# US 10,121,079 B2 · Video tracking systems and methods employing cognitive vision > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,121,079 B2 - Document ID: US10121079B2 - Status: Granted - Kind: B2 - Application number: 14/545,365 - Filed: 2015-04-27 - Published: 2016-03-03 - Granted: 2018-11-06 - Earliest claimed: 2008-05-09 - Assignees: IntuVision Inc. - Applicants: IntuVision Inc. - Inventors: Sadiye Zeyno Guler; Jason Adam Silverstein; Matthew Kevin Farrow; Ian Harris Pushee - Web page: https://patentgrep.com/patent/US10121079B2 ## CPC - G01S 3/7864: {T.V. type tracking systems} - G06T 7/194: involving foreground-background segmentation - G06T 7/246: using feature-based methods, e.g. the tracking of corners or segments - G06V 20/20: in augmented reality scenes - G06V 20/52: Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69) - G08B 13/196: using television cameras - G08B 13/19608: {Tracking movement of a target, e.g. by detecting an object predefined as a target, using target direction and or velocity to predict its new position} - G08B 13/19652: {Systems using zones in a single scene defined for different treatment, e.g. outer zone gives pre-alarm, inner zone gives alarm} - H04N 7/183: {for receiving images from a single remote source} - G06T 2207/30232: Surveillance - G06T 2207/30244: Camera pose - G06T 2210/12: Bounding box - G01S: RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - G08B: SIGNALLING SYSTEMS, e.g. PERSONAL CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS - H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION ## Abstract Video tracking systems and methods include a peripheral master tracking process integrated with one or more tunnel tracking processes. The video tracking systems and methods utilize video data to detect and/or track separately several stationary or moving objects in a manner of tunnel vision. The video tracking system includes a master peripheral tracker for monitoring a scene and detecting an object, and a first tunnel tracker initiated by the master peripheral tracker, wherein the first tunnel tracker is dedicated to track one detected object. ## Claims ### Claim 1 A video tracking system, comprising: a processor designed to execute layered processing comprising: a master peripheral tracker operative to interact with frames of image data, embodying a video scene, said master peripheral tracker including logic to monitor said scene and to detect an object within said frames of image data utilizing a windowed sequence of consecutive frame differences to track multiple objects using condensed object information and preserving spatial relationships of said multiple objects in said scene to coordinate task layers to understand object activities within overall dynamics of said scene utilizing several tunnel trackers; and a first tunnel tracker initiated by said master peripheral tracker, said first tunnel tracker including logic dedicated to track one said detected object, located within a first buffer area, utilizing a first portion of said image data frame-by-frame by building correspondences for said tracked object based on its attributes and detailed object information including a set of object features, said first buffer area being formed by said master peripheral tracker based on said first tracked object's current trajectory, size and location. ### Claim 2 (depends on 1) The video tracking system of claim 1 further including a second tunnel tracker initiated by said master peripheral tracker after detecting a second object within said frames of image data, said second tunnel tracker including logic dedicated to track said second detected object, located within a second buffer area, utilizing a second portion of said image data frame-by-frame by building correspondences for said second tracked object based on its attributes and detailed object information including a set of object features of said second tracked object, said second buffer area being formed by said master peripheral tracker based on said second tracked object's current trajectory, size and location. ### Claim 3 (depends on 2) The video tracking system of claim 2 further including a third tunnel tracker initiated by said master peripheral tracker after detecting a third object within said frames of image data, said third tunnel tracker including logic dedicated to track said third detected object, located within a third buffer area, utilizing a third portion of said image data frame-by-frame by building correspondences for said third tracked object based on its attributes and detailed object information including a set of object features of said third tracked object, said third buffer area being formed by said master peripheral tracker based on said third tracked object's current trajectory, size and location. ### Claim 4 (depends on 2) The video tracking system of claim 2 wherein said master peripheral tracker maintains said first buffer area and said second buffer area co-dependently. ### Claim 5 (depends on 1) The video tracking system of claim 1 wherein said object features of said tracked object are used for frame-to-frame identification of said object. ### Claim 6 (depends on 1) The video tracking system of claim 1 wherein said object features of said tracked object are used for modeling of said object and matching said object instances from frame to frame as well as matching said object to an object model based on said object features. ### Claim 7 (depends on 6) The video tracking system of claim 6 wherein said set of object features includes one of the following: color, texture and edge information. ### Claim 8 (depends on 1) The video tracking system of claim 1 further including a digital video controller constructed and