-
公开(公告)号：US12184840B2
公开(公告)日：2024-12-31
申请号：US17875305
申请日：2022-07-27
Applicant: TEXAS INSTRUMENTS INCORPORATED
Inventor： Soyeb Nagori , Manu Mathew , Pramod Kumar Swami
IPC: H04N19/107 , H04N19/147 , H04N19/176 , H04N19/50
Abstract: This invention predicts that intra mode prediction is more effective for the macroblocks where motion estimation in inter mode prediction fails. This failure is indicated by a large value of the inter mode SAD. This invention performs intra mode prediction for only macro blocks have larger inter mode SADs. The definition of a large inter mode SAD differs for different content. This invention compares the inter mode SAD of a current macroblock with an adaptive threshold. This adaptive threshold depends on the average and variance of the SADs of the previous predicted frame. An adaptive threshold is calculated for each new predictive frame.
-
公开(公告)号：US11915117B2
公开(公告)日：2024-02-27
申请号：US17327988
申请日：2021-05-24
Applicant: TEXAS INSTRUMENTS INCORPORATED
Inventor： Manu Mathew , Kumar Desappan , Pramod Kumar Swami
CPC classification number: G06N3/04 , G06F7/5443 , G06F17/15 , G06F17/153 , G06N3/045 , G06N3/08 , G06N3/082 , G06N3/084 , G06N3/10
Abstract: A method for convolution in a convolutional neural network (CNN) is provided that includes accessing a coefficient value of a filter corresponding to an input feature map of a convolution layer of the CNN, and performing a block multiply accumulation operation on a block of data elements of the input feature map, the block of data elements corresponding to the coefficient value, wherein, for each data element of the block of data elements, a value of the data element is multiplied by the coefficient value and a result of the multiply is added to a corresponding data element in a corresponding output block of data elements comprised in an output feature map.
-
3.发明授权公开(公告)号：US11388434B2
公开(公告)日：2022-07-12
申请号：US16838115
申请日：2020-04-02
Applicant: Texas Instruments Incorporated
Inventor： Soyeb Nagori , Arun Shankar Kudana , Pramod Kumar Swami
IPC: H04N19/523 , H04N19/105 , H04N19/176 , H04N19/147 , H04N19/172 , H04N19/61 , H04N19/109 , H04N19/114 , H04N19/117 , H04N19/156 , H04N19/157
Abstract: Several techniques aimed at reducing computational complexity when encoding uses bi-predictively encoded frames (B-frames) are implemented in a video encoder. In an embodiment, B-frames are not used as reference frames for encoding P-frames and other B-frames. Non-use of B-frames allows a de-blocking filter used in the video encoder to be switched off when reconstructing encoded B-frames, and use of a lower complexity filter for fractional-resolution motion search for B-frames. In another embodiment, cost functions used in motion estimation for B-frames are simplified to reduce computational complexity. In one more embodiment, fractional pixel refinement in motion search for B-frames is simplified. In yet another embodiment, predictors used in motion estimation for a macro-block in a P-frame are selected from a B-frame that uses a same reference frame as the P-frame.
-
公开(公告)号：US11025932B2
公开(公告)日：2021-06-01
申请号：US15089854
申请日：2016-04-04
Applicant: Texas Instruments Incorporated
Inventor： Uday Pudipeddi Kiran , Deepak Kumar Poddar , Pramod Kumar Swami , Arun Shankar Kudana
IPC: H04N11/02 , H04N19/423 , H04N19/577 , H04N19/177 , H04N19/44
Abstract: 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.
-
公开(公告)号：US10977560B2
公开(公告)日：2021-04-13
申请号：US16390082
申请日：2019-04-22
Applicant: Texas Instruments Incorporated
Inventor： Shyam Jagannathan , Pramod Kumar Swami
Abstract: A method for object classification in a decision tree based adaptive boosting (AdaBoost) classifier implemented on a single-instruction multiple-data (SIMD) processor is provided that includes receiving feature vectors extracted from N consecutive window positions in an image in a memory coupled to the SIMD processor and evaluating the N consecutive window positions concurrently by the AdaBoost classifier using the feature vectors and vector instructions of the SIMD processor, in which the AdaBoost classifier concurrently traverses decision trees for the N consecutive window positions until classification is complete for the N consecutive window positions.
