-
公开(公告)号：US09681150B2
公开(公告)日：2017-06-13
申请号：US14737904
申请日：2015-06-12
Applicant: TEXAS INSTRUMENTS INCORPORATED
Abstract: An image processing system includes a processor and optical flow determination logic. The optical flow determination logic is to quantify relative motion of a feature present in a first frame of video and a second frame of video with respect to the two frames of video. The optical flow determination logic configures the processor to convert each of the frames of video into a hierarchical image pyramid. The image pyramid comprises a plurality of image levels. Image resolution is reduced at each higher one of the image levels. For each image level and for each pixel in the first frame, the processor is configured to establish an initial estimate of a location of the pixel in the second frame and to apply a plurality of sequential searches, starting from the initial estimate, that establish refined estimates of the location of the pixel in the second frame.
-
22.发明授权公开(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
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：US11620478B2
公开(公告)日：2023-04-04
申请号：US16784009
申请日：2020-02-06
Applicant: Texas Instruments Incorporated
Inventor： Soyeb Noormohammed Nagori , Deepak Poddar , Hrushikesh Tukaram Garud
Abstract: 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.
-
公开(公告)号：US20220375022A1
公开(公告)日：2022-11-24
申请号：US17879251
申请日：2022-08-02
Applicant: Texas Instruments Incorporated
Abstract: A computer vision system is provided that includes a camera capture component configured to capture an image from a camera, a memory, and an image compression decompression engine (ICDE) coupled to the memory and configured to receive each line of the image, and compress each line to generate a compressed bit stream. To compress a line, the ICDE is configured to divide the line into compression units, and compress each compression unit, wherein to compress a compression unit, the ICDE is configured to perform delta prediction on the compression unit to generate a delta predicted compression unit, compress the delta predicted compression unit using exponential Golomb coding to generate a compressed delta predicted compression unit, and add the compressed delta predicted compression unit to the compressed bit stream.
-
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.
-
Patent Agency Ranking
公开(公告)号：US11417017B2
公开(公告)日：2022-08-16
申请号：US16854590
申请日：2020-04-21
Applicant: TEXAS INSTRUMENTS INCORPORATED
Inventor： Hrushikesh Tukaram Garud , Deepak Poddar , Soyeb Noormohammed Nagori
Abstract: 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.
-
27.发明申请公开(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
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：US10706492B2
公开(公告)日：2020-07-07
申请号：US15695266
申请日：2017-09-05
Applicant: Texas Instruments Incorporated
Abstract: A computer vision system is provided that includes a camera capture component configured to capture an image from a camera, a memory, and an image compression decompression engine (ICDE) coupled to the memory and configured to receive each line of the image, and compress each line to generate a compressed bit stream. To compress a line, the ICDE is configured to divide the line into compression units, and compress each compression unit, wherein to compress a compression unit, the ICDE is configured to perform delta prediction on the compression unit to generate a delta predicted compression unit, compress the delta predicted compression unit using exponential Golomb coding to generate a compressed delta predicted compression unit, and add the compressed delta predicted compression unit to the compressed bit stream.
-
公开(公告)号：US20180181816A1
公开(公告)日：2018-06-28
申请号：US15684321
申请日：2017-08-23
Applicant: Texas Instruments Incorporated
Inventor： Hrushikesh Tukaram Garud , Manu Mathew , Soyeb Noormohammed Nagori
IPC: G06K9/00 , H04N19/20 , H04N19/513 , H04N19/523 , H04N19/53 , H04N19/56 , G06T7/269 , G06T5/20 , G06T5/00
CPC classification number: G06K9/00791 , G06K9/00973 , G06K9/46 , G06K9/6215 , G06K2009/3291 , G06K2009/4666 , G06T5/002 , G06T5/20 , G06T7/246 , G06T7/269 , G06T2207/30252 , H04N19/20 , H04N19/521 , H04N19/523 , H04N19/53 , H04N19/56
Abstract: A method of optical flow estimation is provided that includes identifying a candidate matching pixel in a reference image for a pixel in a query image, determining a scaled binary pixel descriptor for the pixel based on binary census transforms of neighborhood pixels corresponding to scaling ratios in a set of scaling ratios, determining a scaled binary pixel descriptor for the candidate matching pixel based on binary census transforms of neighborhood pixels corresponding to scaling ratios in the set of scaling ratios, and determining a matching cost of the candidate matching pixel based on the scaled binary pixel descriptors.
-
公开(公告)号：US20170011520A1
公开(公告)日：2017-01-12
申请号：US15205598
申请日：2016-07-08
Applicant: Texas Instruments Incorporated
Inventor： Manu Mathew , Soyeb Noormohammed Nagori , Shyam Jagannathan
CPC classification number: G06K9/6215 , G06K9/6218 , G06K9/6232
Abstract: Disclosed examples include image processing methods and systems to process image data, including computing a plurality of scaled images according to input image data for a current image frame, computing feature vectors for locations of the individual scaled images, classifying the feature vectors to determine sets of detection windows, and grouping detection windows to identify objects in the current frame, where the grouping includes determining first clusters of the detection windows using non-maxima suppression grouping processing, determining positions and scores of second clusters using mean shift clustering according to the first clusters, and determining final clusters representing identified objects in the current image frame using non-maxima suppression grouping of the second clusters. Disclosed examples also include methods and systems to track identified objects from one frame to another using feature vectors and overlap of identified objects between frames to minimize computation intensive operations involving feature vectors.
Abstract translation: 公开的示例包括图像处理方法和处理图像数据的系统，包括根据当前图像帧的输入图像数据计算多个缩放图像，计算各个缩放图像的位置的特征向量，对特征向量进行分类以确定 检测窗口和分组检测窗口以识别当前帧中的对象，其中分组包括使用非最大抑制分组处理来确定检测窗口的第一聚类，使用根据第一簇的平均移位聚类来确定第二簇的位置和得分 并且使用第二簇的非最大抑制分组来确定表示当前图像帧中的识别对象的最终簇。 公开的示例还包括使用特征向量来跟踪所识别的对象的方法和系统，以及帧之间的已标识对象的重叠，以使涉及特征向量的计算密集型操作最小化。
-
-
-
-
-
-
-
-
-
Search Results
31
records
(took 0.045 seconds)
