中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

83 records (took 0.037 seconds)

    System and method for decoding scalable video coding
    13.
    发明授权
    System and method for decoding scalable video coding 有权

    公开(公告)号：US09602841B2

    公开(公告)日：2017-03-21

    申请号：US13663707

    申请日：2012-10-30

    Applicant: TEXAS INSTRUMENTS INCORPORATED

    Inventor： Manu Mathew ,  Mullangi Venkata Ratna Reddy

    IPC: H04N19/88 ,  H04N19/30

    CPC classification number: H04N19/88 ,  H04N19/30

    Abstract: A system and method for decoding video encoded using scalable video coding. In one embodiment, a decoder for scalable video coding (SVC) includes an SVC access unit analyzer and decoding logic. The SVC access unit analyzer is configured to examine an SVC access unit prior to layered decoding of the access unit, to determine, based on the examination, what operations the access unit specifies for each layer of the decoding, and to determine, based on the determined operations to be performed for each layer of the decoding, what data to store for use by a subsequent layer of the decoding. The decoding logic is configured to decode the access unit via a plurality of decoding layers; and to store at each decoding layer, for use by a subsequent decoding layer, the data determined by the SVC access unit analyzer to be used by the subsequent decoding layer.

    SYSTEMS AND METHODS FOR OBJECT DETECTION
    14.
    发明申请
    SYSTEMS AND METHODS FOR OBJECT DETECTION 有权
    用于物体检测的系统和方法

    公开(公告)号：US20160148071A1

    公开(公告)日：2016-05-26

    申请号：US14551942

    申请日：2014-11-24

    Applicant: TEXAS INSTRUMENTS INCORPORATED

    Inventor： Kumar Arrakutti Desappan ,  Manu Mathew ,  Pramod Kumar Swami

    IPC: G06K9/46 ,  G06K9/00 ,  G06K9/62

    CPC classification number: G06K9/4647 ,  G06K9/4652 ,  G06K9/6212

    Abstract: An object detection system and a method of detecting an object in an image are disclosed. In an embodiment, a method for detecting the object includes computing one or more feature planes of one or more types for each image pixel of the image. A plurality of cells is defined in the image, where each cell includes first through nth number of pixels, and starting locations of each cell in the image in horizontal and vertical directions are integral multiples of predefined horizontal and vertical step sizes, respectively. One or more feature plane summations of one or more types are computed for each cell. A feature vector is determined for an image portion of the image based on a set of feature plane summations, and the feature vector is compared with a corresponding object classifier to detect a presence of the corresponding object in the image portion of the image.

    Abstract translation: 公开了一种物体检测系统和检测图像中物体的方法。 在一个实施例中，用于检测对象的方法包括为图像的每个图像像素计算一个或多个类型的一个或多个特征面。 在图像中定义多个单元，其中每个单元包括第一至第n个像素数，并且图像中每个单元在水平和垂直方向上的起始位置分别是预定水平和垂直步长的整数倍。 为每个单元计算一个或多个类型的一个或多个特征平面求和。 基于特征平面求和的集合来确定图像的图像部分的特征向量，并且将特征向量与对应的对象分类器进行比较，以检测图像的图像部分中相应对象的存在。

    QUANTIZATION FOR NEURAL NETWORKS
    15.
    发明申请
    QUANTIZATION FOR NEURAL NETWORKS 有权

    公开(公告)号：US20250045572A1

    公开(公告)日：2025-02-06

    申请号：US18408351

    申请日：2024-01-09

    Applicant: TEXAS INSTRUMENTS INCORPORATED

    Inventor： Varun Tripathi ,  Manu Mathew ,  Pramod Swami ,  Kumar Desappan

    IPC: G06N3/0495

    Abstract: Disclosed herein are systems and methods for performing post training quantization. A processor obtains fixed-point output values from a layer of an artificial neural network (ANN) wherein the layer includes fixed-point weights determined based on floating-point weights and a weight scaling factor determined based on an output scaling factor. Next, the processor converts the fixed-point output values to floating-point output values based on the output scaling factor. Then, the processor expands a range of floating-point values. Next, the processor calculates a new output scaling factor based on the expanded range of floating-point output values. Finally, the processor stores the new output scaling factor in an associated memory.

    RATE CONTROL IN VIDEO CODING
    17.
    发明申请
    RATE CONTROL IN VIDEO CODING 有权

    公开(公告)号：US20220248038A1

    公开(公告)日：2022-08-04

    申请号：US17545146

    申请日：2021-12-08

    Applicant: Texas Instruments Incorporated

    Inventor： Soyeb Nagori ,  Arun Shankar Kudana ,  Manu Mathew

    IPC: H04N19/196 ,  H04N19/142 ,  H04N19/177 ,  H04N19/152 ,  H04N19/126

    Abstract: A method of rate control in coding of a video sequence to generate a compressed bit stream is provided that includes computing a sequence base quantization step size for a sequence of pictures in the video sequence, computing a picture base quantization step size for a picture in the sequence of pictures based on the sequence base quantization step size, a type of the picture, and a level of the picture in a rate control hierarchy, and coding the picture using the picture base quantization step size to generate a portion of the compressed bit stream.

    Object detection for distorted images
    19.
    发明授权
    Object detection for distorted images 有权

    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.

    DYNAMIC QUANTIZATION FOR DEEP NEURAL NETWORK INFERENCE SYSTEM AND METHOD
    20.
    发明申请
    DYNAMIC QUANTIZATION FOR DEEP NEURAL NETWORK INFERENCE SYSTEM AND METHOD 有权

    公开(公告)号：US20210150248A1

    公开(公告)日：2021-05-20

    申请号：US17128365

    申请日：2020-12-21

    Applicant: Texas Instruments Incorporated

    Inventor： Kumar Desappan ,  Manu Mathew ,  Pramod Kumar Swami ,  Praveen Eppa

    IPC: G06K9/38 ,  G06K9/62 ,  G06N3/04 ,  G06N3/08 ,  G06N3/063 ,  G06K9/46

    Abstract: A method for dynamically quantizing feature maps of a received image. The method includes convolving an image based on a predicted maximum value, a predicted minimum value, trained kernel weights and the image data. The input data is quantized based on the predicted minimum value and predicted maximum value. The output of the convolution is computed into an accumulator and re-quantized. The re-quantized value is output to an external memory. The predicted min value and the predicted max value are computed based on the previous max values and min values with a weighted average or a pre-determined formula. Initial min value and max value are computed based on known quantization methods and utilized for initializing the predicted min value and predicted max value in the quantization process.

Patent Agency Ranking