公开(公告)号：US11288525B2

公开(公告)日：2022-03-29

申请号：US16588157

申请日：2019-09-30

Applicant: TEXAS INSTRUMENTS INCORPORATED

Inventor： Deepak Poddar ,  Soyeb Nagori ,  Manu Mathew ,  Debapriya Maji

IPC: G06K9/00 ,  G06T11/20 ,  G06T7/70

Abstract: 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.

公开(公告)号：US11763575B2

公开(公告)日：2023-09-19

申请号：US17678411

申请日：2022-02-23

Applicant: TEXAS INSTRUMENTS INCORPORATED

Inventor： Deepak Poddar ,  Soyeb Nagori ,  Manu Mathew ,  Debapriya Maji

IPC: G06T7/70 ,  G06V20/58 ,  G06T11/20

CPC classification number: G06V20/586 ,  G06T7/70 ,  G06T11/203 ,  G06T2207/20081 ,  G06T2207/30264

Abstract: 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.

公开(公告)号：US20240394543A1

公开(公告)日：2024-11-28

申请号：US18795565

申请日：2024-08-06

Applicant: Texas Instruments Incorporated

Inventor： Manu Mathew ,  Kumar Desappan ,  Soyeb Noormohammed Nagori ,  Debapriya Maji ,  Pramod Kumar Swami

IPC: G06N3/084 ,  G06N3/04 ,  G06N3/048

Abstract: In an example, a method includes executing, using one or more processors, a power-of-2 parametric activation (PACT2) function to quantize a set of data. The executing of the PACT2 function includes determining a distribution for the set of data; discarding a portion of the data corresponding to a tail of the distribution to form a remaining set of data; estimating a maximum value of the remaining set of data; determining a new maximum value of the remaining set of data using a moving average and at least one historical value of at least one prior remaining set of data; determining a clipping value by expanding the new maximum value to a nearest power of two value; and quantizing the set of data using the clipping value to form a quantized set of data.

公开(公告)号：US20240153139A1

公开(公告)日：2024-05-09

申请号：US18355594

申请日：2023-07-20

Applicant: TEXAS INSTRUMENTS INCORPORATED

Inventor： Debapriya Maji ,  Soyeb Nagori ,  Deepak Poddar ,  Manu Mathew

IPC: G06T7/73

CPC classification number: G06T7/75 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: Disclosed herein are systems and methods that provide an end-to-end approach for performing multi-dimensional object pose estimation in the context of machine learning models. In an implementation, processing circuitry of a suitable computer inputs image data to a machine learning model that predicts a parameterized rotation vector and a parameterized translation vector for an object in the image. Next, the processing circuitry converts the parameterized rotation vector and the parameterized translation vector into a non-parameterized rotation vector and a non-parameterized translation vector respectively. Finally, the processing circuitry updates the image data based on the non-parameterized rotation vector and the non-parameterized translation vector.

公开(公告)号：US12099930B2

公开(公告)日：2024-09-24

申请号：US17117271

申请日：2020-12-10

Applicant: Texas Instruments Incorporated

Inventor： Manu Mathew ,  Kumar Desappan ,  Soyeb Noormohammed Nagori ,  Debapriya Maji ,  Pramod Kumar Swami

IPC: G06N3/048 ,  G06N3/04 ,  G06N3/084

CPC classification number: G06N3/084 ,  G06N3/04 ,  G06N3/048

Abstract: In described examples of a method for quantizing data for a convolutional neural network (CNN) is provided. A set of data is received and quantized the using a power-of-2 parametric activation (PACT2) function. The PACT2 function arranges the set of data as a histogram and discards a portion of the data corresponding to a tail of the histogram to form a remaining set of data. A clipping value is determined by expanding the remaining set of data to a nearest power of two value. The set of data is then quantized using the clipping value. With PACT2, a model can be quantized either using post training quantization or using quantization aware training. PACT2 helps a quantized model to achieve close accuracy compared to the corresponding floating-point model.

公开(公告)号：US20220327810A1

公开(公告)日：2022-10-13

申请号：US17555435

申请日：2021-12-18

Applicant: Texas Instruments Incorporated

Inventor： Soyeb Noormohammed Nagori ,  Manu Mathew ,  Debapriya Maji ,  Pramod Kumar Swami

IPC: G06V10/774 ,  G06N3/08 ,  G06V10/82

Abstract: A method for multi-label image classification in a convolutional neural network (CNN) is provided that includes forming a composite image from a plurality of clipped images, and processing the composite image by the CNN to generate a probability vector for each clipped image of the plurality of clipped images, wherein a length of a probability vector is equal to a number of classes the CNN is designed to classify.

公开(公告)号：US20210224658A1

公开(公告)日：2021-07-22

申请号：US17117271

申请日：2020-12-10

Applicant: Texas Instruments Incorporated

Inventor： Manu Mathew ,  Kumar Desappan ,  Soyeb Noormohammed Nagori ,  Debapriya Maji ,  Pramod Kumar Swami

IPC: G06N3/08 ,  G06N3/04

Abstract: In described examples of a method for quantizing data for a convolutional neural network (CNN) is provided. A set of data is received and quantized the using a power-of-2 parametric activation (PACT2) function. The PACT2 function arranges the set of data as a histogram and discards a portion of the data corresponding to a tail of the histogram to form a remaining set of data. A clipping value is determined by expanding the remaining set of data to a nearest power of two value. The set of data is then quantized using the clipping value. With PACT2, a model can be quantized either using post training quantization or using quantization aware training. PACT2 helps a quantized model to achieve close accuracy compared to the corresponding floating-point model.