arranged to receive image data. ### Claim 9 (depends on 1) The video tracking system of claim 1 further including a tracker proxy for communicating with said master peripheral tracker and client applications. ### Claim 10 (depends on 1) The video tracking system of claim 1 wherein said master peripheral tracker includes an object detector and an object tracker. ### Claim 11 (depends on 1) The video tracking system of claim 1 wherein said tunnel tracker executes an edge based tunnel tracking algorithm. ### Claim 12 (depends on 1) The video tracking system of claim 1 wherein said tunnel tracker executes a Kernel based tunnel tracking algorithm. ### Claim 13 (depends on 1) The video tracking system of claim 1 wherein said tunnel tracker executes a Background subtraction based tunnel tracking algorithm. ### Claim 14 (depends on 1) The video tracking system of claim 1 wherein said master peripheral tracker includes a perimeter event detector. ### Claim 15 A video tracking method executed by layered processing using a processor, comprising: monitoring a video scene embodied in frames of image data and detecting an object using a master peripheral tracker utilizing a windowed sequence of consecutive frame differences to track multiple objects using condensed object information and preserving spatial relationships of said multiple objects in said scene to coordinate task layers to understand object activities within overall dynamics of said scene utilizing several tunnel trackers; and initiating by said master peripheral tracker a first tunnel tracker dedicated to track one said detected object, located within a first buffer area, utilizing a first portion of video data frame-by-frame by building correspondences for said first tracked object based on its attributes and detailed object information including a set of object features, wherein said first buffer area is provided by said master peripheral tracker based on said first tracked object's current trajectory, size and location. ### Claim 16 (depends on 15) The video tracking method of claim 15 further including: initiating by said master peripheral tracker a second tunnel tracker dedicated to track a second detected object, located within a second buffer area, utilizing a second portion of said image data frame-by-frame by building correspondences for said second tracked object based on its attributes and detailed object information including a set of object features, wherein said second buffer area is provided by said master peripheral tracker based on said second tracked object's current trajectory, size and location, and said master peripheral tracker maintains said first buffer area and said second buffer area co-dependently. ### Claim 17 (depends on 16) The video tracking method of claim 16 further including initiating by said master peripheral tracker a third tunnel tracker dedicated to track a third detected object, located within a third buffer area, utilizing a third portion of said image data frame-by-frame by building correspondences for said third tracked object based on its attributes and detailed object information including a set of object features, wherein said third buffer area is provided by said master peripheral tracker based on said third tracked object's current trajectory, size and location. ### Claim 18 (depends on 15) The video tracking method of claim 15 wherein said master peripheral tracker sends image requests to a digital video controller and wherein said master peripheral tracker and said digital video controller exchange image data streams and notification messages. ### Claim 19 (depends on 15) The video tracking method of claim 15 wherein said master peripheral tracker provides assembled tracking images to a tracker proxy that communicates with client applications. ### Claim 20 (depends on 15) The video tracking method of claim 15 wherein said master peripheral tracker communicates with a tracker proxy including object definitions. ### Claim 21 (depends on 15) The video tracking method of claim 15 further including executing a perimeter event algorithm. ### Claim 22 (depends on 21) The video tracking method of claim 21 wherein said executing said perimeter event algorithm includes: designating a perimeter zone; tracking said objects outside said perimeter zone or inside said perimeter zone; and triggering an alarm after determining any said object moves from outside of said zone to inside said zone as long as said object stays within said zone. ### Claim 23 (depends on 22) The video tracking method of claim 22 wherein said determining includes measuring said Inside and said outside by the percentage of said object's bounding box contained by said perimeter zone. ### Claim 24 (depends on 15) The video tracking method of claim 15 further including executing an abandoned object algorithm. ### Claim 25 (depends on 24) The video tracking method of claim 24 wherein said abandoned object algorithm includes detecting a stationary object, tracking said stationary object, and taking into account other detected moving objects causing occlusion of said stationary object. ### Claim 26 (depends on 15) The video tracking method of claim 15 wherein said object features of said tracked object are used for frame-to-frame identification of said object. ### Claim 27 (depends on 15) The video tracking method of claim 15 wherein said object features of said tracked object are used for modeling of said object and matching said object instances from frame to frame as well as matching said object to an object model based on said object features. ### Claim 28 (depends on 27) The video tracking method of claim 27 wherein said set of object features includes one of the following: color, texture and edge information.