Patents by Inventor Deepak Kumar Poddar
Deepak Kumar 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: 20240078284Abstract: A hardware accelerator is configured to perform matrix multiplication and/or additional operations to optimize keypoint matching. A sum of squared error (SSE) calculation may be determined by utilizing the hardware accelerator to perform matrix multiplication to obtain a cost matrix for two sets of keypoint descriptors from two images. The hardware accelerator may determine a best cost calculation for each keypoint in each direction, which is utilized to perform keypoint matching.Type: ApplicationFiled: November 1, 2023Publication date: March 7, 2024Inventors: Deepak Kumar PODDAR, Soyeb NAGORI, Hrushikesh Tukaram GARUD, Pramod Kumar SWAMI
-
Patent number: 11915431Abstract: A method for sparse optical flow based tracking in a computer vision system is provided that includes detecting feature points in a frame captured by a monocular camera in the computer vision system to generate a plurality of detected feature points, generating a binary image indicating locations of the detected feature points with a bit value of one, wherein all other locations in the binary image have a bit value of zero, generating another binary image indicating neighborhoods of currently tracked points, wherein locations of the neighborhoods in the binary image have a bit value of zero and all other locations in the binary image have a bit value of one, and performing a binary AND of the two binary images to generate another binary image, wherein locations in the binary image having a bit value of one indicate new feature points detected in the frame.Type: GrantFiled: August 6, 2019Date of Patent: February 27, 2024Assignee: Texas Instruments IncorporatedInventors: Deepak Kumar Poddar, Anshu Jain, Desappan Kumar, Pramod Kumar Swami
-
Patent number: 11887346Abstract: An example image feature extraction system comprises an encoder neural network having a first set of layers and a decoder neural network having a second set of layers and a third set of layers. The encoder neural network receives an input image, processes the input image through the first set of layers, and computes an encoded feature map based on the input image. The decoder neural network receives the encoded feature map, processes the encoded feature map through the second set of layers to compute a keypoint score map, and processes the encoded feature map through at least a portion of the third set of layers to compute a feature description map.Type: GrantFiled: March 1, 2023Date of Patent: January 30, 2024Assignee: Texas Instruments IncorporatedInventors: Deepak Kumar Poddar, Soyeb Nagori, Hrushikesh Tukaram Garud, Kumar Desappan
-
Patent number: 11876989Abstract: Several methods and systems for facilitating multimedia data encoding are disclosed. In an embodiment, a plurality of picture buffers associated with multimedia data are received in an order of capture associated with the plurality of picture buffers. Buffer information is configured for each picture buffer from among the plurality of picture buffers comprising at least one of a metadata associated with the corresponding picture buffer and one or more encoding parameters for the corresponding picture buffer. A provision of picture buffers in an order of encoding is facilitated based on the configured buffer information.Type: GrantFiled: April 28, 2021Date of Patent: January 16, 2024Assignee: Texas Instruments IncorporatedInventors: Uday Pudipeddi Kiran, Deepak Kumar Poddar, Pramod Kumar Swami, Arun Shankar Kudana
-
Patent number: 11847184Abstract: A matching accelerator in the form of a hardware accelerator configured to perform matrix multiplication and/or additional operations is used to optimize keypoint matching. An SSE calculation may be determined by utilizing the matching accelerator to perform matrix multiplication to obtain a cost matrix for two sets of keypoint descriptors from two images. The hardware accelerator may determine a best cost calculation for each keypoint in each direction, which is utilized to perform keypoint matching.Type: GrantFiled: January 14, 2021Date of Patent: December 19, 2023Assignee: Texas Instruments IncorporatedInventors: Deepak Kumar Poddar, Soyeb Nagori, Hrushikesh Tukaram Garud, Pramod Kumar Swami
-
