# US 2021/0240764 A1 · Storage System and Method for Optimized Surveillance Search > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2021/0240764 A1 - Document ID: US20210240764A1 - Status: Published application - Kind: A1 - Application number: 16/781,717 - Filed: 2020-02-04 - Published: 2021-08-05 - Earliest claimed: 2020-02-04 - Assignees: Western Digital Technologies, Inc. - Applicants: Western Digital Technologies, Inc. - Inventors: Ramanathan Muthiah - Web page: https://patentgrep.com/patent/US20210240764A1 ## CPC - G06F 16/735: Filtering based on additional data, e.g. user or group profiles - G06F 16/7837: {using objects detected or recognised in the video content} - G06N 5/04: Inference or reasoning models - G06N 20/00: Machine learning - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract A storage system and method for optimized surveillance search are provided. In one embodiment, a storage system is provided comprising a memory and a controller. The controller is configured to: receive, from a host, an image of an object and a logical block address range of video data stored in the memory; search for the image of the object in video data in the logical block address range; and provide the host with possible hits from the search. Other embodiments are provided. ## Claims ### Claim 1 A storage system comprising: a memory; and a controller configured to: receive, from a host, an image of an object and a logical block address range of video data stored in the memory; search for the image of the object in video data in the logical block address range; and provide the host with possible hits from the search. ### Claim 2 (depends on 1) The storage system of claim 1, wherein the controller is further configured to search for the image of the object by: decoding the video data in the logical block address range; and attempting to match a subset of frames from the decoded video data with the image. ### Claim 3 (depends on 2) The storage system of claim 2, wherein the subset of frames comprises Instantaneous Decoder Refresh (IDR) frames. ### Claim 4 (depends on 2) The storage system of claim 2, wherein a distance between adjacent frames in the subset of frames is provided for by a quality of service parameter. ### Claim 5 (depends on 1) The storage system of claim 1, wherein the controller is further configured to search for the image of the object using artificial intelligence. ### Claim 6 (depends on 1) The storage system of claim 1, wherein the controller is further configured to search for the image of the object using machine learning. ### Claim 7 (depends on 1) The storage system of claim 1, wherein the controller is further configured to provide the host with possible hits from the search by providing the host with a table of hits with corresponding match percentages. ### Claim 8 (depends on 1) The storage system of claim 1, wherein the image of the object is part of a rev clip of images received from the host. ### Claim 9 (depends on 1) The storage system of claim 1, wherein the memory comprises a three-dimensional memory. ### Claim 10 (depends on 1) The storage system of claim 1, wherein the storage system is configured to be integrated in the host. ### Claim 11 (depends on 1) The storage system of claim 1, wherein the storage system is configured to be removably connected with the host. ### Claim 12 A method comprising: performing the following in a storage system comprising a memory: receiving, from a host, a request to search for an image in a logical block address range of video data stored in the memory; decoding the video data in the logical block address range; attempting to match a subset of frames from the decoded video data with the image; and providing the host with possible hits and corresponding match percentages. ### Claim 13 (depends on 12) The method of claim 12, wherein the subset of frames comprises Instantaneous Decoder Refresh (IDR) frames. ### Claim 14 (depends on 12) The method of claim 12, wherein a distance between adjacent frames in the subset of frames is provided for by a quality of service parameter. ### Claim 15 (depends on 12) The method of claim 12, further comprising using artificial intelligence in attempting to match the subset of frames with the image. ### Claim 16 (depends on 12) The method of claim 12, further comprising using machine learning in attempting to match the subset of frames with the image. ### Claim 17 A storage system comprising: a memory; means for receiving, from a host, an image of an object and a logical block address range of video data stored in the memory; means for searching for the image of the object in the logical block address range; and means for providing the host with possible hits from the search. ### Claim 18 (depends on 17) The storage system of claim 17, wherein the means for searching comprises means for: decoding the video data in the logical block address range; and attempting to match Instantaneous Decoder Refresh (IDR) frames from the decoded video data with the image. ### Claim 19 (depends on 17) The storage system of claim 17, further comprising means for providing the host with possible hits from the search by providing the host with a table of hits with corresponding match percentages. ### Claim 20 (depends on 17) The storage system of claim 17, further comprising means for searching for the image of the object in the logical block address range using artificial intelligence or machine learning.