公开(公告)号：US20210160422A1

公开(公告)日：2021-05-27

申请号：US17044245

申请日：2018-10-01

Applicant: SRI INTERNATIONAL

Inventor： Michael R. PIACENTINO ,  John R. TOWER ,  Michael A. ISNARDI ,  Sek M. CHAI

IPC: H04N5/232

Abstract: Modules and control units cooperate to simultaneously and independently control and adjust pixel parameters non-uniformly at regional increments across an entire image captured in an image frame by pixels in a pixel array. Pixel parameter changes for pixels in a given region occur, based on i) a contextual understanding of what contextually was happening in the one or more prior image frames and ii) whether salient items are located within that region. Additionally, guidance is sent to the sensor control unit to i) increase or decrease pixel parameters within those regions with salient items and then either to i) maintain, ii) increase or iii) decrease pixel parameters within regions without salient items in order to stay within any i) bandwidth limitations ii) memory storage, and/or iii) power consumptions limitations imposed by 1) one or more image sensors or 2) the communication loop between the sensor control unit and the image processing unit.

公开(公告)号：US20230394637A1

公开(公告)日：2023-12-07

申请号：US18206001

申请日：2023-06-05

Applicant: SRI International

Inventor： David Chao ZHANG ,  Michael A. ISNARDI ,  Michael R. PIACENTINO

IPC: G06T5/10 ,  G06V20/52

CPC classification number: G06T5/10 ,  G06V20/52 ,  G06V2201/07

Abstract: A method, apparatus and system for image privacy protection and actionable response includes distorting an analog image captured using an image capture device in a residential, industrial or commercial environment using a transform filter, digitizing the distorted analog image, analyzing the distorted, digitized image using a trained machine learning process to identify at least one of an individual or an object in the distorted, digitized image, the machine learning process having been trained to identify individuals and objections in the distorted image, and upon identification of at least one of an individual or an object in the distorted image for which action is to be taken, communicating an indication to at least one device in the residential, commercial or industrial environment to cause the device to perform a predetermined action.

公开(公告)号：US20240185591A1

公开(公告)日：2024-06-06

申请号：US18282049

申请日：2022-03-24

Applicant: SRI INTERNATIONAL

Inventor： Aswin NADAMUNI RAGHAVAN ,  Michael R. PIACENTINO ,  Michael A. ISNARDI ,  Indhumathi KANDASWAMY ,  Saurabh FARKYA ,  David Chao ZHANG ,  Gooitzen S. VAN DER WAL ,  Zachary DANIELS ,  Yuzheng ZHANG

IPC: G06V10/82 ,  G06N3/0442 ,  G06V10/764

CPC classification number: G06V10/82 ,  G06N3/0442 ,  G06V10/764

Abstract: Method and apparatus for processing data using a reconfigurable, hyperdimensional neural network architecture comprising a feature extractor and a classifier. The feature extractor comprises a neural network for encoding input information into hyperdimensional (HD) vectors and extracting at least one particular HD vector representing at least one feature within the input information, wherein the neural network comprises no more than one multiply and accumulate operator. The classifier is coupled to the feature extractor for classifying the at least one particular HD vector to produce an indicium of classification for the at least one particular HD vector and wherein the classifier does not comprise any multiply and accumulate operators.