Patents by Inventor Deepak Poddar
Deepak Poddar 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: 20240086681Abstract: A CNN based-signal processing includes receiving of an encrypted output from a first layer of a multi-layer CNN data. The received encrypted output is subsequently decrypted to form a decrypted input to a second layer of the multi-layer CNN data. A convolution of the decrypted input with a corresponding decrypted weight may generate a second layer output, which may be encrypted and used as an encrypted input to a third layer of the multi-layer CNN data.Type: ApplicationFiled: November 14, 2023Publication date: March 14, 2024Inventors: Mihir Narendra Mody, Veeramanikandan Raju, Chaitanya Ghone, Deepak Poddar
-
Patent number: 11891091Abstract: An example driver assistance system includes an object detection (OD) network, a semantic segmentation network, a processor, and a memory. In an example method, an image is received and stored in the memory. An object detection (OD) polygon is generated for each object detected in the image, and each OD polygon encompasses at least a portion of the corresponding object detected in the image. A region of interest (ROI) is associated with each OD polygon. Such method may further comprise generating a mask for each ROI, each mask configured as a bitmap approximating a size of the corresponding ROI; generating at least one boundary polygon for each mask based on the corresponding mask, each boundary polygon having multiple vertices and enclosing the corresponding mask; and reducing a number of vertices of the boundary polygons based on a comparison between points of the boundary polygons and respective points on the bitmaps.Type: GrantFiled: February 22, 2023Date of Patent: February 6, 2024Assignee: Texas Instruments IncorporatedInventors: Soyeb Noormohammed Nagori, Deepak Poddar, Hrushikesh Tukaram Garud
-
Patent number: 11853857Abstract: A convolutional neural network (CNN)-based signal processing includes receiving of an encrypted output from a first layer of a multi-layer CNN data. The received encrypted output is subsequently decrypted to form a decrypted input to a second layer of the multi-layer CNN data. A convolution of the decrypted input with a corresponding decrypted weight may generate a second layer output, which may be encrypted and used as an encrypted input to a third layer of the multi-layer CNN data.Type: GrantFiled: June 2, 2020Date of Patent: December 26, 2023Assignee: Texas Instruments IncorporatedInventors: Mihir Narendra Mody, Veeramanikandan Raju, Chaitanya Ghone, Deepak Poddar
-
Patent number: 11763575Abstract: Techniques including receiving a distorted image from a camera disposed about a vehicle, detecting, in the distorted image, corner points associated with a target object, mapping the corner points to a distortion corrected domain based on one or more camera parameters, mapping the corner points and lines between the corner points back to a distorted domain based on the camera parameters, interpolating one or more intermediate points to generate lines between the corner points in the distortion corrected domain mapping the corner points and the lines between the corner points back to a distorted domain based on the camera parameters, and adjusting a direction of travel of the vehicle based on the located target object.Type: GrantFiled: February 23, 2022Date of Patent: September 19, 2023Assignee: Texas Instruments IncorporatedInventors: Deepak Poddar, Soyeb Nagori, Manu Mathew, Debapriya Maji
-
Publication number: 20230202524Abstract: An example driver assistance system includes an object detection (OD) network, a semantic segmentation network, a processor, and a memory. In an example method, an image is received and stored in the memory. An object detection (OD) polygon is generated for each object detected in the image, and each OD polygon encompasses at least a portion of the corresponding object detected in the image. A region of interest (ROI) is associated with each OD polygon. Such method may further comprise generating a mask for each ROI, each mask configured as a bitmap approximating a size of the corresponding ROI; generating at least one boundary polygon for each mask based on the corresponding mask, each boundary polygon having multiple vertices and enclosing the corresponding mask; and reducing a number of vertices of the boundary polygons based on a comparison between points of the boundary polygons and respective points on the bitmaps.Type: ApplicationFiled: February 22, 2023Publication date: June 29, 2023Inventors: Soyeb Noormohammed Nagori, Deepak Poddar, Hrushikesh Tukaram Garud
-
Patent number: 11620478Abstract: In described examples, an apparatus includes an object detection (OD) network that is configured to generate OD polygons in response to a received at least one camera image and a semantic segmentation (SS) network that is configured to generate SS data in response to the received at least one camera image. A processor is configured to generate an updated occupancy grid in response to the OD polygons and the SS data. A vehicle is optionally configured to respond to a driving action generated in response to the updated occupancy grid.Type: GrantFiled: February 6, 2020Date of Patent: April 4, 2023Assignee: Texas Instruments IncorporatedInventors: Soyeb Noormohammed Nagori, Deepak Poddar, Hrushikesh Tukaram Garud
-
Publication number: 20220392108Abstract: Techniques for localizing a vehicle include obtaining an image from a camera, identifying a set of image feature points in the image, obtaining an approximate location of the vehicle, determining a set of sub-volumes (SVs) of a map to access based on the approximate location, obtaining map feature points and associated map feature descriptors associated with the set of SVs, determining a set of candidate matches between the set of image feature points and the obtained map feature points, determining a set of potential poses of the camera from candidate matches from the set of candidate matches and an associated reprojection error estimated for remaining points to select a first pose of the set of potential poses having a lowest associated reprojection error, determining the first pose is within a threshold value of an expected vehicle location, and outputting a vehicle location based on the first pose.Type: ApplicationFiled: August 15, 2022Publication date: December 8, 2022Inventors: Hrushikesh Tukaram GARUD, Deepak PODDAR, Soyeb Noormohammed NAGORI
