# US 2020/0288140 A1 · Determining redundancy in transformed sensor data > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2020/0288140 A1 - Document ID: US20200288140A1 - Status: Published application - Kind: A1 - Application number: 16/884,558 - Filed: 2020-05-27 - Published: 2020-09-10 - Earliest claimed: 2018-11-13 - Assignees: Seagate Technology LLC - Applicants: Seagate Technology LLC - Inventors: Mehmet Fatih Erden - Web page: https://patentgrep.com/patent/US20200288140A1 ## CPC - H04N 19/137: Motion inside a coding unit, e.g. average field, frame or block difference - H04N 19/23: with coding of regions that are present throughout a whole video segment, e.g. sprites, background or mosaic - H04N 5/917: for bandwidth reduction - H04N 9/804: involving pulse code modulation of the colour picture signal components - H04N 19/1883: {the unit relating to sub-band structure, e.g. hierarchical level, directional tree, e.g. low-high [LH], high-low [HL], high-high [HH]} - H04N 19/63: using sub-band based transform, e.g. wavelets - H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION ## Abstract Two or more video signals from two or more sensors are received and discrete wavelet transformations are performed on the two or more video signals. Temporally stationary and non-stationary background data is determined from the discrete wavelet transformations. Redundancies are determined using the temporally stationary background data, the redundancies indicating an overlap between the two or more video signals Data of the two or more video signals is stored without the redundancies to reduce a storage size. ## Claims ### Claim 1 A method, comprising: receiving two or more video signals from respective two or more sensors; performing discrete wavelet transformations on the two or more video signals; determining temporally stationary background data and temporally non-stationary data from the discrete wavelet transformations; determining redundancies in the temporally stationary background data, the redundancies indicating a partial overlap between the two or more video signals; and storing data of the two or more video signals without the redundancies to reduce a storage size of the data. ### Claim 2 (depends on 1) The method of claim 1, wherein the two or more video signals are separately received at respective two or more edge nodes, the two or more edge nodes independently performing the discrete wavelet transformations on the two or more video signals and further independently performing the determining of temporally stationary background data and determining of the redundancies. ### Claim 3 (depends on 2) The method of claim 2, further comprising processing the two or more video signals at data integrity modules of the two or more edge nodes before the discrete wavelet transformation, the data integrity modules enrolling the two or more edge nodes in a distributed security agreement and storing hashes of the data of the two or more video signals on a ledger. ### Claim 4 (depends on 2) The method of claim 2, wherein storing of the data extracted by the two or more edge nodes comprises storing the data in a RAID-type system distributed between the two or more edge nodes. ### Claim 5 (depends on 2) The method of claim 2, wherein determining the redundancies further comprises scaling and rotating the temporally stationary background data from at least one of the edge nodes to obtain a common reference frame. ### Claim 6 (depends on 1) The method of claim 1, wherein storing the data comprises storing the temporally, stationary background data as images at a larger time period between the images compared to a shorter time period between non-stationary images of the temporally non-stationary data. ### Claim 7 (depends on 1) The method of claim 1, further comprising determining second redundancies between the temporally non-stationary data resulting from the partial overlap between the two or more video signals, the data stored without the second redundancies. ### Claim 8 (depends on 1) The method of claim 1, further comprising: determining second redundancies between the temporally non-stationary data resulting from the partial overlap between the two or more video signals; and identifying a moving object moving between the two or more sensors as a same object based on the second redundancies. ### Claim 9 An apparatus, comprising: a network interface configured to receive two or more video signals from respective two or more sensors; and one or more processors coupled to the network interface, the processor configured to: perform discrete wavelet transformations on the two or more video signals; determine temporally stationary background data from the discrete wavelet transformations; determine redundancies using the temporally stationary background data, the redundancies indicating a partial overlap between the two or more video signals; and store data of the two or more video signals without the redundancies to reduce a storage size of the data. ### Claim 10 (depends on 9) The apparatus of claim 9, wherein determining the redundancies further comprises scaling and rotating the temporally stationary background data from at least one of the two or more sensors to obtain a common reference frame. ### Claim 11 (depends on 9) The apparatus of claim 9, wherein storing the data further comprises storing the temporally stationary background data as images at a larger time period between the images compared to a shorter time period between non-stationary images of the temporally, non-stationary data. ### Claim 12 (depends on 9) The apparatus of claim 9, further comprising determining second redundancies between the temporally non-stationary data resulting from the partial overlap between the two or more video signals, the data stored without the second redundancies. ### Claim 13 (depends on 9) The apparatus of claim 9, further comprising: determining second redundancies between the temporally non-stationary data resulting from the partial overlap between the two or more video signals; and identifying a moving object moving between the two or more sensors as a same object based on the second redundancies. ### Claim 14 A system comprising: two or more sensors providing respective two or more video signals that are accessible via a network; and at least one processing node coupled to the network and operable to: receive the two or more video signals; perform discrete wavelet transformations on the two or more video signals; determine temporally stationary background data and temporally non-stationary data from the discrete wavelet transformations; determine redundancies between the temporally stationary background data, the redundancies indicating a partial overlap between the two or more video signals; and store data of the two or more video signals without the redundancies to reduce a storage size of the data. ### Claim 15 (depends on 14) The system of claim 14, further comprising two or more edge nodes respectively coupled to the two or more sensors, wherein the two or more video signals are separately received at the respective two or more edge nodes, the two or more edge nodes independently performing the discrete wavelet transformations on the two or more video signals, wherein one of the two or more edge nodes is the at least one processing node. ### Claim 16 (depends on 15) The system of claim 15, further comprising processing the two or more video signals at data integrity modules of the two or more edge nodes before the discrete wavelet transformation, the data integrity modules enrolling the two or more edge nodes in a distributed security agreement and storing hashes of the data extracted by the two or more edge nodes on a ledger. ### Claim 17 (depends on 15) The system of claim 15, wherein storing of the data extracted by the two or more edge nodes comprises storing the data in a RAID-type system distributed between the two or more edge nodes. ### Claim 18 (depends on 14) The system of claim 14, wherein storing the data further comprises storing the temporally stationary background data as images at larger time periods between the images compared to shorter time periods between non-stationary images of the temporally non-stationary data. ### Claim 19 (depends on 14) The system of claim 14, wherein the at least one processing node is further operable to determine second redundancies between the temporally non-stationary data resulting from the partial overlap between the two or more video signals, the data stored without the second redundancies. ### Claim 20 (depends on 14) The system of claim 14, wherein the at least one processing node is further operable to: determine second redundancies between the temporally non-stationary data resulting from the partial overlap between the two or more video signals; and identify a moving object moving between the two or more sensors as a same object based on the second redundancies.