公开(公告)号：US20240422368A1

公开(公告)日：2024-12-19

申请号：US18823494

申请日：2024-09-03

Applicant: Micron Technology, Inc.

Inventor： Poorna Kale ,  Te-Chang Lin

IPC: H04N21/2343 ,  G06F9/30 ,  G06F13/38 ,  G06N3/02 ,  G06N3/049 ,  G06N3/08 ,  G06V10/764 ,  G06V10/82 ,  G06V20/52 ,  H04N19/46 ,  H04N19/50 ,  H04N19/70

Abstract: Systems, devices, and methods related to a deep learning accelerator and memory are described. For example, a removable media (e.g., a memory card, or a USB drive) may be configured to execute instructions with matrix operands and configured with: an interface to receive a video stream; and random access memory to buffer a portion of the video stream as an input to an artificial neural network and to store instructions executable by the deep learning accelerator and matrices of the artificial neural network. Such a removable media can be used to replace an existing removable media used in a surveillance camera to record video or images. The deep learning accelerator can execute the instructions to generate analytics of the buffer portion using the artificial neural network, enabling the surveillance camera that is upgraded via the use of the removable media to provide intelligent services based on the analytics.

公开(公告)号：US11711488B2

公开(公告)日：2023-07-25

申请号：US17463408

申请日：2021-08-31

Applicant: Micron Technology, Inc.

Inventor： Poorna Kale ,  Christopher Joseph Bueb ,  Te-Chang Lin ,  Qi Dong

IPC: H04N5/77 ,  G06F12/1009 ,  H04N5/91 ,  H04N7/18 ,  G06F3/0484

CPC classification number: H04N5/77 ,  G06F12/1009 ,  H04N5/91 ,  H04N7/183 ,  G06F3/0484 ,  G06F2212/657

Abstract: A memory system having multiple address tables to translate logical addresses to physical addresses at different granularity levels is disclosed. For example, a first address table is associated with a first block size of translating logical addresses for accessing system files and application files; and a second address table is associated with a second block size of translating logical addresses for storing and/or retrieving data from an image sensor of a surveillance camera. A user interface can be used to access a configuration option to specify the second block size; and a user may indicate a typical size of an image or video file to be recorded by the surveillance camera to calculate the second block size and thus configure the second address table for a partition to record the image or video files.

公开(公告)号：US11405579B2

公开(公告)日：2022-08-02

申请号：US17002707

申请日：2020-08-25

Applicant: Micron Technology, Inc.

Inventor： Poorna Kale ,  Te-Chang Lin

IPC: H04N5/91 ,  H04N5/76 ,  H04N5/765 ,  H04N7/18 ,  G06F21/60 ,  H04N5/907 ,  G06V20/52 ,  H04N5/77 ,  H04L67/10

Abstract: Systems, devices, and methods related to Video Surveillance as a Service (VSaaS) are described. For example, a removable storage device, such as a secure digital (SD) memory card or a micro SD card, can be configured to run a virtual camera agent. When the removable storage device is inserted into a digital camera to provide a storage capacity for the digital camera, the agent can convert the video captured by the digital camera into video captured by a virtual camera. The virtual camera can be configured to be in compliance with the camera requirements of a VSaaS platform. Thus, a digital camera not in compliance with the platform can still be used with the platform through the deployment of the virtual camera that is enabled by the removable storage device.

公开(公告)号：US20230007317A1

公开(公告)日：2023-01-05

申请号：US17944440

申请日：2022-09-14

Applicant: Micron Technology, Inc.

Inventor： Poorna Kale ,  Te-Chang Lin

IPC: H04N21/2343 ,  H04N19/46 ,  G06N3/08 ,  H04N19/70 ,  G06F9/30 ,  G06N3/04 ,  G06V10/82 ,  G06V10/764 ,  G06N3/02 ,  G06F13/38 ,  G06V20/52 ,  H04N19/50

Abstract: Systems, devices, and methods related to a deep learning accelerator and memory are described. For example, a removable media (e.g., a memory card, or a USB drive) may be configured to execute instructions with matrix operands and configured with: an interface to receive a video stream; and random access memory to buffer a portion of the video stream as an input to an artificial neural network and to store instructions executable by the deep learning accelerator and matrices of the artificial neural network. Such a removable media can be used to replace an existing removable media used in a surveillance camera to record video or images. The deep learning accelerator can execute the instructions to generate analytics of the buffer portion using the artificial neural network, enabling the surveillance camera that is upgraded via the use of the removable media to provide intelligent services based on the analytics.

公开(公告)号：US20220368851A1

公开(公告)日：2022-11-17

申请号：US17869634

申请日：2022-07-20

Applicant: Micron Technology, Inc.

Inventor： Poorna Kale ,  Te-Chang Lin

IPC: H04N5/765 ,  H04N7/18 ,  H04N5/91 ,  G06F21/60 ,  H04N5/907 ,  G06V20/52

Abstract: Systems, devices, and methods related to video surveillance as a service (VSaaS) are described. For example, a removable storage device, such as a secure digital (SD) memory card or a micro SD card, can be configured to run a virtual camera agent. When the removable storage device is inserted into a digital camera to provide a storage capacity for the digital camera, the agent can convert the video captured by the digital camera into video captured by a virtual camera. The virtual camera can be configured to be in compliance with the camera requirements of a VSaaS platform. Thus, a digital camera not in compliance with the platform can still be used with the platform through the deployment of the virtual camera that is enabled by the removable storage device.

公开(公告)号：US11490135B2

公开(公告)日：2022-11-01

申请号：US16906253

申请日：2020-06-19

Applicant: Micron Technology, Inc.