Patent number: 11831927Abstract: The disclosure provides a noise filter. The noise filter includes a motion estimation (ME) engine. The ME receives a current frame and a reference frame. The current frame comprising a current block and the reference frame includes a plurality of reference blocks. The ME engine generates final motion vectors. The current block comprises a plurality of current pixels. A motion compensation unit generates a motion compensated block based on the final motion vectors and the reference frame. The motion compensated block includes a plurality of motion compensated pixels. A weighted average filter multiplies each current pixel of the plurality of current pixels and a corresponding motion compensated pixel of the plurality of motion compensated pixels with a first weight and a second weight respectively. The weighted average filter generates a filtered block. A blockiness removal unit is coupled to the weighted average filter and removes artifacts in the filtered block.Type: GrantFiled: May 26, 2021Date of Patent: November 28, 2023Assignee: Texas Instruments IncorporatedInventors: Soyeb Nagori, Shyam Jagannathan, Deepak Kumar Poddar, Arun Shankar Kudana, Pramod Swami, Manoj Koul
-
Patent number: 11763568Abstract: Estimation of the ground plane of a three dimensional (3D) point cloud based modifications to the random sample consensus (RANSAC) algorithm is provided. The modifications may include applying roll and pitch constraints to the selection of random planes in the 3D point cloud, using a cost function based on the number of inliers in the random plane and the number of 3D points below the random plane in the 3D point cloud, and computing a distance threshold for the 3D point cloud that is used in determining whether or not a 3D point in the 3D point cloud is an inlier of a random plane.Type: GrantFiled: December 8, 2020Date of Patent: September 19, 2023Assignee: Texas Instruments IncorporatedInventors: Soyeb Nagori, Poorna Kumar, Manu Mathew, Prashanth Ramanathpur Viswanath, Deepak Kumar Poddar
-
Patent number: 11704391Abstract: In some examples, a system includes storage storing a machine learning model, wherein the machine learning model comprises a plurality of layers comprising multiple weights. The system also includes a processing unit coupled to the storage and operable to group the weights in each layer into a plurality of partitions; determine a number of least significant bits to be used for watermarking in each of the plurality of partitions; insert one or more watermark bits into the determined least significant bits for each of the plurality of partitions; and scramble one or more of the weight bits to produce watermarked and scrambled weights. The system also includes an output device to provide the watermarked and scrambled weights to another device.Type: GrantFiled: September 28, 2021Date of Patent: July 18, 2023Assignee: Texas Instruments IncorporatedInventors: Deepak Kumar Poddar, Mihir Mody, Veeramanikandan Raju, Jason A. T. Jones
-
Publication number: 20230206604Abstract: An example image feature extraction system comprises an encoder neural network having a first set of layers and a decoder neural network having a second set of layers and a third set of layers. The encoder neural network receives an input image, processes the input image through the first set of layers, and computes an encoded feature map based on the input image. The decoder neural network receives the encoded feature map, processes the encoded feature map through the second set of layers to compute a keypoint score map, and processes the encoded feature map through at least a portion of the third set of layers to compute a feature description map.Type: ApplicationFiled: March 1, 2023Publication date: June 29, 2023Inventors: DEEPAK KUMAR PODDAR, SOYEB NAGORI, HRUSHIKESH TUKARAM GARUD, KUMAR DESAPPAN
-
Publication number: 20230137337Abstract: A technique for key-point detection, including receiving, by a machine learning model, an input image, generating a set of image features for the input image, determining, by the machine learning model, based on the set of image features, a bounding box for an object detected in the input image, the bounding box described by bounding box information, identifying, by the machine learning model, based on the set of image features and a center point of the bounding box, a plurality of key-points associated with the object, filtering the plurality of key-points based on a confidence score associated with each key-point of the plurality of key-points, and outputting coordinates of the plurality of key-points, confidence scores associated with the plurality of key-points, and the bounding box information.Type: ApplicationFiled: June 28, 2022Publication date: May 4, 2023Inventors: Debapriya MAJI, Soyeb NAGORI, Manu MATHEW, Deepak Kumar PODDAR
-
