structure allows for simultaneous reconstruction of object and background, thus making it amenable to the new multi-thread/multi-processor architectures.Type: GrantFiled: September 4, 2009Date of Patent: September 30, 2014Assignee: STMicroelectronics International N.V.Inventors: Santanu Chaudhury, Mona Mathur, Aditya Khandelia, Subarna Tripathi, Brejesh Lall, Sumantra Dutta Roy, Saurabh Gorecha
-
Publication number: 20140161359Abstract: An embodiment is a computer-implemented method for detecting a straight line in a digital image comprising a plurality of pixels comprising the steps: detecting an edge in the digital image, generating a first straight line which passes through a first pixel of the detected edge, generating a second straight line which passes through a second pixel of the detected edge, which is different from the first pixel, determining at least two intersections with a boundary of the digital image for each generated straight line, determining a set of two parameter values for each generated straight line based on the respective determined at least two intersections, wherein the set of two parameter values uniquely determines the respective generated straight line, and detecting the straight line in the digital image based on the determined sets of two parameter values.Type: ApplicationFiled: October 31, 2013Publication date: June 12, 2014Applicants: STMICROELECTRONICS INTERNATIONAL N.V., STMICROELECTRONICS S.R.LInventors: Luca MAGRI, Beatrice ROSSI, Subarna TRIPATHI, Pasqualina FRAGNETO, Emiliano Mario PICCINELLI
-
Publication number: 20120177121Abstract: A video compression framework based on parametric object and background compression is proposed. At the encoder, an object is detected and frames are segmented into regions corresponding to the foreground object and the background. The encoder generates object motion and appearance parameters. The motion or warping parameters may include at least two parameters for object translation; two parameters for object scaling in two primary axes and one object orientation parameter indicating a rotation of the object. Particle filtering may be employed to generate the object motion parameters. The proposed methodology is the formalization of the concept and usability for perceptual quality scalability layer for Region(s) of Interest. A coded video sequence format is proposed which aims at “network friendly” video representation supporting appearance and generalized motion of object(s).Type: ApplicationFiled: December 30, 2011Publication date: July 12, 2012Applicant: STMICROELECTRONICS PVT. LTD.Inventors: Subarna Tripathi, Mona Mathur, Santanu Chaudhury
-
Publication number: 20120170659Abstract: A video compression framework based on parametric object and background compression is proposed. At the encoder, an object is detected and frames are segmented into regions corresponding to the foreground object and the background. The encoder generates object motion and appearance parameters. The motion or warping parameters may include at least two parameters for object translation; two parameters for object scaling in two primary axes and one object orientation parameter indicating a rotation of the object. Particle filtering may be employed to generate the object motion parameters. The proposed methodology is the formalization of the concept and usability for perceptual quality scalability layer for Region(s) of Interest. A coded video sequence format is proposed which aims at “network friendly” video representation supporting appearance and generalized motion of object(s).Type: ApplicationFiled: December 30, 2011Publication date: July 5, 2012Applicant: STMICROELECTRONICS PVT. LTD.Inventors: Santanu Chaudhury, Subarna Tripathi, Sumantra Dutta Roy
-
Publication number: 20110142125Abstract: A GOP-independent dynamic bit-rate controller system includes a user interface to receive one or more input parameters, a bit-rate controller and an encoder. The bit-rate controller regulates a bit-rate of an output bit-stream. The bit-rate controller includes multiple bit-rate modules to determine a bit-estimate and a quantization parameter, and a control module to calculate a convergence period based on the received input parameters and a frame rate. The control module selects a bit rate module based on the convergence period and the encoder generates the output bit-stream using the quantization parameter determined by the bit rate module.Type: ApplicationFiled: June 21, 2010Publication date: June 16, 2011Applicant: STMICROELECTRONICS PVT. LTD.Inventors: Subarna TRIPATHI, Emiliano Mario Piccinelli
-
Publication number: 20110058609Abstract: A video compression framework based on parametric object and background compression is proposed. At the encoder, an embodiment detects objects and segments frames into regions corresponding to the foreground object and the background. The object and the background are individually encoded using separate parametric coding techniques. While the object is encoded using the projection of coefficients to the orthonormal basis of the learnt subspace (used for appearance based object tracking), the background is characterized using an auto-regressive (AR) process model. An advantage of the proposed schemes is that the decoder structure allows for simultaneous reconstruction of object and background, thus making it amenable to the new multi-thread/multi-processor architectures.Type: ApplicationFiled: September 4, 2009Publication date: March 10, 2011Applicant: STMICROELECTRONICS PVT. LTD.Inventors: Santanu Chaudhury, Mona Mathur, Aditya Khandelia, Subarna Tripathi, Brejesh Lall, Sumantra Dutta Roy, Saurabh Gorecha
-
Publication number: 20090103622Abstract: A system and corresponding method determines a macroblock partition to transcode digital data from a first video standard to a second video standard with any spatial resolution. The system includes a processing module and an encoding module. The processing module processes digital data to determine a macroblock partition. The encoding module is coupled to the processing module for encoding the digital data based on the macroblock partition. The system is further coupled to a decoding module for receiving the digital data. The method determines the partition of a macroblock for transcoding digital data with any spatial resolution and without any motion estimation.Type: ApplicationFiled: October 16, 2008Publication date: April 23, 2009Applicants: STMicroelectronics Pvt. Ltd., STMicroelectronics S.r.I.Inventors: Subarna Tripathi, Kaushik Saha, Emiliana Picinelli