-
Publication number: 20220327180Abstract: Techniques for resizing data including receiving input data values for resizing, placing a first number of data values from a first line of data values of the input data values in a first portion of a first vector, placing the first number of data values from a second line of data values of the input data values in a second portion of the first vector, receiving a first matrix of weights, wherein each weight of the first matrix of weights corresponds to an amount of weight to apply to a data value for a point on a first line of a set of resized data, multiplying the first vector and the first matrix of weights to determine data values for the first line of the set of resized data, and outputting the set of resized data.Type: ApplicationFiled: September 30, 2021Publication date: October 13, 2022Inventors: Deepak PODDAR, Soyeb NAGORI, Pramod SWAMI
-
Patent number: 11417017Abstract: Techniques for localizing a vehicle including obtaining an image from a camera, identifying a set of image feature points in the image, obtaining an approximate location of the vehicle, determining a set of sub-volumes (SVs) of a map to access based on the approximate location, obtaining map feature points and associated map feature descriptors associated with the set of SVs, determining a set of candidate matches between the set of image feature points and the obtained map feature points, determining a set of potential poses of the camera from candidate matches from the set of candidate matches and an associated reprojection error estimated for remaining points to select a first pose of the set of potential poses having a lowest associated reprojection error, determining the first pose is within a threshold value of an expected vehicle location, and outputting a vehicle location based on the first pose.Type: GrantFiled: April 21, 2020Date of Patent: August 16, 2022Assignee: Texas Instmments IncorporatedInventors: Hrushikesh Tukaram Garud, Deepak Poddar, Soyeb Noormohammed Nagori
-
Publication number: 20220180642Abstract: Techniques including receiving a distorted image from a camera disposed about a vehicle, detecting, in the distorted image, corner points associated with a target object, mapping the corner points to a distortion corrected domain based on one or more camera parameters, mapping the corner points and lines between the corner points back to a distorted domain based on the camera parameters, interpolating one or more intermediate points to generate lines between the corner points in the distortion corrected domain mapping the corner points and the lines between the corner points back to a distorted domain based on the camera parameters, and adjusting a direction of travel of the vehicle based on the located target object.Type: ApplicationFiled: February 23, 2022Publication date: June 9, 2022Inventors: Deepak PODDAR, Soyeb NAGORI, Manu MATHEW, Debapriya MAJI
-
Publication number: 20220147748Abstract: Various embodiments of the present technology relate to using neural networks to detect objects in images. More specifically, some embodiments relate to the reduction of computational analysis regarding object detection via neural networks. In an embodiment, a method of performing object detection is provided. The method comprises determining, via a convolution neural network, at least a classification of an image, wherein the classification corresponds to an object in the image and comprises location vectors corresponding to pixels of the image. The method also comprises, for at least a location vector of the location vectors, obtaining a confidence level, wherein the confidence level represents a probability of the object being present at the location vector, and calculating an upper-bound score based at least on the confidence level.Type: ApplicationFiled: October 27, 2021Publication date: May 12, 2022Inventors: Soyeb Nagori, Deepak Poddar
-
Patent number: 11288525Abstract: Techniques including receiving a distorted image from a camera disposed about a vehicle, detecting, in the distorted image, corner points associated with a target object, mapping the corner points to a distortion corrected domain based on one or more camera parameters, mapping the corner points and lines between the corner points back to a distorted domain based on the camera parameters, interpolating one or more intermediate points to generate lines between the corner points in the distortion corrected domain mapping the corner points and the lines between the corner points back to a distorted domain based on the camera parameters, and adjusting a direction of travel of the vehicle based on the located target object.Type: GrantFiled: September 30, 2019Date of Patent: March 29, 2022Assignee: TEXAS INSTRUMENTS INCORPORATEDInventors: Deepak Poddar, Soyeb Nagori, Manu Mathew, Debapriya Maji
-
Publication number: 20200334857Abstract: Techniques for localizing a vehicle are provided that include obtaining an image from a camera, identifying a set of image feature points in the image, obtaining an approximate location of the vehicle, determining a set of sub-volumes (SVs) of a map to access based on the approximate location, obtaining map feature points and associated map feature descriptors associated with the set of SVs, determining a set of candidate matches between the set of image feature points and the obtained map feature points, determining a set of potential poses of the camera from candidate matches from the set of candidate matches and an associated reprojection error estimated for remaining points to select a first pose of the set of potential poses having a lowest associated reprojection error, determining the first pose is within a threshold value of an expected vehicle location, and outputting a vehicle location based on the first pose.Type: ApplicationFiled: April 21, 2020Publication date: October 22, 2020Inventors: Hrushikesh Tukaram GARUD, Deepak PODDAR, Soyeb Noormohammed NAGORI