Patent number: 11615612Abstract: This description relates to image feature extraction. In some examples, a system can include a keypoint detector and a feature list generator. The keypoint detector can be configured to upsample a keypoint score map to produce an upsampled keypoint score map. The keypoint score map can include feature scores indicative of a likelihood of at least one feature being present at keypoints in an image. The feature list generator can be configured to identify a subset of keypoints of the keypoints in the image using the feature scores of the up sampled keypoint score map, determine descriptors for the subset of keypoints based on a feature description map, and generate a keypoint descriptor map for the image based on the determined descriptors.Type: GrantFiled: December 4, 2020Date of Patent: March 28, 2023Assignee: Texas Instruments IncorporatedInventors: Deepak Kumar Poddar, Soyeb Nagori, Hrushikesh Tukaram Garud, Kumar Desappan
-
Patent number: 11615629Abstract: A method for estimating time to collision (TTC) of a detected object in a computer vision system is provided that includes determining a three dimensional (3D) position of a camera in the computer vision system, determining a 3D position of the detected object based on a 2D position of the detected object in an image captured by the camera and an estimated ground plane corresponding to the image, computing a relative 3D position of the camera, a velocity of the relative 3D position, and an acceleration of the relative 3D position based on the 3D position of the camera and the 3D position of the detected object, wherein the relative 3D position of the camera is relative to the 3D position of the detected object, and computing the TTC of the detected object based on the relative 3D position, the velocity, and the acceleration.Type: GrantFiled: March 9, 2021Date of Patent: March 28, 2023Assignee: Texas Instruments IncorporatedInventors: Prashanth Ramanathpur Viswanath, Deepak Kumar Poddar, Soyeb Nagori, Manu Mathew
-
Publication number: 20220180476Abstract: This description relates to image feature extraction. In some examples, a system can include a keypoint detector and a feature list generator. The keypoint detector can be configured to upsample a keypoint score map to produce an upsampled keypoint score map. The keypoint score map can include feature scores indicative of a likelihood of at least one feature being present at keypoints in an image. The feature list generator can be configured to identify a subset of keypoints of the keypoints in the image using the feature scores of the up sampled keypoint score map, determine descriptors for the subset of keypoints based on a feature description map, and generate a keypoint descriptor map for the image based on the determined descriptors.Type: ApplicationFiled: December 4, 2020Publication date: June 9, 2022Inventors: DEEPAK KUMAR PODDAR, SOYEB NAGORI, HRUSHIKESH TUKARAM GARUD, KUMAR DESAPPAN
-
Publication number: 20220012312Abstract: In some examples, a system includes storage storing a machine learning model, wherein the machine learning model comprises a plurality of layers comprising multiple weights. The system also includes a processing unit coupled to the storage and operable to group the weights in each layer into a plurality of partitions; determine a number of least significant bits to be used for watermarking in each of the plurality of partitions; insert one or more watermark bits into the determined least significant bits for each of the plurality of partitions; and scramble one or more of the weight bits to produce watermarked and scrambled weights. The system also includes an output device to provide the watermarked and scrambled weights to another device.Type: ApplicationFiled: September 28, 2021Publication date: January 13, 2022Inventors: Deepak Kumar PODDAR, Mihir MODY, Veeramanikandan RAJU, Jason A.T. JONES
-
Patent number: 11163861Abstract: In some examples, a system includes storage storing a machine learning model, wherein the machine learning model comprises a plurality of layers comprising multiple weights. The system also includes a processing unit coupled to the storage and operable to group the weights in each layer into a plurality of partitions; determine a number of least significant bits to be used for watermarking in each of the plurality of partitions; insert one or more watermark bits into the determined least significant bits for each of the plurality of partitions; and scramble one or more of the weight bits to produce watermarked and scrambled weights. The system also includes an output device to provide the watermarked and scrambled weights to another device.Type: GrantFiled: November 13, 2018Date of Patent: November 2, 2021Assignee: TEXAS INSTRUMENTS INCORPORATEDInventors: Deepak Kumar Poddar, Mihir Mody, Veeramanikandan Raju, Jason A. T. Jones
-