Inventor： Poorna Kale ,  Te-Chang Lin

IPC: G06K9/00 ,  H04N21/2343 ,  H04N19/70 ,  G06N3/08 ,  G06N3/04 ,  G06F13/38 ,  G06F9/30 ,  G06V20/52 ,  G06N3/02 ,  G06V10/82 ,  G06V10/764 ,  H04N19/50 ,  H04N19/46

Abstract: Systems, devices, and methods related to a Deep Learning Accelerator and memory are described. For example, a removable media (e.g., a memory card, or a USB drive) may be configured to execute instructions with matrix operands and configured with: an interface to receive a video stream; and random access memory to buffer a portion of the video stream as an input to an Artificial Neural Network and to store instructions executable by the Deep Learning Accelerator and matrices of the Artificial Neural Network. Such a removable media can be used to replace an existing removable media used in a surveillance camera to record video or images. The Deep Learning Accelerator can execute the instructions to generate analytics of the buffer portion using the Artificial Neural Network, enabling the surveillance camera that is upgraded via the use of the removable media to provide intelligent services based on the analytics.

公开(公告)号：US20220070407A1

公开(公告)日：2022-03-03

申请号：US17002707

申请日：2020-08-25

Applicant: Micron Technology, Inc.

Inventor： Poorna Kale ,  Te-Chang Lin

IPC: H04N5/765 ,  H04N7/18 ,  H04N5/91 ,  H04N5/907 ,  G06K9/00 ,  G06F21/60

Abstract: Systems, devices, and methods related to Video Surveillance as a Service (VSaaS) are described. For example, a removable storage device, such as a secure digital (SD) memory card or a micro SD card, can be configured to run a virtual camera agent. When the removable storage device is inserted into a digital camera to provide a storage capacity for the digital camera, the agent can convert the video captured by the digital camera into video captured by a virtual camera. The virtual camera can be configured to be in compliance with the camera requirements of a VSaaS platform. Thus, a digital camera not in compliance with the platform can still be used with the platform through the deployment of the virtual camera that is enabled by the removable storage device.

公开(公告)号：US12088861B2

公开(公告)日：2024-09-10

申请号：US17944440

申请日：2022-09-14

Applicant: Micron Technology, Inc.

Inventor： Poorna Kale ,  Te-Chang Lin

IPC: G06K9/00 ,  G06F9/30 ,  G06F13/38 ,  G06N3/02 ,  G06N3/049 ,  G06N3/08 ,  G06V10/764 ,  G06V10/82 ,  G06V20/52 ,  H04N19/46 ,  H04N19/50 ,  H04N19/70 ,  H04N21/2343

CPC classification number: H04N21/2343 ,  G06F9/30036 ,  G06F13/382 ,  G06N3/02 ,  G06N3/049 ,  G06N3/08 ,  G06V10/764 ,  G06V10/82 ,  G06V20/52 ,  H04N19/46 ,  H04N19/50 ,  H04N19/70 ,  G06F2213/0026 ,  G06F2213/0042

Abstract: Systems, devices, and methods related to a deep learning accelerator and memory are described. For example, a removable media (e.g., a memory card, or a USB drive) may be configured to execute instructions with matrix operands and configured with: an interface to receive a video stream; and random access memory to buffer a portion of the video stream as an input to an artificial neural network and to store instructions executable by the deep learning accelerator and matrices of the artificial neural network. Such a removable media can be used to replace an existing removable media used in a surveillance camera to record video or images. The deep learning accelerator can execute the instructions to generate analytics of the buffer portion using the artificial neural network, enabling the surveillance camera that is upgraded via the use of the removable media to provide intelligent services based on the analytics.

公开(公告)号：US20230061879A1

公开(公告)日：2023-03-02

申请号：US17463408

申请日：2021-08-31

Applicant: Micron Technology, Inc.

Inventor： Poorna Kale ,  Christopher Joseph Bueb ,  Te-Chang Lin ,  Qi Dong

IPC: H04N5/77 ,  H04N5/91 ,  H04N7/18 ,  G06F12/1009

Abstract: A memory system having multiple address tables to translate logical addresses to physical addresses at different granularity levels. For example, a first address table is associated with a first block size of translating logical addresses for accessing system files and application files; and a second address table is associated with a second block size of translating logical addresses for storing and/or retrieving data from an image sensor of a surveillance camera. A user interface can be used to access a configuration option to specify the second block size; and a user may indicate a typical size of an image or video file to be recorded by the surveillance camera to calculate the second block size and thus configured the second address table for a partition to record the image or video files.

公开(公告)号：US20210400315A1

公开(公告)日：2021-12-23

申请号：US16906253

申请日：2020-06-19

Applicant: Micron Technology, Inc.

Inventor： Poorna Kale ,  Te-Chang Lin

IPC: H04N21/2343 ,  H04N19/70 ,  G06N3/08 ,  G06N3/04 ,  G06F9/30 ,  G06K9/00 ,  G06F13/38

Abstract: Systems, devices, and methods related to a Deep Learning Accelerator and memory are described. For example, a removable media (e.g., a memory card, or a USB drive) may be configured to execute instructions with matrix operands and configured with: an interface to receive a video stream; and random access memory to buffer a portion of the video stream as an input to an Artificial Neural Network and to store instructions executable by the Deep Learning Accelerator and matrices of the Artificial Neural Network. Such a removable media can be used to replace an existing removable media used in a surveillance camera to record video or images. The Deep Learning Accelerator can execute the instructions to generate analytics of the buffer portion using the Artificial Neural Network, enabling the surveillance camera that is upgraded via the use of the removable media to provide intelligent services based on the analytics.