# US 12,182,456 B2 · Image data based media type selection based on a first identified attribute of the initial image data > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,182,456 B2 - Document ID: US12182456B2 - Status: Granted - Kind: B2 - Application number: 18/507,598 - Filed: 2023-11-13 - Published: 2024-03-07 - Granted: 2024-12-31 - Earliest claimed: 2020-03-02 - Applicants: Lodestar Licensing Group, LLC - Inventors: Carla L. Christensen; Zahra Hosseinimakarem; Bhumika Chhabra - Web page: https://patentgrep.com/patent/US12182456B2 ## CPC - G06F 3/0685: {Hybrid storage combining heterogeneous device types, e.g. hierarchical storage, hybrid arrays} - G06F 3/0607: {by facilitating the process of upgrading existing storage systems, e.g. for improving compatibility between host and storage device} - G06F 3/0631: {by allocating resources to storage systems} - G06F 3/0647: {Migration mechanisms} - G06F 16/535: Filtering based on additional data, e.g. user or group profiles - G06F 16/583: using metadata automatically derived from the content - G06V 20/00: Scenes; Scene-specific elements (control of digital cameras H04N23/60) - G06V 40/10: Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands - G06V 40/19: Sensors therefor - G11C 11/005: {comprising combined but independently operative RAM-ROM, RAM-PROM, RAM-EPROM cells} - G06V 40/174: {Facial expression recognition} - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - G11C: STATIC STORES (semiconductor memory devices H10B) ## Abstract Systems, apparatuses, and methods related to image based media type selection are described. Memory systems can include multiple types of memory media (e.g., volatile and/or non-volatile). Determinations of which memory media types to write image data to can be made and the data can be written (e.g., stored) in the determined type of memory media. A determined memory media type can be based on attributes of the data. In an example, a method can include receiving, by a memory system that comprises a plurality of memory media types, initial image data from an image sensor coupled to the memory system, identifying one or more attributes of the initial image data, determining a type of memory media to write the initial image data to based on the identified attributes of the initial image data, and selecting, based at least in part on the determined type of memory media, a first memory type of the plurality of memory media types to write the initial image data. ## Claims ### Claim 1 An apparatus, comprising: a plurality of memory media types; and a controller coupled to the plurality of memory media types, wherein the controller is configured to: receive initial image data from an image sensor coupled to the controller; generate a setting corresponding to attributes of the initial image data, wherein the setting comprises a threshold that is machine learned from inputs comprising information about attributes included in the initial image data; determine a first type of memory media to write the initial image data to based on the setting; write the initial image data to the first type of memory media; receive subsequent image data from the image sensor; generate a new setting corresponding to attributes of the subsequent image data; determine a second, different type of memory media to write the subsequent image data to based on the new setting; discard a first portion of the subsequent image data received, based at least in part on the different type of memory media; and write a second portion of the subsequent image data received to the different memory media type of the plurality of memory media types. ### Claim 2 (depends on 1) The apparatus of claim 1, comprising the controller configured to write the subsequently received image data to a second type of memory media of the plurality of memory media types based on the setting. ### Claim 3 (depends on 1) The apparatus of claim 1, further comprising the controller configured to discard the subsequently received image data to a second type of memory media of the plurality of memory media types based on the setting. ### Claim 4 (depends on 1) The apparatus of claim 1, comprising the controller configured to generate new settings with new thresholds as additional image data is received at the controller. ### Claim 5 (depends on 1) The apparatus of claim 1, wherein the controller is configured to generate the setting based on a location of an autonomous vehicle host device. ### Claim 6 (depends on 1) The apparatus of claim 1, comprising the controller configured to determine an allowed threshold amount of at least one of the attributes of the initial image data. ### Claim 7 (depends on 1) The apparatus of claim 1, comprising the controller configured to write one or more bits of data that indicate the determined type of memory media to the at least one of the plurality of memory media types. ### Claim 8 (depends on 1) The apparatus of claim 1, wherein the plurality of memory media types includes at least one of dynamic random-access memory (DRAM), storage class memory (SCM), or NAND. ### Claim 9 (depends on 1) The apparatus of claim 1, comprising the controller configured to: write the new setting to at least one of the plurality of memory media types; and apply the setting, the new setting, or both to subsequently received image data. ### Claim 10 (depends on 1) The apparatus of claim 1, comprising the controller configured to discard the initial image data previously written to the first memory media type based on the determined different type of memory media. ### Claim 11 A method, comprising: receiving initial input about an attribute of initial image data received from an image sensor, determining a first setting based on the initial input and based on a location of a host device; wherein the first setting comprises a threshold that is machine learned from inputs comprising information about attributes included in the initial image data to the apparatus; determining a first type of memory media of the plurality of memory media types to write the initial image data to based on the first setting; writing, based on the first setting, the initial image data to a first memory media type; determining a second setting based on the initial input, additional input, the first setting, and based on a location of the host device; transferring the initial image data from the first memory media type to a second, different memory media type responsive to the determination of the second setting; receiving subsequent image data from the image sensor; generating a new setting corresponding to attributes of the subsequent image data; determining a second, different type of memory media to write the subsequent image data to based on the new setting; discarding a first portion of the subsequent image data received, based at least in part on the different type of memory media; and writing a second portion of the subsequent image data received to the different memory media type of the plurality of memory media types. ### Claim 12 (depends on 11) The method of claim 11, further comprising: receiving new input about attributes of the subsequent image data, wherein the new input and the initial input are different, and the new input identifies changes to one or more thresholds related to the attributes of the subsequent image data; determining a third setting based on the new input; and determining a different type of memory media to write the subsequent image data to based in part on the third setting. ### Claim 13 A system, comprising: an image sensor; a plurality of memory media types coupled to the image sensors; and a controller coupled to the plurality of memory media types, wherein the controller is configured to: generate a setting based on attributes associated with received initial image data and based on a location of a host device, wherein the setting comprises a threshold that is machine learned from inputs comprising information about attributes included in the initial image data to the memory system; in response to the initial image data meeting or exceeding a threshold associated with the setting, write the initial image data to a first memory media type; in response to the initial image data not meeting or exceeding the threshold, discard the initial image data; and determine a change to the threshold based on additional input received and associated with received subsequent image data, wherein the subsequent image data includes a number of portions, and the controller is configured to: write a first portion of the subsequent image data to the first memory media type based on the setting; transfer the initial image data from the first memory media type to a second memory media type based on the setting; and discard a second portion of subsequent image data based on the setting. ### Claim 14 (depends on 13) The system of claim 13, comprising the controller configured to transfer the initial image data from the first memory media type to the second memory media type in response to the setting alteration. ### Claim 15 (depends on 13) The system of claim 13, wherein the attribute comprises at least one of: subject blur, pixel characteristics, pixel density, subject features, and subject focus. ### Claim 16 (depends on 13) The system of claim 13, wherein the setting is based on attributes related to a quality of subjects in the initial image data.