Publication number: 20210289233Abstract: The disclosure provides a noise filter. The noise filter includes a motion estimation (ME) engine. The ME receives a current frame and a reference frame. The current frame comprising a current block and the reference frame includes a plurality of reference blocks. The ME engine generates final motion vectors. The current block comprises a plurality of current pixels. A motion compensation unit generates a motion compensated block based on the final motion vectors and the reference frame. The motion compensated block includes a plurality of motion compensated pixels. A weighted average filter multiplies each current pixel of the plurality of current pixels and a corresponding motion compensated pixel of the plurality of motion compensated pixels with a first weight and a second weight respectively. The weighted average filter generates a filtered block. A blockiness removal unit is coupled to the weighted average filter and removes artifacts in the filtered block.Type: ApplicationFiled: May 26, 2021Publication date: September 16, 2021Inventors: Soyeb Nagori, Shyam Jagannathan, Deepak Kumar Poddar, Arun Shankar Kudana, Pramod Swami, Manoj Koul
-
Publication number: 20210287021Abstract: A method for estimating time to collision (TTC) of a detected object in a computer vision system is provided that includes determining a three dimensional (3D) position of a camera in the computer vision system, determining a 3D position of the detected object based on a 2D position of the detected object in an image captured by the camera and an estimated ground plane corresponding to the image, computing a relative 3D position of the camera, a velocity of the relative 3D position, and an acceleration of the relative 3D position based on the 3D position of the camera and the 3D position of the detected object, wherein the relative 3D position of the camera is relative to the 3D position of the detected object, and computing the TTC of the detected object based on the relative 3D position, the velocity, and the acceleration.Type: ApplicationFiled: March 9, 2021Publication date: September 16, 2021Inventors: Prashanth Ramanathpur Viswanath, Deepak Kumar Poddar, Soyeb Nagori, Manu Mathew
-
Publication number: 20210256293Abstract: A matching accelerator in the form of a hardware accelerator configured to perform matrix multiplication and/or additional operations is used to optimize keypoint matching. An SSE calculation may be determined by utilizing the matching accelerator to perform matrix multiplication to obtain a cost matrix for two sets of keypoint descriptors from two images. The hardware accelerator may determine a best cost calculation for each keypoint in each direction, which is utilized to perform keypoint matching.Type: ApplicationFiled: January 14, 2021Publication date: August 19, 2021Inventors: Deepak Kumar PODDAR, Soyeb NAGORI, Hrushikesh Tukaram GARUD, Pramod Kumar SWAMI
-
Publication number: 20210250595Abstract: Several methods and systems for facilitating multimedia data encoding are disclosed. In an embodiment, a plurality of picture buffers associated with multimedia data are received in an order of capture associated with the plurality of picture buffers. Buffer information is configured for each picture buffer from among the plurality of picture buffers comprising at least one of a metadata associated with the corresponding picture buffer and one or more encoding parameters for the corresponding picture buffer. A provision of picture buffers in an order of encoding is facilitated based on the configured buffer information.Type: ApplicationFiled: April 28, 2021Publication date: August 12, 2021Inventors: Uday Pudipeddi Kiran, Deepak Kumar Poddar, Pramod Kumar Swami, Arun Shankar Kudana
-
Patent number: 11051046Abstract: The disclosure provides a noise filter. The noise filter includes a motion estimation (ME) engine. The ME receives a current frame and a reference frame. The current frame comprising a current block and the reference frame includes a plurality of reference blocks. The ME engine generates final motion vectors. The current block comprises a plurality of current pixels. A motion compensation unit generates a motion compensated block based on the final motion vectors and the reference frame. The motion compensated block includes a plurality of motion compensated pixels. A weighted average filter multiplies each current pixel of the plurality of current pixels and a corresponding motion compensated pixel of the plurality of motion compensated pixels with a first weight and a second weight respectively. The weighted average filter generates a filtered block. A blockiness removal unit is coupled to the weighted average filter and removes artifacts in the filtered block.Type: GrantFiled: August 10, 2020Date of Patent: June 29, 2021Assignee: TEXAS INSTRUMENTS INCORPORATEDInventors: Soyeb Nagori, Shyam Jagannathan, Deepak Kumar Poddar, Arun Shankar Kudana, Pramod Swami, Manoj Koul