-
Publication number: 20200293859Abstract: A CNN based-signal processing includes receiving of an encrypted output from a first layer of a multi-layer CNN data. The received encrypted output is subsequently decrypted to form a decrypted input to a second layer of the multi-layer CNN data. A convolution of the decrypted input with a corresponding decrypted weight may generate a second layer output, which may be encrypted and used as an encrypted input to a third layer of the multi-layer CNN data.Type: ApplicationFiled: June 2, 2020Publication date: September 17, 2020Inventors: Mihir Narendra Mody, Veeramanikandan Raju, Chaitanya Ghone, Deepak Poddar
-
Publication number: 20200250485Abstract: In described examples, an apparatus includes an object detection (OD) network that is configured to generate OD polygons in response to a received at least one camera image and a semantic segmentation (SS) network that is configured to generate SS data in response to the received at least one camera image. A processor is configured to generate an updated occupancy grid in response to the OD polygons and the SS data. A vehicle is optionally configured to respond to a driving action generated in response to the updated occupancy grid.Type: ApplicationFiled: February 6, 2020Publication date: August 6, 2020Inventors: Soyeb Noormohammed Nagori, Deepak Poddar, Hrushikesh Tukaram Garud
-
Patent number: 10706349Abstract: A Convolutional Neural Network (CNN) based-signal processing includes receiving of an encrypted output from a first layer of a multi-layer CNN data. The received encrypted output is subsequently decrypted to form a decrypted input to a second layer of the multi-layer CNN data. A convolution of the decrypted input with a corresponding decrypted weight may generate a second layer output, which may be encrypted and used as an encrypted input to a third layer of the multi-layer CNN data.Type: GrantFiled: October 11, 2017Date of Patent: July 7, 2020Assignee: TEXAS INSTRUMENTS INCORPORATEDInventors: Mihir Narendra Mody, Veeramanikandan Raju, Chaitanya Ghone, Deepak Poddar
-
Publication number: 20200134331Abstract: Techniques including receiving a distorted image from a camera disposed about a vehicle, detecting, in the distorted image, corner points associated with a target object, mapping the corner points to a distortion corrected domain based on one or more camera parameters, mapping the corner points and lines between the corner points back to a distorted domain based on the camera parameters, interpolating one or more intermediate points to generate lines between the corner points in the distortion corrected domain mapping the corner points and the lines between the corner points back to a distorted domain based on the camera parameters, and adjusting a direction of travel of the vehicle based on the located target object.Type: ApplicationFiled: September 30, 2019Publication date: April 30, 2020Inventors: Deepak PODDAR, Soyeb NAGORI, Manu MATHEW, Debapriya MAJI
-
Publication number: 20190005375Abstract: A CNN based-signal processing includes receiving of an encrypted output from a first layer of a multi-layer CNN data. The received encrypted output is subsequently decrypted to form a decrypted input to a second layer of the multi-layer CNN data. A convolution of the decrypted input with a corresponding decrypted weight may generate a second layer output, which may be encrypted and used as an encrypted input to a third layer of the multi-layer CNN data.Type: ApplicationFiled: October 11, 2017Publication date: January 3, 2019Applicant: TEXAS INSTRUMENTS INCORPORATEDInventors: Mihir Narendra Mody, Veeramanikandan Raju, Chaitanya Ghone, Deepak Poddar
-
Publication number: 20140183781Abstract: A die for extruding a pipe includes a die head having an inlet for receiving and a bore for mixing an extrudate, a punch placed axially inside the die head, and a die cavity mounted at an outlet thereof. An outer surface of the die cavity includes flat surfaces at points of contact of a first adjustment structure which includes a plurality of flat end bolts perpendicular to each other positioned around the die cavity for adjusting position of the die cavity. The die further includes an extended orifice shaped as a thin walled tube formed around the orifice, and a second adjustment structure located at a tip of the orifice to distort the orifice for maintaining uniform flow of extrudate, and a plurality of segments are located around the orifice to uniformly distribute the load of the second adjustment structure on to the outer circumference of the orifice.Type: ApplicationFiled: November 4, 2011Publication date: July 3, 2014Inventor: Deepak Poddar
-
Patent number: 8246084Abstract: A threaded pipe (11) and coupler (5) made of polyvinyl chloride, the coupler (5) comprising two coupling ends having inner square-shaped threading (3, 14), each receiving a pipe end (4, 11) having an outer square-shaped threading, a sealing ring (2, 13) being provided between each coupling end of an inner surface of the coupler (5) and an outer surface of the corresponding pipe end (4, 11); a groove (10), being formed on the inner surface of the coupler (5), and co-operating with a part of the outer surface of the pipe end after the threading, when the pipe (11) is threadingly coupled in the coupler (5), to form a tangential hole (42) between the outer surface of the pipe (11) and the inner surface of the coupler (5) with the groove made on the outer surface of the coupler aligning with a groove of first pipe, wherein a wire lock (41) is inserted in the tangential hole (42) to lock the coupling of the coupler (5) with the end of the pipe (11).Type: GrantFiled: May 28, 2004Date of Patent: August 21, 2012Assignee: Ashirvad Pipes Pvt. Ltd.Inventor: Deepak Poddar