# US 9,521,377 B2 · Motion detection method and device using the same > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 9,521,377 B2 - Document ID: US9521377B2 - Status: Granted - Kind: B2 - Application number: 14/195,911 - Filed: 2014-03-04 - Published: 2015-04-09 - Granted: 2016-12-13 - Earliest claimed: 2013-10-08 - Assignees: Sercomm Corporation - Applicants: Sercomm Corporation - Inventors: Shiou-Hua Hu - Web page: https://patentgrep.com/patent/US9521377B2 ## CPC - H04N 7/183: {for receiving images from a single remote source} - G06T 7/254: involving subtraction of images - G08B 13/19606: {Discriminating between target movement or movement in an area of interest and other non-signicative movements, e.g. target movements induced by camera shake or movements of pets, falling leaves, rotating fan} - H04N 5/144: {Movement detection (for video coding H04N19/503; analysis of motion in general G06T7/20)} - H04N 5/76: Television signal recording - H04N 5/91: Television signal processing therefor - H04N 9/79: Processing of colour television signals in connection with recording - G06T 2207/10016: Video; Image sequence - G06T 2207/30232: Surveillance - H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G08B: SIGNALLING SYSTEMS, e.g. PERSONAL CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS ## Abstract A motion detection method is provided. The method includes steps of: recording an input video having a plurality of windows of interest (WOIs), extracting a reference frame from the input video in every reference updating cycle, extracting a target frame from the input video and determining whether an event occurs in each of the WOIs by comparing the target frame with the reference frame in every checking cycle, and comparing the number of WOIs in which the event occurs in every observation cycle with a threshold to determine whether the input video contains a motion during the observation cycle. ## Claims ### Claim 1 A motion detection method, comprising: recording an input video having a plurality of image frames, with each image frame having a plurality of windows of interest (WOIs); extracting a reference frame from the input video in every reference updating cycle; extracting a target frame from the input video and determining whether an event occurs in each of the WOIs by comparing the target frame with the reference frame in every checking cycle; and comparing the number of WOIs in which the event occurs in every observation cycle with a threshold to determine whether the input video contains a motion during the observation cycle; wherein the observation cycle is greater than the checking cycle, and the checking cycle is greater than or equal to the reference updating cycle. ### Claim 2 (depends on 1) The motion detection method according to claim 1, wherein the step of extracting the target frame from the input video and determining whether the event occurs in each of the WOIs by comparing the target frame with the reference frame in every checking cycle further comprises: calculating a pixel differential value in each WOI between the target frame and the reference frame; wherein the event occurs when the pixel differential value exceeds an event threshold value, and the pixel differential value is the percentage of pixels having different pixel value between pixels in one of the WOIs of the target frame and pixels in the corresponding WOI of the reference frame. ### Claim 3 (depends on 1) The motion detection method according to claim 1, wherein the input video is determined to contain the motion during the observation cycle if the number of WOIs in which the event occurs in the observation cycle is greater than the threshold. ### Claim 4 (depends on 1) The motion detection method according to claim 1, wherein the threshold is an integer greater than 1. ### Claim 5 (depends on 1) The motion detection method according to claim 1, further comprising: uploading at least one frame of the input video in the observation cycle to a cloud server if the input video is determined to contain the motion during the observation cycle. ### Claim 6 (depends on 1) The motion detection method according to claim 1, further comprising: sending a notification to a user if the input video is determined to contain the motion during the observation cycle. ### Claim 7 (depends on 1) The motion detection method according to claim 1, further comprising: recording a triggered pattern representing a sequence of the WOIs in which the event occurs in the observation cycle. ### Claim 8 (depends on 7) The motion detection method according to claim 7, wherein the triggered pattern is used for determining movement characteristics of an object in the input video. ### Claim 9 (depends on 8) The motion detection method according to claim 8, wherein the movement characteristics comprise at least one of movement direction and movement speed. ### Claim 10 A motion detection device, comprising: a video recording circuit for recording an input video having a plurality of image frames, with each image frame having a plurality of windows of interest (WOIs); a storage circuit for storing the recorded input video; and a processing circuit for extracting a reference frame from the input video in every reference updating cycle, extracting a target frame from the input video and determining whether an event occurs in each of the WOIs by comparing the target frame with the reference frame in every checking cycle, and comparing the number of WOIs in which the event occurs in every observation cycle with a threshold to determine whether the input video contains a motion during the observation cycle, wherein the observation cycle is greater than the checking cycle, and the checking cycle is greater than or equal to the reference updating cycle. ### Claim 11 (depends on 10) The motion detection device according to claim 10, wherein the processing circuit further calculates a pixel differential value in each WOI between the target frame and the reference frame to determine whether the event occurs, wherein the event occurs when the pixel differential value exceeds an event threshold value, and the pixel differential value is the percentage of pixels having different pixel value between pixels in one of the WOIs of the target frame and pixels in the corresponding WOI of the reference frame. ### Claim 12 (depends on 10) The motion detection device according to claim 10, wherein the input video is determined to contain the motion during the observation cycle if the number of WOIs in which the event occurs in the observation cycle is greater than the threshold. ### Claim 13 (depends on 10) The motion detection device according to claim 10, wherein the threshold is an integer greater than 1. ### Claim 14 (depends on 10) The motion detection device according to claim 10, wherein the processing circuit further uploads at least one frame of the input video in the observation cycle to a cloud server if the input video is determined to contain the motion during the observation cycle. ### Claim 15 (depends on 10) The motion detection device according to claim 10, wherein the processing circuit further sends a notification to a user if the input video is determined to contain the motion during the observation cycle. ### Claim 16 (depends on 10) The motion detection device according to claim 10, wherein the processing circuit further records a triggered pattern representing a sequence of the WOIs in which the event occurs in the observation cycle. ### Claim 17 (depends on 16) The motion detection device according to claim 16, wherein the triggered pattern is used for determining movement characteristics of an object in the input video. ### Claim 18 (depends on 17) The motion detection device according to claim 17, wherein the movement characteristics comprise at least one of movement direction and movement speed. ### Claim 19 (depends on 1) The motion detection method according to claim 1, wherein each of the WOIs comprises a plurality of pixels. ### Claim 20 (depends on 10) The motion detection device according to claim 10, wherein each of the WOIs comprises a plurality of pixels.