-
Patent Agency Ranking
6.发明授权公开(公告)号：US10521688B2
公开(公告)日：2019-12-31
申请号：US15989551
申请日：2018-05-25
Applicant: TEXAS INSTRUMENTS INCORPORATED
Inventor： Deepak Kumar Poddar , Pramod Kumar Swami , Prashanth Viswanath
Abstract: This invention transforms a list of feature points in raster scan order into a list of maxima suppressed feature points. A working buffer has two more entries than the width of the original image. Each entry is assigned to an x coordinate of the original image. Each entry stores a combined y coordinate and reliability score for each feature point in the original list. This process involves a forward scan and a backward scan. For each original feature point its x coordinate defines the location within the working buffer where neighbor feature points would be stored if they exist. The working buffer initial data and the y coordinates assure a non-suppress comparison result if the potential neighbors are not actual neighbors. For actual neighbor data, the y coordinates match and the comparison result depends solely upon the relative reliability scores.
-
公开(公告)号：US10460189B2
公开(公告)日：2019-10-29
申请号：US16273930
申请日：2019-02-12
Applicant: Texas Instruments Incorporated
Inventor： Deepak Kumar Poddar , Pramod Kumar Swami
Abstract: A method of determining a summation of pixel characteristics for a rectangular region of a digital image includes determining if a base address for a data element in an integral image buffer is aligned for an SIMD operation by a processor embedded in an electronic assembly configured to perform Haar-like feature calculations. The data element represents a corner of the rectangular region of an integral image. The integral image is a representation of the digital image. The integral image is formed by data elements stored in the integral image buffer. The data element is loaded from the integral image buffer to the processor when the base address is aligned for the SIMD operation. An offset data element of an offset integral image is loaded from an offset integral buffer when the base address is non-aligned for the SIMD operation. The offset data element represents the corner of the rectangular region.
-
公开(公告)号：US20190251451A1
公开(公告)日：2019-08-15
申请号：US16390082
申请日：2019-04-22
Applicant: Texas Instruments Incorporated
Inventor： Shyam Jagannathan , Pramod Kumar Swami
CPC classification number: G06N5/02 , G06F9/3887 , G06K9/00973 , G06K9/6257 , G06N5/003 , G06N20/00
Abstract: A method for object classification in a decision tree based adaptive boosting (AdaBoost) classifier implemented on a single-instruction multiple-data (SIMD) processor is provided that includes receiving feature vectors extracted from N consecutive window positions in an image in a memory coupled to the SIMD processor and evaluating the N consecutive window positions concurrently by the AdaBoost classifier using the feature vectors and vector instructions of the SIMD processor, in which the AdaBoost classifier concurrently traverses decision trees for the N consecutive window positions until classification is complete for the N consecutive window positions.
-
公开(公告)号：US20190012559A1
公开(公告)日：2019-01-10
申请号：US16028773
申请日：2018-07-06
Applicant: Texas Instruments Incorporated
Inventor： Kumar Desappan , Manu Mathew , Pramod Kumar Swami , Praveen Eppa
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.
-
10.发明申请Efficient Decision Tree Traversal in an Adaptive Boosting (ADABOOST) Classifier 审中-公开自适应提升（ADABOOST）分类器中的有效决策树遍历公开(公告)号：US20170011294A1
公开(公告)日：2017-01-12
申请号：US14792596
申请日：2015-07-06
Applicant: Texas Instruments Incorporated
Inventor： Shyam Jagannathan , Pramod Kumar Swami
CPC classification number: G06N5/02 , G06F9/3887 , G06K9/00973 , G06K9/6257
Abstract: A method for object classification in a decision tree based adaptive boosting (AdaBoost) classifier implemented on a single-instruction multiple-data (SIMD) processor is provided that includes receiving feature vectors extracted from N consecutive window positions in an image in a memory coupled to the SIMD processor and evaluating the N consecutive window positions concurrently by the AdaBoost classifier using the feature vectors and vector instructions of the SIMD processor, in which the AdaBoost classifier concurrently traverses decision trees for the N consecutive window positions until classification is complete for the N consecutive window positions.
Abstract translation: 提供了一种在单指令多数据（SIMD）处理器上实现的基于决策树的自适应提升（AdaBoost）分类器中的对象分类方法，该方法包括接收从存储器中的N个连续窗口位置提取的特征矢量， SIMD处理器，并且使用AdaBoost分类器使用SIMD处理器的特征向量和向量指令来并行地评估N个连续窗口位置，其中AdaBoost分类器并行遍历N个连续窗口位置的决策树，直到N个连续的分类完成 窗口位置
-
-
-
-
-
-
-
-
-
Search Results
59
records
(took 0.026 seconds)
